[PATCH v3 4/6] net/mlx4: restore Tx checksum offloads

[Adrien Mazarguil <adrien.mazarguil@6wind.com>]

From: Moti Haimovsky <motih@mellanox.com>

This patch adds hardware offloading support for IPv4, UDP and TCP checksum
calculation, including inner/outer checksums on supported tunnel types.

Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
---
 drivers/net/mlx4/mlx4.c        | 11 +++++++++++
 drivers/net/mlx4/mlx4.h        |  2 ++
 drivers/net/mlx4/mlx4_ethdev.c |  6 ++++++
 drivers/net/mlx4/mlx4_prm.h    |  2 ++
 drivers/net/mlx4/mlx4_rxtx.c   | 19 +++++++++++++++++++
 drivers/net/mlx4/mlx4_rxtx.h   |  2 ++
 drivers/net/mlx4/mlx4_txq.c    |  2 ++
 7 files changed, 44 insertions(+)

diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
index b084903..385ddaa 100644
--- a/drivers/net/mlx4/mlx4.c
+++ b/drivers/net/mlx4/mlx4.c
@@ -529,6 +529,17 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 		priv->pd = pd;
 		priv->mtu = ETHER_MTU;
 		priv->vf = vf;
+		priv->hw_csum =	!!(device_attr.device_cap_flags &
+				   IBV_DEVICE_RAW_IP_CSUM);
+		DEBUG("checksum offloading is %ssupported",
+		      (priv->hw_csum ? "" : "not "));
+		/* Only ConnectX-3 Pro supports tunneling. */
+		priv->hw_csum_l2tun =
+			priv->hw_csum &&
+			(device_attr.vendor_part_id ==
+			 PCI_DEVICE_ID_MELLANOX_CONNECTX3PRO);
+		DEBUG("L2 tunnel checksum offloads are %ssupported",
+		      (priv->hw_csum_l2tun ? "" : "not "));
 		/* Configure the first MAC address by default. */
 		if (mlx4_get_mac(priv, &mac.addr_bytes)) {
 			ERROR("cannot get MAC address, is mlx4_en loaded?"
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 93e5502..0b71867 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -104,6 +104,8 @@ struct priv {
 	unsigned int vf:1; /* This is a VF device. */
 	unsigned int intr_alarm:1; /* An interrupt alarm is scheduled. */
 	unsigned int isolated:1; /* Toggle isolated mode. */
+	unsigned int hw_csum:1; /* Checksum offload is supported. */
+	unsigned int hw_csum_l2tun:1; /* Checksum support for L2 tunnels. */
 	struct rte_intr_handle intr_handle; /* Port interrupt handle. */
 	struct rte_flow_drop *flow_drop_queue; /* Flow drop queue. */
 	LIST_HEAD(mlx4_flows, rte_flow) flows;
diff --git a/drivers/net/mlx4/mlx4_ethdev.c b/drivers/net/mlx4/mlx4_ethdev.c
index a9e8059..bec1787 100644
--- a/drivers/net/mlx4/mlx4_ethdev.c
+++ b/drivers/net/mlx4/mlx4_ethdev.c
@@ -553,6 +553,12 @@ mlx4_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
 	info->max_mac_addrs = 1;
 	info->rx_offload_capa = 0;
 	info->tx_offload_capa = 0;
+	if (priv->hw_csum)
+		info->tx_offload_capa |= (DEV_TX_OFFLOAD_IPV4_CKSUM |
+					  DEV_TX_OFFLOAD_UDP_CKSUM |
+					  DEV_TX_OFFLOAD_TCP_CKSUM);
+	if (priv->hw_csum_l2tun)
+		info->tx_offload_capa |= DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM;
 	if (mlx4_get_ifname(priv, &ifname) == 0)
 		info->if_index = if_nametoindex(ifname);
 	info->speed_capa =
diff --git a/drivers/net/mlx4/mlx4_prm.h b/drivers/net/mlx4/mlx4_prm.h
index 085a595..df5a6b4 100644
--- a/drivers/net/mlx4/mlx4_prm.h
+++ b/drivers/net/mlx4/mlx4_prm.h
@@ -64,6 +64,8 @@
 
