net/mlx5: Eswitch, enable RoCE loopback traffic

When in switchdev mode, we would like to treat loopback RoCE
traffic (on eswitch manager) as RDMA and not as regular
Ethernet traffic
In order to enable it we add flow steering rule that forward RoCE
loopback traffic to the HW RoCE filter (by adding allow rule).
In addition we add RoCE address in GID index 0, which will be
set in the RoCE loopback packet.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Acked-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 1a16f6d73cbc59a16294b124ceedb68f09796da9..5f0be9b36a04b6028377fe6e418792a1c517f6eb 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tu
 #
 # Core extra
 #
-mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 6c8a17ca236e88c6274076de98b672991924e54e..9a1598bca4d1282ee3ad4bf467c8d09f59578f66 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -37,6 +37,7 @@
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
 #include "eswitch.h"
+#include "rdma.h"
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
@@ -1713,6 +1714,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
                esw->host_info.num_vfs = vf_nvports;
        }
 
+       mlx5_rdma_enable_roce(esw->dev);
+
        return 0;
 
 err_reps:
@@ -1751,6 +1754,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
                num_vfs = esw->dev->priv.sriov.num_vfs;
        }
 
+       mlx5_rdma_disable_roce(esw->dev);
        esw_offloads_devcom_cleanup(esw);
        esw_offloads_unload_all_reps(esw, num_vfs);
        esw_offloads_steering_cleanup(esw);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
new file mode 100644 (file)
index 0000000..86f7745
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <linux/mlx5/vport.h>
+#include <rdma/ib_verbs.h>
+#include <net/addrconf.h>
+
+#include "lib/mlx5.h"
+#include "eswitch.h"
+#include "fs_core.h"
+#include "rdma.h"
+
+static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev)
+{
+       struct mlx5_core_roce *roce = &dev->priv.roce;
+
+       if (!roce->ft)
+               return;
+
+       mlx5_del_flow_rules(roce->allow_rule);
+       mlx5_destroy_flow_group(roce->fg);
+       mlx5_destroy_flow_table(roce->ft);
+}
+
+static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev)
+{
+       int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+       struct mlx5_core_roce *roce = &dev->priv.roce;
+       struct mlx5_flow_handle *flow_rule = NULL;
+       struct mlx5_flow_table_attr ft_attr = {};
+       struct mlx5_flow_namespace *ns = NULL;
+       struct mlx5_flow_act flow_act = {};
+       struct mlx5_flow_spec *spec;
+       struct mlx5_flow_table *ft;
+       struct mlx5_flow_group *fg;
+       void *match_criteria;
+       u32 *flow_group_in;
+       void *misc;
+       int err;
+
+       if (!(MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
+             MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)))
+               return -EOPNOTSUPP;
+
+       flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+       if (!flow_group_in)
+               return -ENOMEM;
+       spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+       if (!spec) {
+               kvfree(flow_group_in);
+               return -ENOMEM;
+       }
+
+       ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX);
+       if (!ns) {
+               mlx5_core_err(dev, "Failed to get RDMA RX namespace");
+               err = -EOPNOTSUPP;
+               goto free;
+       }
+
+       ft_attr.max_fte = 1;
+       ft = mlx5_create_flow_table(ns, &ft_attr);
+       if (IS_ERR(ft)) {
+               mlx5_core_err(dev, "Failed to create RDMA RX flow table");
+               err = PTR_ERR(ft);
+               goto free;
+       }
+
+       MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+                MLX5_MATCH_MISC_PARAMETERS);
+       match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+                                     match_criteria);
+       MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+                        misc_parameters.source_port);
+
+       fg = mlx5_create_flow_group(ft, flow_group_in);
+       if (IS_ERR(fg)) {
+               err = PTR_ERR(fg);
+               mlx5_core_err(dev, "Failed to create RDMA RX flow group err(%d)\n", err);
