Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

17 files changed, 17029 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/Kconfig b/drivers/infiniband/hw/bnxt_re/Kconfig
new file mode 100644
index 000000000..6a17f5cdb
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/Kconfig
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config INFINIBAND_BNXT_RE
+	tristate "Broadcom Netxtreme HCA support"
+	depends on 64BIT
+	depends on INET && DCB && BNXT
+	help
+	  This driver supports Broadcom NetXtreme-E 10/25/40/50 gigabit
+	  RoCE HCAs.  To compile this driver as a module, choose M here:
+	  the module will be called bnxt_re.
diff --git a/drivers/infiniband/hw/bnxt_re/Makefile b/drivers/infiniband/hw/bnxt_re/Makefile
new file mode 100644
index 000000000..ee9bb1be6
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ccflags-y := -I $(srctree)/drivers/net/ethernet/broadcom/bnxt
+obj-$(CONFIG_INFINIBAND_BNXT_RE) += bnxt_re.o
+bnxt_re-y := main.o ib_verbs.o \
+	     qplib_res.o qplib_rcfw.o	\
+	     qplib_sp.o qplib_fp.o  hw_counters.o
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
new file mode 100644
index 000000000..785c37cae
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -0,0 +1,198 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Slow Path Operators (header)
+ *
+ */
+
+#ifndef __BNXT_RE_H__
+#define __BNXT_RE_H__
+#include "hw_counters.h"
+#define ROCE_DRV_MODULE_NAME		"bnxt_re"
+
+#define BNXT_RE_DESC	"Broadcom NetXtreme-C/E RoCE Driver"
+
+#define BNXT_RE_PAGE_SHIFT_1G		(30)
+#define BNXT_RE_PAGE_SIZE_SUPPORTED	0x7FFFF000 /* 4kb - 1G */
+
+#define BNXT_RE_MAX_MR_SIZE_LOW		BIT_ULL(BNXT_RE_PAGE_SHIFT_1G)
+#define BNXT_RE_MAX_MR_SIZE_HIGH	BIT_ULL(39)
+#define BNXT_RE_MAX_MR_SIZE		BNXT_RE_MAX_MR_SIZE_HIGH
+
+#define BNXT_RE_MAX_QPC_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_SRQC_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_CQ_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_64K	(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_256K	(256 * 1024)
+
+/* Number of MRs to reserve for PF, leaving remainder for VFs */
+#define BNXT_RE_RESVD_MR_FOR_PF         (32 * 1024)
+#define BNXT_RE_MAX_GID_PER_VF          128
+
+/*
+ * Percentage of resources of each type reserved for PF.
+ * Remaining resources are divided equally among VFs.
+ * [0, 100]
+ */
+#define BNXT_RE_PCT_RSVD_FOR_PF         50
+
+#define BNXT_RE_UD_QP_HW_STALL		0x400000
+
+#define BNXT_RE_RQ_WQE_THRESHOLD	32
+
+/*
+ * Setting the default ack delay value to 16, which means
+ * the default timeout is approx. 260ms(4 usec * 2 ^(timeout))
