net-next/hinic:add rx checksum offload for HiNIC

In order to improve performance, this patch adds rx checksum offload
for the HiNIC driver. Performance test(Iperf) shows more than 80%
improvement in TCP streams.
Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h

@@ -50,6 +50,8 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_GET_LINK_STATE   = 24,
 
+	HINIC_PORT_CMD_SET_RX_CSUM	= 26,
+
 	HINIC_PORT_CMD_SET_PORT_STATE   = 41,
 
 	HINIC_PORT_CMD_FWCTXT_INIT      = 69,

drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h

@@ -170,6 +170,10 @@
 
 #define HINIC_RQ_CQE_STATUS_RXDONE_MASK         0x1
 
+#define HINIC_RQ_CQE_STATUS_CSUM_ERR_SHIFT	0
+
+#define HINIC_RQ_CQE_STATUS_CSUM_ERR_MASK	0xFFFFU
+
 #define HINIC_RQ_CQE_STATUS_GET(val, member)    \
 		(((val) >> HINIC_RQ_CQE_STATUS_##member##_SHIFT) & \
 		 HINIC_RQ_CQE_STATUS_##member##_MASK)

drivers/net/ethernet/huawei/hinic/hinic_main.c

@@ -806,7 +806,8 @@ static const struct net_device_ops hinic_netdev_ops = {
 static void netdev_features_init(struct net_device *netdev)
 {
 	netdev->hw_features = NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_IP_CSUM |
-			      NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			      NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			      NETIF_F_RXCSUM;
 
 	netdev->vlan_features = netdev->hw_features;
 
@@ -869,12 +870,16 @@ static int set_features(struct hinic_dev *nic_dev,
 			netdev_features_t features, bool force_change)
 {
 	netdev_features_t changed = force_change ? ~0 : pre_features ^ features;
+	u32 csum_en = HINIC_RX_CSUM_OFFLOAD_EN;
 	int err = 0;
 
 	if (changed & NETIF_F_TSO)
 		err = hinic_port_set_tso(nic_dev, (features & NETIF_F_TSO) ?
 					 HINIC_TSO_ENABLE : HINIC_TSO_DISABLE);
 
+	if (changed & NETIF_F_RXCSUM)
+		err = hinic_set_rx_csum_offload(nic_dev, csum_en);
+
 	return err;
 }
 

drivers/net/ethernet/huawei/hinic/hinic_port.c

@@ -409,3 +409,31 @@ int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state)
 
 	return 0;
 }
+
+int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en)
+{
+	struct hinic_checksum_offload rx_csum_cfg = {0};
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size;
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	rx_csum_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rx_csum_cfg.rx_csum_offload = en;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RX_CSUM,
+				 &rx_csum_cfg, sizeof(rx_csum_cfg),
+				 &rx_csum_cfg, &out_size);
+	if (err || !out_size || rx_csum_cfg.status) {
+		dev_err(&pdev->dev,
+			"Failed to set rx csum offload, ret = %d\n",
+			rx_csum_cfg.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}

drivers/net/ethernet/huawei/hinic/hinic_port.h

@@ -183,6 +183,15 @@ struct hinic_tso_config {
 	u8	resv2[3];
 };
 
+struct hinic_checksum_offload {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u32	rx_csum_offload;
+};
 int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		       u16 vlan_id);
 
@@ -213,4 +222,5 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev,
 
 int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state);
 
+int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en);
 #endif

drivers/net/ethernet/huawei/hinic/hinic_rx.c

@@ -89,6 +89,28 @@ static void rxq_stats_init(struct hinic_rxq *rxq)
 	hinic_rxq_clean_stats(rxq);
 }
 
+static void rx_csum(struct hinic_rxq *rxq, u16 cons_idx,
+		    struct sk_buff *skb)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct hinic_rq_cqe *cqe;
+	struct hinic_rq *rq;
+	u32 csum_err;
+	u32 status;
+
+	rq = rxq->rq;
+	cqe = rq->cqe[cons_idx];
+	status = be32_to_cpu(cqe->status);
+	csum_err = HINIC_RQ_CQE_STATUS_GET(status, CSUM_ERR);
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (!csum_err)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	else
+		skb->ip_summed = CHECKSUM_NONE;
+}
 /**
  * rx_alloc_skb - allocate skb and map it to dma address
  * @rxq: rx queue
@@ -328,6 +350,8 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 
 		rx_unmap_skb(rxq, hinic_sge_to_dma(&sge));
 
+		rx_csum(rxq, ci, skb);
+
 		prefetch(skb->data);
 
 		pkt_len = sge.len;

drivers/net/ethernet/huawei/hinic/hinic_rx.h

@@ -23,6 +23,10 @@
 
 #include "hinic_hw_qp.h"
 
+#define HINIC_RX_CSUM_OFFLOAD_EN	0xFFF
+#define HINIC_RX_CSUM_HW_CHECK_NONE	BIT(7)
+#define HINIC_RX_CSUM_IPSU_OTHER_ERR	BIT(8)
+
 struct hinic_rxq_stats {
 	u64                     pkts;
 	u64                     bytes;