+               goto destroy_flow_table;
+       }
+
+       spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+       misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+                           misc_parameters);
+       MLX5_SET(fte_match_set_misc, misc, source_port,
+                dev->priv.eswitch->manager_vport);
+       misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+                           misc_parameters);
+       MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+       flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+       flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0);
+       if (IS_ERR(flow_rule)) {
+               err = PTR_ERR(flow_rule);
+               mlx5_core_err(dev, "Failed to add RoCE allow rule, err=%d\n",
+                             err);
+               goto destroy_flow_group;
+       }
+
+       kvfree(spec);
+       kvfree(flow_group_in);
+       roce->ft = ft;
+       roce->fg = fg;
+       roce->allow_rule = flow_rule;
+
+       return 0;
+
+destroy_flow_table:
+       mlx5_destroy_flow_table(ft);
+destroy_flow_group:
+       mlx5_destroy_flow_group(fg);
+free:
+       kvfree(spec);
+       kvfree(flow_group_in);
+       return err;
+}
+
+static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
+{
+       mlx5_core_roce_gid_set(dev, 0, 0, 0,
+                              NULL, NULL, false, 0, 0);
+}
+
+static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)
+{
+       u8 hw_id[ETH_ALEN];
+
+       mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
+       gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+       addrconf_addr_eui48(&gid->raw[8], hw_id);
+}
+
+static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
+{
+       union ib_gid gid;
+       u8 mac[ETH_ALEN];
+
+       mlx5_rdma_make_default_gid(dev, &gid);
+       return mlx5_core_roce_gid_set(dev, 0,
+                                     MLX5_ROCE_VERSION_1,
+                                     0, gid.raw, mac,
+                                     false, 0, 1);
+}
+
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
+{
+       mlx5_rdma_disable_roce_steering(dev);
+       mlx5_rdma_del_roce_addr(dev);
+       mlx5_nic_vport_disable_roce(dev);
+}
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+{
+       int err;
+
+       err = mlx5_nic_vport_enable_roce(dev);
+       if (err) {
+               mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
+               return;
+       }
+
+       err = mlx5_rdma_add_roce_addr(dev);
+       if (err) {
+               mlx5_core_err(dev, "Failed to add RoCE address: %d\n", err);
+               goto disable_roce;
+       }
+
+       err = mlx5_rdma_enable_roce_steering(dev);
+       if (err) {
+               mlx5_core_err(dev, "Failed to enable RoCE steering: %d\n", err);
+               goto del_roce_addr;
+       }
+
+       return;
+
+del_roce_addr:
+       mlx5_rdma_del_roce_addr(dev);
+disable_roce:
+       mlx5_nic_vport_disable_roce(dev);
+       return;
+}

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
new file mode 100644 (file)
index 0000000..750cff2
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_RDMA_H__
+#define __MLX5_RDMA_H__
+
+#include "mlx5_core.h"
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
+
+#else /* CONFIG_MLX5_ESWITCH */
+
+static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_RDMA_H__ */

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 582a9680b182f06377551a5db279b18883ae1678..7fa95270dd5978aea8d6391a2b0c3096c2df9cc0 100644 (file)
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -512,6 +512,12 @@ struct mlx5_rl_table {
        struct mlx5_rl_entry   *rl_entry;
 };
 
+struct mlx5_core_roce {
+       struct mlx5_flow_table *ft;
+       struct mlx5_flow_group *fg;
+       struct mlx5_flow_handle *allow_rule;
+};
+
 struct mlx5_priv {
        struct mlx5_eq_table    *eq_table;
 
@@ -565,6 +571,7 @@ struct mlx5_priv {
        struct mlx5_lag         *lag;
        struct mlx5_devcom      *devcom;
        unsigned long           pci_dev_data;
+       struct mlx5_core_roce   roce;
        struct mlx5_fc_stats            fc_stats;
        struct mlx5_rl_table            rl_table;