+ */
+
+#define BNXT_RE_DEFAULT_ACK_DELAY	16
+
+struct bnxt_re_ring_attr {
+	dma_addr_t	*dma_arr;
+	int		pages;
+	int		type;
+	u32		depth;
+	u32		lrid; /* Logical ring id */
+	u8		mode;
+};
+
+struct bnxt_re_work {
+	struct work_struct	work;
+	unsigned long		event;
+	struct bnxt_re_dev      *rdev;
+	struct net_device	*vlan_dev;
+};
+
+struct bnxt_re_sqp_entries {
+	struct bnxt_qplib_sge sge;
+	u64 wrid;
+	/* For storing the actual qp1 cqe */
+	struct bnxt_qplib_cqe cqe;
+	struct bnxt_re_qp *qp1_qp;
+};
+
+#define BNXT_RE_MAX_GSI_SQP_ENTRIES	1024
+struct bnxt_re_gsi_context {
+	struct	bnxt_re_qp *gsi_qp;
+	struct	bnxt_re_qp *gsi_sqp;
+	struct	bnxt_re_ah *gsi_sah;
+	struct	bnxt_re_sqp_entries *sqp_tbl;
+};
+
+#define BNXT_RE_MIN_MSIX		2
+#define BNXT_RE_MAX_MSIX		9
+#define BNXT_RE_AEQ_IDX			0
+#define BNXT_RE_NQ_IDX			1
+#define BNXT_RE_GEN_P5_MAX_VF		64
+
+struct bnxt_re_dev {
+	struct ib_device		ibdev;
+	struct list_head		list;
+	unsigned long			flags;
+#define BNXT_RE_FLAG_NETDEV_REGISTERED		0
+#define BNXT_RE_FLAG_GOT_MSIX			2
+#define BNXT_RE_FLAG_HAVE_L2_REF		3
+#define BNXT_RE_FLAG_RCFW_CHANNEL_EN		4
+#define BNXT_RE_FLAG_QOS_WORK_REG		5
+#define BNXT_RE_FLAG_RESOURCES_ALLOCATED	7
+#define BNXT_RE_FLAG_RESOURCES_INITIALIZED	8
+#define BNXT_RE_FLAG_ERR_DEVICE_DETACHED       17
+#define BNXT_RE_FLAG_ISSUE_ROCE_STATS          29
+	struct net_device		*netdev;
+	unsigned int			version, major, minor;
+	struct bnxt_qplib_chip_ctx	*chip_ctx;
+	struct bnxt_en_dev		*en_dev;
+	struct bnxt_msix_entry		msix_entries[BNXT_RE_MAX_MSIX];
+	int				num_msix;
+
+	int				id;
+
+	struct delayed_work		worker;
+	u8				cur_prio_map;
+	u16				active_speed;
+	u8				active_width;
+
+	/* FP Notification Queue (CQ & SRQ) */
+	struct tasklet_struct		nq_task;
+
+	/* RCFW Channel */
+	struct bnxt_qplib_rcfw		rcfw;
+
+	/* NQ */
+	struct bnxt_qplib_nq		nq[BNXT_RE_MAX_MSIX];
+
+	/* Device Resources */
+	struct bnxt_qplib_dev_attr	dev_attr;
+	struct bnxt_qplib_ctx		qplib_ctx;
+	struct bnxt_qplib_res		qplib_res;
+	struct bnxt_qplib_dpi		dpi_privileged;
+
+	atomic_t			qp_count;
+	struct mutex			qp_lock;	/* protect qp list */
+	struct list_head		qp_list;
+
+	atomic_t			cq_count;
+	atomic_t			srq_count;
+	atomic_t			mr_count;
+	atomic_t			mw_count;
+	atomic_t			ah_count;
+	atomic_t			pd_count;
+	/* Max of 2 lossless traffic class supported per port */
+	u16				cosq[2];
+
+	/* QP for handling QP1 packets */
+	struct bnxt_re_gsi_context	gsi_ctx;
+	struct bnxt_re_stats		stats;
+	atomic_t nq_alloc_cnt;
+	u32 is_virtfn;
+	u32 num_vfs;
+};
+