 /* Work queue element (WQE) flags. */
 #define MLX4_BIT_WQE_OWN 0x80000000
+#define MLX4_WQE_CTRL_IIP_HDR_CSUM (1 << 28)
+#define MLX4_WQE_CTRL_IL4_HDR_CSUM (1 << 27)
 
 #define MLX4_SIZE_TO_TXBBS(size) \
 	(RTE_ALIGN((size), (MLX4_TXBB_SIZE)) >> (MLX4_TXBB_SHIFT))
diff --git a/drivers/net/mlx4/mlx4_rxtx.c b/drivers/net/mlx4/mlx4_rxtx.c
index cc0baaa..fe7d5d0 100644
--- a/drivers/net/mlx4/mlx4_rxtx.c
+++ b/drivers/net/mlx4/mlx4_rxtx.c
@@ -431,6 +431,25 @@ mlx4_post_send(struct txq *txq, struct rte_mbuf *pkt)
 	} else {
 		srcrb_flags = RTE_BE32(MLX4_WQE_CTRL_SOLICIT);
 	}
+	/* Enable HW checksum offload if requested */
+	if (txq->csum &&
+	    (pkt->ol_flags &
+	     (PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM | PKT_TX_UDP_CKSUM))) {
+		const uint64_t is_tunneled = (pkt->ol_flags &
+					      (PKT_TX_TUNNEL_GRE |
+					       PKT_TX_TUNNEL_VXLAN));
+
+		if (is_tunneled && txq->csum_l2tun) {
+			owner_opcode |= MLX4_WQE_CTRL_IIP_HDR_CSUM |
+					MLX4_WQE_CTRL_IL4_HDR_CSUM;
+			if (pkt->ol_flags & PKT_TX_OUTER_IP_CKSUM)
+				srcrb_flags |=
+					RTE_BE32(MLX4_WQE_CTRL_IP_HDR_CSUM);
+		} else {
+			srcrb_flags |= RTE_BE32(MLX4_WQE_CTRL_IP_HDR_CSUM |
+						MLX4_WQE_CTRL_TCP_UDP_CSUM);
+		}
+	}
 	ctrl->srcrb_flags = srcrb_flags;
 	/*
 	 * Make sure descriptor is fully written before
diff --git a/drivers/net/mlx4/mlx4_rxtx.h b/drivers/net/mlx4/mlx4_rxtx.h
index 528e286..a742f61 100644
--- a/drivers/net/mlx4/mlx4_rxtx.h
+++ b/drivers/net/mlx4/mlx4_rxtx.h
@@ -108,6 +108,8 @@ struct txq {
 	struct txq_elt (*elts)[]; /**< Tx elements. */
 	struct mlx4_txq_stats stats; /**< Tx queue counters. */
 	uint32_t max_inline; /**< Max inline send size. */
+	uint32_t csum:1; /**< Enable checksum offloading. */
+	uint32_t csum_l2tun:1; /**< Same for L2 tunnels. */
 	uint8_t *bounce_buf;
 	/**< Memory used for storing the first DWORD of data TXBBs. */
 	struct {
diff --git a/drivers/net/mlx4/mlx4_txq.c b/drivers/net/mlx4/mlx4_txq.c
index 7552a88..96429bc 100644
--- a/drivers/net/mlx4/mlx4_txq.c
+++ b/drivers/net/mlx4/mlx4_txq.c
@@ -338,6 +338,8 @@ mlx4_txq_setup(struct rte_eth_dev *dev, struct txq *txq, uint16_t desc,
 		      (void *)dev, strerror(rte_errno));
 		goto error;
 	}
+	tmpl.csum = priv->hw_csum;
+	tmpl.csum_l2tun = priv->hw_csum_l2tun;
 	DEBUG("priv->device_attr.max_qp_wr is %d",
 	      priv->device_attr.max_qp_wr);
 	DEBUG("priv->device_attr.max_sge is %d",
-- 
2.1.4