Merge branch 'hns3-next'

Huazhong Tan says:

====================
net: hns3: add some bugfixes & optimizations & cleanups for HNS3 driver

This patch-set includes code optimizations, bugfixes and cleanups for
the HNS3 ethernet controller driver.

[patch 01/12] fixes a GFP flag error.

[patch 02/12] fixes a VF interrupt error.

[patch 03/12] adds a cleanup for VLAN handling.

[patch 04/12] fixes a bug in debugfs.

[patch 05/12] modifies pause displaying format.

[patch 06/12] adds more DFX information for ethtool -d.

[patch 07/12] adds more TX statistics information.

[patch 08/12] adds a check for TX BD number.

[patch 09/12] adds a cleanup for dumping NCL_CONFIG.

[patch 10/12] refines function for querying MAC pause statistics.

[patch 11/12] adds a handshake with VF when doing PF reset.

[patch 12/12] refines some macro definitions.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 615 insertions, 242 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index a4624db3b5d5..6c9fd58c436f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -58,10 +58,10 @@
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
 
 #define hnae3_dev_roce_supported(hdev) \
-	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
 
 #define hnae3_dev_dcb_supported(hdev) \
-	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
+	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
 
 #define hnae3_dev_fd_supported(hdev) \
 	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B)
@@ -91,6 +91,11 @@ struct hnae3_queue {
 	u16 rx_desc_num;/* total number of rx desc */
 };
 
+struct hns3_mac_stats {
+	u64 tx_pause_cnt;
+	u64 rx_pause_cnt;
+};
+
 /*hnae3 loop mode*/
 enum hnae3_loop {
 	HNAE3_LOOP_APP,
@@ -298,6 +303,8 @@ struct hnae3_ae_dev {
  *   Remove multicast address from mac table
  * update_stats()
  *   Update Old network device statistics
+ * get_mac_stats()
+ *   get mac pause statistics including tx_cnt and rx_cnt
  * get_ethtool_stats()
  *   Get ethtool network device statistics
  * get_strings()
@@ -426,8 +433,8 @@ struct hnae3_ae_ops {
 	void (*update_stats)(struct hnae3_handle *handle,
 			     struct net_device_stats *net_stats);
 	void (*get_stats)(struct hnae3_handle *handle, u64 *data);
-	void (*get_mac_pause_stats)(struct hnae3_handle *handle, u64 *tx_cnt,
-				    u64 *rx_cnt);
+	void (*get_mac_stats)(struct hnae3_handle *handle,
+			      struct hns3_mac_stats *mac_stats);
 	void (*get_strings)(struct hnae3_handle *handle,
 			    u32 stringset, u8 *data);
 	int (*get_sset_count)(struct hnae3_handle *handle, int stringset);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index a4b937286f55..7996dcc21cf6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -8,6 +8,7 @@
 #include "hns3_enet.h"
 
 #define HNS3_DBG_READ_LEN 256
+#define HNS3_DBG_WRITE_LEN 1024
 
 static struct dentry *hns3_dbgfs_root;
 
@@ -322,6 +323,9 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 		return 0;
 
+	if (count > HNS3_DBG_WRITE_LEN)
+		return -ENOSPC;
+
 	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
 	if (!cmd_buf)
 		return count;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index ed05fb9f04ed..1750f80341e7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -28,6 +28,12 @@
 #define hns3_set_field(origin, shift, val)	((origin) |= ((val) << (shift)))
 #define hns3_tx_bd_count(S)	DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE)
 
+#define hns3_rl_err(fmt, ...)						\
+	do {								\
+		if (net_ratelimit())					\
+			netdev_err(fmt, ##__VA_ARGS__);			\
+	} while (0)
+
 static void hns3_clear_all_ring(struct hnae3_handle *h, bool force);
 static void hns3_remove_hw_addr(struct net_device *netdev);
 
@@ -45,6 +51,9 @@ MODULE_PARM_DESC(debug, " Network interface message level setting");
 #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \
 			   NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
 
+#define HNS3_INNER_VLAN_TAG	1
+#define HNS3_OUTER_VLAN_TAG	2
+
 /* hns3_pci_tbl - PCI Device ID Table
  *
  * Last entry must be all 0s
@@ -961,16 +970,16 @@ static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
 	hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1U);
 }
 
-static int hns3_fill_desc_vtags(struct sk_buff *skb,
-				struct hns3_enet_ring *tx_ring,
-				u32 *inner_vlan_flag,
-				u32 *out_vlan_flag,
-				u16 *inner_vtag,
-				u16 *out_vtag)
+static int hns3_handle_vtags(struct hns3_enet_ring *tx_ring,
+			     struct sk_buff *skb)
 {
-#define HNS3_TX_VLAN_PRIO_SHIFT 13
-
 	struct hnae3_handle *handle = tx_ring->tqp->handle;
+	struct vlan_ethhdr *vhdr;
+	int rc;
+
+	if (!(skb->protocol == htons(ETH_P_8021Q) ||
+	      skb_vlan_tag_present(skb)))
+		return 0;
 
