net/mlx5: LAG, factor out shared FDB code into dedicated file

Refactor shared FDB LAG logic into a new lag/shared_fdb.c file to
improve code organization and enable reuse. Move shared FDB specific
functions from lag.c and introduce consolidated APIs:
- mlx5_lag_shared_fdb_create() handles LAG activation with shared FDB
- mlx5_lag_shared_fdb_destroy() handles LAG deactivation with shared FDB

Update mlx5_do_bond(), mlx5_disable_lag() and mpesw.c to use the new
APIs, which simplifies the shared FDB code paths.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260531113954.395443-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d39fe9c4a87cd9dd95e686d1937ae772af6dd7af..19e50f0d55af3c204d281a4f999768793211444e 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -41,7 +41,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
 mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)     += lag/mp.o lag/port_sel.o lib/geneve.o lib/port_tun.o \
                                        en_rep.o en/rep/bond.o en/mod_hdr.o \
-                                       en/mapping.o lag/mpesw.o
+                                       en/mapping.o lag/mpesw.o lag/shared_fdb.o
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
                                        lib/fs_chains.o en/tc_tun.o \
                                        esw/indir_table.o en/tc_tun_encap.o \

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 22b7efea34b836464a5068c7030b50980b1fb903..5dfdd799828f1dcaf6ad2f48c8d0391d5023160d 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -817,43 +817,6 @@ char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)
        }
 }
 
-static int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev)
-{
-       int master_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
-       struct mlx5_eswitch *master_esw;
-       struct mlx5_core_dev *dev0;
-       int i, j;
-       int err;
-
-       if (master_idx < 0)
-               return -EINVAL;
-
-       dev0 = mlx5_lag_pf(ldev, master_idx)->dev;
-       master_esw = dev0->priv.eswitch;
-       mlx5_ldev_for_each(i, 0, ldev) {
-               struct mlx5_eswitch *slave_esw;
-
-               if (i == master_idx)
-                       continue;
-
-               slave_esw = mlx5_lag_pf(ldev, i)->dev->priv.eswitch;
-
-               err = mlx5_eswitch_offloads_single_fdb_add_one(master_esw,
-                                                              slave_esw, ldev->ports);
-               if (err)
-                       goto err;
-       }
-       return 0;
-err:
-       mlx5_ldev_for_each_reverse(j, i, 0, ldev) {
-               if (j == master_idx)
-                       continue;
-               mlx5_eswitch_offloads_single_fdb_del_one(master_esw,
-                                                        mlx5_lag_pf(ldev, j)->dev->priv.eswitch);
-       }
-       return err;
-}
-
 static int mlx5_create_lag(struct mlx5_lag *ldev,
                           struct lag_tracker *tracker,
                           enum mlx5_lag_mode mode,
@@ -1218,12 +1181,15 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
        if (idx < 0)
                return;
 
+       if (shared_fdb) {
+               mlx5_lag_shared_fdb_destroy(ldev);
+               return;
+       }
+
        dev0 = mlx5_lag_pf(ldev, idx)->dev;
        roce_lag = __mlx5_lag_is_roce(ldev);
 
-       if (shared_fdb) {
-               mlx5_lag_remove_devices(ldev);
-       } else if (roce_lag) {
+       if (roce_lag) {
                mlx5_lag_rescan_dev_locked(ldev, dev0, false);
                mlx5_ldev_for_each(i, 0, ldev) {
                        if (i == idx)
@@ -1236,49 +1202,8 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
        if (err)
                return;
 
