net/mlx5e: Introduce SRIOV VF representors

Implement the relevant profile functions to create mlx5e driver instance
serving as VF representor. When SRIOV offloads mode is enabled, each VF
will have a representor netdevice instance on the host.

To do that, we also export set of shared service functions from en_main.c,
such that they can be used by both NIC and repsresentors netdevs.

The newly created representor netdevice has a basic set of net_device_ops
which are the same ndo functions as the NIC netdevice and an ndo of it's
own for phys port name.

The profiling infrastructure allow sharing code between the NIC and the
vport representor even though the representor has only a subset of the
NIC functionality.

The VF reps and the PF which is used in that mode to represent the uplink,
expose switchdev ops. Currently the only op supposed is attr get for the
port parent ID which here serves to identify net-devices belonging to the
same HW E-Switch. Other than that, no offloading is implemented and hence
switching functionality is achieved if one sets SW switching rules, e.g
using tc, bridge or ovs.

Port phys name (ndo_get_phys_port_name) is implemented to allow exporting
to user-space the VF vport number and along with the switchdev port parent
id (phys_switch_id) enable a udev base consistent naming scheme:

SUBSYSTEM=="net", ACTION=="add", ATTR{phys_switch_id}=="<phys_switch_id>", \
        ATTR{phys_port_name}!="", NAME="$PF_NIC$attr{phys_port_name}"

where phys_switch_id is exposed by the PF (and VF reps) and $PF_NIC is
the name of the PF netdevice.

Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 95 insertions, 1 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f84aa794d080..ed8ad988f07a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -38,7 +38,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 
-struct mlx5_flow_rule *
+static struct mlx5_flow_rule *
 mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn)
 {
 	struct mlx5_flow_destination dest;
@@ -77,6 +77,63 @@ out:
 	return flow_rule;
 }
 
+void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5_esw_sq *esw_sq, *tmp;
+
+	if (esw->mode != SRIOV_OFFLOADS)
+		return;
+
+	list_for_each_entry_safe(esw_sq, tmp, &rep->vport_sqs_list, list) {
+		mlx5_del_flow_rule(esw_sq->send_to_vport_rule);
+		list_del(&esw_sq->list);
+		kfree(esw_sq);
+	}
+}
+
+int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
+				 struct mlx5_eswitch_rep *rep,
+				 u16 *sqns_array, int sqns_num)
+{
+	struct mlx5_flow_rule *flow_rule;
+	struct mlx5_esw_sq *esw_sq;
+	int vport;
+	int err;
+	int i;
+
+	if (esw->mode != SRIOV_OFFLOADS)
+		return 0;
+
+	vport = rep->vport == 0 ?
+		FDB_UPLINK_VPORT : rep->vport;
+
+	for (i = 0; i < sqns_num; i++) {
+		esw_sq = kzalloc(sizeof(*esw_sq), GFP_KERNEL);
+		if (!esw_sq) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+
+		/* Add re-inject rule to the PF/representor sqs */
+		flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw,
+								vport,
+								sqns_array[i]);
+		if (IS_ERR(flow_rule)) {
+			err = PTR_ERR(flow_rule);
+			kfree(esw_sq);
+			goto out_err;
+		}
+		esw_sq->send_to_vport_rule = flow_rule;
+		list_add(&esw_sq->list, &rep->vport_sqs_list);
+	}
+	return 0;
+
+out_err:
+	mlx5_eswitch_sqs2vport_stop(esw, rep);
+	return err;
+}
+
 static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 {
 	struct mlx5_flow_destination dest;
@@ -347,6 +404,8 @@ static int esw_offloads_start(struct mlx5_eswitch *esw)
 
 int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 {
+	struct mlx5_eswitch_rep *rep;
+	int vport;
 	int err;
 
 	err = esw_create_offloads_fdb_table(esw, nvports);
@@ -361,8 +420,26 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		goto create_fg_err;
 
+	for (vport = 0; vport < nvports; vport++) {
+		rep = &esw->offloads.vport_reps[vport];
+		if (!rep->valid)
+			continue;
+
+		err = rep->load(esw, rep);
+		if (err)
+			goto err_reps;
+	}
 	return 0;
 
+err_reps:
+	for (vport--; vport >= 0; vport--) {
+		rep = &esw->offloads.vport_reps[vport];
+		if (!rep->valid)
+			continue;
+		rep->unload(esw, rep);
+	}
+	esw_destroy_vport_rx_group(esw);
+
 create_fg_err:
 	esw_destroy_offloads_table(esw);
 
@@ -385,6 +462,16 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw)
 
 void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
 {
+	struct mlx5_eswitch_rep *rep;
+	int vport;
+
+	for (vport = 0; vport < nvports; vport++) {
+		rep = &esw->offloads.vport_reps[vport];
+		if (!rep->valid)
+			continue;
+		rep->unload(esw, rep);
+	}
+
 	esw_destroy_vport_rx_group(esw);
 	esw_destroy_offloads_table(esw);
 	esw_destroy_offloads_fdb_table(esw);
@@ -460,6 +547,7 @@ void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
 	memcpy(&offloads->vport_reps[rep->vport], rep,
 	       sizeof(struct mlx5_eswitch_rep));
 
+	INIT_LIST_HEAD(&offloads->vport_reps[rep->vport].vport_sqs_list);
 	offloads->vport_reps[rep->vport].valid = true;
 }
 
@@ -467,6 +555,12 @@ void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
 				       int vport)
 {
 	struct mlx5_esw_offload *offloads = &esw->offloads;
+	struct mlx5_eswitch_rep *rep;
+
+	rep = &offloads->vport_reps[vport];
+
+	if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport].enabled)
+		rep->unload(esw, rep);
 
 	offloads->vport_reps[vport].valid = false;
 }