 	/* Since HW limitation, if port based insert VLAN enabled, only one VLAN
 	 * header is allowed in skb, otherwise it will cause RAS error.
@@ -981,8 +990,7 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		return -EINVAL;
 
 	if (skb->protocol == htons(ETH_P_8021Q) &&
-	    !(tx_ring->tqp->handle->kinfo.netdev->features &
-	    NETIF_F_HW_VLAN_CTAG_TX)) {
+	    !(handle->kinfo.netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) {
 		/* When HW VLAN acceleration is turned off, and the stack
 		 * sets the protocol to 802.1q, the driver just need to
 		 * set the protocol to the encapsulated ethertype.
@@ -992,45 +1000,107 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 	}
 
 	if (skb_vlan_tag_present(skb)) {
-		u16 vlan_tag;
-
-		vlan_tag = skb_vlan_tag_get(skb);
-		vlan_tag |= (skb->priority & 0x7) << HNS3_TX_VLAN_PRIO_SHIFT;
-
 		/* Based on hw strategy, use out_vtag in two layer tag case,
 		 * and use inner_vtag in one tag case.
 		 */
-		if (skb->protocol == htons(ETH_P_8021Q)) {
-			if (handle->port_base_vlan_state ==
-			    HNAE3_PORT_BASE_VLAN_DISABLE){
-				hns3_set_field(*out_vlan_flag,
-					       HNS3_TXD_OVLAN_B, 1);
-				*out_vtag = vlan_tag;
-			} else {
-				hns3_set_field(*inner_vlan_flag,
-					       HNS3_TXD_VLAN_B, 1);
-				*inner_vtag = vlan_tag;
-			}
-		} else {
-			hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
-			*inner_vtag = vlan_tag;
-		}
-	} else if (skb->protocol == htons(ETH_P_8021Q)) {
-		struct vlan_ethhdr *vhdr;
-		int rc;
+		if (skb->protocol == htons(ETH_P_8021Q) &&
+		    handle->port_base_vlan_state ==
+		    HNAE3_PORT_BASE_VLAN_DISABLE)
+			rc = HNS3_OUTER_VLAN_TAG;
+		else
+			rc = HNS3_INNER_VLAN_TAG;
 
-		rc = skb_cow_head(skb, 0);
-		if (unlikely(rc < 0))
-			return rc;
-		vhdr = (struct vlan_ethhdr *)skb->data;
-		vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority & 0x7)
-					<< HNS3_TX_VLAN_PRIO_SHIFT);
+		skb->protocol = vlan_get_protocol(skb);
+		return rc;
 	}
 
+	rc = skb_cow_head(skb, 0);
+	if (unlikely(rc < 0))
+		return rc;
+
+	vhdr = (struct vlan_ethhdr *)skb->data;
+	vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority << VLAN_PRIO_SHIFT)
+					 & VLAN_PRIO_MASK);
+
 	skb->protocol = vlan_get_protocol(skb);
 	return 0;
 }
 
+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 type_cs_vlan_tso = 0;
+	u32 paylen = skb->len;
+	u16 inner_vtag = 0;
+	u16 out_vtag = 0;
+	u16 mss = 0;
+	int ret;
+
+	ret = hns3_handle_vtags(ring, skb);
+	if (unlikely(ret < 0)) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_vlan_err++;
+		u64_stats_update_end(&ring->syncp);
+		return ret;
+	} else if (ret == HNS3_INNER_VLAN_TAG) {
+		inner_vtag = skb_vlan_tag_get(skb);
+		inner_vtag |= (skb->priority << VLAN_PRIO_SHIFT) &
+				VLAN_PRIO_MASK;
+		hns3_set_field(type_cs_vlan_tso, HNS3_TXD_VLAN_B, 1);
+	} else if (ret == HNS3_OUTER_VLAN_TAG) {
+		out_vtag = skb_vlan_tag_get(skb);
+		out_vtag |= (skb->priority << VLAN_PRIO_SHIFT) &
+				VLAN_PRIO_MASK;
+		hns3_set_field(ol_type_vlan_len_msec, HNS3_TXD_OVLAN_B,
+			       1);
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		u8 ol4_proto, il4_proto;
+
+		skb_reset_mac_len(skb);
+
+		ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
+		if (unlikely(ret)) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.tx_l4_proto_err++;
+			u64_stats_update_end(&ring->syncp);
+			return ret;
+		}
+
+		ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto,
+				      &type_cs_vlan_tso,
+				      &ol_type_vlan_len_msec);
+		if (unlikely(ret)) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.tx_l2l3l4_err++;
+			u64_stats_update_end(&ring->syncp);
+			return ret;
+		}
+
+		ret = hns3_set_tso(skb, &paylen, &mss,
+				   &type_cs_vlan_tso);
+		if (unlikely(ret)) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.tx_tso_err++;
+			u64_stats_update_end(&ring->syncp);
+			return ret;
+		}
+	}
+
+	/* 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.vlan_tag = cpu_to_le16(inner_vtag);
+	desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag);
+
+	return 0;
+}
+
 static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 			  unsigned int size, int frag_end,
 			  enum hns_desc_type type)
@@ -1045,50 +1115,12 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 
 	if (type == DESC_TYPE_SKB) {
 		struct sk_buff *skb = (struct sk_buff *)priv;
-		u32 ol_type_vlan_len_msec = 0;
-		u32 type_cs_vlan_tso = 0;
-		u32 paylen = skb->len;
-		u16 inner_vtag = 0;
-		u16 out_vtag = 0;
-		u16 mss = 0;
 		int ret;
 
-		ret = hns3_fill_desc_vtags(skb, ring, &type_cs_vlan_tso,
-					   &ol_type_vlan_len_msec,
-					   &inner_vtag, &out_vtag);
+		ret = hns3_fill_skb_desc(ring, skb, desc);
 		if (unlikely(ret))
 			return ret;
 
