net/mlx5e: Add indirect tc offload of ovs internal port

Register callbacks for tc blocks of ovs internal port devices.

This allows an indirect offloading rules that apply on
such devices as the filter device.

In case a rule is added to a tc block of an internal port,
the mlx5 driver will implicitly add a matching on the internal
port's unique vport metadata value to the rule's matching list.
Therefore, only packets that previously hit a rule that redirects
to an internal port and got the vport metadata overwritten to the
internal port's unique metadata, can match on such indirect rule.

Offloading of both ingress and egress tc blocks of internal ports
is supported as opposed to other devices where only ingress block
offloading is supported.

Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

1 files changed, 25 insertions, 7 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index c69129940268..fcb0892c08a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -25,6 +25,7 @@
 struct mlx5e_rep_indr_block_priv {
 	struct net_device *netdev;
 	struct mlx5e_rep_priv *rpriv;
+	enum flow_block_binder_type binder_type;
 
 	struct list_head list;
 };
@@ -299,14 +300,16 @@ int mlx5e_rep_tc_event_port_affinity(struct mlx5e_priv *priv)
 
 static struct mlx5e_rep_indr_block_priv *
 mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv,
-				 struct net_device *netdev)
+				 struct net_device *netdev,
+				 enum flow_block_binder_type binder_type)
 {
 	struct mlx5e_rep_indr_block_priv *cb_priv;
 
 	list_for_each_entry(cb_priv,
 			    &rpriv->uplink_priv.tc_indr_block_priv_list,
 			    list)
-		if (cb_priv->netdev == netdev)
+		if (cb_priv->netdev == netdev &&
+		    cb_priv->binder_type == binder_type)
 			return cb_priv;
 
 	return NULL;
@@ -344,9 +347,13 @@ mlx5e_rep_indr_offload(struct net_device *netdev,
 static int mlx5e_rep_indr_setup_tc_cb(enum tc_setup_type type,
 				      void *type_data, void *indr_priv)
 {
-	unsigned long flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD);
+	unsigned long flags = MLX5_TC_FLAG(ESW_OFFLOAD);
 	struct mlx5e_rep_indr_block_priv *priv = indr_priv;
 
+	flags |= (priv->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) ?
+		MLX5_TC_FLAG(EGRESS) :
+		MLX5_TC_FLAG(INGRESS);
+
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return mlx5e_rep_indr_offload(priv->netdev, type_data, priv,
@@ -428,11 +435,14 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch,
 			   void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	bool is_ovs_int_port = netif_is_ovs_master(netdev);
 	struct mlx5e_rep_indr_block_priv *indr_priv;
 	struct flow_block_cb *block_cb;
 
 	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
-	    !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev)) {
+	    !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev) &&
+	    !is_ovs_int_port) {
 		if (!(netif_is_macvlan(netdev) && macvlan_dev_real_dev(netdev) == rpriv->netdev))
 			return -EOPNOTSUPP;
 		if (!mlx5e_rep_macvlan_mode_supported(netdev)) {
@@ -441,7 +451,14 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch,
 		}
 	}
 
-	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
+	    f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		return -EOPNOTSUPP;
+
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS && !is_ovs_int_port)
+		return -EOPNOTSUPP;
+
+	if (is_ovs_int_port && !mlx5e_tc_int_port_supported(esw))
 		return -EOPNOTSUPP;
 
 	f->unlocked_driver_cb = true;
@@ -449,7 +466,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch,
 
 	switch (f->command) {
 	case FLOW_BLOCK_BIND:
-		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev, f->binder_type);
 		if (indr_priv)
 			return -EEXIST;
 
@@ -459,6 +476,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch,
 
 		indr_priv->netdev = netdev;
 		indr_priv->rpriv = rpriv;
+		indr_priv->binder_type = f->binder_type;
 		list_add(&indr_priv->list,
 			 &rpriv->uplink_priv.tc_indr_block_priv_list);
 
@@ -476,7 +494,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch,
 
 		return 0;
 	case FLOW_BLOCK_UNBIND:
-		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev, f->binder_type);
 		if (!indr_priv)
 			return -ENOENT;