Merge branch 'net-hns3-updates-for-next'

Huazhong Tan says:

====================
net: hns3: updates for -next

This series includes some updates for the HNS3 ethernet driver.

 #1~#6: add some updates related to the checksum offload.
 #7: add support for multiple TCs' MAC pauce mode.
====================

Link: https://lore.kernel.org/r/1606535510-44346-1-git-send-email-tanhuazhong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 207 insertions, 52 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index f6fac2418648..78b48861ff8b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -81,12 +81,13 @@ enum HNAE3_DEV_CAP_BITS {
 	HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B,
 	HNAE3_DEV_SUPPORT_PTP_B,
 	HNAE3_DEV_SUPPORT_INT_QL_B,
-	HNAE3_DEV_SUPPORT_SIMPLE_BD_B,
+	HNAE3_DEV_SUPPORT_HW_TX_CSUM_B,
 	HNAE3_DEV_SUPPORT_TX_PUSH_B,
 	HNAE3_DEV_SUPPORT_PHY_IMP_B,
 	HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B,
 	HNAE3_DEV_SUPPORT_HW_PAD_B,
 	HNAE3_DEV_SUPPORT_STASH_B,
+	HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B,
 };
 
 #define hnae3_dev_fd_supported(hdev) \
@@ -113,8 +114,8 @@ enum HNAE3_DEV_CAP_BITS {
 #define hnae3_dev_int_ql_supported(hdev) \
 	test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, (hdev)->ae_dev->caps)
 
-#define hnae3_dev_simple_bd_supported(hdev) \
-	test_bit(HNAE3_DEV_SUPPORT_SIMPLE_BD_B, (hdev)->ae_dev->caps)
+#define hnae3_dev_hw_csum_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, (hdev)->ae_dev->caps)
 
 #define hnae3_dev_tx_push_supported(hdev) \
 	test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, (hdev)->ae_dev->caps)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index a5ebca888ee0..cb26742e2ed8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -178,6 +178,8 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
 	u32 tx_index, rx_index;
 	u32 q_num, value;
 	dma_addr_t addr;
+	u16 mss_hw_csum;
+	u32 l234info;
 	int cnt;
 
 	cnt = sscanf(&cmd_buf[8], "%u %u", &q_num, &tx_index);
@@ -206,26 +208,46 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
 
 	tx_desc = &ring->desc[tx_index];
 	addr = le64_to_cpu(tx_desc->addr);
+	mss_hw_csum = le16_to_cpu(tx_desc->tx.mss_hw_csum);
 	dev_info(dev, "TX Queue Num: %u, BD Index: %u\n", q_num, tx_index);
 	dev_info(dev, "(TX)addr: %pad\n", &addr);
 	dev_info(dev, "(TX)vlan_tag: %u\n", le16_to_cpu(tx_desc->tx.vlan_tag));
 	dev_info(dev, "(TX)send_size: %u\n",
 		 le16_to_cpu(tx_desc->tx.send_size));
-	dev_info(dev, "(TX)vlan_tso: %u\n", tx_desc->tx.type_cs_vlan_tso);
-	dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len);
-	dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len);
-	dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len);
+
+	if (mss_hw_csum & BIT(HNS3_TXD_HW_CS_B)) {
+		u32 offset = le32_to_cpu(tx_desc->tx.ol_type_vlan_len_msec);
+		u32 start = le32_to_cpu(tx_desc->tx.type_cs_vlan_tso_len);
+
+		dev_info(dev, "(TX)csum start: %u\n",
+			 hnae3_get_field(start,
+					 HNS3_TXD_CSUM_START_M,
+					 HNS3_TXD_CSUM_START_S));
+		dev_info(dev, "(TX)csum offset: %u\n",
+			 hnae3_get_field(offset,
+					 HNS3_TXD_CSUM_OFFSET_M,
+					 HNS3_TXD_CSUM_OFFSET_S));
+	} else {
+		dev_info(dev, "(TX)vlan_tso: %u\n",
+			 tx_desc->tx.type_cs_vlan_tso);
+		dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len);
+		dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len);
+		dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len);
+		dev_info(dev, "(TX)vlan_msec: %u\n",
+			 tx_desc->tx.ol_type_vlan_msec);
+		dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len);
+		dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len);
+		dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len);
+	}
+
 	dev_info(dev, "(TX)vlan_tag: %u\n",
 		 le16_to_cpu(tx_desc->tx.outer_vlan_tag));
 	dev_info(dev, "(TX)tv: %u\n", le16_to_cpu(tx_desc->tx.tv));
-	dev_info(dev, "(TX)vlan_msec: %u\n", tx_desc->tx.ol_type_vlan_msec);
-	dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len);
-	dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len);
-	dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len);
-	dev_info(dev, "(TX)paylen: %u\n", le32_to_cpu(tx_desc->tx.paylen));
+	dev_info(dev, "(TX)paylen_ol4cs: %u\n",
+		 le32_to_cpu(tx_desc->tx.paylen_ol4cs));
 	dev_info(dev, "(TX)vld_ra_ri: %u\n",
 		 le16_to_cpu(tx_desc->tx.bdtp_fe_sc_vld_ra_ri));
-	dev_info(dev, "(TX)mss: %u\n", le16_to_cpu(tx_desc->tx.mss));
+	dev_info(dev, "(TX)mss_hw_csum: %u\n", mss_hw_csum);
 
