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, 432 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
new file mode 100644
index 000000000..5d4b3bc16
--- /dev/null
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -0,0 +1,432 @@
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * 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 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.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Contact Information:
+ * linux-drivers@emulex.com
+ *
+ * Emulex
+ * 3333 Susan Street
+ * Costa Mesa, CA 92626
+ */
+
+#include <linux/module.h>
+#include <linux/idr.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_addr.h>
+#include <rdma/ib_mad.h>
+
+#include <linux/netdevice.h>
+#include <net/addrconf.h>
+
+#include "ocrdma.h"
+#include "ocrdma_verbs.h"
+#include "ocrdma_ah.h"
+#include "be_roce.h"
+#include "ocrdma_hw.h"
+#include "ocrdma_stats.h"
+#include <rdma/ocrdma-abi.h>
+
+MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION);
+MODULE_AUTHOR("Emulex Corporation");
+MODULE_LICENSE("Dual BSD/GPL");
+
+static enum rdma_link_layer ocrdma_link_layer(struct ib_device *device,
+					      u32 port_num)
+{
+	return IB_LINK_LAYER_ETHERNET;
+}
+
+static int ocrdma_port_immutable(struct ib_device *ibdev, u32 port_num,
+			         struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	struct ocrdma_dev *dev;
+	int err;
+
+	dev = get_ocrdma_dev(ibdev);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+	if (ocrdma_is_udp_encap_supported(dev))
+		immutable->core_cap_flags |= RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
+
+	err = ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
+static void get_dev_fw_str(struct ib_device *device, char *str)
+{
+	struct ocrdma_dev *dev = get_ocrdma_dev(device);
+
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", &dev->attr.fw_ver[0]);
+}
+
+/* OCRDMA sysfs interface */
+static ssize_t hw_rev_show(struct device *device,
+			   struct device_attribute *attr, char *buf)
+{
+	struct ocrdma_dev *dev =
+		rdma_device_to_drv_device(device, struct ocrdma_dev, ibdev);
+
+	return sysfs_emit(buf, "0x%x\n", dev->nic_info.pdev->vendor);
+}
+static DEVICE_ATTR_RO(hw_rev);
+
+static ssize_t hca_type_show(struct device *device,
+			     struct device_attribute *attr, char *buf)
+{
+	struct ocrdma_dev *dev =
+		rdma_device_to_drv_device(device, struct ocrdma_dev, ibdev);
+
+	return sysfs_emit(buf, "%s\n", &dev->model_number[0]);
+}
+static DEVICE_ATTR_RO(hca_type);
+
+static struct attribute *ocrdma_attributes[] = {
+	&dev_attr_hw_rev.attr,
+	&dev_attr_hca_type.attr,
+	NULL
+};
+
+static const struct attribute_group ocrdma_attr_group = {
+	.attrs = ocrdma_attributes,
+};
+
+static const struct ib_device_ops ocrdma_dev_ops = {
+	.owner = THIS_MODULE,
+	.driver_id = RDMA_DRIVER_OCRDMA,
+	.uverbs_abi_ver = OCRDMA_ABI_VERSION,
+
+	.alloc_mr = ocrdma_alloc_mr,
+	.alloc_pd = ocrdma_alloc_pd,
+	.alloc_ucontext = ocrdma_alloc_ucontext,
+	.create_ah = ocrdma_create_ah,
+	.create_cq = ocrdma_create_cq,
+	.create_qp = ocrdma_create_qp,
+	.create_user_ah = ocrdma_create_ah,
+	.dealloc_pd = ocrdma_dealloc_pd,
+	.dealloc_ucontext = ocrdma_dealloc_ucontext,
+	.dereg_mr = ocrdma_dereg_mr,
+	.destroy_ah = ocrdma_destroy_ah,
+	.destroy_cq = ocrdma_destroy_cq,
+	.destroy_qp = ocrdma_destroy_qp,
+	.device_group = &ocrdma_attr_group,
+	.get_dev_fw_str = get_dev_fw_str,
+	.get_dma_mr = ocrdma_get_dma_mr,
+	.get_link_layer = ocrdma_link_layer,
+	.get_port_immutable = ocrdma_port_immutable,
