From bdf549a7a4d738838d50833168881a0b6247446a Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 18 Mar 2025 22:51:16 +0200 Subject: [PATCH 1/2] net/mlx5: LAG, reload representors on LAG creation failure When LAG creation fails, the driver reloads the RDMA devices. If RDMA representors are present, they should also be reloaded. This step was missed in the cited commit. Fixes: 598fe77df855 ("net/mlx5: Lag, Create shared FDB when in switchdev mode") Signed-off-by: Mark Bloch Reviewed-by: Shay Drori Signed-off-by: Tariq Toukan Reviewed-by: Michal Swiatkowski Reviewed-by: Kalesh AP Link: https://patch.msgid.link/1742331077-102038-2-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index ed2ba272946b..6c9737c53734 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1052,6 +1052,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) if (err) { if (shared_fdb || roce_lag) mlx5_lag_add_devices(ldev); + if (shared_fdb) { + mlx5_ldev_for_each(i, 0, ldev) + mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); + } return; } else if (roce_lag) { From 1726ad035cb0c93cc5c3f2227ec71322ccd7c2f8 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Tue, 18 Mar 2025 22:51:17 +0200 Subject: [PATCH 2/2] net/mlx5: Start health poll after enable hca The health poll mechanism performs periodic checks to detect firmware errors. One of the checks verifies the function is still enabled on firmware side, but the function is enabled only after enable_hca command completed. Start health poll after enable_hca command to avoid a race between function enabled and first health polling. Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load") Signed-off-by: Moshe Shemesh Reviewed-by: Shay Drori Signed-off-by: Tariq Toukan Reviewed-by: Michal Swiatkowski Reviewed-by: Kalesh AP Link: https://patch.msgid.link/1742331077-102038-3-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index ec956c4bcebd..7c3312d6aed9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1205,24 +1205,24 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP); - mlx5_start_health_poll(dev); - err = mlx5_core_enable_hca(dev, 0); if (err) { mlx5_core_err(dev, "enable hca failed\n"); - goto stop_health_poll; + goto err_cmd_cleanup; } + mlx5_start_health_poll(dev); + err = mlx5_core_set_issi(dev); if (err) { mlx5_core_err(dev, "failed to set issi\n"); - goto err_disable_hca; + goto stop_health_poll; } err = mlx5_satisfy_startup_pages(dev, 1); if (err) { mlx5_core_err(dev, "failed to allocate boot pages\n"); - goto err_disable_hca; + goto stop_health_poll; } err = mlx5_tout_query_dtor(dev); @@ -1235,10 +1235,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou reclaim_boot_pages: mlx5_reclaim_startup_pages(dev); -err_disable_hca: - mlx5_core_disable_hca(dev, 0); stop_health_poll: mlx5_stop_health_poll(dev, boot); + mlx5_core_disable_hca(dev, 0); err_cmd_cleanup: mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_disable(dev); @@ -1249,8 +1248,8 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot) { mlx5_reclaim_startup_pages(dev); - mlx5_core_disable_hca(dev, 0); mlx5_stop_health_poll(dev, boot); + mlx5_core_disable_hca(dev, 0); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_disable(dev); }