Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 533 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
new file mode 100644
index 000000000..736dc2f99
--- /dev/null
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -0,0 +1,533 @@
+/*
+ * Copyright (c) 2016 Hisilicon Limited.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <rdma/ib_umem.h>
+#include <rdma/uverbs_ioctl.h>
+#include "hns_roce_device.h"
+#include "hns_roce_cmd.h"
+#include "hns_roce_hem.h"
+#include "hns_roce_common.h"
+
+static u8 get_least_load_bankid_for_cq(struct hns_roce_bank *bank)
+{
+	u32 least_load = bank[0].inuse;
+	u8 bankid = 0;
+	u32 bankcnt;
+	u8 i;
+
+	for (i = 1; i < HNS_ROCE_CQ_BANK_NUM; i++) {
+		bankcnt = bank[i].inuse;
+		if (bankcnt < least_load) {
+			least_load = bankcnt;
+			bankid = i;
+		}
+	}
+
+	return bankid;
+}
+
+static int alloc_cqn(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
+{
+	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
+	struct hns_roce_bank *bank;
+	u8 bankid;
+	int id;
+
+	mutex_lock(&cq_table->bank_mutex);
+	bankid = get_least_load_bankid_for_cq(cq_table->bank);
+	bank = &cq_table->bank[bankid];
+
+	id = ida_alloc_range(&bank->ida, bank->min, bank->max, GFP_KERNEL);
+	if (id < 0) {
+		mutex_unlock(&cq_table->bank_mutex);
+		return id;
+	}
+
+	/* the lower 2 bits is bankid */
+	hr_cq->cqn = (id << CQ_BANKID_SHIFT) | bankid;
+	bank->inuse++;
+	mutex_unlock(&cq_table->bank_mutex);
+
+	return 0;
+}
+
+static inline u8 get_cq_bankid(unsigned long cqn)
+{
+	/* The lower 2 bits of CQN are used to hash to different banks */
+	return (u8)(cqn & GENMASK(1, 0));
+}
+
+static void free_cqn(struct hns_roce_dev *hr_dev, unsigned long cqn)
+{
+	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
+	struct hns_roce_bank *bank;
+
+	bank = &cq_table->bank[get_cq_bankid(cqn)];
+
+	ida_free(&bank->ida, cqn >> CQ_BANKID_SHIFT);
+
+	mutex_lock(&cq_table->bank_mutex);
+	bank->inuse--;
+	mutex_unlock(&cq_table->bank_mutex);
+}
+
+static int hns_roce_create_cqc(struct hns_roce_dev *hr_dev,
+			       struct hns_roce_cq *hr_cq,
+			       u64 *mtts, dma_addr_t dma_handle)
+{
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_cmd_mailbox *mailbox;
+	int ret;
+
+	mailbox = hns_roce_alloc_cmd_mailbox(hr_dev);
+	if (IS_ERR(mailbox)) {
+		ibdev_err(ibdev, "failed to alloc mailbox for CQC.\n");
+		return PTR_ERR(mailbox);
+	}
+
+	hr_dev->hw->write_cqc(hr_dev, hr_cq, mailbox->buf, mtts, dma_handle);
+
+	ret = hns_roce_create_hw_ctx(hr_dev, mailbox, HNS_ROCE_CMD_CREATE_CQC,
+				     hr_cq->cqn);
+	if (ret)
+		ibdev_err(ibdev,
+			  "failed to send create cmd for CQ(0x%lx), ret = %d.\n",
+			  hr_cq->cqn, ret);
+
+	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
+
+	return ret;
+}
+
+static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
+{
+	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	u64 mtts[MTT_MIN_COUNT] = {};
+	dma_addr_t dma_handle;
+	int ret;
+
+	ret = hns_roce_mtr_find(hr_dev, &hr_cq->mtr, 0, mtts, ARRAY_SIZE(mtts),
+				&dma_handle);
+	if (!ret) {
+		ibdev_err(ibdev, "failed to find CQ mtr, ret = %d.\n", ret);
+		return -EINVAL;
+	}
+
+	/* Get CQC memory HEM(Hardware Entry Memory) table */
+	ret = hns_roce_table_get(hr_dev, &cq_table->table, hr_cq->cqn);
+	if (ret) {
