net/mlx5e: Small improvements for XDP TX MPWQE logic

Use MLX5E_XDP_MPW_MAX_WQEBBS to reserve space for a MPWQE, because it's
actually the maximal size a MPWQE can take.

Reorganize the logic that checks when to close the MPWQE session:

1. Put all checks into a single function.

2. When inline is on, make only one comparison - if it's false, the less
strict one will also be false. The compiler probably optimized it out
anyway, but it's clearer to also reflect it in the code.

The MLX5E_XDP_INLINE_WQE_* defines are also changed to make the
calculations more correct from the logical point of view. Though
MLX5E_XDP_INLINE_WQE_MAX_DS_CNT used to be 16 and didn't change its
value, the calculation used to be DIV_ROUND_UP(max inline packet size,
MLX5_SEND_WQE_DS), and the numerator should have included sizeof(struct
mlx5_wqe_inline_seg).
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -198,7 +198,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 	u16 pi;
 
-	pi = mlx5e_xdpsq_get_next_pi(sq, MLX5_SEND_WQE_MAX_WQEBBS);
+	pi = mlx5e_xdpsq_get_next_pi(sq, MLX5E_XDP_MPW_MAX_WQEBBS);
 	session->wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
 	net_prefetchw(session->wqe->data);
@@ -284,8 +284,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *x
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
 
-	if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) ||
-		     session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS))
+	if (unlikely(mlx5e_xdp_mpqwe_is_full(session)))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h

@@ -42,9 +42,10 @@
 	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
-#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
-#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \
-	DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS)
+#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT 16
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD \
+	(MLX5E_XDP_INLINE_WQE_MAX_DS_CNT * MLX5_SEND_WQE_DS - \
+	 sizeof(struct mlx5_wqe_inline_seg))
 
 /* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
  * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
@@ -141,11 +142,12 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
 		session->inline_on = 1;
 }
 
-static inline bool
-mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session)
+static inline bool mlx5e_xdp_mpqwe_is_full(struct mlx5e_xdp_mpwqe *session)
 {
-	return session->inline_on &&
-	       session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS;
+	if (session->inline_on)
+		return session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT >
+		       MLX5E_XDP_MPW_MAX_NUM_DS;
+	return session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS;
 }
 
 struct mlx5e_xdp_wqe_info {