diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f794ffaf1e04..29b10ef787b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -174,8 +174,8 @@ struct page_pool;
 	ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT)
 
 #define MLX5E_MAX_KLM_PER_WQE(mdev) \
-	MLX5E_KLM_ENTRIES_PER_WQE(mlx5e_get_sw_max_sq_mpw_wqebbs(mlx5e_get_max_sq_wqebbs(mdev)) \
-				   << MLX5_MKEY_BSF_OCTO_SIZE)
+	MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * \
+		mlx5e_get_sw_max_sq_mpw_wqebbs(mlx5e_get_max_sq_wqebbs(mdev)))
 
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
 
@@ -233,7 +233,7 @@ static inline u16 mlx5e_get_max_sq_wqebbs(struct mlx5_core_dev *mdev)
 		     MLX5_CAP_GEN(mdev, max_wqe_sz_sq) / MLX5_SEND_WQE_BB);
 }
 
-static inline u16 mlx5e_get_sw_max_sq_mpw_wqebbs(u16 max_sq_wqebbs)
+static inline u8 mlx5e_get_sw_max_sq_mpw_wqebbs(u8 max_sq_wqebbs)
 {
 /* The return value will be multiplied by MLX5_SEND_WQEBB_NUM_DS.
  * Since max_sq_wqebbs may be up to MLX5_SEND_WQE_MAX_WQEBBS == 16,
@@ -242,11 +242,12 @@ static inline u16 mlx5e_get_sw_max_sq_mpw_wqebbs(u16 max_sq_wqebbs)
  * than MLX5_SEND_WQE_MAX_WQEBBS to let a full-session WQE be
  * cache-aligned.
  */
-#if L1_CACHE_BYTES < 128
-	return min_t(u16, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 1);
-#else
-	return min_t(u16, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 2);
+	u8 wqebbs = min_t(u8, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 1);
+
+#if L1_CACHE_BYTES >= 128
+	wqebbs = ALIGN_DOWN(wqebbs, 2);
 #endif
+	return wqebbs;
 }
 
 struct mlx5e_tx_wqe {
@@ -455,7 +456,7 @@ struct mlx5e_txqsq {
 	struct netdev_queue       *txq;
 	u32                        sqn;
 	u16                        stop_room;
-	u16                        max_sq_mpw_wqebbs;
+	u8                         max_sq_mpw_wqebbs;
 	u8                         min_inline_mode;
 	struct device             *pdev;
 	__be32                     mkey_be;
@@ -570,7 +571,7 @@ struct mlx5e_xdpsq {
 	struct device             *pdev;
 	__be32                     mkey_be;
 	u16                        stop_room;
-	u16                        max_sq_mpw_wqebbs;
+	u8                         max_sq_mpw_wqebbs;
 	u8                         min_inline_mode;
 	unsigned long              state;
 	unsigned int               hw_mtu;