-       if (shared_fdb || roce_lag)
+       if (roce_lag)
                mlx5_lag_add_devices(ldev);
-
-       if (shared_fdb)
-               mlx5_lag_reload_ib_reps_from_locked(ldev,
-                                                   MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV,
-                                                   true);
-}
-
-bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
-{
-       struct mlx5_core_dev *dev;
-       bool ret = false;
-       int idx;
-       int i;
-
-       idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
-       if (idx < 0)
-               return false;
-
-       mlx5_ldev_for_each(i, 0, ldev) {
-               if (i == idx)
-                       continue;
-               dev = mlx5_lag_pf(ldev, i)->dev;
-               if (is_mdev_switchdev_mode(dev) &&
-                   mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) &&
-                   MLX5_CAP_GEN(dev, lag_native_fdb_selection) &&
-                   MLX5_CAP_ESW(dev, root_ft_on_other_esw) &&
-                   mlx5_eswitch_get_npeers(dev->priv.eswitch) ==
-                   MLX5_CAP_GEN(dev, num_lag_ports) - 1)
-                       continue;
-               return false;
-       }
-
-       dev = mlx5_lag_pf(ldev, idx)->dev;
-       if (is_mdev_switchdev_mode(dev) &&
-           mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) &&
-           mlx5_esw_offloads_devcom_is_ready(dev->priv.eswitch) &&
-           MLX5_CAP_ESW(dev, esw_shared_ingress_acl) &&
-           mlx5_eswitch_get_npeers(dev->priv.eswitch) == MLX5_CAP_GEN(dev, num_lag_ports) - 1)
-               ret = true;
-
-       return ret;
 }
 
 static bool mlx5_lag_is_roce_lag(struct mlx5_lag *ldev)
@@ -1493,47 +1418,37 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 
                roce_lag = mlx5_lag_is_roce_lag(ldev);
 
-               if (shared_fdb || roce_lag)
-                       mlx5_lag_remove_devices(ldev);
-
-               err = mlx5_activate_lag(ldev, &tracker,
-                                       roce_lag ? MLX5_LAG_MODE_ROCE :
-                                                  MLX5_LAG_MODE_SRIOV,
-                                       shared_fdb);
-               if (err) {
-                       if (shared_fdb || roce_lag)
-                               mlx5_lag_add_devices(ldev);
-                       if (shared_fdb)
-                               mlx5_lag_reload_ib_reps_from_locked(ldev, 0,
-                                                                   true);
-
-                       return;
-               }
+               if (shared_fdb) {
+                       err = mlx5_lag_shared_fdb_create(ldev, &tracker,
+                                                        MLX5_LAG_MODE_SRIOV);
+                       if (err)
+                               return;
+               } else {
+                       if (roce_lag)
+                               mlx5_lag_remove_devices(ldev);
 
-               if (roce_lag) {
-                       struct mlx5_core_dev *dev;
-
-                       mlx5_lag_rescan_dev_locked(ldev, dev0, true);
-                       mlx5_ldev_for_each(i, 0, ldev) {
-                               if (i == idx)
-                                       continue;
-                               dev = mlx5_lag_pf(ldev, i)->dev;
-                               if (mlx5_get_roce_state(dev))
-                                       mlx5_nic_vport_enable_roce(dev);
-                       }
-               } else if (shared_fdb) {
-                       mlx5_lag_rescan_dev_locked(ldev, dev0, true);
-                       err = mlx5_lag_reload_ib_reps_from_locked(ldev, 0,
-                                                                 false);
+                       err = mlx5_activate_lag(ldev, &tracker,
+                                               roce_lag ? MLX5_LAG_MODE_ROCE :
+                                                          MLX5_LAG_MODE_SRIOV,
+                                               false);
                        if (err) {
-                               mlx5_lag_rescan_dev_locked(ldev, dev0, false);
-                               mlx5_deactivate_lag(ldev);
-                               mlx5_lag_add_devices(ldev);
-                               mlx5_lag_reload_ib_reps_from_locked(ldev, 0,
-                                                                   true);
-                               mlx5_core_err(dev0, "Failed to enable lag\n");
+                               if (roce_lag)
+                                       mlx5_lag_add_devices(ldev);
                                return;
                        }
+
+                       if (roce_lag) {
+                               struct mlx5_core_dev *dev;
+
+                               mlx5_lag_rescan_dev_locked(ldev, dev0, true);
+                               mlx5_ldev_for_each(i, 0, ldev) {
+                                       if (i == idx)
+                                               continue;
+                                       dev = mlx5_lag_pf(ldev, i)->dev;
+                                       if (mlx5_get_roce_state(dev))
+                                               mlx5_nic_vport_enable_roce(dev);
+                               }
+                       }
                }
                if (tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
                        ndev = mlx5_lag_active_backup_get_netdev(dev0);
@@ -1545,7 +1460,8 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
                                                     ndev);
                        dev_put(ndev);
                }
-               mlx5_lag_set_vports_agg_speed(ldev);
+               if (!shared_fdb)
+                       mlx5_lag_set_vports_agg_speed(ldev);
        } else if (mlx5_lag_should_modify_lag(ldev, do_bond)) {
                mlx5_modify_lag(ldev, &tracker);
                mlx5_lag_set_vports_agg_speed(ldev);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 6afe7707d076ef03f3d34770080c47c8275fa43a..23c0457ce79933330307a672a35639f263e15701 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -137,7 +137,33 @@ mlx5_lag_is_ready(struct mlx5_lag *ldev)
        return test_bit(MLX5_LAG_FLAG_NDEVS_READY, &ldev->state_flags);
 }
 
