Commit 15b103df authored by Patrisious Haddad's avatar Patrisious Haddad Committed by Leon Romanovsky
Browse files

net/mlx5: fs, add RDMA TRANSPORT steering domain support 



Add RX and TX RDMA_TRANSPORT flow table namespace, and the ability
to create flow tables in those namespaces.

The RDMA_TRANSPORT RX and TX are per vport.

Packets will traverse through RDMA_TRANSPORT_RX after RDMA_RX and through
RDMA_TRANSPORT_TX before RDMA_TX, ensuring proper control and management.

RDMA_TRANSPORT domains are managed by the vport group manager.

Signed-off-by: default avatarPatrisious Haddad <phaddad@nvidia.com>
Reviewed-by: default avatarMark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/a6b550d9859a197eafa804b9a8d76916ca481da9.1740574103.git.leon@kernel.org


Signed-off-by: default avatarLeon Romanovsky <leon@kernel.org>
parent ab7d228c

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c

+1 −1
Original line number Diff line number Diff line
@@ -27,7 +27,7 @@ esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns, 
	esw_debug(dev, "Create vport[%d] %s ACL table\n", vport_num,

		  ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress");



	root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport->index);

	root_ns = mlx5_get_flow_vport_namespace(dev, ns, vport->index);

	if (!root_ns) {

		esw_warn(dev, "Failed to get E-Switch root namespace for vport (%d)\n",

			 vport_num);

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

+3 −3
Original line number Diff line number Diff line
@@ -2828,7 +2828,7 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master, 
	if (IS_ERR(vport))

		return PTR_ERR(vport);



	egress_ns = mlx5_get_flow_vport_acl_namespace(master,

	egress_ns = mlx5_get_flow_vport_namespace(master,

						  MLX5_FLOW_NAMESPACE_ESW_EGRESS,

						  vport->index);

	if (!egress_ns)

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

+2 −0
Original line number Diff line number Diff line
@@ -1142,6 +1142,8 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ 
	case FS_FT_RDMA_RX:

	case FS_FT_RDMA_TX:

	case FS_FT_PORT_SEL:

	case FS_FT_RDMA_TRANSPORT_RX:

	case FS_FT_RDMA_TRANSPORT_TX:

		return mlx5_fs_cmd_get_fw_cmds();

	default:

		return mlx5_fs_cmd_get_stub_cmds();

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

+166 −12
Original line number Diff line number Diff line
@@ -1456,7 +1456,7 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, 
	struct mlx5_flow_table *ft;

	int autogroups_max_fte;



	ft = mlx5_create_flow_table(ns, ft_attr);

	ft = mlx5_create_vport_flow_table(ns, ft_attr, ft_attr->vport);

	if (IS_ERR(ft))

		return ft;
@@ -2764,9 +2764,9 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, 
}

EXPORT_SYMBOL(mlx5_get_flow_namespace);



struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev,

							      enum mlx5_flow_namespace_type type,

							      int vport)

struct mlx5_flow_namespace *

mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev,

			      enum mlx5_flow_namespace_type type, int vport_idx)

{

	struct mlx5_flow_steering *steering = dev->priv.steering;
@@ -2775,25 +2775,43 @@ struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_d 


	switch (type) {

	case MLX5_FLOW_NAMESPACE_ESW_EGRESS:

		if (vport >= steering->esw_egress_acl_vports)

		if (vport_idx >= steering->esw_egress_acl_vports)

			return NULL;

		if (steering->esw_egress_root_ns &&

		    steering->esw_egress_root_ns[vport])

			return &steering->esw_egress_root_ns[vport]->ns;

		    steering->esw_egress_root_ns[vport_idx])

			return &steering->esw_egress_root_ns[vport_idx]->ns;

		else

			return NULL;

	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:

		if (vport >= steering->esw_ingress_acl_vports)

		if (vport_idx >= steering->esw_ingress_acl_vports)

			return NULL;

		if (steering->esw_ingress_root_ns &&

		    steering->esw_ingress_root_ns[vport])

			return &steering->esw_ingress_root_ns[vport]->ns;

		    steering->esw_ingress_root_ns[vport_idx])

			return &steering->esw_ingress_root_ns[vport_idx]->ns;

		else

			return NULL;