+	.map_mr_sg = ocrdma_map_mr_sg,
+	.mmap = ocrdma_mmap,
+	.modify_qp = ocrdma_modify_qp,
+	.poll_cq = ocrdma_poll_cq,
+	.post_recv = ocrdma_post_recv,
+	.post_send = ocrdma_post_send,
+	.process_mad = ocrdma_process_mad,
+	.query_ah = ocrdma_query_ah,
+	.query_device = ocrdma_query_device,
+	.query_pkey = ocrdma_query_pkey,
+	.query_port = ocrdma_query_port,
+	.query_qp = ocrdma_query_qp,
+	.reg_user_mr = ocrdma_reg_user_mr,
+	.req_notify_cq = ocrdma_arm_cq,
+	.resize_cq = ocrdma_resize_cq,
+
+	INIT_RDMA_OBJ_SIZE(ib_ah, ocrdma_ah, ibah),
+	INIT_RDMA_OBJ_SIZE(ib_cq, ocrdma_cq, ibcq),
+	INIT_RDMA_OBJ_SIZE(ib_pd, ocrdma_pd, ibpd),
+	INIT_RDMA_OBJ_SIZE(ib_qp, ocrdma_qp, ibqp),
+	INIT_RDMA_OBJ_SIZE(ib_ucontext, ocrdma_ucontext, ibucontext),
+};
+
+static const struct ib_device_ops ocrdma_dev_srq_ops = {
+	.create_srq = ocrdma_create_srq,
+	.destroy_srq = ocrdma_destroy_srq,
+	.modify_srq = ocrdma_modify_srq,
+	.post_srq_recv = ocrdma_post_srq_recv,
+	.query_srq = ocrdma_query_srq,
+
+	INIT_RDMA_OBJ_SIZE(ib_srq, ocrdma_srq, ibsrq),
+};
+
+static int ocrdma_register_device(struct ocrdma_dev *dev)
+{
+	int ret;
+
+	addrconf_addr_eui48((u8 *)&dev->ibdev.node_guid,
+			    dev->nic_info.mac_addr);
+	BUILD_BUG_ON(sizeof(OCRDMA_NODE_DESC) > IB_DEVICE_NODE_DESC_MAX);
+	memcpy(dev->ibdev.node_desc, OCRDMA_NODE_DESC,
+	       sizeof(OCRDMA_NODE_DESC));
+
+	dev->ibdev.node_type = RDMA_NODE_IB_CA;
+	dev->ibdev.phys_port_cnt = 1;
+	dev->ibdev.num_comp_vectors = dev->eq_cnt;
+
+	/* mandatory to support user space verbs consumer. */
+	dev->ibdev.dev.parent = &dev->nic_info.pdev->dev;
+
+	ib_set_device_ops(&dev->ibdev, &ocrdma_dev_ops);
+
+	if (ocrdma_get_asic_type(dev) == OCRDMA_ASIC_GEN_SKH_R)
+		ib_set_device_ops(&dev->ibdev, &ocrdma_dev_srq_ops);
+
+	ret = ib_device_set_netdev(&dev->ibdev, dev->nic_info.netdev, 1);
+	if (ret)
+		return ret;
+
+	dma_set_max_seg_size(&dev->nic_info.pdev->dev, UINT_MAX);
+	return ib_register_device(&dev->ibdev, "ocrdma%d",
+				  &dev->nic_info.pdev->dev);
+}
+
+static int ocrdma_alloc_resources(struct ocrdma_dev *dev)
+{
+	mutex_init(&dev->dev_lock);
+	dev->cq_tbl = kcalloc(OCRDMA_MAX_CQ, sizeof(struct ocrdma_cq *),
+			      GFP_KERNEL);
+	if (!dev->cq_tbl)
+		goto alloc_err;
+
+	if (dev->attr.max_qp) {
+		dev->qp_tbl = kcalloc(OCRDMA_MAX_QP,
+				      sizeof(struct ocrdma_qp *),
+				      GFP_KERNEL);
+		if (!dev->qp_tbl)
+			goto alloc_err;
+	}
+
+	dev->stag_arr = kcalloc(OCRDMA_MAX_STAG, sizeof(u64), GFP_KERNEL);
+	if (dev->stag_arr == NULL)
+		goto alloc_err;
+
+	ocrdma_alloc_pd_pool(dev);
+
+	if (!ocrdma_alloc_stats_resources(dev)) {
+		pr_err("%s: stats resource allocation failed\n", __func__);
+		goto alloc_err;
+	}
+
+	spin_lock_init(&dev->av_tbl.lock);
+	spin_lock_init(&dev->flush_q_lock);
+	return 0;
+alloc_err:
+	pr_err("%s(%d) error.\n", __func__, dev->id);
+	return -ENOMEM;
+}
+
+static void ocrdma_free_resources(struct ocrdma_dev *dev)
+{
+	ocrdma_release_stats_resources(dev);
+	kfree(dev->stag_arr);
+	kfree(dev->qp_tbl);
+	kfree(dev->cq_tbl);
+}
+
+static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info)
+{
+	int status = 0;
+	u8 lstate = 0;
+	struct ocrdma_dev *dev;
+
+	dev = ib_alloc_device(ocrdma_dev, ibdev);
+	if (!dev) {
+		pr_err("Unable to allocate ib device\n");
+		return NULL;
+	}
+
+	dev->mbx_cmd = kzalloc(sizeof(struct ocrdma_mqe_emb_cmd), GFP_KERNEL);
+	if (!dev->mbx_cmd)
+		goto init_err;
+
+	memcpy(&dev->nic_info, dev_info, sizeof(*dev_info));
+	dev->id = PCI_FUNC(dev->nic_info.pdev->devfn);
