Merge tag 'mlx5-updates-2019-03-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-03-01

This series adds multipath offload support and contains some small updates
to mlx5 driver.

Multipath offload support from Roi Dayan:

We are going to track SW multipath route and related nexthops and reflect
that as port affinity to the HW.

1) Some patches are preparation.
2) add the multipath mode and fib events handling.
3) add support to handle offload failure for net error, i.e.
port down.
4) Small updates to match the behavior of multipath

Two small updates from Eran Ben Elisha,
5) Make a function static
6) Update PCIe supported devices list.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -30,7 +30,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o
 
 #
 # Core extra

drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c

@@ -179,7 +179,7 @@ int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
 /* state lock cannot be grabbed within this function.
  * It can cause a dead lock or a read-after-free.
  */
-int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
+static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
 {
 	return err_ctx->recover(err_ctx->sq);
 }

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c

@@ -54,12 +54,24 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	struct neighbour *n = NULL;
 
 #if IS_ENABLED(CONFIG_INET)
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct net_device *uplink_dev;
 	int ret;
 
+	if (mlx5_lag_is_multipath(mdev)) {
+		struct mlx5_eswitch *esw = mdev->priv.eswitch;
+
+		uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+		fl4->flowi4_oif = uplink_dev->ifindex;
+	}
+
 	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
 	ret = PTR_ERR_OR_ZERO(rt);
 	if (ret)
 		return ret;
+
+	if (mlx5_lag_is_multipath(mdev) && !rt->rt_gateway)
+		return -ENETUNREACH;
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -295,7 +307,9 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(n, NULL);
-		err = -EAGAIN;
+		/* the encap entry will be made valid on neigh update event
+		 * and not used before that.
+		 */
 		goto out;
 	}
 
@@ -408,7 +422,9 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(n, NULL);
-		err = -EAGAIN;
+		/* the encap entry will be made valid on neigh update event
+		 * and not used before that.
+		 */
 		goto out;
 	}
 

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

@@ -1573,6 +1573,8 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
 		uplink_priv = &rpriv->uplink_priv;
 
+		INIT_LIST_HEAD(&uplink_priv->unready_flows);
+
 		/* init shared tc flow table */
 		err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
 		if (err)
@@ -1632,34 +1634,48 @@ static void mlx5e_vf_rep_enable(struct mlx5e_priv *priv)
 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);
-	struct mlx5_eqe   *eqe = data;
 
-	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
-		return NOTIFY_DONE;
+	if (event == MLX5_EVENT_TYPE_PORT_CHANGE) {
+		struct mlx5_eqe *eqe = data;
 
-	switch (eqe->sub_type) {
-	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-		queue_work(priv->wq, &priv->update_carrier_work);
-		break;
-	default:
-		return NOTIFY_DONE;
+		switch (eqe->sub_type) {
+		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+			queue_work(priv->wq, &priv->update_carrier_work);
+			break;
+		default:
+			return NOTIFY_DONE;
+		}
+
+		return NOTIFY_OK;
 	}
 
-	return NOTIFY_OK;
+	if (event == MLX5_DEV_EVENT_PORT_AFFINITY) {
+		struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+		queue_work(priv->wq, &rpriv->uplink_priv.reoffload_flows_work);
+
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
 }
 
 static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	u16 max_mtu;
 
 	netdev->min_mtu = ETH_MIN_MTU;
 	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
 	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
 	mlx5e_set_dev_port_mtu(priv);
 
+	INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work,
+		  mlx5e_tc_reoffload_flows_work);
+
 	mlx5_lag_add(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);
@@ -1672,11 +1688,13 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
 #endif
 	mlx5_notifier_unregister(mdev, &priv->events_nb);
+	cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
 	mlx5_lag_remove(mdev);
 }
 

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

@@ -74,6 +74,9 @@ struct mlx5_rep_uplink_priv {
 	struct notifier_block	    netdevice_nb;
 
 	struct mlx5_tun_entropy tun_entropy;
+
+	struct list_head            unready_flows;
+	struct work_struct          reoffload_flows_work;
 };
 
 struct mlx5e_rep_priv {