+#ifdef CONFIG_MLX5_ESWITCH
+int mlx5_lag_shared_fdb_create(struct mlx5_lag *ldev,
+                              struct lag_tracker *tracker,
+                              enum mlx5_lag_mode mode);
+void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev);
+int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev);
 bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev);
+#else
+static inline int mlx5_lag_shared_fdb_create(struct mlx5_lag *ldev,
+                                            struct lag_tracker *tracker,
+                                            enum mlx5_lag_mode mode)
+{
+       return -EOPNOTSUPP;
+}
+
+static inline void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev) {}
+
+static inline int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev)
+{
+       return -EOPNOTSUPP;
+}
+
+static inline bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
+{
+       return false;
+}
+#endif
 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev);
 int mlx5_lag_demux_init(struct mlx5_core_dev *dev,
                        struct mlx5_flow_table_attr *ft_attr);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 8a349f8fd82335d73bd583c2fade7d5c45e35258..64e2d1dd5308734349423fc3bdbe82e559066818 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -92,38 +92,21 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
        if (err)
                return err;
 
-       mlx5_lag_remove_devices(ldev);
-
-       err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, true);
+       err = mlx5_lag_shared_fdb_create(ldev, NULL, MLX5_LAG_MODE_MPESW);
        if (err) {
                mlx5_core_warn(dev0, "Failed to create LAG in MPESW mode (%d)\n", err);
-               goto err_add_devices;
+               mlx5_mpesw_metadata_cleanup(ldev);
+               return err;
        }
 
-       mlx5_lag_rescan_dev_locked(ldev, dev0, true);
-       err = mlx5_lag_reload_ib_reps_from_locked(ldev, 0, false);
-       if (err)
-               goto err_rescan_drivers;
-
-       mlx5_lag_set_vports_agg_speed(ldev);
-
        return 0;
-
-err_rescan_drivers:
-       mlx5_lag_rescan_dev_locked(ldev, dev0, false);
-       mlx5_deactivate_lag(ldev);
-err_add_devices:
-       mlx5_lag_add_devices(ldev);
-       mlx5_lag_reload_ib_reps_from_locked(ldev, 0, true);
-       mlx5_mpesw_metadata_cleanup(ldev);
-       return err;
 }
 
 void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev)
 {
        if (ldev->mode == MLX5_LAG_MODE_MPESW) {
                mlx5_mpesw_metadata_cleanup(ldev);
-               mlx5_disable_lag(ldev);
+               mlx5_lag_shared_fdb_destroy(ldev);
        }
 }
 

