net/mlx5e: Tx, Soften inline mode VLAN dependencies

If capable, use zero inline mode in TX WQE for non-VLAN packets.
For VLAN ones, keep the enforcement of at least L2 inline mode,
unless the WQE VLAN insertion offload cap is on.

Performance:
Tested single core packet rate of 64Bytes.

NIC: ConnectX-5
CPU: Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz

pktgen:
Before: 12.46 Mpps
After:  14.65 Mpps (+17.5%)

XDP_TX:
The MPWQE flow is not affected, as it already has this optimization.
So we test with priv-flag xdp_tx_mpwqe: off.

Before:  9.90 Mpps
After:  10.20 Mpps (+3%)

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Tested-by: Noam Stolero <noams@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

7 files changed, 33 insertions, 23 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 745bcc25c6f8..30f13f81c965 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -359,6 +359,7 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
+	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -1132,7 +1133,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 			   struct mlx5e_params *params);
 void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 			    u16 num_channels);
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 7da22b413a48..87be96747902 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 	mlx5_write64((__be32 *)ctrl, uar_map);
 }
 
-static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe)
+static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg)
 {
-	return !!wqe->ctrl.tisn;
+	return cseg && !!cseg->tisn;
+}
+
+static inline u8
+mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
+			 struct sk_buff *skb)
+{
+	u8 mode;
+
+	if (mlx5e_transport_inline_tx_wqe(cseg))
+		return MLX5_INLINE_MODE_TCP_UDP;
+
+	mode = sq->min_inline_mode;
+
+	if (skb_vlan_tag_present(skb) &&
+	    test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state))
+		mode = max_t(u8, MLX5_INLINE_MODE_L2, mode);
+
+	return mode;
 }
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 1539cf3de5dc..f7890e0ce96c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -180,15 +180,3 @@ out:
 
 	return err;
 }
-
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev)
-{
-	u8 min_inline_mode;
-
-	mlx5_query_min_inline(mdev, &min_inline_mode);
-	if (min_inline_mode == MLX5_INLINE_MODE_NONE &&
-	    !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
-		min_inline_mode = MLX5_INLINE_MODE_L2;
-
-	return min_inline_mode;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8dd31b5c740c..01f2918063af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv)
 static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv,
 						  struct mlx5e_params *params)
 {
-	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev);
+	mlx5_query_min_inline(priv->mdev, &params->tx_min_inline_mode);
 	if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP &&
 	    params->tx_min_inline_mode == MLX5_INLINE_MODE_L2)
 		params->tx_min_inline_mode = MLX5_INLINE_MODE_IP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b2618dd6dd10..e75cb18c2256 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1131,6 +1131,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
 	sq->stop_room = MLX5E_SQ_STOP_ROOM;
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
+	if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert))
+		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (mlx5_accel_is_tls_device(c->priv->mdev)) {
@@ -4777,7 +4779,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 
 	/* TX inline */
-	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev);
+	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
 	/* RSS */
 	mlx5e_build_rss_params(rss_params, params->num_channels);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index acf25cc38fa1..d3a67a9b4eba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -292,8 +292,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 		stats->packets += skb_shinfo(skb)->gso_segs;
 	} else {
-		u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ?
-			MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode;
+		u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb);
 
 		opcode    = MLX5_OPCODE_SEND;
 		mss       = 0;
@@ -608,9 +607,11 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 		stats->packets += skb_shinfo(skb)->gso_segs;
 	} else {
+		u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb);
+
 		opcode    = MLX5_OPCODE_SEND;
 		mss       = 0;
-		ihs       = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+		ihs       = mlx5e_calc_min_inline(mode, skb);
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 		stats->packets++;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index c912d82ca64b..30f7848a6f88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -122,12 +122,13 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev,
 			   u8 *min_inline_mode)
 {
 	switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) {
+	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+		if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode))
+			break;
+		/* fall through */
 	case MLX5_CAP_INLINE_MODE_L2:
 		*min_inline_mode = MLX5_INLINE_MODE_L2;
 		break;
-	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
-		mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode);
-		break;
 	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
 		*min_inline_mode = MLX5_INLINE_MODE_NONE;
 		break;