 	ring = &priv->ring[q_num + h->kinfo.num_tqps];
 	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG);
@@ -233,10 +255,21 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
 	rx_desc = &ring->desc[rx_index];
 
 	addr = le64_to_cpu(rx_desc->addr);
+	l234info = le32_to_cpu(rx_desc->rx.l234_info);
 	dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index);
 	dev_info(dev, "(RX)addr: %pad\n", &addr);
-	dev_info(dev, "(RX)l234_info: %u\n",
-		 le32_to_cpu(rx_desc->rx.l234_info));
+	dev_info(dev, "(RX)l234_info: %u\n", l234info);
+
+	if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) {
+		u32 lo, hi;
+
+		lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M,
+				     HNS3_RXD_L2_CSUM_L_S);
+		hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M,
+				     HNS3_RXD_L2_CSUM_H_S);
+		dev_info(dev, "(RX)csum: %u\n", lo | hi << 8);
+	}
+
 	dev_info(dev, "(RX)pkt_len: %u\n", le16_to_cpu(rx_desc->rx.pkt_len));
 	dev_info(dev, "(RX)size: %u\n", le16_to_cpu(rx_desc->rx.size));
 	dev_info(dev, "(RX)rss_hash: %u\n", le32_to_cpu(rx_desc->rx.rss_hash));
@@ -324,6 +357,11 @@ static void hns3_dbg_dev_caps(struct hnae3_handle *h)
 		 test_bit(HNAE3_DEV_SUPPORT_PTP_B, caps) ? "yes" : "no");
 	dev_info(&h->pdev->dev, "support INT QL: %s\n",
 		 test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, caps) ? "yes" : "no");
+	dev_info(&h->pdev->dev, "support HW TX csum: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, caps) ? "yes" : "no");
+	dev_info(&h->pdev->dev, "support UDP tunnel csum: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, caps) ?
+		 "yes" : "no");
 }
 
 static void hns3_dbg_dev_specs(struct hnae3_handle *h)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 632ad4257b18..1798c0a04b0e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -695,7 +695,7 @@ void hns3_enable_vlan_filter(struct net_device *netdev, bool enable)
 	}
 }
 
-static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
+static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs,
 			u16 *mss, u32 *type_cs_vlan_tso)
 {
 	u32 l4_offset, hdr_len;
@@ -725,15 +725,6 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 					 SKB_GSO_GRE_CSUM |
 					 SKB_GSO_UDP_TUNNEL |
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
-		if ((!(skb_shinfo(skb)->gso_type &
-		    SKB_GSO_PARTIAL)) &&
-		    (skb_shinfo(skb)->gso_type &
-		    SKB_GSO_UDP_TUNNEL_CSUM)) {
-			/* Software should clear the udp's checksum
-			 * field when tso is needed.
-			 */
-			l4.udp->check = 0;
-		}
 		/* reset l3&l4 pointers from outer to inner headers */
 		l3.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
@@ -762,9 +753,13 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 	}
 