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c
new file mode 100644 (file)
index 0000000..e5b8e9f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <linux/netdevice.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
+#include "mlx5_core.h"
+#include "lag.h"
+#include "eswitch.h"
+
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
+{
+       struct mlx5_core_dev *dev;
+       bool ret = false;
+       int idx;
+       int i;
+
+       idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+       if (idx < 0)
+               return false;
+
+       mlx5_ldev_for_each(i, 0, ldev) {
+               if (i == idx)
+                       continue;
+               dev = mlx5_lag_pf(ldev, i)->dev;
+               if (is_mdev_switchdev_mode(dev) &&
+                   mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) &&
+                   MLX5_CAP_GEN(dev, lag_native_fdb_selection) &&
+                   MLX5_CAP_ESW(dev, root_ft_on_other_esw) &&
+                   mlx5_eswitch_get_npeers(dev->priv.eswitch) ==
+                   MLX5_CAP_GEN(dev, num_lag_ports) - 1)
+                       continue;
+               return false;
+       }
+
+       dev = mlx5_lag_pf(ldev, idx)->dev;
+       if (is_mdev_switchdev_mode(dev) &&
+           mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) &&
+           mlx5_esw_offloads_devcom_is_ready(dev->priv.eswitch) &&
+           MLX5_CAP_ESW(dev, esw_shared_ingress_acl) &&
+           mlx5_eswitch_get_npeers(dev->priv.eswitch) ==
+           MLX5_CAP_GEN(dev, num_lag_ports) - 1)
+               ret = true;
+
+       return ret;
+}
+
+int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev)
+{
+       int master_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+       struct mlx5_eswitch *master_esw;
+       struct mlx5_core_dev *dev0;
+       int i, j;
+       int err;
+
+       if (master_idx < 0)
+               return -EINVAL;
+
+       dev0 = mlx5_lag_pf(ldev, master_idx)->dev;
+       master_esw = dev0->priv.eswitch;
+       mlx5_ldev_for_each(i, 0, ldev) {
+               struct mlx5_eswitch *slave_esw;
+
+               if (i == master_idx)
+                       continue;
+
+               slave_esw = mlx5_lag_pf(ldev, i)->dev->priv.eswitch;
+
+               err = mlx5_eswitch_offloads_single_fdb_add_one(master_esw,
+                                                              slave_esw,
+                                                              ldev->ports);
+               if (err)
+                       goto err;
+       }
+       return 0;
+err:
+       mlx5_ldev_for_each_reverse(j, i, 0, ldev) {
+               struct mlx5_eswitch *slave_esw;
+
+               if (j == master_idx)
+                       continue;
+               slave_esw = mlx5_lag_pf(ldev, j)->dev->priv.eswitch;
+               mlx5_eswitch_offloads_single_fdb_del_one(master_esw, slave_esw);
+       }
+       return err;
+}
+
+int mlx5_lag_shared_fdb_create(struct mlx5_lag *ldev,
+                              struct lag_tracker *tracker,
+                              enum mlx5_lag_mode mode)
+{
+       int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
+       struct mlx5_core_dev *dev0;
+       int err;
+
+       if (idx < 0)
+               return -EINVAL;
+
+       dev0 = mlx5_lag_pf(ldev, idx)->dev;
+
+       mlx5_lag_remove_devices(ldev);
+
+       err = mlx5_activate_lag(ldev, tracker, mode, true);
+       if (err) {
+               mlx5_core_warn(dev0, "Failed to create LAG in shared FDB mode (%d)\n",
+                              err);
+               goto err_add_devices;
+       }
+
+       mlx5_lag_rescan_dev_locked(ldev, dev0, true);
+       err = mlx5_lag_reload_ib_reps_from_locked(ldev, 0, false);
+       if (err) {
+               mlx5_core_err(dev0, "Failed to enable lag\n");
+               goto err_rescan_drivers;
+       }
+
+       mlx5_lag_set_vports_agg_speed(ldev);
+       return 0;
+
+err_rescan_drivers:
+       mlx5_lag_rescan_dev_locked(ldev, dev0, false);
+       mlx5_deactivate_lag(ldev);
+err_add_devices:
+       mlx5_lag_add_devices(ldev);
+       mlx5_lag_reload_ib_reps_from_locked(ldev, 0, true);
+       return err;
+}
+
+void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev)
+{
+       int err;
+
+       mlx5_lag_remove_devices(ldev);
+
+       err = mlx5_deactivate_lag(ldev);
+       if (err)
+               return;
+
+       mlx5_lag_add_devices(ldev);
+       mlx5_lag_reload_ib_reps_from_locked(ldev,
+                                           MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV,
+                                           true);
+}