+		ibdev_err(ibdev, "failed to get CQ(0x%lx) context, ret = %d.\n",
+			  hr_cq->cqn, ret);
+		return ret;
+	}
+
+	ret = xa_err(xa_store(&cq_table->array, hr_cq->cqn, hr_cq, GFP_KERNEL));
+	if (ret) {
+		ibdev_err(ibdev, "failed to xa_store CQ, ret = %d.\n", ret);
+		goto err_put;
+	}
+
+	ret = hns_roce_create_cqc(hr_dev, hr_cq, mtts, dma_handle);
+	if (ret)
+		goto err_xa;
+
+	return 0;
+
+err_xa:
+	xa_erase(&cq_table->array, hr_cq->cqn);
+err_put:
+	hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn);
+
+	return ret;
+}
+
+static void free_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
+{
+	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
+	struct device *dev = hr_dev->dev;
+	int ret;
+
+	ret = hns_roce_destroy_hw_ctx(hr_dev, HNS_ROCE_CMD_DESTROY_CQC,
+				      hr_cq->cqn);
+	if (ret)
+		dev_err(dev, "DESTROY_CQ failed (%d) for CQN %06lx\n", ret,
+			hr_cq->cqn);
+
+	xa_erase(&cq_table->array, hr_cq->cqn);
+
+	/* Waiting interrupt process procedure carried out */
+	synchronize_irq(hr_dev->eq_table.eq[hr_cq->vector].irq);
+
+	/* wait for all interrupt processed */
+	if (refcount_dec_and_test(&hr_cq->refcount))
+		complete(&hr_cq->free);
+	wait_for_completion(&hr_cq->free);
+
+	hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn);
+}
+
+static int alloc_cq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
+			struct ib_udata *udata, unsigned long addr)
+{
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_buf_attr buf_attr = {};
+	int ret;
+
+	buf_attr.page_shift = hr_dev->caps.cqe_buf_pg_sz + PAGE_SHIFT;
+	buf_attr.region[0].size = hr_cq->cq_depth * hr_cq->cqe_size;
+	buf_attr.region[0].hopnum = hr_dev->caps.cqe_hop_num;
+	buf_attr.region_count = 1;
+
+	ret = hns_roce_mtr_create(hr_dev, &hr_cq->mtr, &buf_attr,
+				  hr_dev->caps.cqe_ba_pg_sz + PAGE_SHIFT,
+				  udata, addr);
+	if (ret)
+		ibdev_err(ibdev, "failed to alloc CQ mtr, ret = %d.\n", ret);
+
+	return ret;
+}
+
+static void free_cq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
+{
+	hns_roce_mtr_destroy(hr_dev, &hr_cq->mtr);
+}
+
+static int alloc_cq_db(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
+		       struct ib_udata *udata, unsigned long addr,
+		       struct hns_roce_ib_create_cq_resp *resp)
+{
+	bool has_db = hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_CQ_RECORD_DB;
+	struct hns_roce_ucontext *uctx;
+	int err;
+
+	if (udata) {
+		if (has_db &&
+		    udata->outlen >= offsetofend(typeof(*resp), cap_flags)) {
+			uctx = rdma_udata_to_drv_context(udata,
+					struct hns_roce_ucontext, ibucontext);
+			err = hns_roce_db_map_user(uctx, addr, &hr_cq->db);
+			if (err)
+				return err;
+			hr_cq->flags |= HNS_ROCE_CQ_FLAG_RECORD_DB;
+			resp->cap_flags |= HNS_ROCE_CQ_FLAG_RECORD_DB;
+		}
+	} else {
+		if (has_db) {
+			err = hns_roce_alloc_db(hr_dev, &hr_cq->db, 1);
+			if (err)
+				return err;
+			hr_cq->set_ci_db = hr_cq->db.db_record;
+			*hr_cq->set_ci_db = 0;
+			hr_cq->flags |= HNS_ROCE_CQ_FLAG_RECORD_DB;
+		}
+		hr_cq->db_reg = hr_dev->reg_base + hr_dev->odb_offset +
+				DB_REG_OFFSET * hr_dev->priv_uar.index;
+	}
+
+	return 0;
+}
+
+static void free_cq_db(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
+		       struct ib_udata *udata)
+{
+	struct hns_roce_ucontext *uctx;
+
+	if (!(hr_cq->flags & HNS_ROCE_CQ_FLAG_RECORD_DB))