+	status = ocrdma_init_hw(dev);
+	if (status)
+		goto init_err;
+
+	status = ocrdma_alloc_resources(dev);
+	if (status)
+		goto alloc_err;
+
+	ocrdma_init_service_level(dev);
+	status = ocrdma_register_device(dev);
+	if (status)
+		goto alloc_err;
+
+	/* Query Link state and update */
+	status = ocrdma_mbx_get_link_speed(dev, NULL, &lstate);
+	if (!status)
+		ocrdma_update_link_state(dev, lstate);
+
+	/* Init stats */
+	ocrdma_add_port_stats(dev);
+	/* Interrupt Moderation */
+	INIT_DELAYED_WORK(&dev->eqd_work, ocrdma_eqd_set_task);
+	schedule_delayed_work(&dev->eqd_work, msecs_to_jiffies(1000));
+
+	pr_info("%s %s: %s \"%s\" port %d\n",
+		dev_name(&dev->nic_info.pdev->dev), hca_name(dev),
+		port_speed_string(dev), dev->model_number,
+		dev->hba_port_num);
+	pr_info("%s ocrdma%d driver loaded successfully\n",
+		dev_name(&dev->nic_info.pdev->dev), dev->id);
+	return dev;
+
+alloc_err:
+	ocrdma_free_resources(dev);
+	ocrdma_cleanup_hw(dev);
+init_err:
+	kfree(dev->mbx_cmd);
+	ib_dealloc_device(&dev->ibdev);
+	pr_err("%s() leaving. ret=%d\n", __func__, status);
+	return NULL;
+}
+
+static void ocrdma_remove_free(struct ocrdma_dev *dev)
+{
+
+	kfree(dev->mbx_cmd);
+	ib_dealloc_device(&dev->ibdev);
+}
+
+static void ocrdma_remove(struct ocrdma_dev *dev)
+{
+	/* first unregister with stack to stop all the active traffic
+	 * of the registered clients.
+	 */
+	cancel_delayed_work_sync(&dev->eqd_work);
+	ib_unregister_device(&dev->ibdev);
+
+	ocrdma_rem_port_stats(dev);
+	ocrdma_free_resources(dev);
+	ocrdma_cleanup_hw(dev);
+	ocrdma_remove_free(dev);
+}
+
+static int ocrdma_dispatch_port_active(struct ocrdma_dev *dev)
+{
+	struct ib_event port_event;
+
+	port_event.event = IB_EVENT_PORT_ACTIVE;
+	port_event.element.port_num = 1;
+	port_event.device = &dev->ibdev;
+	ib_dispatch_event(&port_event);
+	return 0;
+}
+
+static int ocrdma_dispatch_port_error(struct ocrdma_dev *dev)
+{
+	struct ib_event err_event;
+
+	err_event.event = IB_EVENT_PORT_ERR;
+	err_event.element.port_num = 1;
+	err_event.device = &dev->ibdev;
+	ib_dispatch_event(&err_event);
+	return 0;
+}
+
+static void ocrdma_shutdown(struct ocrdma_dev *dev)
+{
+	ocrdma_dispatch_port_error(dev);
+	ocrdma_remove(dev);
+}
+
+/* event handling via NIC driver ensures that all the NIC specific
+ * initialization done before RoCE driver notifies
+ * event to stack.
+ */
+static void ocrdma_event_handler(struct ocrdma_dev *dev, u32 event)
+{
+	switch (event) {
+	case BE_DEV_SHUTDOWN:
+		ocrdma_shutdown(dev);
+		break;
+	default:
+		break;
+	}
+}
+
+void ocrdma_update_link_state(struct ocrdma_dev *dev, u8 lstate)
+{
+	if (!(dev->flags & OCRDMA_FLAGS_LINK_STATUS_INIT)) {
+		dev->flags |= OCRDMA_FLAGS_LINK_STATUS_INIT;
+		if (!lstate)
+			return;
+	}
+
+	if (!lstate)
+		ocrdma_dispatch_port_error(dev);
+	else
+		ocrdma_dispatch_port_active(dev);
+}
+
+static struct ocrdma_driver ocrdma_drv = {
+	.name			= "ocrdma_driver",
+	.add			= ocrdma_add,
+	.remove			= ocrdma_remove,
+	.state_change_handler	= ocrdma_event_handler,
+	.be_abi_version		= OCRDMA_BE_ROCE_ABI_VERSION,
+};
+
+static int __init ocrdma_init_module(void)
+{
+	int status;
+
+	ocrdma_init_debugfs();
+
+	status = be_roce_register_driver(&ocrdma_drv);
+	if (status)
+		goto err_be_reg;
+
+	return 0;
+
+err_be_reg:
+
+	return status;
+}
+
+static void __exit ocrdma_exit_module(void)
+{
+	be_roce_unregister_driver(&ocrdma_drv);
+	ocrdma_rem_debugfs();
+}
+
+module_init(ocrdma_init_module);
+module_exit(ocrdma_exit_module);