RDMA/mlx5: Add multiple priorities support to RDMA TRANSPORT userspace tables

Support the creation of RDMA TRANSPORT tables over multiple priorities
via matcher creation.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/bb38e50ae4504e979c6568d41939402a4cf15635.1750148083.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>

3 files changed, 33 insertions, 19 deletions

diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 680627f1de33..ebcc05f766e1 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -1966,7 +1966,8 @@ _get_flow_table(struct mlx5_ib_dev *dev, u16 user_priority,
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:
 	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:
-		if (ib_port == 0 || user_priority > MLX5_RDMA_TRANSPORT_BYPASS_PRIO)
+		if (ib_port == 0 ||
+		    user_priority >= MLX5_RDMA_TRANSPORT_BYPASS_PRIO)
 			return ERR_PTR(-EINVAL);
 		ret = mlx5_ib_fill_transport_ns_info(dev, ns_type, &flags,
 						     &vport_idx, &vport,
@@ -2016,10 +2017,10 @@ _get_flow_table(struct mlx5_ib_dev *dev, u16 user_priority,
 		prio = &dev->flow_db->rdma_tx[priority];
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:
-		prio = &dev->flow_db->rdma_transport_rx[ib_port - 1];
+		prio = &dev->flow_db->rdma_transport_rx[priority][ib_port - 1];
 		break;
 	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:
-		prio = &dev->flow_db->rdma_transport_tx[ib_port - 1];
+		prio = &dev->flow_db->rdma_transport_tx[priority][ib_port - 1];
 		break;
 	default: return ERR_PTR(-EINVAL);
 	}
@@ -3466,31 +3467,40 @@ static const struct ib_device_ops flow_ops = {
 
 int mlx5_ib_fs_init(struct mlx5_ib_dev *dev)
 {
+	int i, j;
+
 	dev->flow_db = kzalloc(sizeof(*dev->flow_db), GFP_KERNEL);
 
 	if (!dev->flow_db)
 		return -ENOMEM;
 
-	dev->flow_db->rdma_transport_rx = kcalloc(dev->num_ports,
-					sizeof(struct mlx5_ib_flow_prio),
-					GFP_KERNEL);
-	if (!dev->flow_db->rdma_transport_rx)
-		goto free_flow_db;
+	for (i = 0; i < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; i++) {
+		dev->flow_db->rdma_transport_rx[i] =
+			kcalloc(dev->num_ports,
+				sizeof(struct mlx5_ib_flow_prio), GFP_KERNEL);
+		if (!dev->flow_db->rdma_transport_rx[i])
+			goto free_rdma_transport_rx;
+	}
 
-	dev->flow_db->rdma_transport_tx = kcalloc(dev->num_ports,
-					sizeof(struct mlx5_ib_flow_prio),
-					GFP_KERNEL);
-	if (!dev->flow_db->rdma_transport_tx)
-		goto free_rdma_transport_rx;
+	for (j = 0; j < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; j++) {
+		dev->flow_db->rdma_transport_tx[j] =
+			kcalloc(dev->num_ports,
+				sizeof(struct mlx5_ib_flow_prio), GFP_KERNEL);
+		if (!dev->flow_db->rdma_transport_tx[j])
+			goto free_rdma_transport_tx;
+	}
 
 	mutex_init(&dev->flow_db->lock);
 
 	ib_set_device_ops(&dev->ib_dev, &flow_ops);
 	return 0;
 
+free_rdma_transport_tx:
+	while (j--)
+		kfree(dev->flow_db->rdma_transport_tx[j]);
 free_rdma_transport_rx:
-	kfree(dev->flow_db->rdma_transport_rx);
-free_flow_db:
+	while (i--)
+		kfree(dev->flow_db->rdma_transport_rx[i]);
 	kfree(dev->flow_db);
 	return -ENOMEM;
 }
diff --git a/drivers/infiniband/hw/mlx5/fs.h b/drivers/infiniband/hw/mlx5/fs.h
index 2ebe86e5be10..7abba0e2837c 100644
--- a/drivers/infiniband/hw/mlx5/fs.h
+++ b/drivers/infiniband/hw/mlx5/fs.h
@@ -13,6 +13,8 @@ void mlx5_ib_fs_cleanup_anchor(struct mlx5_ib_dev *dev);
 
 static inline void mlx5_ib_fs_cleanup(struct mlx5_ib_dev *dev)
 {
+	int i;
+
 	/* When a steering anchor is created, a special flow table is also
 	 * created for the user to reference. Since the user can reference it,
 	 * the kernel cannot trust that when the user destroys the steering
@@ -25,8 +27,10 @@ static inline void mlx5_ib_fs_cleanup(struct mlx5_ib_dev *dev)
 	 * is a safe assumption that all references are gone.
 	 */
 	mlx5_ib_fs_cleanup_anchor(dev);
-	kfree(dev->flow_db->rdma_transport_tx);
-	kfree(dev->flow_db->rdma_transport_rx);
+	for (i = 0; i < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; i++)
+		kfree(dev->flow_db->rdma_transport_tx[i]);
+	for (i = 0; i < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; i++)
+		kfree(dev->flow_db->rdma_transport_rx[i]);
 	kfree(dev->flow_db);
 }
 #endif /* _MLX5_IB_FS_H */
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 802633ccf9d9..a012e24d3afe 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -320,8 +320,8 @@ struct mlx5_ib_flow_db {
 	struct mlx5_ib_flow_prio	rdma_tx[MLX5_IB_NUM_FLOW_FT];
 	struct mlx5_ib_flow_prio	opfcs[MLX5_IB_OPCOUNTER_MAX];
 	struct mlx5_flow_table		*lag_demux_ft;
-	struct mlx5_ib_flow_prio        *rdma_transport_rx;
-	struct mlx5_ib_flow_prio        *rdma_transport_tx;
+	struct mlx5_ib_flow_prio        *rdma_transport_rx[MLX5_RDMA_TRANSPORT_BYPASS_PRIO];
+	struct mlx5_ib_flow_prio        *rdma_transport_tx[MLX5_RDMA_TRANSPORT_BYPASS_PRIO];
 	/* Protect flow steering bypass flow tables
 	 * when add/del flow rules.
 	 * only single add/removal of flow steering rule could be done