Commit 4a561817 authored by Roi Dayan's avatar Roi Dayan Committed by Saeed Mahameed
Browse files

net/mlx5: E-Switch, Split creating fdb tables into smaller chunks 



Split esw_create_offloads_fdb_tables() into smaller functions.
This will help maintenance.

Signed-off-by: default avatarRoi Dayan <roid@nvidia.com>
Reviewed-by: default avatarMark Bloch <mbloch@nvidia.com>
Reviewed-by: default avatarMaor Dickman <maord@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
parent 8ea7bcf6

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

+206 −124
Original line number Diff line number Diff line
@@ -1669,93 +1669,19 @@ esw_chains_destroy(struct mlx5_eswitch *esw, struct mlx5_fs_chains *chains) 


#endif



static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)

static int

esw_create_send_to_vport_group(struct mlx5_eswitch *esw,

			       struct mlx5_flow_table *fdb,

			       u32 *flow_group_in,

			       int *ix)

{

	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);

	struct mlx5_flow_table_attr ft_attr = {};

	int num_vfs, table_size, ix, err = 0;

	struct mlx5_core_dev *dev = esw->dev;

	struct mlx5_flow_namespace *root_ns;

	struct mlx5_flow_table *fdb = NULL;

	u32 flags = 0, *flow_group_in;

	struct mlx5_flow_group *g;

	void *match_criteria;

	u8 *dmac;



	esw_debug(esw->dev, "Create offloads FDB Tables\n");



	flow_group_in = kvzalloc(inlen, GFP_KERNEL);

	if (!flow_group_in)

		return -ENOMEM;



	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);

	if (!root_ns) {

		esw_warn(dev, "Failed to get FDB flow namespace\n");

		err = -EOPNOTSUPP;

		goto ns_err;

	}

	esw->fdb_table.offloads.ns = root_ns;

	err = mlx5_flow_namespace_set_mode(root_ns,

					   esw->dev->priv.steering->mode);

	if (err) {

		esw_warn(dev, "Failed to set FDB namespace steering mode\n");

		goto ns_err;

	}



	/* To be strictly correct:

	 *	MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ)

	 * should be:

	 *	esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ +

	 *	peer_esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ

	 * but as the peer device might not be in switchdev mode it's not

	 * possible. We use the fact that by default FW sets max vfs and max sfs

	 * to the same value on both devices. If it needs to be changed in the future note

	 * the peer miss group should also be created based on the number of

	 * total vports of the peer (currently is also uses esw->total_vports).

	 */

	table_size = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ) +

		MLX5_ESW_MISS_FLOWS + esw->total_vports + esw->esw_funcs.num_vfs;



	/* create the slow path fdb with encap set, so further table instances

	 * can be created at run time while VFs are probed if the FW allows that.

	 */

	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)

		flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |

			  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);



	ft_attr.flags = flags;

	ft_attr.max_fte = table_size;

	ft_attr.prio = FDB_SLOW_PATH;



	fdb = mlx5_create_flow_table(root_ns, &ft_attr);

	if (IS_ERR(fdb)) {

		err = PTR_ERR(fdb);

		esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err);

		goto slow_fdb_err;

	}

	esw->fdb_table.offloads.slow_fdb = fdb;



	/* Create empty TC-miss managed table. This allows plugging in following

	 * priorities without directly exposing their level 0 table to

	 * eswitch_offloads and passing it as miss_fdb to following call to

	 * esw_chains_create().

	 */

	memset(&ft_attr, 0, sizeof(ft_attr));

	ft_attr.prio = FDB_TC_MISS;

	esw->fdb_table.offloads.tc_miss_table = mlx5_create_flow_table(root_ns, &ft_attr);

	if (IS_ERR(esw->fdb_table.offloads.tc_miss_table)) {

		err = PTR_ERR(esw->fdb_table.offloads.tc_miss_table);

		esw_warn(dev, "Failed to create TC miss FDB Table err %d\n", err);

		goto tc_miss_table_err;

	}

	int count, err = 0;



	err = esw_chains_create(esw, esw->fdb_table.offloads.tc_miss_table);

	if (err) {

		esw_warn(dev, "Failed to open fdb chains err(%d)\n", err);

		goto fdb_chains_err;

	}

	memset(flow_group_in, 0, inlen);



	/* create send-to-vport group */

	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,

		 MLX5_MATCH_MISC_PARAMETERS);
@@ -1770,22 +1696,41 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) 
			 source_eswitch_owner_vhca_id_valid, 1);

	}



	/* See comment above table_size calculation */

	ix = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ);

	/* See comment at table_size calculation */

	count = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ);

	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);

	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1);

	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, *ix + count - 1);

	*ix += count;



	g = mlx5_create_flow_group(fdb, flow_group_in);

	if (IS_ERR(g)) {

		err = PTR_ERR(g);

		esw_warn(dev, "Failed to create send-to-vport flow group err(%d)\n", err);

		goto send_vport_err;

		esw_warn(esw->dev, "Failed to create send-to-vport flow group err(%d)\n", err);

		goto out;

	}

	esw->fdb_table.offloads.send_to_vport_grp = g;



	if (esw_src_port_rewrite_supported(esw)) {

		/* meta send to vport */

out:

	return err;

}



static int

esw_create_meta_send_to_vport_group(struct mlx5_eswitch *esw,

				    struct mlx5_flow_table *fdb,

				    u32 *flow_group_in,

				    int *ix)

{

	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);

	int num_vfs = esw->esw_funcs.num_vfs;

	struct mlx5_flow_group *g;

	void *match_criteria;

	int err = 0;



	if (!esw_src_port_rewrite_supported(esw))

		return 0;



	memset(flow_group_in, 0, inlen);



	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,

		 MLX5_MATCH_MISC_PARAMETERS_2);
@@ -1797,18 +1742,17 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) 
	MLX5_SET(fte_match_param, match_criteria,

		 misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK);



		num_vfs = esw->esw_funcs.num_vfs;

	if (num_vfs) {

			MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);

		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, *ix);

		MLX5_SET(create_flow_group_in, flow_group_in,

				 end_flow_index, ix + num_vfs - 1);

			ix += num_vfs;

			 end_flow_index, *ix + num_vfs - 1);

		*ix += num_vfs;



		g = mlx5_create_flow_group(fdb, flow_group_in);

		if (IS_ERR(g)) {

			err = PTR_ERR(g);

				esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n",

					 err);

			esw_warn(esw->dev,

				 "Failed to create send-to-vport meta flow group err(%d)\n", err);

			goto send_vport_meta_err;

		}

		esw->fdb_table.offloads.send_to_vport_meta_grp = g;
@@ -1817,10 +1761,29 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) 
		if (err)

			goto meta_rule_err;

	}



	return 0;



meta_rule_err:

	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_meta_grp);

send_vport_meta_err:

	return err;

}



	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {

		/* create peer esw miss group */

static int

esw_create_peer_esw_miss_group(struct mlx5_eswitch *esw,

			       struct mlx5_flow_table *fdb,

			       u32 *flow_group_in,

			       int *ix)

{

	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);

	struct mlx5_flow_group *g;

	void *match_criteria;

	int err = 0;



	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))

		return 0;



	memset(flow_group_in, 0, inlen);



	esw_set_flow_group_source_port(esw, flow_group_in);
@@ -1837,22 +1800,37 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) 
			 source_eswitch_owner_vhca_id_valid, 1);

	}



		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);

	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, *ix);

	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,

			 ix + esw->total_vports - 1);

		ix += esw->total_vports;

		 *ix + esw->total_vports - 1);

	*ix += esw->total_vports;



	g = mlx5_create_flow_group(fdb, flow_group_in);

	if (IS_ERR(g)) {

		err = PTR_ERR(g);

			esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);

			goto peer_miss_err;

		esw_warn(esw->dev, "Failed to create peer miss flow group err(%d)\n", err);

		goto out;

	}

	esw->fdb_table.offloads.peer_miss_grp = g;



out:

	return err;

}



	/* create miss group */

static int

esw_create_miss_group(struct mlx5_eswitch *esw,

		      struct mlx5_flow_table *fdb,

		      u32 *flow_group_in,

		      int *ix)

{

	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);

	struct mlx5_flow_group *g;

	void *match_criteria;

	int err = 0;

	u8 *dmac;



	memset(flow_group_in, 0, inlen);



	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,

		 MLX5_MATCH_OUTER_HEADERS);

	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
@@ -1861,14 +1839,14 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) 
			    outer_headers.dmac_47_16);

	dmac[0] = 0x01;



	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);

	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, *ix);

	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,

		 ix + MLX5_ESW_MISS_FLOWS);

		 *ix + MLX5_ESW_MISS_FLOWS);



	g = mlx5_create_flow_group(fdb, flow_group_in);

	if (IS_ERR(g)) {

		err = PTR_ERR(g);

		esw_warn(dev, "Failed to create miss flow group err(%d)\n", err);

		esw_warn(esw->dev, "Failed to create miss flow group err(%d)\n", err);

		goto miss_err;