 	/* find the txbd field values */
-	*paylen = skb->len - hdr_len;
+	*paylen_fdop_ol4cs = skb->len - hdr_len;
 	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_TSO_B, 1);
 
+	/* offload outer UDP header checksum */
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)
+		hns3_set_field(*paylen_fdop_ol4cs, HNS3_TXD_OL4CS_B, 1);
+
 	/* get MSS for TSO */
 	*mss = skb_shinfo(skb)->gso_size;
 
@@ -833,8 +828,16 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto,
  */
 static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 {
+	struct hns3_nic_priv *priv = netdev_priv(skb->dev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(priv->ae_handle->pdev);
 	union l4_hdr_info l4;
 
+	/* device version above V3(include V3), the hardware can
+	 * do this checksum offload.
+	 */
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+		return false;
+
 	l4.hdr = skb_transport_header(skb);
 
 	if (!(!skb->encapsulation &&
@@ -1055,15 +1058,31 @@ static int hns3_handle_vtags(struct hns3_enet_ring *tx_ring,
 	return 0;
 }
 
+/* check if the hardware is capable of checksum offloading */
+static bool hns3_check_hw_tx_csum(struct sk_buff *skb)
+{
+	struct hns3_nic_priv *priv = netdev_priv(skb->dev);
+
+	/* Kindly note, due to backward compatibility of the TX descriptor,
+	 * HW checksum of the non-IP packets and GSO packets is handled at
+	 * different place in the following code
+	 */
+	if (skb->csum_not_inet || skb_is_gso(skb) ||
+	    !test_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state))
+		return false;
+
+	return true;
+}
+
 static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 			      struct sk_buff *skb, struct hns3_desc *desc)
 {
 	u32 ol_type_vlan_len_msec = 0;
+	u32 paylen_ol4cs = skb->len;
 	u32 type_cs_vlan_tso = 0;
-	u32 paylen = skb->len;
+	u16 mss_hw_csum = 0;
 	u16 inner_vtag = 0;
 	u16 out_vtag = 0;
-	u16 mss = 0;
 	int ret;
 
 	ret = hns3_handle_vtags(ring, skb);
@@ -1088,6 +1107,17 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u8 ol4_proto, il4_proto;
 
+		if (hns3_check_hw_tx_csum(skb)) {
+			/* set checksum start and offset, defined in 2 Bytes */
+			hns3_set_field(type_cs_vlan_tso, HNS3_TXD_CSUM_START_S,
+				       skb_checksum_start_offset(skb) >> 1);
+			hns3_set_field(ol_type_vlan_len_msec,
+				       HNS3_TXD_CSUM_OFFSET_S,
+				       skb->csum_offset >> 1);
+			mss_hw_csum |= BIT(HNS3_TXD_HW_CS_B);
+			goto out_hw_tx_csum;
+		}
+
 		skb_reset_mac_len(skb);
 
 		ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
@@ -1108,7 +1138,7 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 			return ret;
 		}
 
-		ret = hns3_set_tso(skb, &paylen, &mss,
+		ret = hns3_set_tso(skb, &paylen_ol4cs, &mss_hw_csum,
 				   &type_cs_vlan_tso);
 		if (unlikely(ret < 0)) {
 			u64_stats_update_begin(&ring->syncp);
@@ -1118,12 +1148,13 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 		}
 	}
 