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			u8 ol4_proto, il4_proto;
-
-			skb_reset_mac_len(skb);
-
-			ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
-			if (unlikely(ret))
-				return ret;
-
-			ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto,
-					      &type_cs_vlan_tso,
-					      &ol_type_vlan_len_msec);
-			if (unlikely(ret))
-				return ret;
-
-			ret = hns3_set_tso(skb, &paylen, &mss,
-					   &type_cs_vlan_tso);
-			if (unlikely(ret))
-				return ret;
-		}
-
-		/* 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.vlan_tag = cpu_to_le16(inner_vtag);
-		desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag);
-
 		dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE);
 	} else {
 		frag = (skb_frag_t *)priv;
@@ -1096,7 +1128,9 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	}
 
 	if (unlikely(dma_mapping_error(dev, dma))) {
+		u64_stats_update_begin(&ring->syncp);
 		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
 		return -ENOMEM;
 	}
 
@@ -1152,28 +1186,20 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	return 0;
 }
 
-static int hns3_nic_bd_num(struct sk_buff *skb)
+static unsigned int hns3_nic_bd_num(struct sk_buff *skb)
 {
-	int size = skb_headlen(skb);
-	int i, bd_num;
+	unsigned int bd_num;
+	int i;
 
 	/* if the total len is within the max bd limit */
 	if (likely(skb->len <= HNS3_MAX_BD_SIZE))
 		return skb_shinfo(skb)->nr_frags + 1;
 
-	bd_num = hns3_tx_bd_count(size);
+	bd_num = hns3_tx_bd_count(skb_headlen(skb));
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-		int frag_bd_num;
-
-		size = skb_frag_size(frag);
-		frag_bd_num = hns3_tx_bd_count(size);
-
-		if (unlikely(frag_bd_num > HNS3_MAX_BD_PER_FRAG))
-			return -ENOMEM;
-
-		bd_num += frag_bd_num;
+		bd_num += hns3_tx_bd_count(skb_frag_size(frag));
 	}
 
 	return bd_num;
@@ -1194,7 +1220,7 @@ static unsigned int hns3_gso_hdr_len(struct sk_buff *skb)
  */
 static bool hns3_skb_need_linearized(struct sk_buff *skb)
 {
-	int bd_limit = HNS3_MAX_BD_PER_FRAG - 1;
+	int bd_limit = HNS3_MAX_BD_NUM_NORMAL - 1;
 	unsigned int tot_len = 0;
 	int i;
 
@@ -1224,21 +1250,16 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 				  struct sk_buff **out_skb)
 {
 	struct sk_buff *skb = *out_skb;
-	int bd_num;
+	unsigned int bd_num;
 
 	bd_num = hns3_nic_bd_num(skb);
-	if (bd_num < 0)
-		return bd_num;
-
-	if (unlikely(bd_num > HNS3_MAX_BD_PER_FRAG)) {
+	if (unlikely(bd_num > HNS3_MAX_BD_NUM_NORMAL)) {
 		struct sk_buff *new_skb;
 
-		if (skb_is_gso(skb) && !hns3_skb_need_linearized(skb))
+		if (skb_is_gso(skb) && bd_num <= HNS3_MAX_BD_NUM_TSO &&
+		    !hns3_skb_need_linearized(skb))
 			goto out;
 
-		bd_num = hns3_tx_bd_count(skb->len);
-		if (unlikely(ring_space(ring) < bd_num))
-			return -EBUSY;
 		/* manual split the send packet */
 		new_skb = skb_copy(skb, GFP_ATOMIC);
 		if (!new_skb)
@@ -1246,6 +1267,11 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 		dev_kfree_skb_any(skb);
 		*out_skb = new_skb;
 
+		bd_num = hns3_nic_bd_num(new_skb);
+		if ((skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_TSO) ||
+		    (!skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_NORMAL))
+			return -ENOMEM;
+
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.tx_copy++;
 		u64_stats_update_end(&ring->syncp);
@@ -1319,9 +1345,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 			u64_stats_update_end(&ring->syncp);
 		}
 
-		if (net_ratelimit())
-			netdev_err(netdev, "xmit error: %d!\n", buf_num);
-
+		hns3_rl_err(netdev, "xmit error: %d!\n", buf_num);
 		goto out_err_tx_ok;
 	}
 
@@ -1487,7 +1511,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			tx_bytes += ring->stats.tx_bytes;
 			tx_pkts += ring->stats.tx_pkts;
 			tx_drop += ring->stats.sw_err_cnt;
+			tx_drop += ring->stats.tx_vlan_err;
+			tx_drop += ring->stats.tx_l4_proto_err;
+			tx_drop += ring->stats.tx_l2l3l4_err;
+			tx_drop += ring->stats.tx_tso_err;
 			tx_errors += ring->stats.sw_err_cnt;
+			tx_errors += ring->stats.tx_vlan_err;
+			tx_errors += ring->stats.tx_l4_proto_err;
+			tx_errors += ring->stats.tx_l2l3l4_err;
+			tx_errors += ring->stats.tx_tso_err;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -1694,15 +1726,12 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
 	/* When mac received many pause frames continuous, it's unable to send
 	 * packets, which may cause tx timeout
 	 */
-	if (h->ae_algo->ops->update_stats &&
-	    h->ae_algo->ops->get_mac_pause_stats) {
-		u64 tx_pause_cnt, rx_pause_cnt;
+	if (h->ae_algo->ops->get_mac_stats) {
+		struct hns3_mac_stats mac_stats;
 
-		h->ae_algo->ops->update_stats(h, &ndev->stats);
-		h->ae_algo->ops->get_mac_pause_stats(h, &tx_pause_cnt,
-						     &rx_pause_cnt);
+		h->ae_algo->ops->get_mac_stats(h, &mac_stats);
 		netdev_info(ndev, "tx_pause_cnt: %llu, rx_pause_cnt: %llu\n",
-			    tx_pause_cnt, rx_pause_cnt);
+			    mac_stats.tx_pause_cnt, mac_stats.rx_pause_cnt);
 	}
 
 	hw_head = readl_relaxed(tx_ring->tqp->io_base +
@@ -2371,8 +2400,9 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
 				ring->stats.sw_err_cnt++;
 				u64_stats_update_end(&ring->syncp);
 
