IB/mlx5: Merge vports flow steering during LAG

This is done in two steps:
1) Issuing CREATE_VPORT_LAG in order to have Ethernet traffic from
both ports arriving on PF0 root flowtable, so we will be able to catch
all raw-eth traffic on PF0.
2) Creation of LAG demux flowtable in order to direct all non-raw-eth
traffic back to its source port, assuring that normal Ethernet
traffic "jumps" to the root flowtable of its RX port (non-LAG behavior).

Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

2 files changed, 50 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index ed038b7a96fc..70e7c8dcd4e0 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2703,6 +2703,47 @@ static void get_dev_fw_str(struct ib_device *ibdev, char *str,
                        fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
 }
 
+static int mlx5_roce_lag_init(struct mlx5_ib_dev *dev)
+{
+        struct mlx5_core_dev *mdev = dev->mdev;
+        struct mlx5_flow_namespace *ns = mlx5_get_flow_namespace(mdev,
+                                                                 MLX5_FLOW_NAMESPACE_LAG);
+        struct mlx5_flow_table *ft;
+        int err;
+
+        if (!ns || !mlx5_lag_is_active(mdev))
+                return 0;
+
+        err = mlx5_cmd_create_vport_lag(mdev);
+        if (err)
+                return err;
+
+        ft = mlx5_create_lag_demux_flow_table(ns, 0, 0);
+        if (IS_ERR(ft)) {
+                err = PTR_ERR(ft);
+                goto err_destroy_vport_lag;
+        }
+
+        dev->flow_db.lag_demux_ft = ft;
+        return 0;
+
+err_destroy_vport_lag:
+        mlx5_cmd_destroy_vport_lag(mdev);
+        return err;
+}
+
+static void mlx5_roce_lag_cleanup(struct mlx5_ib_dev *dev)
+{
+        struct mlx5_core_dev *mdev = dev->mdev;
+
+        if (dev->flow_db.lag_demux_ft) {
+                mlx5_destroy_flow_table(dev->flow_db.lag_demux_ft);
+                dev->flow_db.lag_demux_ft = NULL;
+
+                mlx5_cmd_destroy_vport_lag(mdev);
+        }
+}
+
 static void mlx5_remove_roce_notifier(struct mlx5_ib_dev *dev)
 {
         if (dev->roce.nb.notifier_call) {
@@ -2726,8 +2767,15 @@ static int mlx5_enable_roce(struct mlx5_ib_dev *dev)
         if (err)
                 goto err_unregister_netdevice_notifier;
 
+        err = mlx5_roce_lag_init(dev);
+        if (err)
+                goto err_disable_roce;
+
         return 0;
 
+err_disable_roce:
+        mlx5_nic_vport_disable_roce(dev->mdev);
+
 err_unregister_netdevice_notifier:
         mlx5_remove_roce_notifier(dev);
         return err;
@@ -2735,6 +2783,7 @@ err_unregister_netdevice_notifier:
 
 static void mlx5_disable_roce(struct mlx5_ib_dev *dev)
 {
+        mlx5_roce_lag_cleanup(dev);
         mlx5_nic_vport_disable_roce(dev->mdev);
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index f8a62a643613..53e1f1dc0000 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -158,6 +158,7 @@ struct mlx5_ib_flow_handler {
 struct mlx5_ib_flow_db {
         struct mlx5_ib_flow_prio        prios[MLX5_IB_NUM_FLOW_FT];
         struct mlx5_ib_flow_prio        sniffer[MLX5_IB_NUM_SNIFFER_FTS];
+        struct mlx5_flow_table          *lag_demux_ft;
         /* Protect flow steering bypass flow tables
          * when add/del flow rules.
          * only single add/removal of flow steering rule could be done