+out_hw_tx_csum:
 	/* Set txbd */
 	desc->tx.ol_type_vlan_len_msec =
 		cpu_to_le32(ol_type_vlan_len_msec);
 	desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso);
-	desc->tx.paylen = cpu_to_le32(paylen);
-	desc->tx.mss = cpu_to_le16(mss);
+	desc->tx.paylen_ol4cs = cpu_to_le32(paylen_ol4cs);
+	desc->tx.mss_hw_csum = cpu_to_le16(mss_hw_csum);
 	desc->tx.vlan_tag = cpu_to_le16(inner_vtag);
 	desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag);
 
@@ -2326,39 +2357,32 @@ static void hns3_set_default_feature(struct net_device *netdev)
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
-	netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
+	netdev->hw_enc_features |= NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
 		NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
 		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
-		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
-		NETIF_F_TSO_MANGLEID | NETIF_F_FRAGLIST;
+		NETIF_F_SCTP_CRC | NETIF_F_TSO_MANGLEID | NETIF_F_FRAGLIST;
 
 	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
-	netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		NETIF_F_HW_VLAN_CTAG_FILTER |
+	netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 		NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
 		NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
 		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
-		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
-		NETIF_F_FRAGLIST;
+		NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
 
-	netdev->vlan_features |=
-		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
+	netdev->vlan_features |= NETIF_F_RXCSUM |
 		NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO |
 		NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
 		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
-		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
-		NETIF_F_FRAGLIST;
+		NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
 
-	netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+	netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX |
+		NETIF_F_HW_VLAN_CTAG_RX |
 		NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
 		NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
 		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
-		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
-		NETIF_F_FRAGLIST;
+		NETIF_F_SCTP_CRC | NETIF_F_FRAGLIST;
 
 	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		netdev->hw_features |= NETIF_F_GRO_HW;
@@ -2376,6 +2400,25 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		netdev->vlan_features |= NETIF_F_GSO_UDP_L4;
 		netdev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
 	}
+
+	if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps)) {
+		netdev->hw_features |= NETIF_F_HW_CSUM;
+		netdev->features |= NETIF_F_HW_CSUM;
+		netdev->vlan_features |= NETIF_F_HW_CSUM;
+		netdev->hw_enc_features |= NETIF_F_HW_CSUM;
+	} else {
+		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+		netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+		netdev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+		netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	}
+
+	if (test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps)) {
+		netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+	}
 }
 
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
@@ -2798,6 +2841,22 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
 	return 0;
 }
 
+static void hns3_checksum_complete(struct hns3_enet_ring *ring,
+				   struct sk_buff *skb, u32 l234info)
+{
+	u32 lo, hi;
+
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.csum_complete++;
+	u64_stats_update_end(&ring->syncp);
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M,
+			     HNS3_RXD_L2_CSUM_L_S);
+	hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M,
+			     HNS3_RXD_L2_CSUM_H_S);
+	skb->csum = csum_unfold((__force __sum16)(lo | hi << 8));
+}
+
 static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 			     u32 l234info, u32 bd_base_info, u32 ol_info)
 {
@@ -2812,6 +2871,11 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	if (!(netdev->features & NETIF_F_RXCSUM))
 		return;
 
+	if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) {
+		hns3_checksum_complete(ring, skb, l234info);
+		return;
+	}
+
 	/* check if hardware has done checksum */
 	if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
 		return;
@@ -4157,6 +4221,9 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	/* MTU range: (ETH_MIN_MTU(kernel default) - 9702) */
 	netdev->max_mtu = HNS3_MAX_MTU;
 
+	if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps))
+		set_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state);
+
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
 	if (netif_msg_drv(handle))
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 8d3365231bfd..0a7b606e7c93 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -18,6 +18,7 @@ enum hns3_nic_state {
 	HNS3_NIC_STATE_SERVICE_INITED,
 	HNS3_NIC_STATE_SERVICE_SCHED,
 	HNS3_NIC_STATE2_RESET_REQUESTED,
+	HNS3_NIC_STATE_HW_TX_CSUM_ENABLE,
 	HNS3_NIC_STATE_MAX
 };
 