+#define to_bnxt_re_dev(ptr, member)	\
+	container_of((ptr), struct bnxt_re_dev, member)
+
+#define BNXT_RE_ROCE_V1_PACKET		0
+#define BNXT_RE_ROCEV2_IPV4_PACKET	2
+#define BNXT_RE_ROCEV2_IPV6_PACKET	3
+
+static inline struct device *rdev_to_dev(struct bnxt_re_dev *rdev)
+{
+	if (rdev)
+		return  &rdev->ibdev.dev;
+	return NULL;
+}
+
+#endif
diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c
new file mode 100644
index 000000000..825d51279
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c
@@ -0,0 +1,327 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Statistics
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/prefetch.h>
+#include <linux/delay.h>
+
+#include <rdma/ib_addr.h>
+
+#include "bnxt_ulp.h"
+#include "roce_hsi.h"
+#include "qplib_res.h"
+#include "qplib_sp.h"
+#include "qplib_fp.h"
+#include "qplib_rcfw.h"
+#include "bnxt_re.h"
+#include "hw_counters.h"
+
+static const struct rdma_stat_desc bnxt_re_stat_descs[] = {
+	[BNXT_RE_ACTIVE_PD].name		=  "active_pds",
+	[BNXT_RE_ACTIVE_AH].name		=  "active_ahs",
+	[BNXT_RE_ACTIVE_QP].name		=  "active_qps",
+	[BNXT_RE_ACTIVE_SRQ].name		=  "active_srqs",
+	[BNXT_RE_ACTIVE_CQ].name		=  "active_cqs",
+	[BNXT_RE_ACTIVE_MR].name		=  "active_mrs",
+	[BNXT_RE_ACTIVE_MW].name		=  "active_mws",
+	[BNXT_RE_RX_PKTS].name		=  "rx_pkts",
+	[BNXT_RE_RX_BYTES].name		=  "rx_bytes",
+	[BNXT_RE_TX_PKTS].name		=  "tx_pkts",
+	[BNXT_RE_TX_BYTES].name		=  "tx_bytes",
+	[BNXT_RE_RECOVERABLE_ERRORS].name	=  "recoverable_errors",
+	[BNXT_RE_RX_ERRORS].name		=  "rx_roce_errors",
+	[BNXT_RE_RX_DISCARDS].name		=  "rx_roce_discards",
+	[BNXT_RE_TO_RETRANSMITS].name        = "to_retransmits",
+	[BNXT_RE_SEQ_ERR_NAKS_RCVD].name     = "seq_err_naks_rcvd",
+	[BNXT_RE_MAX_RETRY_EXCEEDED].name    = "max_retry_exceeded",
+	[BNXT_RE_RNR_NAKS_RCVD].name         = "rnr_naks_rcvd",
+	[BNXT_RE_MISSING_RESP].name          = "missing_resp",
+	[BNXT_RE_UNRECOVERABLE_ERR].name     = "unrecoverable_err",
+	[BNXT_RE_BAD_RESP_ERR].name          = "bad_resp_err",
+	[BNXT_RE_LOCAL_QP_OP_ERR].name       = "local_qp_op_err",
+	[BNXT_RE_LOCAL_PROTECTION_ERR].name  = "local_protection_err",
+	[BNXT_RE_MEM_MGMT_OP_ERR].name       = "mem_mgmt_op_err",
+	[BNXT_RE_REMOTE_INVALID_REQ_ERR].name = "remote_invalid_req_err",
+	[BNXT_RE_REMOTE_ACCESS_ERR].name     = "remote_access_err",
+	[BNXT_RE_REMOTE_OP_ERR].name         = "remote_op_err",
+	[BNXT_RE_DUP_REQ].name               = "dup_req",
+	[BNXT_RE_RES_EXCEED_MAX].name        = "res_exceed_max",
+	[BNXT_RE_RES_LENGTH_MISMATCH].name   = "res_length_mismatch",