	}

	esw->fdb_table.offloads.miss_grp = g;
@@ -1877,17 +1855,121 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) 
	if (err)

		goto miss_rule_err;



	kvfree(flow_group_in);

	return 0;



miss_rule_err:

	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);

miss_err:

	return err;

}



static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)

{

	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);

	struct mlx5_flow_table_attr ft_attr = {};

	struct mlx5_core_dev *dev = esw->dev;

	struct mlx5_flow_namespace *root_ns;

	struct mlx5_flow_table *fdb = NULL;

	int table_size, ix = 0, err = 0;

	u32 flags = 0, *flow_group_in;



	esw_debug(esw->dev, "Create offloads FDB Tables\n");



	flow_group_in = kvzalloc(inlen, GFP_KERNEL);

	if (!flow_group_in)

		return -ENOMEM;



	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);

	if (!root_ns) {

		esw_warn(dev, "Failed to get FDB flow namespace\n");

		err = -EOPNOTSUPP;

		goto ns_err;

	}

	esw->fdb_table.offloads.ns = root_ns;

	err = mlx5_flow_namespace_set_mode(root_ns,

					   esw->dev->priv.steering->mode);

	if (err) {

		esw_warn(dev, "Failed to set FDB namespace steering mode\n");

		goto ns_err;

	}



	/* To be strictly correct:

	 *	MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ)

	 * should be:

	 *	esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ +

	 *	peer_esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ

	 * but as the peer device might not be in switchdev mode it's not

	 * possible. We use the fact that by default FW sets max vfs and max sfs

	 * to the same value on both devices. If it needs to be changed in the future note

	 * the peer miss group should also be created based on the number of

	 * total vports of the peer (currently is also uses esw->total_vports).

	 */

	table_size = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ) +

		     MLX5_ESW_MISS_FLOWS + esw->total_vports + esw->esw_funcs.num_vfs;



	/* create the slow path fdb with encap set, so further table instances

	 * can be created at run time while VFs are probed if the FW allows that.

	 */

	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)

		flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |

			  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);



	ft_attr.flags = flags;

	ft_attr.max_fte = table_size;

	ft_attr.prio = FDB_SLOW_PATH;



	fdb = mlx5_create_flow_table(root_ns, &ft_attr);

	if (IS_ERR(fdb)) {

		err = PTR_ERR(fdb);

		esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err);

		goto slow_fdb_err;

	}

	esw->fdb_table.offloads.slow_fdb = fdb;



	/* Create empty TC-miss managed table. This allows plugging in following

	 * priorities without directly exposing their level 0 table to

	 * eswitch_offloads and passing it as miss_fdb to following call to

	 * esw_chains_create().

	 */

	memset(&ft_attr, 0, sizeof(ft_attr));

	ft_attr.prio = FDB_TC_MISS;

	esw->fdb_table.offloads.tc_miss_table = mlx5_create_flow_table(root_ns, &ft_attr);

	if (IS_ERR(esw->fdb_table.offloads.tc_miss_table)) {

		err = PTR_ERR(esw->fdb_table.offloads.tc_miss_table);

		esw_warn(dev, "Failed to create TC miss FDB Table err %d\n", err);

		goto tc_miss_table_err;

	}



	err = esw_chains_create(esw, esw->fdb_table.offloads.tc_miss_table);

	if (err) {

		esw_warn(dev, "Failed to open fdb chains err(%d)\n", err);

		goto fdb_chains_err;

	}



	err = esw_create_send_to_vport_group(esw, fdb, flow_group_in, &ix);

	if (err)

		goto send_vport_err;



	err = esw_create_meta_send_to_vport_group(esw, fdb, flow_group_in, &ix);

	if (err)

		goto send_vport_meta_err;



	err = esw_create_peer_esw_miss_group(esw, fdb, flow_group_in, &ix);

	if (err)

		goto peer_miss_err;



	err = esw_create_miss_group(esw, fdb, flow_group_in, &ix);

	if (err)

		goto miss_err;



	kvfree(flow_group_in);

	return 0;



miss_err:

	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))

		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);

peer_miss_err:

	mlx5_eswitch_del_send_to_vport_meta_rules(esw);

meta_rule_err:

	if (esw->fdb_table.offloads.send_to_vport_meta_grp)

		mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_meta_grp);

send_vport_meta_err: