[PATCH v5 net-next 33/36] net/mlx5e: NVMEoTCP DDGST TX Data path

From: Boris Pismenny <borisp@nvidia.com>
To: <dsahern@gmail.com>, <kuba@kernel.org>, <davem@davemloft.net>,
	<saeedm@nvidia.com>, <hch@lst.de>, <sagi@grimberg.me>,
	<axboe@fb.com>, <kbusch@kernel.org>, <viro@zeniv.linux.org.uk>,
	<edumazet@google.com>, <smalin@marvell.com>
Cc: <boris.pismenny@gmail.com>, <linux-nvme@lists.infradead.org>,
	<netdev@vger.kernel.org>, <benishay@nvidia.com>,
	<ogerlitz@nvidia.com>, <yorayz@nvidia.com>
Subject: [PATCH v5 net-next 33/36] net/mlx5e: NVMEoTCP DDGST TX Data path
Date: Thu, 22 Jul 2021 14:03:22 +0300	[thread overview]
Message-ID: <20210722110325.371-34-borisp@nvidia.com> (raw)
In-Reply-To: <20210722110325.371-1-borisp@nvidia.com>

From: Yoray Zack <yorayz@nvidia.com>

This patch handles only the good flow for the DDGST Tx offload
 skb and wqe.
Later patches will handle bad flow (OOO packets)

1.  add mlx5e_nvmeotcp_handle_tx_skb function(skb,...):
	check if the skb can be offlaoded.
        this function track the tcp_seq of the skb,
	and check if this is the next tcp_seq.
	and if so, send this skb with DDGST Tx offload.

2. add mlx5e_nvmeotcp_handle_tx_wqe function :
	send the wqe with the correct tis number for the offload.

Signed-off-by: Yoray Zack <yorayz@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/en_accel.h    | 13 ++++
 .../mellanox/mlx5/core/en_accel/nvmeotcp.c    | 63 +++++++++++++++++++
 .../mellanox/mlx5/core/en_accel/nvmeotcp.h    |  6 ++
 .../net/ethernet/mellanox/mlx5/core/en_tx.c   | 11 ++++
 4 files changed, 93 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index b9404366e6e8..2e5a7741736f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -113,6 +113,9 @@ struct mlx5e_accel_tx_state {
 #ifdef CONFIG_MLX5_EN_IPSEC
 	struct mlx5e_accel_tx_ipsec_state ipsec;
 #endif
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	int tisn;
+#endif
 };
 
 static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
@@ -137,6 +140,12 @@ static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
 	}
 #endif
 
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	if (test_bit(MLX5E_SQ_STATE_NVMEOTCP, &sq->state)) {
+		if (unlikely(!mlx5e_nvmeotcp_handle_tx_skb(dev, sq, skb, &state->tisn)))
+			return false;
+	}
+#endif
 	return true;
 }
 
@@ -187,6 +196,10 @@ static inline void mlx5e_accel_tx_finish(struct mlx5e_txqsq *sq,
 	mlx5e_tls_handle_tx_wqe(&wqe->ctrl, &state->tls);
 #endif
 
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	mlx5e_nvmeotcp_handle_tx_wqe(sq, &wqe->ctrl, state->tisn);
+#endif
+
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state) &&
 	    state->ipsec.xo && state->ipsec.tailen)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
index 624d8a28dc21..d9f6125f5dbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.c
@@ -1160,6 +1160,69 @@ void mlx5e_nvmeotcp_tx_post_param_wqes(struct mlx5e_txqsq *sq, struct sock *sk,
 	mlx5e_nvmeotcp_tx_post_progress_params(ctx, sq, tcp_sk(sk)->copied_seq, false);
 }
 