	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:

		if (vport_idx >= steering->rdma_transport_rx_vports)

			return NULL;

		if (steering->rdma_transport_rx_root_ns &&

		    steering->rdma_transport_rx_root_ns[vport_idx])

			return &steering->rdma_transport_rx_root_ns[vport_idx]->ns;

		else

			return NULL;

	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:

		if (vport_idx >= steering->rdma_transport_tx_vports)

			return NULL;



		if (steering->rdma_transport_tx_root_ns &&

		    steering->rdma_transport_tx_root_ns[vport_idx])

			return &steering->rdma_transport_tx_root_ns[vport_idx]->ns;

		else

			return NULL;

	default:

		return NULL;

	}

}

EXPORT_SYMBOL(mlx5_get_flow_vport_namespace);



static struct fs_prio *_fs_create_prio(struct mlx5_flow_namespace *ns,

				       unsigned int prio,
@@ -3199,6 +3217,127 @@ static int init_rdma_tx_root_ns(struct mlx5_flow_steering *steering) 
	return err;

}



static int

init_rdma_transport_rx_root_ns_one(struct mlx5_flow_steering *steering,

				   int vport_idx)

{

	struct fs_prio *prio;



	steering->rdma_transport_rx_root_ns[vport_idx] =

		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_RX);

	if (!steering->rdma_transport_rx_root_ns[vport_idx])

		return -ENOMEM;



	/* create 1 prio*/

	prio = fs_create_prio(&steering->rdma_transport_rx_root_ns[vport_idx]->ns,

			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);

	return PTR_ERR_OR_ZERO(prio);

}



static int

init_rdma_transport_tx_root_ns_one(struct mlx5_flow_steering *steering,

				   int vport_idx)

{

	struct fs_prio *prio;



	steering->rdma_transport_tx_root_ns[vport_idx] =

		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_TX);

	if (!steering->rdma_transport_tx_root_ns[vport_idx])

		return -ENOMEM;



	/* create 1 prio*/

	prio = fs_create_prio(&steering->rdma_transport_tx_root_ns[vport_idx]->ns,

			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);

	return PTR_ERR_OR_ZERO(prio);

}



static int init_rdma_transport_rx_root_ns(struct mlx5_flow_steering *steering)

{

	struct mlx5_core_dev *dev = steering->dev;

	int total_vports;

	int err;

	int i;



	/* In case eswitch not supported and working in legacy mode */

	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;



	steering->rdma_transport_rx_root_ns =

			kcalloc(total_vports,

				sizeof(*steering->rdma_transport_rx_root_ns),

				GFP_KERNEL);

	if (!steering->rdma_transport_rx_root_ns)

		return -ENOMEM;



	for (i = 0; i < total_vports; i++) {

		err = init_rdma_transport_rx_root_ns_one(steering, i);

		if (err)

			goto cleanup_root_ns;

	}

	steering->rdma_transport_rx_vports = total_vports;

	return 0;



cleanup_root_ns:

	while (i--)

		cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);

	kfree(steering->rdma_transport_rx_root_ns);

	steering->rdma_transport_rx_root_ns = NULL;

	return err;

}



static int init_rdma_transport_tx_root_ns(struct mlx5_flow_steering *steering)

{

	struct mlx5_core_dev *dev = steering->dev;

	int total_vports;

	int err;

	int i;



	/* In case eswitch not supported and working in legacy mode */

	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;



	steering->rdma_transport_tx_root_ns =

			kcalloc(total_vports,

				sizeof(*steering->rdma_transport_tx_root_ns),

				GFP_KERNEL);

	if (!steering->rdma_transport_tx_root_ns)

		return -ENOMEM;



	for (i = 0; i < total_vports; i++) {

		err = init_rdma_transport_tx_root_ns_one(steering, i);

		if (err)

			goto cleanup_root_ns;