+	[BNXT_RE_RES_EXCEEDS_WQE].name       = "res_exceeds_wqe",
+	[BNXT_RE_RES_OPCODE_ERR].name        = "res_opcode_err",
+	[BNXT_RE_RES_RX_INVALID_RKEY].name   = "res_rx_invalid_rkey",
+	[BNXT_RE_RES_RX_DOMAIN_ERR].name     = "res_rx_domain_err",
+	[BNXT_RE_RES_RX_NO_PERM].name        = "res_rx_no_perm",
+	[BNXT_RE_RES_RX_RANGE_ERR].name      = "res_rx_range_err",
+	[BNXT_RE_RES_TX_INVALID_RKEY].name   = "res_tx_invalid_rkey",
+	[BNXT_RE_RES_TX_DOMAIN_ERR].name     = "res_tx_domain_err",
+	[BNXT_RE_RES_TX_NO_PERM].name        = "res_tx_no_perm",
+	[BNXT_RE_RES_TX_RANGE_ERR].name      = "res_tx_range_err",
+	[BNXT_RE_RES_IRRQ_OFLOW].name        = "res_irrq_oflow",
+	[BNXT_RE_RES_UNSUP_OPCODE].name      = "res_unsup_opcode",
+	[BNXT_RE_RES_UNALIGNED_ATOMIC].name  = "res_unaligned_atomic",
+	[BNXT_RE_RES_REM_INV_ERR].name       = "res_rem_inv_err",
+	[BNXT_RE_RES_MEM_ERROR].name         = "res_mem_err",
+	[BNXT_RE_RES_SRQ_ERR].name           = "res_srq_err",
+	[BNXT_RE_RES_CMP_ERR].name           = "res_cmp_err",
+	[BNXT_RE_RES_INVALID_DUP_RKEY].name  = "res_invalid_dup_rkey",
+	[BNXT_RE_RES_WQE_FORMAT_ERR].name    = "res_wqe_format_err",
+	[BNXT_RE_RES_CQ_LOAD_ERR].name       = "res_cq_load_err",
+	[BNXT_RE_RES_SRQ_LOAD_ERR].name      = "res_srq_load_err",
+	[BNXT_RE_RES_TX_PCI_ERR].name        = "res_tx_pci_err",
+	[BNXT_RE_RES_RX_PCI_ERR].name        = "res_rx_pci_err",
+	[BNXT_RE_OUT_OF_SEQ_ERR].name        = "oos_drop_count",
+	[BNXT_RE_TX_ATOMIC_REQ].name	     = "tx_atomic_req",
+	[BNXT_RE_TX_READ_REQ].name	     = "tx_read_req",
+	[BNXT_RE_TX_READ_RES].name	     = "tx_read_resp",
+	[BNXT_RE_TX_WRITE_REQ].name	     = "tx_write_req",
+	[BNXT_RE_TX_SEND_REQ].name	     = "tx_send_req",
+	[BNXT_RE_RX_ATOMIC_REQ].name	     = "rx_atomic_req",
+	[BNXT_RE_RX_READ_REQ].name	     = "rx_read_req",
+	[BNXT_RE_RX_READ_RESP].name	     = "rx_read_resp",
+	[BNXT_RE_RX_WRITE_REQ].name	     = "rx_write_req",
+	[BNXT_RE_RX_SEND_REQ].name	     = "rx_send_req",
+	[BNXT_RE_RX_ROCE_GOOD_PKTS].name     = "rx_roce_good_pkts",
+	[BNXT_RE_RX_ROCE_GOOD_BYTES].name    = "rx_roce_good_bytes",
+	[BNXT_RE_OOB].name		     = "rx_out_of_buffer"
+};
+
+static void bnxt_re_copy_ext_stats(struct bnxt_re_dev *rdev,
+				   struct rdma_hw_stats *stats,
+				   struct bnxt_qplib_ext_stat *s)
+{
+	stats->value[BNXT_RE_TX_ATOMIC_REQ] = s->tx_atomic_req;
+	stats->value[BNXT_RE_TX_READ_REQ]   = s->tx_read_req;
+	stats->value[BNXT_RE_TX_READ_RES]   = s->tx_read_res;
+	stats->value[BNXT_RE_TX_WRITE_REQ]  = s->tx_write_req;
+	stats->value[BNXT_RE_TX_SEND_REQ]   = s->tx_send_req;
