net/mlx5e: Disable TX MPWQE in kdump mode

Under kdump environment we want to use the smallest possible amount
of resources, that includes setting SQ size to minimum.
However, when running on a device that supports TX MPWQE, then the SQ stop
room becomes larger than with non-capable device and requires increasing
the SQ size.

Since TX MPWQE offload is not necessary in kdump mode, disable it to
reduce the memory requirements for capable devices.

With this change, the needed SQ stop room size drops by 31.

Signed-off-by: Alaa Hleihel <alaa@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

1 files changed, 7 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d966d5f40e78..b1b51bbba054 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1162,6 +1162,13 @@ mlx5e_calc_max_nch(struct mlx5e_priv *priv, const struct mlx5e_profile *profile)
 	return priv->netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
 }
 
+static inline bool
+mlx5e_tx_mpwqe_supported(struct mlx5_core_dev *mdev)
+{
+	return !is_kdump_kernel() &&
+		MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe);
+}
+
 int mlx5e_priv_init(struct mlx5e_priv *priv,
 		    struct net_device *netdev,
 		    struct mlx5_core_dev *mdev);