	}

	steering->rdma_transport_tx_vports = total_vports;

	return 0;



cleanup_root_ns:

	while (i--)

		cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);

	kfree(steering->rdma_transport_tx_root_ns);

	steering->rdma_transport_tx_root_ns = NULL;

	return err;

}



static void cleanup_rdma_transport_roots_ns(struct mlx5_flow_steering *steering)

{

	int i;



	if (steering->rdma_transport_rx_root_ns) {

		for (i = 0; i < steering->rdma_transport_rx_vports; i++)

			cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);



		kfree(steering->rdma_transport_rx_root_ns);

		steering->rdma_transport_rx_root_ns = NULL;

	}



	if (steering->rdma_transport_tx_root_ns) {

		for (i = 0; i < steering->rdma_transport_tx_vports; i++)

			cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);



		kfree(steering->rdma_transport_tx_root_ns);

		steering->rdma_transport_tx_root_ns = NULL;

	}

}



/* FT and tc chains are stored in the same array so we can re-use the

 * mlx5_get_fdb_sub_ns() and tc api for FT chains.

 * When creating a new ns for each chain store it in the first available slot.
@@ -3631,6 +3770,7 @@ void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev) 
	cleanup_root_ns(steering->rdma_rx_root_ns);

	cleanup_root_ns(steering->rdma_tx_root_ns);

	cleanup_root_ns(steering->egress_root_ns);

	cleanup_rdma_transport_roots_ns(steering);



	devl_params_unregister(priv_to_devlink(dev), mlx5_fs_params,

			       ARRAY_SIZE(mlx5_fs_params));
@@ -3700,6 +3840,18 @@ int mlx5_fs_core_init(struct mlx5_core_dev *dev) 
			goto err;

	}



	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(dev, ft_support)) {

		err = init_rdma_transport_rx_root_ns(steering);

		if (err)

			goto err;

	}



	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(dev, ft_support)) {

		err = init_rdma_transport_tx_root_ns(steering);

		if (err)

			goto err;

	}



	return 0;



err:
@@ -3850,8 +4002,10 @@ mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type 
	struct mlx5_flow_namespace *ns;



	if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS ||

	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS)

		ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0);

	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS ||

	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX ||

	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX)

		ns = mlx5_get_flow_vport_namespace(dev, ns_type, 0);

	else

		ns = mlx5_get_flow_namespace(dev, ns_type);

	if (!ns)

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

+10 −2
Original line number Diff line number Diff line
@@ -115,7 +115,9 @@ enum fs_flow_table_type { 
	FS_FT_PORT_SEL		= 0X9,

	FS_FT_FDB_RX		= 0xa,

	FS_FT_FDB_TX		= 0xb,

	FS_FT_MAX_TYPE = FS_FT_FDB_TX,

	FS_FT_RDMA_TRANSPORT_RX	= 0xd,

	FS_FT_RDMA_TRANSPORT_TX	= 0xe,

	FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX,

};



enum fs_flow_table_op_mod {
@@ -158,6 +160,10 @@ struct mlx5_flow_steering { 
	struct mlx5_flow_root_namespace	*port_sel_root_ns;

	int esw_egress_acl_vports;

	int esw_ingress_acl_vports;

	struct mlx5_flow_root_namespace **rdma_transport_rx_root_ns;

	struct mlx5_flow_root_namespace **rdma_transport_tx_root_ns;

	int rdma_transport_rx_vports;

	int rdma_transport_tx_vports;

};



struct fs_node {
@@ -434,7 +440,9 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node); 
	(type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) :      \

	(type == FS_FT_FDB_RX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \

	(type == FS_FT_FDB_TX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \

	(BUILD_BUG_ON_ZERO(FS_FT_FDB_TX != FS_FT_MAX_TYPE))\

	(type == FS_FT_RDMA_TRANSPORT_RX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) :      \

	(type == FS_FT_RDMA_TRANSPORT_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) :      \

	(BUILD_BUG_ON_ZERO(FS_FT_RDMA_TRANSPORT_TX != FS_FT_MAX_TYPE))\

	)



#endif