net/mlx5e: Refactor xmit functions

A huge function mlx5e_sq_xmit was split into several to achieve multiple
goals:

1. Reuse the code in IPoIB.

2. Better intergrate with TLS, IPSEC, GENEVE and checksum offloads. Now
it's possible to reserve space in the WQ before running eseg-based
offloads, so:

2.1. It's not needed to copy cseg and eseg after mlx5e_fill_sq_frag_edge
anymore.

2.2. mlx5e_txqsq_get_next_pi will be used instead of the legacy
mlx5e_fill_sq_frag_edge for better code maintainability and reuse.

3. Prepare for the upcoming TX MPWQE for SKBs. It will intervene after
mlx5e_sq_calc_wqe_attr to check if it's possible to use MPWQE, and the
code flow will split into two paths: MPWQE and non-MPWQE.

Two high-level functions are provided to send packets:

* mlx5e_xmit is called by the networking stack, runs offloads and sends
the packet. In one of the following patches, MPWQE support will be added
to this flow.

* mlx5e_sq_xmit_simple is called by the TLS offload, runs only the
checksum offload and sends the packet.

This change has no performance impact in TCP single stream test and
XDP_TX single stream test.

When compiled with a recent GCC, this change shows no visible
performance impact on UDP pktgen (burst 32) single stream test either:
  Packet rate: 16.86 Mpps (±0.15 Mpps) -> 16.95 Mpps (±0.15 Mpps)
  Instructions per packet: 434 -> 429
  Cycles per packet: 158 -> 160
  Instructions per cycle: 2.75 -> 2.69

CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz (x86_64)
NIC: Mellanox ConnectX-6 Dx
GCC 10.2.0
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/txrx.h

@@ -41,8 +41,6 @@ void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
-void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-		   struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
 
@@ -188,23 +186,6 @@ static inline u16 mlx5e_icosq_get_next_pi(struct mlx5e_icosq *sq, u16 size)
 	return pi;
 }
 
-static inline void
-mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, struct mlx5_wq_cyc *wq,
-			u16 pi, u16 nnops)
-{
-	struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-
-	edge_wi = wi + nnops;
-
-	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
-	for (; wi < edge_wi; wi++) {
-		memset(wi, 0, sizeof(*wi));
-		wi->num_wqebbs = 1;
-		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	}
-	sq->stats->nop += nnops;
-}
-
 static inline void
 mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 		struct mlx5_wqe_ctrl_seg *ctrl)
@@ -263,6 +244,8 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 	}
 }
 
+void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit_more);
+
 static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
 {
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {

drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h

@@ -145,6 +145,11 @@ static inline bool mlx5e_accel_tx_finish(struct mlx5e_priv *priv,
 	}
 #endif
 
+#if IS_ENABLED(CONFIG_GENEVE)
+	if (skb->encapsulation)
+		mlx5e_tx_tunnel_accel(skb, &wqe->eth);
+#endif
+
 	return true;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c

@@ -189,12 +189,10 @@ static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 				 struct mlx5e_tls *tls)
 {
 	u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
-	struct mlx5e_tx_wqe *wqe;
 	struct sync_info info;
 	struct sk_buff *nskb;
 	int linear_len = 0;
 	int headln;
-	u16 pi;
 	int i;
 
 	sq->stats->tls_ooo++;
@@ -246,9 +244,7 @@ static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 	sq->stats->tls_resync_bytes += nskb->len;
 	mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
 				    cpu_to_be64(info.rcd_sn));
-	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
-	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
-	mlx5e_sq_xmit(sq, nskb, wqe, pi, true);
+	mlx5e_sq_xmit_simple(sq, nskb, true);
 
 	return true;