+		return;
+
+	hr_cq->flags &= ~HNS_ROCE_CQ_FLAG_RECORD_DB;
+	if (udata) {
+		uctx = rdma_udata_to_drv_context(udata,
+						 struct hns_roce_ucontext,
+						 ibucontext);
+		hns_roce_db_unmap_user(uctx, &hr_cq->db);
+	} else {
+		hns_roce_free_db(hr_dev, &hr_cq->db);
+	}
+}
+
+static int verify_cq_create_attr(struct hns_roce_dev *hr_dev,
+				 const struct ib_cq_init_attr *attr)
+{
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+
+	if (!attr->cqe || attr->cqe > hr_dev->caps.max_cqes) {
+		ibdev_err(ibdev, "failed to check CQ count %u, max = %u.\n",
+			  attr->cqe, hr_dev->caps.max_cqes);
+		return -EINVAL;
+	}
+
+	if (attr->comp_vector >= hr_dev->caps.num_comp_vectors) {
+		ibdev_err(ibdev, "failed to check CQ vector = %u, max = %d.\n",
+			  attr->comp_vector, hr_dev->caps.num_comp_vectors);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int get_cq_ucmd(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
+		       struct hns_roce_ib_create_cq *ucmd)
+{
+	struct ib_device *ibdev = hr_cq->ib_cq.device;
+	int ret;
+
+	ret = ib_copy_from_udata(ucmd, udata, min(udata->inlen, sizeof(*ucmd)));
+	if (ret) {
+		ibdev_err(ibdev, "failed to copy CQ udata, ret = %d.\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void set_cq_param(struct hns_roce_cq *hr_cq, u32 cq_entries, int vector,
+			 struct hns_roce_ib_create_cq *ucmd)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device);
+
+	cq_entries = max(cq_entries, hr_dev->caps.min_cqes);
+	cq_entries = roundup_pow_of_two(cq_entries);
+	hr_cq->ib_cq.cqe = cq_entries - 1; /* used as cqe index */
+	hr_cq->cq_depth = cq_entries;
+	hr_cq->vector = vector;
+
+	spin_lock_init(&hr_cq->lock);
+	INIT_LIST_HEAD(&hr_cq->sq_list);
+	INIT_LIST_HEAD(&hr_cq->rq_list);
+}
+
+static int set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
+			struct hns_roce_ib_create_cq *ucmd)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device);
+
+	if (!udata) {
+		hr_cq->cqe_size = hr_dev->caps.cqe_sz;
+		return 0;
+	}
+
+	if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size)) {
+		if (ucmd->cqe_size != HNS_ROCE_V2_CQE_SIZE &&
+		    ucmd->cqe_size != HNS_ROCE_V3_CQE_SIZE) {
+			ibdev_err(&hr_dev->ib_dev,
+				  "invalid cqe size %u.\n", ucmd->cqe_size);
+			return -EINVAL;
+		}
+
+		hr_cq->cqe_size = ucmd->cqe_size;
+	} else {
+		hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
+	}
+
+	return 0;
+}
+
+int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
+		       struct ib_udata *udata)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
+	struct hns_roce_ib_create_cq_resp resp = {};
+	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_ib_create_cq ucmd = {};
+	int ret;
+
+	if (attr->flags)
+		return -EOPNOTSUPP;
+
+	ret = verify_cq_create_attr(hr_dev, attr);
+	if (ret)
+		return ret;
+
+	if (udata) {
+		ret = get_cq_ucmd(hr_cq, udata, &ucmd);
+		if (ret)
+			return ret;
+	}
+
+	set_cq_param(hr_cq, attr->cqe, attr->comp_vector, &ucmd);
+
+	ret = set_cqe_size(hr_cq, udata, &ucmd);
+	if (ret)
+		return ret;
+
+	ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr);
+	if (ret) {
+		ibdev_err(ibdev, "failed to alloc CQ buf, ret = %d.\n", ret);
+		return ret;
+	}
+
+	ret = alloc_cq_db(hr_dev, hr_cq, udata, ucmd.db_addr, &resp);
