net/mlx5: E-Switch, Tie rep load/unload to SD LAG state

On an SD device, vport representors are not functional until the SD
group is combined and shared FDB is active. Skip the initial load and
the reload paths in that window; reps are loaded as part of the SD LAG
activation flow once it becomes active.

In addition, explicitly unload representors when SD LAG is destroyed.

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/20260612113904.537595-14-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index a5f0774834febc16f7cd5d583f99e8aab9f250ef..b2b3150f1f04119243a0977f2cf611b8d17ff6f9 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -959,6 +959,7 @@ int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw,
 void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw,
                                              struct mlx5_eswitch *slave_esw);
 int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw);
+void mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw);
 bool mlx5_eswitch_is_peer(struct mlx5_eswitch *esw,
                          struct mlx5_eswitch *peer_esw);
 
@@ -1063,6 +1064,9 @@ mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
        return 0;
 }
 
+static inline void
+mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw) {}
+
 static inline bool
 mlx5_eswitch_block_encap(struct mlx5_core_dev *dev, bool from_fdb)
 {

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a24719cfba34f87f77558454e72f9cdd3b1c7d41..4dc190a4e7b28fb519cc7d3934a2687f36ecc5f1 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2863,6 +2863,10 @@ static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num)
        int rep_type;
        int err;
 
+       if (vport_num != MLX5_VPORT_UPLINK &&
+           mlx5_get_sd(esw->dev) && !mlx5_lag_is_active(esw->dev))
+               return 0;
+
        rep = mlx5_eswitch_get_rep(esw, vport_num);
        for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
                err = __esw_offloads_load_rep(esw, rep, rep_type,
@@ -3779,6 +3783,21 @@ static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
                esw_vport_destroy_offloads_acl_tables(esw, vport);
 }
 
+void mlx5_eswitch_unload_reps(struct mlx5_eswitch *esw)
+{
+       struct mlx5_eswitch_rep *rep;
+       unsigned long i;
+
+       if (!esw || esw->mode != MLX5_ESWITCH_OFFLOADS)
+               return;
+
+       mlx5_esw_for_each_rep(esw, i, rep) {
+               if (rep->vport == MLX5_VPORT_UPLINK)
+                       continue;
+               mlx5_esw_offloads_rep_unload(esw, rep->vport);
+       }
+}
+
 int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
 {
        struct mlx5_eswitch_rep *rep;
@@ -3805,6 +3824,10 @@ int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
                if (!mlx5_sd_is_primary(esw->dev) &&
                    rep->vport == MLX5_VPORT_UPLINK)
                        continue;
+               if (rep->vport != MLX5_VPORT_UPLINK &&
+                   mlx5_get_sd(esw->dev) && !mlx5_lag_is_active(esw->dev))
+                       continue;
+
                if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED)
                        __esw_offloads_load_rep(esw, rep, REP_IB, NULL);
        }
@@ -4764,6 +4787,9 @@ static void mlx5_eswitch_reload_reps_blocked(struct mlx5_eswitch *esw)
                return;
        }
 
+       if (mlx5_get_sd(esw->dev) && !mlx5_lag_is_active(esw->dev))
+               return;
+
        mlx5_esw_for_each_vport(esw, i, vport) {
                if (!vport)
                        continue;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 424478e649ef589ceaeaecd9c6c41e15c7928f44..28d16fdc3f061503c58b65e2b56d85077055885a 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1312,6 +1312,32 @@ int mlx5_lag_reload_ib_reps_from_locked(struct mlx5_lag *ldev, u32 flags,
        return mlx5_lag_reload_ib_reps(ldev, flags, filter, cont_on_fail);
 }
 
+static void mlx5_lag_unload_reps_unlocked(struct mlx5_lag *ldev, u32 filter)
+{
+       struct lag_func *pf;
+       int i;
+
+       mlx5_lag_for_each(i, 0, ldev, filter) {
+               struct mlx5_eswitch *esw;
+
+               pf = mlx5_lag_pf(ldev, i);
+               esw = pf->dev->priv.eswitch;
+               mlx5_esw_reps_block(esw);
+               mlx5_eswitch_unload_reps(esw);
+               mlx5_esw_reps_unblock(esw);
+       }
+}
+
+void mlx5_lag_unload_reps_from_locked(struct mlx5_lag *ldev, u32 filter)
+{
+       /* Same lock dance as mlx5_lag_reload_ib_reps: drop ldev->lock around
+        * the per-eswitch reps_lock to keep the reps_lock -> ldev->lock order.
+        */
+       mlx5_lag_drop_lock_for_reps(ldev, filter);
+       mlx5_lag_unload_reps_unlocked(ldev, filter);
+       mlx5_lag_retake_lock_after_reps(ldev);
+}
+
 void mlx5_disable_lag(struct mlx5_lag *ldev)
 {
        bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 8481ce55c10ae9ea021e10964ce5c496fe94cc01..e9f0ef83ce1d258f1f48a33b341b8cc4afaefb29 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -310,6 +310,7 @@ int mlx5_lag_num_devs(struct mlx5_lag *ldev);
 int mlx5_lag_num_netdevs(struct mlx5_lag *ldev);
 int mlx5_lag_reload_ib_reps_from_locked(struct mlx5_lag *ldev, u32 flags,
                                        u32 filter, bool cont_on_fail);
+void mlx5_lag_unload_reps_from_locked(struct mlx5_lag *ldev, u32 filter);
 int mlx5_ldev_add_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev,
                       u32 group_id);
 void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c
index 8d4f2903a1016c60081165cf3e6dbbae210cb35c..113866494d164bee26b87668700ceac1cfef59e7 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c
@@ -296,6 +296,7 @@ void mlx5_lag_shared_fdb_destroy(struct mlx5_lag *ldev, u32 group_id)
                        pf->sd_fdb_active = false;
                }
                mlx5_lag_destroy_single_fdb_filter(ldev, group_id);
+               mlx5_lag_unload_reps_from_locked(ldev, filter);
        }
 
        mlx5_lag_add_devices_filter(ldev, filter);