Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

1 files changed, 136 insertions, 74 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index bf4302a5cf95..c21dd11baed9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -210,7 +210,6 @@ void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector,
 	 * Rl defines rate of interrupts i.e. number of interrupts-per-second
 	 * GL and RL(Rate Limiter) are 2 ways to acheive interrupt coalescing
 	 */
-
 	if (rl_reg > 0 && !tqp_vector->tx_group.coal.adapt_enable &&
 	    !tqp_vector->rx_group.coal.adapt_enable)
 		/* According to the hardware, the range of rl_reg is
@@ -695,7 +694,7 @@ void hns3_enable_vlan_filter(struct net_device *netdev, bool enable)
 }
 
 static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs,
-			u16 *mss, u32 *type_cs_vlan_tso)
+			u16 *mss, u32 *type_cs_vlan_tso, u32 *send_bytes)
 {
 	u32 l4_offset, hdr_len;
 	union l3_hdr_info l3;
@@ -751,6 +750,8 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs,
 				     (__force __wsum)htonl(l4_paylen));
 	}
 
+	*send_bytes = (skb_shinfo(skb)->gso_segs - 1) * hdr_len + skb->len;
+
 	/* find the txbd field values */
 	*paylen_fdop_ol4cs = skb->len - hdr_len;
 	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_TSO_B, 1);
@@ -883,7 +884,6 @@ static void hns3_set_outer_l2l3l4(struct sk_buff *skb, u8 ol4_proto,
 			hns3_set_field(*ol_type_vlan_len_msec,
 				       HNS3_TXD_OL3T_S,
 				       HNS3_OL3T_IPV4_NO_CSUM);
-
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
 		hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_S,
 			       HNS3_OL3T_IPV6);
@@ -1078,7 +1078,8 @@ static bool hns3_check_hw_tx_csum(struct sk_buff *skb)
 }
 
 static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
-			      struct sk_buff *skb, struct hns3_desc *desc)
+			      struct sk_buff *skb, struct hns3_desc *desc,
+			      struct hns3_desc_cb *desc_cb)
 {
 	u32 ol_type_vlan_len_msec = 0;
 	u32 paylen_ol4cs = skb->len;
@@ -1107,6 +1108,8 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 			       1);
 	}
 
+	desc_cb->send_bytes = skb->len;
+
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u8 ol4_proto, il4_proto;
 
@@ -1142,7 +1145,7 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 		}
 
 		ret = hns3_set_tso(skb, &paylen_ol4cs, &mss_hw_csum,
-				   &type_cs_vlan_tso);
+				   &type_cs_vlan_tso, &desc_cb->send_bytes);
 		if (unlikely(ret < 0)) {
 			u64_stats_update_begin(&ring->syncp);
 			ring->stats.tx_tso_err++;
@@ -1277,31 +1280,29 @@ static unsigned int hns3_skb_bd_num(struct sk_buff *skb, unsigned int *bd_size,
 }
 
 static unsigned int hns3_tx_bd_num(struct sk_buff *skb, unsigned int *bd_size,
-				   u8 max_non_tso_bd_num)
+				   u8 max_non_tso_bd_num, unsigned int bd_num,
+				   unsigned int recursion_level)
 {
+#define HNS3_MAX_RECURSION_LEVEL	24
+
 	struct sk_buff *frag_skb;
-	unsigned int bd_num = 0;
 
 	/* If the total len is within the max bd limit */
-	if (likely(skb->len <= HNS3_MAX_BD_SIZE && !skb_has_frag_list(skb) &&
+	if (likely(skb->len <= HNS3_MAX_BD_SIZE && !recursion_level &&
+		   !skb_has_frag_list(skb) &&
 		   skb_shinfo(skb)->nr_frags < max_non_tso_bd_num))
 		return skb_shinfo(skb)->nr_frags + 1U;
 
-	/* The below case will always be linearized, return
-	 * HNS3_MAX_BD_NUM_TSO + 1U to make sure it is linearized.
-	 */
-	if (unlikely(skb->len > HNS3_MAX_TSO_SIZE ||
-		     (!skb_is_gso(skb) && skb->len >
-		      HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))))
-		return HNS3_MAX_TSO_BD_NUM + 1U;
+	if (unlikely(recursion_level >= HNS3_MAX_RECURSION_LEVEL))
+		return UINT_MAX;
 
 	bd_num = hns3_skb_bd_num(skb, bd_size, bd_num);
-
 	if (!skb_has_frag_list(skb) || bd_num > HNS3_MAX_TSO_BD_NUM)
 		return bd_num;
 
 	skb_walk_frags(skb, frag_skb) {
-		bd_num = hns3_skb_bd_num(frag_skb, bd_size, bd_num);
+		bd_num = hns3_tx_bd_num(frag_skb, bd_size, max_non_tso_bd_num,
+					bd_num, recursion_level + 1);
 		if (bd_num > HNS3_MAX_TSO_BD_NUM)
 			return bd_num;
 	}
@@ -1361,6 +1362,43 @@ void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size)
 		size[i] = skb_frag_size(&shinfo->frags[i]);
 }
 