-				netdev_err(ring->tqp->handle->kinfo.netdev,
-					   "hnae reserve buffer map failed.\n");
+				hns3_rl_err(ring->tqp_vector->napi.dev,
+					    "alloc rx buffer failed: %d\n",
+					    ret);
 				break;
 			}
 			hns3_replace_buffer(ring, ring->next_to_use, &res_cbs);
@@ -2457,9 +2487,9 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
 		th->check = ~tcp_v6_check(skb->len - depth, &iph->saddr,
 					  &iph->daddr, 0);
 	} else {
-		netdev_err(skb->dev,
-			   "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n",
-			   be16_to_cpu(type), depth);
+		hns3_rl_err(skb->dev,
+			    "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n",
+			    be16_to_cpu(type), depth);
 		return -EFAULT;
 	}
 
@@ -2601,7 +2631,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 	ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE);
 	skb = ring->skb;
 	if (unlikely(!skb)) {
-		netdev_err(netdev, "alloc rx skb fail\n");
+		hns3_rl_err(netdev, "alloc rx skb fail\n");
 
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.sw_err_cnt++;
@@ -2676,8 +2706,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 			new_skb = napi_alloc_skb(&ring->tqp_vector->napi,
 						 HNS3_RX_HEAD_SIZE);
 			if (unlikely(!new_skb)) {
-				netdev_err(ring->tqp->handle->kinfo.netdev,
-					   "alloc rx skb frag fail\n");
+				hns3_rl_err(ring->tqp_vector->napi.dev,
+					    "alloc rx fraglist skb fail\n");
 				return -ENXIO;
 			}
 			ring->frag_num = 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 0a970f5fed10..5b0ee1fe40f1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -195,7 +195,8 @@ enum hns3_nic_state {
 #define HNS3_VECTOR_INITED			1
 
 #define HNS3_MAX_BD_SIZE			65535
-#define HNS3_MAX_BD_PER_FRAG			8
+#define HNS3_MAX_BD_NUM_NORMAL			8
+#define HNS3_MAX_BD_NUM_TSO			63
 #define HNS3_MAX_BD_PER_PKT			MAX_SKB_FRAGS
 
 #define HNS3_VECTOR_GL0_OFFSET			0x100
@@ -377,6 +378,10 @@ struct ring_stats {
 			u64 restart_queue;
 			u64 tx_busy;
 			u64 tx_copy;
+			u64 tx_vlan_err;
+			u64 tx_l4_proto_err;
+			u64 tx_l2l3l4_err;
+			u64 tx_tso_err;
 		};
 		struct {
 			u64 rx_pkts;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 02f46c73ac3b..185ff32262e4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -30,6 +30,10 @@ static const struct hns3_stats hns3_txq_stats[] = {
 	HNS3_TQP_STAT("wake", restart_queue),
 	HNS3_TQP_STAT("busy", tx_busy),
 	HNS3_TQP_STAT("copy", tx_copy),
+	HNS3_TQP_STAT("vlan_err", tx_vlan_err),
+	HNS3_TQP_STAT("l4_proto_err", tx_l4_proto_err),
+	HNS3_TQP_STAT("l2l3l4_err", tx_l2l3l4_err),
+	HNS3_TQP_STAT("tso_err", tx_tso_err),
 };
 
 #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index dade20a37d40..29979be9e33a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -87,6 +87,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QUERY_VF_RSRC		= 0x0024,
 	HCLGE_OPC_GET_CFG_PARAM		= 0x0025,
 	HCLGE_OPC_PF_RST_DONE		= 0x0026,
+	HCLGE_OPC_QUERY_VF_RST_RDY	= 0x0027,
 
 	HCLGE_OPC_STATS_64_BIT		= 0x0030,
 	HCLGE_OPC_STATS_32_BIT		= 0x0031,
@@ -588,6 +589,12 @@ struct hclge_config_mac_mode_cmd {
 	u8 rsv[20];
 };
 
+struct hclge_pf_rst_sync_cmd {
+#define HCLGE_PF_RST_ALL_VF_RDY_B	0
+	u8 all_vf_ready;
+	u8 rsv[23];
+};
+
 #define HCLGE_CFG_SPEED_S		0
 #define HCLGE_CFG_SPEED_M		GENMASK(5, 0)
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index f16bfc67412a..f0295d12a1b6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -14,16 +14,8 @@ static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset)
 	struct hclge_desc desc[4];
 	int ret;
 
-	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true);
-
-	ret = hclge_cmd_send(&hdev->hw, desc, 4);
-	if (ret != HCLGE_CMD_EXEC_SUCCESS) {
+	ret = hclge_query_bd_num_cmd_send(hdev, desc);
+	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"get dfx bdnum fail, status is %d.\n", ret);
 		return ret;
@@ -1003,6 +995,33 @@ void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev)
 	kfree(desc_src);
 }
 
+#define HCLGE_CMD_NCL_CONFIG_BD_NUM	5
+
+static void hclge_ncl_config_data_print(struct hclge_dev *hdev,
+					struct hclge_desc *desc, int *offset,
+					int *length)
+{
+#define HCLGE_CMD_DATA_NUM		6
+
+	int i;
+	int j;
+
+	for (i = 0; i < HCLGE_CMD_NCL_CONFIG_BD_NUM; i++) {
+		for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) {
+			if (i == 0 && j == 0)
+				continue;
+
+			dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n",
+				 *offset,
+				 le32_to_cpu(desc[i].data[j]));
+			*offset += sizeof(u32);
+			*length -= sizeof(u32);
+			if (*length <= 0)
+				return;
+		}
+	}
+}
+
 /* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file
  * @hdev: pointer to struct hclge_dev
  * @cmd_buf: string that contains offset and length
@@ -1012,17 +1031,13 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
 {
 #define HCLGE_MAX_NCL_CONFIG_OFFSET	4096
 #define HCLGE_MAX_NCL_CONFIG_LENGTH	(20 + 24 * 4)
-#define HCLGE_CMD_DATA_NUM		6
 
-	struct hclge_desc desc[5];
-	u32 byte_offset;
-	int bd_num = 5;
+	struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM];
+	int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM;
 	int offset;
 	int length;
 	int data0;
 	int ret;
-	int i;
-	int j;
 
 	ret = sscanf(cmd_buf, "%x %x", &offset, &length);
 	if (ret != 2 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET ||
@@ -1048,22 +1063,7 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
 		if (ret)
 			return;
 
-		byte_offset = offset;
-		for (i = 0; i < bd_num; i++) {
-			for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) {
-				if (i == 0 && j == 0)
-					continue;
-
-				dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n",
-					 byte_offset,
-					 le32_to_cpu(desc[i].data[j]));
-				byte_offset += sizeof(u32);
-				length -= sizeof(u32);
-				if (length <= 0)
-					return;
-			}
-		}
-		offset += HCLGE_MAX_NCL_CONFIG_LENGTH;
+		hclge_ncl_config_data_print(hdev, desc, &offset, &length);
 	}
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b7399f5ba2c3..d207dac1fd5e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -35,6 +35,23 @@
 #define BUF_RESERVE_PERCENT	90
 
 #define HCLGE_RESET_MAX_FAIL_CNT	5
+#define HCLGE_RESET_SYNC_TIME		100
+#define HCLGE_PF_RESET_SYNC_TIME	20
+#define HCLGE_PF_RESET_SYNC_CNT		1500
+
+/* Get DFX BD number offset */
+#define HCLGE_DFX_BIOS_BD_OFFSET        1
+#define HCLGE_DFX_SSU_0_BD_OFFSET       2
+#define HCLGE_DFX_SSU_1_BD_OFFSET       3
+#define HCLGE_DFX_IGU_BD_OFFSET         4
+#define HCLGE_DFX_RPU_0_BD_OFFSET       5
+#define HCLGE_DFX_RPU_1_BD_OFFSET       6
+#define HCLGE_DFX_NCSI_BD_OFFSET        7
+#define HCLGE_DFX_RTC_BD_OFFSET         8
+#define HCLGE_DFX_PPP_BD_OFFSET         9
+#define HCLGE_DFX_RCB_BD_OFFSET         10
+#define HCLGE_DFX_TQP_BD_OFFSET         11
+#define HCLGE_DFX_SSU_2_BD_OFFSET       12
 
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
@@ -317,6 +334,36 @@ static const u8 hclge_hash_key[] = {
 	0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA
 };
 
+static const u32 hclge_dfx_bd_offset_list[] = {
+	HCLGE_DFX_BIOS_BD_OFFSET,
+	HCLGE_DFX_SSU_0_BD_OFFSET,
+	HCLGE_DFX_SSU_1_BD_OFFSET,
+	HCLGE_DFX_IGU_BD_OFFSET,
+	HCLGE_DFX_RPU_0_BD_OFFSET,
+	HCLGE_DFX_RPU_1_BD_OFFSET,
+	HCLGE_DFX_NCSI_BD_OFFSET,
+	HCLGE_DFX_RTC_BD_OFFSET,
+	HCLGE_DFX_PPP_BD_OFFSET,
+	HCLGE_DFX_RCB_BD_OFFSET,
+	HCLGE_DFX_TQP_BD_OFFSET,
+	HCLGE_DFX_SSU_2_BD_OFFSET
+};
+
+static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = {
+	HCLGE_OPC_DFX_BIOS_COMMON_REG,
+	HCLGE_OPC_DFX_SSU_REG_0,
+	HCLGE_OPC_DFX_SSU_REG_1,
+	HCLGE_OPC_DFX_IGU_EGU_REG,
+	HCLGE_OPC_DFX_RPU_REG_0,
+	HCLGE_OPC_DFX_RPU_REG_1,
+	HCLGE_OPC_DFX_NCSI_REG,
+	HCLGE_OPC_DFX_RTC_REG,
+	HCLGE_OPC_DFX_PPP_REG,
+	HCLGE_OPC_DFX_RCB_REG,
+	HCLGE_OPC_DFX_TQP_REG,
+	HCLGE_OPC_DFX_SSU_REG_2
+};
+
 static int hclge_mac_update_stats_defective(struct hclge_dev *hdev)
 {
 #define HCLGE_MAC_CMD_NUM 21
@@ -364,9 +411,13 @@ static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num)
 	u16 i, k, n;
 	int ret;
 
-	desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	/* This may be called inside atomic sections,
+	 * so GFP_ATOMIC is more suitalbe here
+	 */
+	desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_ATOMIC);
 	if (!desc)
 		return -ENOMEM;
+
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true);
 	ret = hclge_cmd_send(&hdev->hw, desc, desc_num);
 	if (ret) {
@@ -702,14 +753,16 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data)
 	p = hclge_tqps_get_stats(handle, p);
 }
 
-static void hclge_get_mac_pause_stat(struct hnae3_handle *handle, u64 *tx_cnt,
-				     u64 *rx_cnt)
+static void hclge_get_mac_stat(struct hnae3_handle *handle,
+			       struct hns3_mac_stats *mac_stats)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	*tx_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num;
-	*rx_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num;
+	hclge_update_stats(handle, NULL);
+
+	mac_stats->tx_pause_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num;
+	mac_stats->rx_pause_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num;
 }
 
 static int hclge_parse_func_status(struct hclge_dev *hdev,
@@ -3134,6 +3187,39 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
 	return 0;
 }
 
+int hclge_func_reset_sync_vf(struct hclge_dev *hdev)
+{
+	struct hclge_pf_rst_sync_cmd *req;
+	struct hclge_desc desc;
+	int cnt = 0;
+	int ret;
+
+	req = (struct hclge_pf_rst_sync_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_VF_RST_RDY, true);
+
+	do {
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		/* for compatible with old firmware, wait
+		 * 100 ms for VF to stop IO
+		 */
+		if (ret == -EOPNOTSUPP) {
+			msleep(HCLGE_RESET_SYNC_TIME);
+			return 0;
+		} else if (ret) {
+			dev_err(&hdev->pdev->dev, "sync with VF fail %d!\n",
+				ret);
+			return ret;
+		} else if (req->all_vf_ready) {
+			return 0;
+		}
+		msleep(HCLGE_PF_RESET_SYNC_TIME);
+		hclge_cmd_reuse_desc(&desc, true);
+	} while (cnt++ < HCLGE_PF_RESET_SYNC_CNT);
+
+	dev_err(&hdev->pdev->dev, "sync with VF timeout!\n");
+	return -ETIME;
+}
+
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 {
 	struct hclge_desc desc;
@@ -3300,17 +3386,18 @@ static void hclge_reset_handshake(struct hclge_dev *hdev, bool enable)
 
 static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 {
-#define HCLGE_RESET_SYNC_TIME 100
-
 	u32 reg_val;
 	int ret = 0;
 
 	switch (hdev->reset_type) {
 	case HNAE3_FUNC_RESET:
-		/* There is no mechanism for PF to know if VF has stopped IO
-		 * for now, just wait 100 ms for VF to stop IO
+		/* to confirm whether all running VF is ready
+		 * before request PF reset
 		 */
-		msleep(HCLGE_RESET_SYNC_TIME);
+		ret = hclge_func_reset_sync_vf(hdev);
+		if (ret)
+			return ret;
+
 		ret = hclge_func_reset_cmd(hdev, 0);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -3327,10 +3414,13 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		hdev->rst_stats.pf_rst_cnt++;
 		break;
 	case HNAE3_FLR_RESET:
-		/* There is no mechanism for PF to know if VF has stopped IO
-		 * for now, just wait 100 ms for VF to stop IO
+		/* to confirm whether all running VF is ready
+		 * before request PF reset
 		 */
-		msleep(HCLGE_RESET_SYNC_TIME);
+		ret = hclge_func_reset_sync_vf(hdev);
+		if (ret)
+			return ret;
+
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
 		hdev->rst_stats.flr_rst_cnt++;
@@ -8203,28 +8293,15 @@ static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en)
 {
 	int ret;
 
-	if (rx_en && tx_en)
-		hdev->fc_mode_last_time = HCLGE_FC_FULL;
-	else if (rx_en && !tx_en)
-		hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE;
-	else if (!rx_en && tx_en)
-		hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE;
-	else
-		hdev->fc_mode_last_time = HCLGE_FC_NONE;
-
 	if (hdev->tm_info.fc_mode == HCLGE_FC_PFC)
 		return 0;
 
 	ret = hclge_mac_pause_en_cfg(hdev, tx_en, rx_en);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "configure pauseparam error, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"configure pauseparam error, ret = %d.\n", ret);
 
-	return 0;
+	return ret;
 }
 
 int hclge_cfg_flowctrl(struct hclge_dev *hdev)
@@ -8289,6 +8366,21 @@ static void hclge_get_pauseparam(struct hnae3_handle *handle, u32 *auto_neg,
 	}
 }
 
+static void hclge_record_user_pauseparam(struct hclge_dev *hdev,
+					 u32 rx_en, u32 tx_en)
+{
+	if (rx_en && tx_en)
+		hdev->fc_mode_last_time = HCLGE_FC_FULL;
+	else if (rx_en && !tx_en)
+		hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE;
+	else if (!rx_en && tx_en)
+		hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE;
+	else
+		hdev->fc_mode_last_time = HCLGE_FC_NONE;
+
+	hdev->tm_info.fc_mode = hdev->fc_mode_last_time;
+}
+
 static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg,
 				u32 rx_en, u32 tx_en)
 {
@@ -8314,6 +8406,8 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg,
 
 	hclge_set_flowctrl_adv(hdev, rx_en, tx_en);
 
+	hclge_record_user_pauseparam(hdev, rx_en, tx_en);
+
 	if (!auto_neg)
 		return hclge_cfg_pauseparam(hdev, rx_en, tx_en);
 
@@ -9324,106 +9418,314 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 }
 
 #define MAX_SEPARATE_NUM	4
-#define SEPARATOR_VALUE		0xFFFFFFFF
+#define SEPARATOR_VALUE		0xFDFCFBFA
 #define REG_NUM_PER_LINE	4
 #define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+#define REG_SEPARATOR_LINE	1
+#define REG_NUM_REMAIN_MASK	3
+#define BD_LIST_MAX_NUM		30
 
-static int hclge_get_regs_len(struct hnae3_handle *handle)
+int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc)
 {
-	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
-	u32 regs_num_32_bit, regs_num_64_bit;
+	/*prepare 4 commands to query DFX BD number*/
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true);
+
+	return hclge_cmd_send(&hdev->hw, desc, 4);
+}
+
+static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev,
+				    int *bd_num_list,
+				    u32 type_num)
+{
+#define HCLGE_DFX_REG_BD_NUM	4
+
+	u32 entries_per_desc, desc_index, index, offset, i;
+	struct hclge_desc desc[HCLGE_DFX_REG_BD_NUM];
 	int ret;
 
-	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
+	ret = hclge_query_bd_num_cmd_send(hdev, desc);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"Get register number failed, ret = %d.\n", ret);
-		return -EOPNOTSUPP;
+			"Get dfx bd num fail, status is %d.\n", ret);
+		return ret;
 	}
 
-	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
-	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	entries_per_desc = ARRAY_SIZE(desc[0].data);
+	for (i = 0; i < type_num; i++) {
+		offset = hclge_dfx_bd_offset_list[i];
+		index = offset % entries_per_desc;
+		desc_index = offset / entries_per_desc;
+		bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]);
+	}
 
-	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
-		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE +
-		regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64);
+	return ret;
 }
 
-static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
-			   void *data)
+static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev,
+				  struct hclge_desc *desc_src, int bd_num,
+				  enum hclge_opcode_type cmd)
 {
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
-	u32 regs_num_32_bit, regs_num_64_bit;
-	int i, j, reg_um, separator_num;
+	struct hclge_desc *desc = desc_src;
+	int i, ret;
+
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	for (i = 0; i < bd_num - 1; i++) {
+		desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+		desc++;
+		hclge_cmd_setup_basic_desc(desc, cmd, true);
+	}
+
+	desc = desc_src;
+	ret = hclge_cmd_send(&hdev->hw, desc, bd_num);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"Query dfx reg cmd(0x%x) send fail, status is %d.\n",
+			cmd, ret);
+
+	return ret;
+}
+
+static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num,
+				    void *data)
+{
+	int entries_per_desc, reg_num, separator_num, desc_index, index, i;
+	struct hclge_desc *desc = desc_src;
 	u32 *reg = data;
+
+	entries_per_desc = ARRAY_SIZE(desc->data);
+	reg_num = entries_per_desc * bd_num;
+	separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++) {
+		index = i % entries_per_desc;
+		desc_index = i / entries_per_desc;
+		*reg++ = le32_to_cpu(desc[desc_index].data[index]);
+	}
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	return reg_num + separator_num;
+}
+
+static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
+{
+	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
+	int data_len_per_desc, data_len, bd_num, i;
+	int bd_num_list[BD_LIST_MAX_NUM];
 	int ret;
 
-	*version = hdev->fw_version;
+	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg bd num fail, status is %d.\n", ret);
+		return ret;
+	}
 
-	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
+	data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data);
+	*len = 0;
+	for (i = 0; i < dfx_reg_type_num; i++) {
+		bd_num = bd_num_list[i];
+		data_len = data_len_per_desc * bd_num;
+		*len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE;
+	}
+
+	return ret;
+}
+
+static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
+{
+	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
+	int bd_num, bd_num_max, buf_len, i;
+	int bd_num_list[BD_LIST_MAX_NUM];
+	struct hclge_desc *desc_src;
+	u32 *reg = data;
+	int ret;
+
+	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"Get register number failed, ret = %d.\n", ret);
-		return;
+			"Get dfx reg bd num fail, status is %d.\n", ret);
+		return ret;
 	}
 
+	bd_num_max = bd_num_list[0];
+	for (i = 1; i < dfx_reg_type_num; i++)
+		bd_num_max = max_t(int, bd_num_max, bd_num_list[i]);
+
+	buf_len = sizeof(*desc_src) * bd_num_max;
+	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	if (!desc_src) {
+		dev_err(&hdev->pdev->dev, "%s kzalloc failed\n", __func__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < dfx_reg_type_num; i++) {
+		bd_num = bd_num_list[i];
+		ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num,
+					     hclge_dfx_reg_opcode_list[i]);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"Get dfx reg fail, status is %d.\n", ret);
+			break;
+		}
+
+		reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg);
+	}
+
+	kfree(desc_src);
+	return ret;
+}
+
+static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
+			      struct hnae3_knic_private_info *kinfo)
+{
+#define HCLGE_RING_REG_OFFSET		0x200
+#define HCLGE_RING_INT_REG_OFFSET	0x4
+
+	int i, j, reg_num, separator_num;
+	int data_num_sum;
+	u32 *reg = data;
+
 	/* fetching per-PF registers valus from PF PCIe register space */
-	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (i = 0; i < reg_um; i++)
+	reg_num = ARRAY_SIZE(cmdq_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++)
 		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
 	for (i = 0; i < separator_num; i++)
 		*reg++ = SEPARATOR_VALUE;
+	data_num_sum = reg_num + separator_num;
 
-	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
-	for (i = 0; i < reg_um; i++)
+	reg_num = ARRAY_SIZE(common_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < reg_num; i++)
 		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
 	for (i = 0; i < separator_num; i++)
 		*reg++ = SEPARATOR_VALUE;
+	data_num_sum += reg_num + separator_num;
 
-	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	reg_num = ARRAY_SIZE(ring_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
 	for (j = 0; j < kinfo->num_tqps; j++) {
-		for (i = 0; i < reg_um; i++)
+		for (i = 0; i < reg_num; i++)
 			*reg++ = hclge_read_dev(&hdev->hw,
 						ring_reg_addr_list[i] +
-						0x200 * j);
+						HCLGE_RING_REG_OFFSET * j);
 		for (i = 0; i < separator_num; i++)
 			*reg++ = SEPARATOR_VALUE;
 	}
+	data_num_sum += (reg_num + separator_num) * kinfo->num_tqps;
 
-	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
-	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list);
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
 	for (j = 0; j < hdev->num_msi_used - 1; j++) {
-		for (i = 0; i < reg_um; i++)
+		for (i = 0; i < reg_num; i++)
 			*reg++ = hclge_read_dev(&hdev->hw,
 						tqp_intr_reg_addr_list[i] +
-						4 * j);
+						HCLGE_RING_INT_REG_OFFSET * j);
 		for (i = 0; i < separator_num; i++)
 			*reg++ = SEPARATOR_VALUE;
 	}
+	data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1);
+
+	return data_num_sum;
+}
+
+static int hclge_get_regs_len(struct hnae3_handle *handle)
+{
+	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	int regs_num_32_bit, regs_num_64_bit, dfx_regs_len;
+	int regs_lines_32_bit, regs_lines_64_bit;
+	int ret;
+
+	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get register number failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get dfx reg len failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+	regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE +
+		REG_SEPARATOR_LINE;
+
+	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
+		tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit +
+		regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len;
+}
+
+static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
+			   void *data)
+{
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	u32 regs_num_32_bit, regs_num_64_bit;
+	int i, reg_num, separator_num, ret;
+	u32 *reg = data;
+
+	*version = hdev->fw_version;
+
+	ret = hclge_get_regs_num(hdev, &regs_num_32_bit, &regs_num_64_bit);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Get register number failed, ret = %d.\n", ret);
+		return;
+	}
+
+	reg += hclge_fetch_pf_reg(hdev, reg, kinfo);
 
-	/* fetching PF common registers values from firmware */
 	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 32 bit register failed, ret = %d.\n", ret);
 		return;
 	}
+	reg_num = regs_num_32_bit;
+	reg += reg_num;
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
 
-	reg += regs_num_32_bit;
 	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg);
-	if (ret)
+	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 64 bit register failed, ret = %d.\n", ret);
+		return;
+	}
+	reg_num = regs_num_64_bit * 2;
+	reg += reg_num;
+	separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	ret = hclge_get_dfx_reg(hdev, reg);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"Get dfx register failed, ret = %d.\n", ret);
 }
 
 static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status)
@@ -9538,7 +9840,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_mtu = hclge_set_mtu,
 	.reset_queue = hclge_reset_tqp,
 	.get_stats = hclge_get_stats,
-	.get_mac_pause_stats = hclge_get_mac_pause_stat,
+	.get_mac_stats = hclge_get_mac_stat,
 	.update_stats = hclge_update_stats,
 	.get_strings = hclge_get_strings,
 	.get_sset_count = hclge_get_sset_count,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index c9b9867fc226..f6d9b57830fb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1029,4 +1029,6 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
 				      u16 state, u16 vlan_tag, u16 qos,
 				      u16 vlan_proto);
 void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time);
+int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev,
+				struct hclge_desc *desc);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index ce82b2b0f8f5..d8b828180aa8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1889,21 +1889,20 @@ static void hclgevf_clear_event_cause(struct hclgevf_dev *hdev, u32 regclr)
 static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 						      u32 *clearval)
 {
-	u32 val, cmdq_src_reg, rst_ing_reg;
+	u32 val, cmdq_stat_reg, rst_ing_reg;
 
 	/* fetch the events from their corresponding regs */
-	cmdq_src_reg = hclgevf_read_dev(&hdev->hw,
-					HCLGEVF_VECTOR0_CMDQ_SRC_REG);
+	cmdq_stat_reg = hclgevf_read_dev(&hdev->hw,
+					 HCLGEVF_VECTOR0_CMDQ_STAT_REG);
 
-	if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_src_reg) {
+	if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_stat_reg) {
 		rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 		dev_info(&hdev->pdev->dev,
 			 "receive reset interrupt 0x%x!\n", rst_ing_reg);
 		set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
 		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
-		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B);
-		*clearval = cmdq_src_reg;
+		*clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B);
 		hdev->rst_stats.vf_rst_cnt++;
 		/* set up VF hardware reset status, its PF will clear
 		 * this status when PF has initialized done.
@@ -1915,9 +1914,20 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 	}
 
 	/* check for vector0 mailbox(=CMDQ RX) event source */
-	if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
-		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
-		*clearval = cmdq_src_reg;
+	if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_stat_reg) {
+		/* for revision 0x21, clearing interrupt is writing bit 0
+		 * to the clear register, writing bit 1 means to keep the
+		 * old value.
+		 * for revision 0x20, the clear register is a read & write
+		 * register, so we should just write 0 to the bit we are
+		 * handling, and keep other bits as cmdq_stat_reg.
+		 */
+		if (hdev->pdev->revision >= 0x21)
+			*clearval = ~(1U << HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
+		else
+			*clearval = cmdq_stat_reg &
+				    ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
+
 		return HCLGEVF_VECTOR0_EVENT_MBX;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index f0736b060884..bdde3afc286b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -87,6 +87,8 @@
 
 /* Vector0 interrupt CMDQ event source register(RW) */
 #define HCLGEVF_VECTOR0_CMDQ_SRC_REG	0x27100
+/* Vector0 interrupt CMDQ event status register(RO) */
+#define HCLGEVF_VECTOR0_CMDQ_STAT_REG	0x27104
 /* CMDQ register bits for RX event(=MBX event) */
 #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B	1
 /* RST register bits for RESET event */
@@ -123,7 +125,7 @@
 #define HCLGEVF_S_IP_BIT		BIT(3)
 #define HCLGEVF_V_TAG_BIT		BIT(4)
 
-#define HCLGEVF_STATS_TIMER_INTERVAL	(36)
+#define HCLGEVF_STATS_TIMER_INTERVAL	36U
 
 enum hclgevf_evt_cause {
 	HCLGEVF_VECTOR0_EVENT_RST,