@@ -82,6 +83,12 @@ enum hns3_nic_state {
 #define HNS3_RXD_STRP_TAGP_S			13
 #define HNS3_RXD_STRP_TAGP_M			(0x3 << HNS3_RXD_STRP_TAGP_S)
 
+#define HNS3_RXD_L2_CSUM_B			15
+#define HNS3_RXD_L2_CSUM_L_S			4
+#define HNS3_RXD_L2_CSUM_L_M			(0xff << HNS3_RXD_L2_CSUM_L_S)
+#define HNS3_RXD_L2_CSUM_H_S			24
+#define HNS3_RXD_L2_CSUM_H_M			(0xff << HNS3_RXD_L2_CSUM_H_S)
+
 #define HNS3_RXD_L2E_B				16
 #define HNS3_RXD_L3E_B				17
 #define HNS3_RXD_L4E_B				18
@@ -139,6 +146,9 @@ enum hns3_nic_state {
 #define HNS3_TXD_L4LEN_S			24
 #define HNS3_TXD_L4LEN_M			(0xff << HNS3_TXD_L4LEN_S)
 
+#define HNS3_TXD_CSUM_START_S		8
+#define HNS3_TXD_CSUM_START_M		(0xffff << HNS3_TXD_CSUM_START_S)
+
 #define HNS3_TXD_OL3T_S				0
 #define HNS3_TXD_OL3T_M				(0x3 << HNS3_TXD_OL3T_S)
 #define HNS3_TXD_OVLAN_B			2
@@ -146,6 +156,9 @@ enum hns3_nic_state {
 #define HNS3_TXD_TUNTYPE_S			4
 #define HNS3_TXD_TUNTYPE_M			(0xf << HNS3_TXD_TUNTYPE_S)
 
+#define HNS3_TXD_CSUM_OFFSET_S		8
+#define HNS3_TXD_CSUM_OFFSET_M		(0xffff << HNS3_TXD_CSUM_OFFSET_S)
+
 #define HNS3_TXD_BDTYPE_S			0
 #define HNS3_TXD_BDTYPE_M			(0xf << HNS3_TXD_BDTYPE_S)
 #define HNS3_TXD_FE_B				4
@@ -159,8 +172,11 @@ enum hns3_nic_state {
 #define HNS3_TXD_DECTTL_S			12
 #define HNS3_TXD_DECTTL_M			(0xf << HNS3_TXD_DECTTL_S)
 
+#define HNS3_TXD_OL4CS_B			22
+
 #define HNS3_TXD_MSS_S				0
 #define HNS3_TXD_MSS_M				(0x3fff << HNS3_TXD_MSS_S)
+#define HNS3_TXD_HW_CS_B			14
 
 #define HNS3_VECTOR_TX_IRQ			BIT_ULL(0)
 #define HNS3_VECTOR_RX_IRQ			BIT_ULL(1)
@@ -250,9 +266,9 @@ struct __packed hns3_desc {
 			};
 		};
 
-			__le32 paylen;
+			__le32 paylen_ol4cs;
 			__le16 bdtp_fe_sc_vld_ra_ri;
-			__le16 mss;
+			__le16 mss_hw_csum;
 		} tx;
 
 		struct {
@@ -371,6 +387,7 @@ struct ring_stats {
 			u64 err_bd_num;
 			u64 l2_err;
 			u64 l3l4_csum_err;
+			u64 csum_complete;
 			u64 rx_multicast;
 			u64 non_reuse_pg;
 		};
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index c30d5d3786c4..3cca3c125c03 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -55,6 +55,7 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 	HNS3_TQP_STAT("err_bd_num", err_bd_num),
 	HNS3_TQP_STAT("l2_err", l2_err),
 	HNS3_TQP_STAT("l3l4_csum_err", l3l4_csum_err),
+	HNS3_TQP_STAT("csum_complete", csum_complete),
 	HNS3_TQP_STAT("multicast", rx_multicast),
 	HNS3_TQP_STAT("non_reuse_pg", non_reuse_pg),
 };
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index e6321dda0f3f..85986c7d71fa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -355,6 +355,10 @@ static void hclge_parse_capability(struct hclge_dev *hdev,
 		set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
 	if (hnae3_get_bit(caps, HCLGE_CAP_TQP_TXRX_INDEP_B))
 		set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_HW_TX_CSUM_B))
+		set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_UDP_TUNNEL_CSUM_B))
+		set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps);
 }
 