+static int hns3_skb_linearize(struct hns3_enet_ring *ring,
+			      struct sk_buff *skb,
+			      u8 max_non_tso_bd_num,
+			      unsigned int bd_num)
+{
+	/* 'bd_num == UINT_MAX' means the skb' fraglist has a
+	 * recursion level of over HNS3_MAX_RECURSION_LEVEL.
+	 */
+	if (bd_num == UINT_MAX) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.over_max_recursion++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	/* The skb->len has exceeded the hw limitation, linearization
+	 * will not help.
+	 */
+	if (skb->len > HNS3_MAX_TSO_SIZE ||
+	    (!skb_is_gso(skb) && skb->len >
+	     HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.hw_limitation++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	if (__skb_linearize(skb)) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 				  struct net_device *netdev,
 				  struct sk_buff *skb)
@@ -1370,7 +1408,7 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 	unsigned int bd_size[HNS3_MAX_TSO_BD_NUM + 1U];
 	unsigned int bd_num;
 
-	bd_num = hns3_tx_bd_num(skb, bd_size, max_non_tso_bd_num);
+	bd_num = hns3_tx_bd_num(skb, bd_size, max_non_tso_bd_num, 0, 0);
 	if (unlikely(bd_num > max_non_tso_bd_num)) {
 		if (bd_num <= HNS3_MAX_TSO_BD_NUM && skb_is_gso(skb) &&
 		    !hns3_skb_need_linearized(skb, bd_size, bd_num,
@@ -1379,16 +1417,11 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 			goto out;
 		}
 
-		if (__skb_linearize(skb))
+		if (hns3_skb_linearize(ring, skb, max_non_tso_bd_num,
+				       bd_num))
 			return -ENOMEM;
 
 		bd_num = hns3_tx_bd_count(skb->len);
-		if ((skb_is_gso(skb) && bd_num > HNS3_MAX_TSO_BD_NUM) ||
-		    (!skb_is_gso(skb) &&
-		     bd_num > max_non_tso_bd_num)) {
-			trace_hns3_over_max_bd(skb);
-			return -ENOMEM;
-		}
 
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.tx_copy++;
@@ -1412,6 +1445,10 @@ out:
 		return bd_num;
 	}
 
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.tx_busy++;
+	u64_stats_update_end(&ring->syncp);
+
 	return -EBUSY;
 }
 
@@ -1459,6 +1496,7 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 				 struct sk_buff *skb, enum hns_desc_type type)
 {
 	unsigned int size = skb_headlen(skb);
+	struct sk_buff *frag_skb;
 	int i, ret, bd_num = 0;
 
 	if (size) {
@@ -1483,6 +1521,15 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 		bd_num += ret;
 	}
 
+	skb_walk_frags(skb, frag_skb) {
+		ret = hns3_fill_skb_to_desc(ring, frag_skb,
+					    DESC_TYPE_FRAGLIST_SKB);
+		if (unlikely(ret < 0))
+			return ret;
+
+		bd_num += ret;
+	}
+
 	return bd_num;
 }
 
@@ -1511,16 +1558,20 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_enet_ring *ring = &priv->ring[skb->queue_mapping];
+	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
 	struct netdev_queue *dev_queue;
 	int pre_ntu, next_to_use_head;
-	struct sk_buff *frag_skb;
-	int bd_num = 0;
 	bool doorbell;
 	int ret;
 
 	/* Hardware can only handle short frames above 32 bytes */
 	if (skb_put_padto(skb, HNS3_MIN_TX_LEN)) {
 		hns3_tx_doorbell(ring, 0, !netdev_xmit_more());
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+
 		return NETDEV_TX_OK;
 	}
 
@@ -1530,15 +1581,8 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = hns3_nic_maybe_stop_tx(ring, netdev, skb);
 	if (unlikely(ret <= 0)) {
 		if (ret == -EBUSY) {
-			u64_stats_update_begin(&ring->syncp);
-			ring->stats.tx_busy++;
-			u64_stats_update_end(&ring->syncp);
 			hns3_tx_doorbell(ring, 0, true);
 			return NETDEV_TX_BUSY;
-		} else if (ret == -ENOMEM) {
-			u64_stats_update_begin(&ring->syncp);
-			ring->stats.sw_err_cnt++;
-			u64_stats_update_end(&ring->syncp);
 		}
 
 		hns3_rl_err(netdev, "xmit error: %d!\n", ret);
@@ -1547,25 +1591,19 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	next_to_use_head = ring->next_to_use;
 
