net/mlx5: Lag, fix multipath lag activation

When handling FIB_EVENT_ENTRY_REPLACE event for a new multipath route,
lag activation can be missed if a stale (struct lag_mp)->mfi pointer
exists, which was associated with an older multipath route that had been
removed.

Normally, when a route is removed, it triggers mlx5_lag_fib_event(),
which handles FIB_EVENT_ENTRY_DEL and clears mfi pointer. But, if
mlx5_lag_check_prereq() condition isn't met, for example when eswitch is
in legacy mode, the fib event is skipped and mfi pointer becomes stale.

Fix by resetting mfi pointer to NULL in mlx5_deactivate_lag().

Fixes: 8a66e4585979 ("net/mlx5: Change ownership model for lag")
Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 5c043c5cc40354bedf1d33bff436e9c1fd017812..40ef60f562b427188bb82452d429f32c01486dfc 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -277,6 +277,7 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
        int err;
 
        ldev->flags &= ~MLX5_LAG_MODE_FLAGS;
+       mlx5_lag_mp_reset(ldev);
 
        MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG);
        err = mlx5_cmd_exec_in(dev0, destroy_lag, in);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index c4bf8b679541ee4f575cca2c4f62703e685df2dd..516bfc2bd797bf3c4dc53ad9373227dd8facca6f 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -302,6 +302,14 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
        return NOTIFY_DONE;
 }
 
+void mlx5_lag_mp_reset(struct mlx5_lag *ldev)
+{
+       /* Clear mfi, as it might become stale when a route delete event
+        * has been missed, see mlx5_lag_fib_route_event().
+        */
+       ldev->lag_mp.mfi = NULL;
+}
+
 int mlx5_lag_mp_init(struct mlx5_lag *ldev)
 {
        struct lag_mp *mp = &ldev->lag_mp;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
index 258ac7b2964e8a0612f61e9c692a3f3fb17de44d..729c839397a89f65e86d17df17186536288d0d68 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
@@ -21,11 +21,13 @@ struct lag_mp {
 
 #ifdef CONFIG_MLX5_ESWITCH
 
+void mlx5_lag_mp_reset(struct mlx5_lag *ldev);
 int mlx5_lag_mp_init(struct mlx5_lag *ldev);
 void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 
+static inline void mlx5_lag_mp_reset(struct mlx5_lag *ldev) {};
 static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; }
 static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {}