Merge tag 'net-next-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "The sprinkling of SPI drivers is because we added a new one and Mark
  sent us a SPI driver interface conversion pull request.

  Core
  ----

   - Introduce XDP multi-buffer support, allowing the use of XDP with
     jumbo frame MTUs and combination with Rx coalescing offloads (LRO).

   - Speed up netns dismantling (5x) and lower the memory cost a little.
     Remove unnecessary per-netns sockets. Scope some lists to a netns.
     Cut down RCU syncing. Use batch methods. Allow netdev registration
     to complete out of order.

   - Support distinguishing timestamp types (ingress vs egress) and
     maintaining them across packet scrubbing points (e.g. redirect).

   - Continue the work of annotating packet drop reasons throughout the
     stack.

   - Switch netdev error counters from an atomic to dynamically
     allocated per-CPU counters.

   - Rework a few preempt_disable(), local_irq_save() and busy waiting
     sections problematic on PREEMPT_RT.

   - Extend the ref_tracker to allow catching use-after-free bugs.

  BPF
  ---

   - Introduce "packing allocator" for BPF JIT images. JITed code is
     marked read only, and used to be allocated at page granularity.
     Custom allocator allows for more efficient memory use, lower iTLB
     pressure and prevents identity mapping huge pages from getting
     split.

   - Make use of BTF type annotations (e.g. __user, __percpu) to enforce
     the correct probe read access method, add appropriate helpers.

   - Convert the BPF preload to use light skeleton and drop the
     user-mode-driver dependency.

   - Allow XDP BPF_PROG_RUN test infra to send real packets, enabling
     its use as a packet generator.

   - Allow local storage memory to be allocated with GFP_KERNEL if
     called from a hook allowed to sleep.

   - Introduce fprobe (multi kprobe) to speed up mass attachment (arch
     bits to come later).

   - Add unstable conntrack lookup helpers for BPF by using the BPF
     kfunc infra.

   - Allow cgroup BPF progs to return custom errors to user space.

   - Add support for AF_UNIX iterator batching.

   - Allow iterator programs to use sleepable helpers.

   - Support JIT of add, and, or, xor and xchg atomic ops on arm64.

   - Add BTFGen support to bpftool which allows to use CO-RE in kernels
     without BTF info.

   - Large number of libbpf API improvements, cleanups and deprecations.

  Protocols
  ---------

   - Micro-optimize UDPv6 Tx, gaining up to 5% in test on dummy netdev.

   - Adjust TSO packet sizes based on min_rtt, allowing very low latency
     links (data centers) to always send full-sized TSO super-frames.

   - Make IPv6 flow label changes (AKA hash rethink) more configurable,
     via sysctl and setsockopt. Distinguish between server and client
     behavior.

   - VxLAN support to "collect metadata" devices to terminate only
     configured VNIs. This is similar to VLAN filtering in the bridge.

   - Support inserting IPv6 IOAM information to a fraction of frames.

   - Add protocol attribute to IP addresses to allow identifying where
     given address comes from (kernel-generated, DHCP etc.)

   - Support setting socket and IPv6 options via cmsg on ping6 sockets.

   - Reject mis-use of ECN bits in IP headers as part of DSCP/TOS.
     Define dscp_t and stop taking ECN bits into account in fib-rules.

   - Add support for locked bridge ports (for 802.1X).

   - tun: support NAPI for packets received from batched XDP buffs,
     doubling the performance in some scenarios.

   - IPv6 extension header handling in Open vSwitch.

   - Support IPv6 control message load balancing in bonding, prevent
     neighbor solicitation and advertisement from using the wrong port.
     Support NS/NA monitor selection similar to existing ARP monitor.

   - SMC
      - improve performance with TCP_CORK and sendfile()
      - support auto-corking
      - support TCP_NODELAY

   - MCTP (Management Component Transport Protocol)
      - add user space tag control interface
      - I2C binding driver (as specified by DMTF DSP0237)

   - Multi-BSSID beacon handling in AP mode for WiFi.

   - Bluetooth:
      - handle MSFT Monitor Device Event
      - add MGMT Adv Monitor Device Found/Lost events

   - Multi-Path TCP:
      - add support for the SO_SNDTIMEO socket option
      - lots of selftest cleanups and improvements

   - Increase the max PDU size in CAN ISOTP to 64 kB.

  Driver API
  ----------

   - Add HW counters for SW netdevs, a mechanism for devices which
     offload packet forwarding to report packet statistics back to
     software interfaces such as tunnels.

   - Select the default NIC queue count as a fraction of number of
     physical CPU cores, instead of hard-coding to 8.

   - Expose devlink instance locks to drivers. Allow device layer of
     drivers to use that lock directly instead of creating their own
     which always runs into ordering issues in devlink callbacks.

   - Add header/data split indication to guide user space enabling of
     TCP zero-copy Rx.

   - Allow configuring completion queue event size.

   - Refactor page_pool to enable fragmenting after allocation.

   - Add allocation and page reuse statistics to page_pool.

   - Improve Multiple Spanning Trees support in the bridge to allow
     reuse of topologies across VLANs, saving HW resources in switches.

   - DSA (Distributed Switch Architecture):
      - replay and offload of host VLAN entries
      - offload of static and local FDB entries on LAG interfaces
      - FDB isolation and unicast filtering

  New hardware / drivers
  ----------------------

   - Ethernet:
      - LAN937x T1 PHYs
      - Davicom DM9051 SPI NIC driver
      - Realtek RTL8367S, RTL8367RB-VB switch and MDIO
      - Microchip ksz8563 switches
      - Netronome NFP3800 SmartNICs
      - Fungible SmartNICs
      - MediaTek MT8195 switches

   - WiFi:
      - mt76: MediaTek mt7916
      - mt76: MediaTek mt7921u USB adapters
      - brcmfmac: Broadcom BCM43454/6

   - Mobile:
      - iosm: Intel M.2 7360 WWAN card

  Drivers
  -------

   - Convert many drivers to the new phylink API built for split PCS
     designs but also simplifying other cases.

   - Intel Ethernet NICs:
      - add TTY for GNSS module for E810T device
      - improve AF_XDP performance
      - GTP-C and GTP-U filter offload
      - QinQ VLAN support

   - Mellanox Ethernet NICs (mlx5):
      - support xdp->data_meta
      - multi-buffer XDP
      - offload tc push_eth and pop_eth actions

   - Netronome Ethernet NICs (nfp):
      - flow-independent tc action hardware offload (police / meter)
      - AF_XDP

   - Other Ethernet NICs:
      - at803x: fiber and SFP support
      - xgmac: mdio: preamble suppression and custom MDC frequencies
      - r8169: enable ASPM L1.2 if system vendor flags it as safe
      - macb/gem: ZynqMP SGMII
      - hns3: add TX push mode
      - dpaa2-eth: software TSO
      - lan743x: multi-queue, mdio, SGMII, PTP
      - axienet: NAPI and GRO support

   - Mellanox Ethernet switches (mlxsw):
      - source and dest IP address rewrites
      - RJ45 ports

   - Marvell Ethernet switches (prestera):
      - basic routing offload
      - multi-chain TC ACL offload

   - NXP embedded Ethernet switches (ocelot & felix):
      - PTP over UDP with the ocelot-8021q DSA tagging protocol
      - basic QoS classification on Felix DSA switch using dcbnl
      - port mirroring for ocelot switches

   - Microchip high-speed industrial Ethernet (sparx5):
      - offloading of bridge port flooding flags
      - PTP Hardware Clock

   - Other embedded switches:
      - lan966x: PTP Hardward Clock
      - qca8k: mdio read/write operations via crafted Ethernet packets

   - Qualcomm 802.11ax WiFi (ath11k):
      - add LDPC FEC type and 802.11ax High Efficiency data in radiotap
      - enable RX PPDU stats in monitor co-exist mode

   - Intel WiFi (iwlwifi):
      - UHB TAS enablement via BIOS
      - band disablement via BIOS
      - channel switch offload
      - 32 Rx AMPDU sessions in newer devices

   - MediaTek WiFi (mt76):
      - background radar detection
      - thermal management improvements on mt7915
      - SAR support for more mt76 platforms
      - MBSSID and 6 GHz band on mt7915

   - RealTek WiFi:
      - rtw89: AP mode
      - rtw89: 160 MHz channels and 6 GHz band
      - rtw89: hardware scan

   - Bluetooth:
      - mt7921s: wake on Bluetooth, SCO over I2S, wide-band-speed (WBS)

   - Microchip CAN (mcp251xfd):
      - multiple RX-FIFOs and runtime configurable RX/TX rings
      - internal PLL, runtime PM handling simplification
      - improve chip detection and error handling after wakeup"

* tag 'net-next-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2521 commits)
  llc: fix netdevice reference leaks in llc_ui_bind()
  drivers: ethernet: cpsw: fix panic when interrupt coaleceing is set via ethtool
  ice: don't allow to run ice_send_event_to_aux() in atomic ctx
  ice: fix 'scheduling while atomic' on aux critical err interrupt
  net/sched: fix incorrect vlan_push_eth dest field
  net: bridge: mst: Restrict info size queries to bridge ports
  net: marvell: prestera: add missing destroy_workqueue() in prestera_module_init()
  drivers: net: xgene: Fix regression in CRC stripping
  net: geneve: add missing netlink policy and size for IFLA_GENEVE_INNER_PROTO_INHERIT
  net: dsa: fix missing host-filtered multicast addresses
  net/mlx5e: Fix build warning, detected write beyond size of field
  iwlwifi: mvm: Don't fail if PPAG isn't supported
  selftests/bpf: Fix kprobe_multi test.
  Revert "rethook: x86: Add rethook x86 implementation"
  Revert "arm64: rethook: Add arm64 rethook implementation"
  Revert "powerpc: Add rethook support"
  Revert "ARM: rethook: Add rethook arm implementation"
  netdevice: add missing dm_private kdoc
  net: bridge: mst: prevent NULL deref in br_mst_info_size()
  selftests: forwarding: Use same VRF for port and VLAN upper
  ...

9 files changed, 119 insertions, 14 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 9298fbecb31a..6f18c9a03231 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -167,6 +167,7 @@ struct hnae3_handle;
 
 struct hnae3_queue {
 	void __iomem *io_base;
+	void __iomem *mem_base;
 	struct hnae3_ae_algo *ae_algo;
 	struct hnae3_handle *handle;
 	int tqp_index;		/* index in a handle */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index babc5d7a3b52..0b8a73c40b12 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2028,9 +2028,73 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 	return bd_num;
 }
 
+static void hns3_tx_push_bd(struct hns3_enet_ring *ring, int num)
+{
+#define HNS3_BYTES_PER_64BIT		8
+
+	struct hns3_desc desc[HNS3_MAX_PUSH_BD_NUM] = {};
+	int offset = 0;
+
+	/* make sure everything is visible to device before
+	 * excuting tx push or updating doorbell
+	 */
+	dma_wmb();
+
+	do {
+		int idx = (ring->next_to_use - num + ring->desc_num) %
+			  ring->desc_num;
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_push++;
+		u64_stats_update_end(&ring->syncp);
+		memcpy(&desc[offset], &ring->desc[idx],
+		       sizeof(struct hns3_desc));
+		offset++;
+	} while (--num);
+
+	__iowrite64_copy(ring->tqp->mem_base, desc,
+			 (sizeof(struct hns3_desc) * HNS3_MAX_PUSH_BD_NUM) /
+			 HNS3_BYTES_PER_64BIT);
+
+	io_stop_wc();
+}
+
+static void hns3_tx_mem_doorbell(struct hns3_enet_ring *ring)
+{
+#define HNS3_MEM_DOORBELL_OFFSET	64
+
+	__le64 bd_num = cpu_to_le64((u64)ring->pending_buf);
+
+	/* make sure everything is visible to device before
+	 * excuting tx push or updating doorbell
+	 */
+	dma_wmb();
+
+	__iowrite64_copy(ring->tqp->mem_base + HNS3_MEM_DOORBELL_OFFSET,
+			 &bd_num, 1);
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.tx_mem_doorbell += ring->pending_buf;
+	u64_stats_update_end(&ring->syncp);
+
+	io_stop_wc();
+}
+
 static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 			     bool doorbell)
 {
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	/* when tx push is enabled, the packet whose number of BD below
+	 * HNS3_MAX_PUSH_BD_NUM can be pushed directly.
+	 */
+	if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num &&
+	    !ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) {
+		hns3_tx_push_bd(ring, num);
+		WRITE_ONCE(ring->last_to_use, ring->next_to_use);
+		return;
+	}
+
 	ring->pending_buf += num;
 
 	if (!doorbell) {
@@ -2038,11 +2102,12 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 		return;
 	}
 
-	if (!ring->pending_buf)
-		return;
+	if (ring->tqp->mem_base)
+		hns3_tx_mem_doorbell(ring);
+	else
+		writel(ring->pending_buf,
+		       ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
 
-	writel(ring->pending_buf,
-	       ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
 	ring->pending_buf = 0;
 	WRITE_ONCE(ring->last_to_use, ring->next_to_use);
 }
@@ -2732,6 +2797,9 @@ static void hns3_dump_queue_stats(struct net_device *ndev,
 		    "seg_pkt_cnt: %llu, tx_more: %llu, restart_queue: %llu, tx_busy: %llu\n",
 		    tx_ring->stats.seg_pkt_cnt, tx_ring->stats.tx_more,
 		    tx_ring->stats.restart_queue, tx_ring->stats.tx_busy);
+
+	netdev_info(ndev, "tx_push: %llu, tx_mem_doorbell: %llu\n",
+		    tx_ring->stats.tx_push, tx_ring->stats.tx_mem_doorbell);
 }
 
 static void hns3_dump_queue_reg(struct net_device *ndev,
@@ -5094,6 +5162,9 @@ static void hns3_state_init(struct hnae3_handle *handle)
 
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
+	if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps))
+		set_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state);
+
 	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
 		set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index a05a0c7423ce..4a3253692dcc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -7,6 +7,7 @@
 #include <linux/dim.h>
 #include <linux/if_vlan.h>
 #include <net/page_pool.h>
+#include <asm/barrier.h>
 
 #include "hnae3.h"
 
@@ -25,9 +26,12 @@ enum hns3_nic_state {
 	HNS3_NIC_STATE2_RESET_REQUESTED,
 	HNS3_NIC_STATE_HW_TX_CSUM_ENABLE,
 	HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE,
+	HNS3_NIC_STATE_TX_PUSH_ENABLE,
 	HNS3_NIC_STATE_MAX
 };
 
+#define HNS3_MAX_PUSH_BD_NUM		2
+
 #define HNS3_RING_RX_RING_BASEADDR_L_REG	0x00000
 #define HNS3_RING_RX_RING_BASEADDR_H_REG	0x00004
 #define HNS3_RING_RX_RING_BD_NUM_REG		0x00008
@@ -410,6 +414,8 @@ struct ring_stats {
 			u64 tx_pkts;
 			u64 tx_bytes;
 			u64 tx_more;
+			u64 tx_push;
+			u64 tx_mem_doorbell;
 			u64 restart_queue;
 			u64 tx_busy;
 			u64 tx_copy;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index c06c39ece80d..6469238ae090 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -23,6 +23,8 @@ static const struct hns3_stats hns3_txq_stats[] = {
 	HNS3_TQP_STAT("packets", tx_pkts),
 	HNS3_TQP_STAT("bytes", tx_bytes),
 	HNS3_TQP_STAT("more", tx_more),
+	HNS3_TQP_STAT("push", tx_push),
+	HNS3_TQP_STAT("mem_doorbell", tx_mem_doorbell),
 	HNS3_TQP_STAT("wake", restart_queue),
 	HNS3_TQP_STAT("busy", tx_busy),
 	HNS3_TQP_STAT("copy", tx_copy),
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 24f7afacae02..78d0498bdabc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1643,6 +1643,7 @@ static int hclge_config_gro(struct hclge_dev *hdev)
 
 static int hclge_alloc_tqps(struct hclge_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	struct hclge_comm_tqp *tqp;
 	int i;
 
@@ -1676,6 +1677,14 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev)
 					 (i - HCLGE_TQP_MAX_SIZE_DEV_V2) *
 					 HCLGE_TQP_REG_SIZE;
 
+		/* when device supports tx push and has device memory,
+		 * the queue can execute push mode or doorbell mode on
+		 * device memory.
+		 */
+		if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps))
+			tqp->q.mem_base = hdev->hw.hw.mem_base +
+					  HCLGE_TQP_MEM_OFFSET(hdev, i);
+
 		tqp++;
 	}
 
@@ -11008,8 +11017,6 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 
 static int hclge_dev_mem_map(struct hclge_dev *hdev)
 {
-#define HCLGE_MEM_BAR		4
-
 	struct pci_dev *pdev = hdev->pdev;
 	struct hclge_hw *hw = &hdev->hw;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index adfb26e79262..fc92ae385e30 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -169,6 +169,14 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_VECTOR0_ALL_MSIX_ERR_B	6U
 #define HCLGE_TRIGGER_IMP_RESET_B	7U
 
+#define HCLGE_TQP_MEM_SIZE		0x10000
+#define HCLGE_MEM_BAR			4
+/* in the bar4, the first half is for roce, and the second half is for nic */
+#define HCLGE_NIC_MEM_OFFSET(hdev)	\
+	(pci_resource_len((hdev)->pdev, HCLGE_MEM_BAR) >> 1)
+#define HCLGE_TQP_MEM_OFFSET(hdev, i)	\
+	(HCLGE_NIC_MEM_OFFSET(hdev) + HCLGE_TQP_MEM_SIZE * (i))
+
 #define HCLGE_MAC_DEFAULT_FRAME \
 	(ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN)
 #define HCLGE_MAC_MIN_FRAME		64
@@ -1060,11 +1068,6 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue)
 	return tqp->index;
 }
 
-static inline bool hclge_is_reset_pending(struct hclge_dev *hdev)
-{
-	return !!hdev->reset_pending;
-}
-
 int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport);
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
 int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 089f4444b7e3..1f87a8a3fe32 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1225,7 +1225,7 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
 		ret = hclge_tm_ets_tc_dwrr_cfg(hdev);
 		if (ret == -EOPNOTSUPP) {
 			dev_warn(&hdev->pdev->dev,
-				 "fw %08x does't support ets tc weight cmd\n",
+				 "fw %08x doesn't support ets tc weight cmd\n",
 				 hdev->fw_version);
 			ret = 0;
 		}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 21442a9bb996..93389bec8d89 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -321,6 +321,7 @@ static int hclgevf_get_pf_media_type(struct hclgevf_dev *hdev)
 
 static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	struct hclge_comm_tqp *tqp;
 	int i;
 
@@ -354,6 +355,14 @@ static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 					 (i - HCLGEVF_TQP_MAX_SIZE_DEV_V2) *
 					 HCLGEVF_TQP_REG_SIZE;
 
+		/* when device supports tx push and has device memory,
+		 * the queue can execute push mode or doorbell mode on
+		 * device memory.
+		 */
+		if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps))
+			tqp->q.mem_base = hdev->hw.hw.mem_base +
+					  HCLGEVF_TQP_MEM_OFFSET(hdev, i);
+
 		tqp++;
 	}
 
@@ -2546,8 +2555,6 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client,
 
 static int hclgevf_dev_mem_map(struct hclgevf_dev *hdev)
 {
-#define HCLGEVF_MEM_BAR		4
-
 	struct pci_dev *pdev = hdev->pdev;
 	struct hclgevf_hw *hw = &hdev->hw;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 502ca1ce1a90..4b00fd44f118 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -96,6 +96,14 @@
 
 #define HCLGEVF_RSS_IND_TBL_SIZE		512
 
+#define HCLGEVF_TQP_MEM_SIZE		0x10000
+#define HCLGEVF_MEM_BAR			4
+/* in the bar4, the first half is for roce, and the second half is for nic */
+#define HCLGEVF_NIC_MEM_OFFSET(hdev)	\
+	(pci_resource_len((hdev)->pdev, HCLGEVF_MEM_BAR) >> 1)
+#define HCLGEVF_TQP_MEM_OFFSET(hdev, i)		\
+	(HCLGEVF_NIC_MEM_OFFSET(hdev) + HCLGEVF_TQP_MEM_SIZE * (i))
+
 #define HCLGEVF_MAC_MAX_FRAME		9728
 
 #define HCLGEVF_STATS_TIMER_INTERVAL	36U