+static inline bool mlx5e_is_sk_tx_device_offloaded(struct sock *sk)
+{
+	/* Return True after smp_store_release assing in
+	 * mlx5e_nvmeotcp_queue_tx_init().
+	 */
+	return sk && sk_fullsock(sk) &&
+		(smp_load_acquire(&sk->sk_validate_xmit_skb) ==
+		 &ulp_ddp_validate_xmit_skb);
+}
+
+bool mlx5e_nvmeotcp_handle_tx_skb(struct net_device *netdev,
+				  struct mlx5e_txqsq *sq,
+				  struct sk_buff *skb, int *nvmeotcp_tisn)
+{
+	struct mlx5e_nvmeotcp_queue *ctx;
+	int datalen;
+	u32 seq;
+
+	if (!mlx5e_is_sk_tx_device_offloaded(skb->sk))
+		goto out;
+
+	datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
+	if (!datalen)
+		goto out;
+
+	ctx = container_of(ulp_ddp_get_ctx(skb->sk),
+			   struct mlx5e_nvmeotcp_queue, ulp_ddp_ctx);
+	if (!ctx)
+		goto out;
+
+	mlx5e_tx_mpwqe_ensure_complete(sq);
+
+	if (WARN_ON_ONCE(ctx->ulp_ddp_ctx.netdev != netdev))
+		goto err_out;
+
+	if (unlikely(mlx5e_nvmeotcp_test_and_clear_pending(ctx)))
+		mlx5e_nvmeotcp_tx_post_param_wqes(sq, skb->sk, ctx);
+
+	seq = ntohl(tcp_hdr(skb)->seq);
+	if (unlikely(ctx->ulp_ddp_ctx.expected_seq != seq))
+		goto err_out;
+
+	*nvmeotcp_tisn = ctx->tisn;
+	ctx->ulp_ddp_ctx.expected_seq = seq + datalen;
+	goto good_out;
+out:
+	*nvmeotcp_tisn = 0;
+good_out:
+	return true;
+err_out:
+	dev_kfree_skb(skb);
+	return false;
+}
+
+void mlx5e_nvmeotcp_handle_tx_wqe(struct mlx5e_txqsq *sq,
+				  struct mlx5_wqe_ctrl_seg *cseg,
+				  int tisn)
+{
+	if (tisn) {
+		cseg->tis_tir_num = cpu_to_be32(tisn << 8);
+	}
+}
+
 void mlx5e_nvmeotcp_cleanup(struct mlx5e_priv *priv)
 {
 	struct mlx5e_nvmeotcp *nvmeotcp = priv->nvmeotcp;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h
index 3bc45b81da06..0451b3ac3687 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/nvmeotcp.h
@@ -119,6 +119,12 @@ void mlx5e_nvmeotcp_ddp_inv_done(struct mlx5e_icosq_wqe_info *wi);
 void mlx5e_nvmeotcp_ctx_comp(struct mlx5e_icosq_wqe_info *wi);
 int mlx5e_nvmeotcp_init_rx(struct mlx5e_priv *priv);
 void mlx5e_nvmeotcp_cleanup_rx(struct mlx5e_priv *priv);
+bool mlx5e_nvmeotcp_handle_tx_skb(struct net_device *netdev,
+				  struct mlx5e_txqsq *sq,
+				  struct sk_buff *skb, int *tisn);
+void mlx5e_nvmeotcp_handle_tx_wqe(struct mlx5e_txqsq *sq,
+				  struct mlx5_wqe_ctrl_seg *csegl,
+				  int tisn);
 #else
 
 static inline void mlx5e_nvmeotcp_build_netdev(struct mlx5e_priv *priv) { }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index c63d78eda606..7feaf5608b9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -249,6 +249,13 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
 		sq->stats->csum_partial++;
 #endif
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	} else if (unlikely(accel && accel->tisn)) {
+		eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
+		sq->stats->csum_partial++;
+#endif
+
+
 	} else if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) {
 		ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
 	} else
@@ -352,6 +359,10 @@ mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	if (accel && accel->tls.tls_tisn)
 		return MLX5_INLINE_MODE_TCP_UDP;
 #endif
+#ifdef CONFIG_MLX5_EN_NVMEOTCP
+	if (accel && accel->tisn)
+		return MLX5_INLINE_MODE_TCP_UDP;
+#endif
 
 	mode = sq->min_inline_mode;
 
-- 
2.24.1


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