 static enum hclge_cmd_status
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 6d7ba2052848..49cbd954f76b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -376,12 +376,13 @@ enum HCLGE_CAP_BITS {
 	HCLGE_CAP_FD_FORWARD_TC_B,
 	HCLGE_CAP_PTP_B,
 	HCLGE_CAP_INT_QL_B,
-	HCLGE_CAP_SIMPLE_BD_B,
+	HCLGE_CAP_HW_TX_CSUM_B,
 	HCLGE_CAP_TX_PUSH_B,
 	HCLGE_CAP_PHY_IMP_B,
 	HCLGE_CAP_TQP_TXRX_INDEP_B,
 	HCLGE_CAP_HW_PAD_B,
 	HCLGE_CAP_STASH_B,
+	HCLGE_CAP_UDP_TUNNEL_CSUM_B,
 };
 
 #define HCLGE_QUERY_CAP_LENGTH		3
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 54767b06ca6b..b1026cd1ba0a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -715,7 +715,7 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
 	}
 }
 
-static void hclge_pfc_info_init(struct hclge_dev *hdev)
+static void hclge_update_fc_mode_by_dcb_flag(struct hclge_dev *hdev)
 {
 	if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) {
 		if (hdev->fc_mode_last_time == HCLGE_FC_PFC)
@@ -733,6 +733,27 @@ static void hclge_pfc_info_init(struct hclge_dev *hdev)
 	}
 }
 
+static void hclge_update_fc_mode(struct hclge_dev *hdev)
+{
+	if (!hdev->tm_info.pfc_en) {
+		hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+		return;
+	}
+
+	if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) {
+		hdev->fc_mode_last_time = hdev->tm_info.fc_mode;
+		hdev->tm_info.fc_mode = HCLGE_FC_PFC;
+	}
+}
+
+static void hclge_pfc_info_init(struct hclge_dev *hdev)
+{
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+		hclge_update_fc_mode(hdev);
+	else
+		hclge_update_fc_mode_by_dcb_flag(hdev);
+}
+
 static void hclge_tm_schd_info_init(struct hclge_dev *hdev)
 {
 	hclge_tm_pg_info_init(hdev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index 66866c1cfb12..e04c0cfeb95c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -336,6 +336,10 @@ static void hclgevf_parse_capability(struct hclgevf_dev *hdev,
 		set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
 	if (hnae3_get_bit(caps, HCLGEVF_CAP_TQP_TXRX_INDEP_B))
 		set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGEVF_CAP_HW_TX_CSUM_B))
+		set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGEVF_CAP_UDP_TUNNEL_CSUM_B))
+		set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps);
 }
 
 static int hclgevf_cmd_query_version_and_capability(struct hclgevf_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 8b34a632b65a..82eed258e8c1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -152,12 +152,13 @@ enum HCLGEVF_CAP_BITS {
 	HCLGEVF_CAP_FD_FORWARD_TC_B,
 	HCLGEVF_CAP_PTP_B,
 	HCLGEVF_CAP_INT_QL_B,
-	HCLGEVF_CAP_SIMPLE_BD_B,
+	HCLGEVF_CAP_HW_TX_CSUM_B,
 	HCLGEVF_CAP_TX_PUSH_B,
 	HCLGEVF_CAP_PHY_IMP_B,
 	HCLGEVF_CAP_TQP_TXRX_INDEP_B,
 	HCLGEVF_CAP_HW_PAD_B,
 	HCLGEVF_CAP_STASH_B,
+	HCLGEVF_CAP_UDP_TUNNEL_CSUM_B,
 };
 
 #define HCLGEVF_QUERY_CAP_LENGTH		3