net/mlx5: Lag, set different uplink vport metadata in multiport eswitch mode

In a follow-up commit multiport eswitch mode will use a shared fdb.
In shared fdb there is a single eswitch fdb and traffic could come from any
port. to distinguish between the ports set a different metadata per uplink port.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Maor Dickman <maord@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c

@@ -1007,8 +1007,23 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 	priv->rx_res = NULL;
 }
 
+static void mlx5e_rep_mpesw_work(struct work_struct *work)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv =
+		container_of(work, struct mlx5_rep_uplink_priv,
+			     mpesw_work);
+	struct mlx5e_rep_priv *rpriv =
+		container_of(uplink_priv, struct mlx5e_rep_priv,
+			     uplink_priv);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+
+	rep_vport_rx_rule_destroy(priv);
+	mlx5e_create_rep_vport_rx_rule(priv);
+}
+
 static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	int err;
 
 	mlx5e_create_q_counters(priv);
@@ -1018,12 +1033,17 @@ static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
 
 	mlx5e_tc_int_port_init_rep_rx(priv);
 
+	INIT_WORK(&rpriv->uplink_priv.mpesw_work, mlx5e_rep_mpesw_work);
+
 out:
 	return err;
 }
 
 static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	cancel_work_sync(&rpriv->uplink_priv.mpesw_work);
 	mlx5e_tc_int_port_cleanup_rep_rx(priv);
 	mlx5e_cleanup_rep_rx(priv);
 	mlx5e_destroy_q_counters(priv);
@@ -1132,6 +1152,19 @@ static int mlx5e_update_rep_rx(struct mlx5e_priv *priv)
 	return 0;
 }
 
+static int mlx5e_rep_event_mpesw(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		return NOTIFY_DONE;
+
+	queue_work(priv->wq, &rpriv->uplink_priv.mpesw_work);
+
+	return NOTIFY_OK;
+}
+
 static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event, void *data)
 {
 	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
@@ -1153,6 +1186,8 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event
 
 	if (event == MLX5_DEV_EVENT_PORT_AFFINITY)
 		return mlx5e_rep_tc_event_port_affinity(priv);
+	else if (event == MLX5_DEV_EVENT_MULTIPORT_ESW)
+		return mlx5e_rep_event_mpesw(priv);
 
 	return NOTIFY_DONE;
 }

drivers/net/ethernet/mellanox/mlx5/core/en_rep.h

@@ -103,6 +103,8 @@ struct mlx5_rep_uplink_priv {
 
 	/* tc action stats */
 	struct mlx5e_tc_act_stats_handle *action_stats_handle;
+
+	struct work_struct mpesw_work;
 };
 
 struct mlx5e_rep_priv {

drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c

@@ -5,8 +5,66 @@
 #include <net/nexthop.h>
 #include "lag/lag.h"
 #include "eswitch.h"
+#include "esw/acl/ofld.h"
 #include "lib/mlx5.h"
 
+static void mlx5_mpesw_metadata_cleanup(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev;
+	struct mlx5_eswitch *esw;
+	u32 pf_metadata;
+	int i;
+
+	for (i = 0; i < ldev->ports; i++) {
+		dev = ldev->pf[i].dev;
+		esw = dev->priv.eswitch;
+		pf_metadata = ldev->lag_mpesw.pf_metadata[i];
+		if (!pf_metadata)
+			continue;
+		mlx5_esw_acl_ingress_vport_metadata_update(esw, MLX5_VPORT_UPLINK, 0);
+		mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW,
+					 (void *)0);
+		mlx5_esw_match_metadata_free(esw, pf_metadata);
+		ldev->lag_mpesw.pf_metadata[i] = 0;
+	}
+}
+
+static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev;
+	struct mlx5_eswitch *esw;
+	u32 pf_metadata;
+	int i, err;
+
+	for (i = 0; i < ldev->ports; i++) {
+		dev = ldev->pf[i].dev;
+		esw = dev->priv.eswitch;
+		pf_metadata = mlx5_esw_match_metadata_alloc(esw);
+		if (!pf_metadata) {
+			err = -ENOSPC;
+			goto err_metadata;
+		}
+
+		ldev->lag_mpesw.pf_metadata[i] = pf_metadata;
+		err = mlx5_esw_acl_ingress_vport_metadata_update(esw, MLX5_VPORT_UPLINK,
+								 pf_metadata);
+		if (err)
+			goto err_metadata;
+	}
+
+	for (i = 0; i < ldev->ports; i++) {
+		dev = ldev->pf[i].dev;
+		mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_MULTIPORT_ESW,
+					 (void *)0);
+	}
+
+	return 0;
+
+err_metadata:
+	mlx5_mpesw_metadata_cleanup(ldev);
+	return err;
+}
+
 static int enable_mpesw(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
@@ -21,6 +79,10 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	    !mlx5_lag_check_prereq(ldev))
 		return -EOPNOTSUPP;
 
+	err = mlx5_mpesw_metadata_set(ldev);
+	if (err)
+		return err;
+
 	err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false);
 	if (err) {
 		mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err);
@@ -30,13 +92,16 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	return 0;
 
 out_err:
+	mlx5_mpesw_metadata_cleanup(ldev);
 	return err;
 }
 
 static void disable_mpesw(struct mlx5_lag *ldev)
 {
-	if (ldev->mode == MLX5_LAG_MODE_MPESW)
+	if (ldev->mode == MLX5_LAG_MODE_MPESW) {
+		mlx5_mpesw_metadata_cleanup(ldev);
 		mlx5_disable_lag(ldev);
+	}
 }
 
 static void mlx5_mpesw_work(struct work_struct *work)

drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h

@@ -9,6 +9,7 @@
 
 struct lag_mpesw {
 	struct work_struct mpesw_work;
+	u32 pf_metadata[MLX5_MAX_PORTS];
 };
 
 enum mpesw_op {

include/linux/mlx5/driver.h

@@ -217,6 +217,7 @@ struct mlx5_rsc_debug {
 enum mlx5_dev_event {
 	MLX5_DEV_EVENT_SYS_ERROR = 128, /* 0 - 127 are FW events */
 	MLX5_DEV_EVENT_PORT_AFFINITY = 129,
+	MLX5_DEV_EVENT_MULTIPORT_ESW = 130,
 };
 
 enum mlx5_port_status {