Commit 51ef9305 authored by Maher Sanalla's avatar Maher Sanalla Committed by David S. Miller
Browse files

net/mlx5: Lag, do bond only if slaves agree on roce state



Currently, the driver does not enforce that lag bond slaves must have
matching roce capabilities. Yet, in mlx5_do_bond(), the driver attempts
to enable roce on all vports of the bond slaves, causing the following
syndrome when one slave has no roce fw support:

mlx5_cmd_out_err:809:(pid 25427): MODIFY_NIC_VPORT_CONTEXT(0×755) op_mod(0×0)
failed, status bad parameter(0×3), syndrome (0xc1f678), err(-22)

Thus, create HW lag only if bond's slaves agree on roce state,
either all slaves have roce support resulting in a roce lag bond,
or none do, resulting in a raw eth bond.

Fixes: 7907f23a ("net/mlx5: Implement RoCE LAG feature")
Signed-off-by: default avatarMaher Sanalla <msanalla@nvidia.com>
Signed-off-by: default avatarTariq Toukan <tariqt@nvidia.com>
Reviewed-by: default avatarSimon Horman <horms@kernel.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 128d54fb
Loading
Loading
Loading
Loading
+10 −2
Original line number Diff line number Diff line
@@ -719,6 +719,7 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
	struct mlx5_core_dev *dev;
	u8 mode;
#endif
	bool roce_support;
	int i;

	for (i = 0; i < ldev->ports; i++)
@@ -743,6 +744,11 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
		if (mlx5_sriov_is_enabled(ldev->pf[i].dev))
			return false;
#endif
	roce_support = mlx5_get_roce_state(ldev->pf[MLX5_LAG_P1].dev);
	for (i = 1; i < ldev->ports; i++)
		if (mlx5_get_roce_state(ldev->pf[i].dev) != roce_support)
			return false;

	return true;
}

@@ -910,8 +916,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
		} else if (roce_lag) {
			dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
			mlx5_rescan_drivers_locked(dev0);
			for (i = 1; i < ldev->ports; i++)
			for (i = 1; i < ldev->ports; i++) {
				if (mlx5_get_roce_state(ldev->pf[i].dev))
					mlx5_nic_vport_enable_roce(ldev->pf[i].dev);
			}
		} else if (shared_fdb) {
			int i;