+	if (ret) {
+		ibdev_err(ibdev, "failed to alloc CQ db, ret = %d.\n", ret);
+		goto err_cq_buf;
+	}
+
+	ret = alloc_cqn(hr_dev, hr_cq);
+	if (ret) {
+		ibdev_err(ibdev, "failed to alloc CQN, ret = %d.\n", ret);
+		goto err_cq_db;
+	}
+
+	ret = alloc_cqc(hr_dev, hr_cq);
+	if (ret) {
+		ibdev_err(ibdev,
+			  "failed to alloc CQ context, ret = %d.\n", ret);
+		goto err_cqn;
+	}
+
+	if (udata) {
+		resp.cqn = hr_cq->cqn;
+		ret = ib_copy_to_udata(udata, &resp,
+				       min(udata->outlen, sizeof(resp)));
+		if (ret)
+			goto err_cqc;
+	}
+
+	hr_cq->cons_index = 0;
+	hr_cq->arm_sn = 1;
+	refcount_set(&hr_cq->refcount, 1);
+	init_completion(&hr_cq->free);
+
+	return 0;
+
+err_cqc:
+	free_cqc(hr_dev, hr_cq);
+err_cqn:
+	free_cqn(hr_dev, hr_cq->cqn);
+err_cq_db:
+	free_cq_db(hr_dev, hr_cq, udata);
+err_cq_buf:
+	free_cq_buf(hr_dev, hr_cq);
+	return ret;
+}
+
+int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
+	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
+
+	free_cqc(hr_dev, hr_cq);
+	free_cqn(hr_dev, hr_cq->cqn);
+	free_cq_db(hr_dev, hr_cq, udata);
+	free_cq_buf(hr_dev, hr_cq);
+
+	return 0;
+}
+
+void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn)
+{
+	struct hns_roce_cq *hr_cq;
+	struct ib_cq *ibcq;
+
+	hr_cq = xa_load(&hr_dev->cq_table.array,
+			cqn & (hr_dev->caps.num_cqs - 1));
+	if (!hr_cq) {
+		dev_warn(hr_dev->dev, "completion event for bogus CQ 0x%06x\n",
+			 cqn);
+		return;
+	}
+
+	++hr_cq->arm_sn;
+	ibcq = &hr_cq->ib_cq;
+	if (ibcq->comp_handler)
+		ibcq->comp_handler(ibcq, ibcq->cq_context);
+}
+
+void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type)
+{
+	struct device *dev = hr_dev->dev;
+	struct hns_roce_cq *hr_cq;
+	struct ib_event event;
+	struct ib_cq *ibcq;
+
+	hr_cq = xa_load(&hr_dev->cq_table.array,
+			cqn & (hr_dev->caps.num_cqs - 1));
+	if (!hr_cq) {
+		dev_warn(dev, "async event for bogus CQ 0x%06x\n", cqn);
+		return;
+	}
+
+	if (event_type != HNS_ROCE_EVENT_TYPE_CQ_ID_INVALID &&
+	    event_type != HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR &&
+	    event_type != HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW) {
+		dev_err(dev, "unexpected event type 0x%x on CQ 0x%06x\n",
+			event_type, cqn);
+		return;
+	}
+
+	refcount_inc(&hr_cq->refcount);
+
+	ibcq = &hr_cq->ib_cq;
+	if (ibcq->event_handler) {
+		event.device = ibcq->device;
+		event.element.cq = ibcq;
+		event.event = IB_EVENT_CQ_ERR;
+		ibcq->event_handler(&event, ibcq->cq_context);
+	}
+
+	if (refcount_dec_and_test(&hr_cq->refcount))
+		complete(&hr_cq->free);
+}
+
+void hns_roce_init_cq_table(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
+	unsigned int reserved_from_bot;
+	unsigned int i;
+
+	mutex_init(&cq_table->bank_mutex);
+	xa_init(&cq_table->array);
+
+	reserved_from_bot = hr_dev->caps.reserved_cqs;
+
+	for (i = 0; i < reserved_from_bot; i++) {
+		cq_table->bank[get_cq_bankid(i)].inuse++;
+		cq_table->bank[get_cq_bankid(i)].min++;
+	}
+
+	for (i = 0; i < HNS_ROCE_CQ_BANK_NUM; i++) {
+		ida_init(&cq_table->bank[i].ida);
+		cq_table->bank[i].max = hr_dev->caps.num_cqs /
+					HNS_ROCE_CQ_BANK_NUM - 1;
+	}
+}
+
+void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev)
+{
+	int i;
+
+	for (i = 0; i < HNS_ROCE_CQ_BANK_NUM; i++)
+		ida_destroy(&hr_dev->cq_table.bank[i].ida);
+}