-	ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use]);
+	ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use],
+				 desc_cb);
 	if (unlikely(ret < 0))
 		goto fill_err;
 
+	/* 'ret < 0' means filling error, 'ret == 0' means skb->len is
+	 * zero, which is unlikely, and 'ret > 0' means how many tx desc
+	 * need to be notified to the hw.
+	 */
 	ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB);
-	if (unlikely(ret < 0))
+	if (unlikely(ret <= 0))
 		goto fill_err;
 
-	bd_num += ret;
-
-	skb_walk_frags(skb, frag_skb) {
-		ret = hns3_fill_skb_to_desc(ring, frag_skb,
-					    DESC_TYPE_FRAGLIST_SKB);
-		if (unlikely(ret < 0))
-			goto fill_err;
-
-		bd_num += ret;
-	}
-
 	pre_ntu = ring->next_to_use ? (ring->next_to_use - 1) :
 					(ring->desc_num - 1);
 	ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |=
@@ -1574,9 +1612,9 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	/* Complete translate all packets */
 	dev_queue = netdev_get_tx_queue(netdev, ring->queue_index);
-	doorbell = __netdev_tx_sent_queue(dev_queue, skb->len,
+	doorbell = __netdev_tx_sent_queue(dev_queue, desc_cb->send_bytes,
 					  netdev_xmit_more());
-	hns3_tx_doorbell(ring, bd_num, doorbell);
+	hns3_tx_doorbell(ring, ret, doorbell);
 
 	return NETDEV_TX_OK;
 
@@ -1748,11 +1786,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			tx_drop += ring->stats.tx_l4_proto_err;
 			tx_drop += ring->stats.tx_l2l3l4_err;
 			tx_drop += ring->stats.tx_tso_err;
+			tx_drop += ring->stats.over_max_recursion;
+			tx_drop += ring->stats.hw_limitation;
 			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;
+			tx_errors += ring->stats.over_max_recursion;
+			tx_errors += ring->stats.hw_limitation;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -2323,6 +2365,32 @@ static void hns3_shutdown(struct pci_dev *pdev)
 		pci_set_power_state(pdev, PCI_D3hot);
 }
 
+static int __maybe_unused hns3_suspend(struct device *dev)
+{
+	struct hnae3_ae_dev *ae_dev = dev_get_drvdata(dev);
+
+	if (ae_dev && hns3_is_phys_func(ae_dev->pdev)) {
+		dev_info(dev, "Begin to suspend.\n");
+		if (ae_dev->ops && ae_dev->ops->reset_prepare)
+			ae_dev->ops->reset_prepare(ae_dev, HNAE3_FUNC_RESET);
+	}
+
+	return 0;
+}
+
+static int __maybe_unused hns3_resume(struct device *dev)
+{
+	struct hnae3_ae_dev *ae_dev = dev_get_drvdata(dev);
+
+	if (ae_dev && hns3_is_phys_func(ae_dev->pdev)) {
+		dev_info(dev, "Begin to resume.\n");
+		if (ae_dev->ops && ae_dev->ops->reset_done)
+			ae_dev->ops->reset_done(ae_dev);
+	}
+
+	return 0;
+}
+
 static pci_ers_result_t hns3_error_detected(struct pci_dev *pdev,
 					    pci_channel_state_t state)
 {
@@ -2381,8 +2449,8 @@ static void hns3_reset_prepare(struct pci_dev *pdev)
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 
 	dev_info(&pdev->dev, "FLR prepare\n");
-	if (ae_dev && ae_dev->ops && ae_dev->ops->flr_prepare)
-		ae_dev->ops->flr_prepare(ae_dev);
+	if (ae_dev && ae_dev->ops && ae_dev->ops->reset_prepare)
+		ae_dev->ops->reset_prepare(ae_dev, HNAE3_FLR_RESET);
 }
 
 static void hns3_reset_done(struct pci_dev *pdev)
@@ -2390,8 +2458,8 @@ static void hns3_reset_done(struct pci_dev *pdev)
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 
 	dev_info(&pdev->dev, "FLR done\n");
-	if (ae_dev && ae_dev->ops && ae_dev->ops->flr_done)
-		ae_dev->ops->flr_done(ae_dev);
+	if (ae_dev && ae_dev->ops && ae_dev->ops->reset_done)
+		ae_dev->ops->reset_done(ae_dev);
 }
 
 static const struct pci_error_handlers hns3_err_handler = {
@@ -2401,12 +2469,15 @@ static const struct pci_error_handlers hns3_err_handler = {
 	.reset_done	= hns3_reset_done,
 };
 
+static SIMPLE_DEV_PM_OPS(hns3_pm_ops, hns3_suspend, hns3_resume);
+
 static struct pci_driver hns3_driver = {
 	.name     = hns3_driver_name,
 	.id_table = hns3_pci_tbl,
 	.probe    = hns3_probe,
 	.remove   = hns3_remove,
 	.shutdown = hns3_shutdown,
+	.driver.pm  = &hns3_pm_ops,
 	.sriov_configure = hns3_pci_sriov_configure,
 	.err_handler    = &hns3_err_handler,
 };
@@ -2691,8 +2762,12 @@ static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring,
 			break;
 
 		desc_cb = &ring->desc_cb[ntc];
-		(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
-		(*bytes) += desc_cb->length;
+
+		if (desc_cb->type == DESC_TYPE_SKB) {
+			(*pkts)++;
+			(*bytes) += desc_cb->send_bytes;
+		}
+
 		/* desc_cb will be cleaned, after hnae3_free_buffer_detach */
 		hns3_free_buffer_detach(ring, ntc, budget);
 
@@ -2965,7 +3040,6 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 					  HNS3_RXD_L3ID_S);
 		l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
 					  HNS3_RXD_L4ID_S);
-
 		/* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */
 		if ((l3_type == HNS3_L3_TYPE_IPV4 ||
 		     l3_type == HNS3_L3_TYPE_IPV6) &&
@@ -3295,7 +3369,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring)
 
 	if (!skb) {
 		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-
 		/* Check valid BD */
 		if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B))))
 			return -ENXIO;
@@ -3557,7 +3630,6 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	hns3_for_each_ring(ring, tqp_vector->rx_group) {
 		int rx_cleaned = hns3_clean_rx_ring(ring, rx_budget,
 						    hns3_rx_skb);
-
 		if (rx_cleaned >= rx_budget)
 			clean_complete = false;
 
@@ -3704,7 +3776,6 @@ static void hns3_nic_set_cpumask(struct hns3_nic_priv *priv)
 
 static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 {
-	struct hnae3_ring_chain_node vector_ring_chain;
 	struct hnae3_handle *h = priv->ae_handle;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	int ret;
@@ -3736,6 +3807,8 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 	}
 
 	for (i = 0; i < priv->vector_num; i++) {
+		struct hnae3_ring_chain_node vector_ring_chain;
+
 		tqp_vector = &priv->tqp_vector[i];
 
 		tqp_vector->rx_group.total_bytes = 0;
@@ -4024,7 +4097,6 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring)
 			       hns3_buf_size2type(ring->buf_size));
 		hns3_write_dev(q, HNS3_RING_RX_RING_BD_NUM_REG,
 			       ring->desc_num / 8 - 1);
-
 	} else {
 		hns3_write_dev(q, HNS3_RING_TX_RING_BASEADDR_L_REG,
 			       (u32)dma);
@@ -4143,14 +4215,6 @@ static void hns3_uninit_phy(struct net_device *netdev)
 		h->ae_algo->ops->mac_disconnect_phy(h);
 }
 
-static void hns3_del_all_fd_rules(struct net_device *netdev, bool clear_list)
-{
-	struct hnae3_handle *h = hns3_get_handle(netdev);
-
-	if (h->ae_algo->ops->del_all_fd_entries)
-		h->ae_algo->ops->del_all_fd_entries(h, clear_list);
-}
-
 static int hns3_client_start(struct hnae3_handle *handle)
 {
 	if (!handle->ae_algo->ops->client_start)
@@ -4337,8 +4401,6 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	hns3_nic_uninit_irq(priv);
 
-	hns3_del_all_fd_rules(netdev, true);
-
 	hns3_clear_all_ring(handle, true);
 
 	hns3_nic_uninit_vector_data(priv);
@@ -4472,11 +4534,11 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h)
 	int i, j;
 	int ret;
 
-	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		ret = h->ae_algo->ops->reset_queue(h, i);
-		if (ret)
-			return ret;
+	ret = h->ae_algo->ops->reset_queue(h);
+	if (ret)
+		return ret;
 
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		hns3_init_ring_hw(&priv->ring[i]);
 
 		/* We need to clear tx ring here because self test will