+	stats->value[BNXT_RE_RX_ATOMIC_REQ] = s->rx_atomic_req;
+	stats->value[BNXT_RE_RX_READ_REQ]   = s->rx_read_req;
+	stats->value[BNXT_RE_RX_READ_RESP]  = s->rx_read_res;
+	stats->value[BNXT_RE_RX_WRITE_REQ]  = s->rx_write_req;
+	stats->value[BNXT_RE_RX_SEND_REQ]   = s->rx_send_req;
+	stats->value[BNXT_RE_RX_ROCE_GOOD_PKTS] = s->rx_roce_good_pkts;
+	stats->value[BNXT_RE_RX_ROCE_GOOD_BYTES] = s->rx_roce_good_bytes;
+	stats->value[BNXT_RE_OOB] = s->rx_out_of_buffer;
+}
+
+static int bnxt_re_get_ext_stat(struct bnxt_re_dev *rdev,
+				struct rdma_hw_stats *stats)
+{
+	struct bnxt_qplib_ext_stat *estat = &rdev->stats.rstat.ext_stat;
+	u32 fid;
+	int rc;
+
+	fid = PCI_FUNC(rdev->en_dev->pdev->devfn);
+	rc = bnxt_qplib_qext_stat(&rdev->rcfw, fid, estat);
+	if (rc)
+		goto done;
+	bnxt_re_copy_ext_stats(rdev, stats, estat);
+
+done:
+	return rc;
+}
+
+static void bnxt_re_copy_err_stats(struct bnxt_re_dev *rdev,
+				   struct rdma_hw_stats *stats,
+				   struct bnxt_qplib_roce_stats *err_s)
+{
+	stats->value[BNXT_RE_TO_RETRANSMITS] =
+				err_s->to_retransmits;
+	stats->value[BNXT_RE_SEQ_ERR_NAKS_RCVD] =
+				err_s->seq_err_naks_rcvd;
+	stats->value[BNXT_RE_MAX_RETRY_EXCEEDED] =
+				err_s->max_retry_exceeded;
+	stats->value[BNXT_RE_RNR_NAKS_RCVD] =
+				err_s->rnr_naks_rcvd;
+	stats->value[BNXT_RE_MISSING_RESP] =
+				err_s->missing_resp;
+	stats->value[BNXT_RE_UNRECOVERABLE_ERR] =
+				err_s->unrecoverable_err;
+	stats->value[BNXT_RE_BAD_RESP_ERR] =
+				err_s->bad_resp_err;
+	stats->value[BNXT_RE_LOCAL_QP_OP_ERR]	=
+			err_s->local_qp_op_err;
+	stats->value[BNXT_RE_LOCAL_PROTECTION_ERR] =
+			err_s->local_protection_err;
+	stats->value[BNXT_RE_MEM_MGMT_OP_ERR] =
+			err_s->mem_mgmt_op_err;
+	stats->value[BNXT_RE_REMOTE_INVALID_REQ_ERR] =
+			err_s->remote_invalid_req_err;
+	stats->value[BNXT_RE_REMOTE_ACCESS_ERR] =
+			err_s->remote_access_err;
+	stats->value[BNXT_RE_REMOTE_OP_ERR] =
+			err_s->remote_op_err;
+	stats->value[BNXT_RE_DUP_REQ] =
+			err_s->dup_req;
+	stats->value[BNXT_RE_RES_EXCEED_MAX] =
+			err_s->res_exceed_max;
+	stats->value[BNXT_RE_RES_LENGTH_MISMATCH] =
+			err_s->res_length_mismatch;
+	stats->value[BNXT_RE_RES_EXCEEDS_WQE] =
+			err_s->res_exceeds_wqe;
+	stats->value[BNXT_RE_RES_OPCODE_ERR] =
+			err_s->res_opcode_err;
+	stats->value[BNXT_RE_RES_RX_INVALID_RKEY] =
+			err_s->res_rx_invalid_rkey;
+	stats->value[BNXT_RE_RES_RX_DOMAIN_ERR] =
+			err_s->res_rx_domain_err;
+	stats->value[BNXT_RE_RES_RX_NO_PERM] =
+			err_s->res_rx_no_perm;
+	stats->value[BNXT_RE_RES_RX_RANGE_ERR]  =
+			err_s->res_rx_range_err;
+	stats->value[BNXT_RE_RES_TX_INVALID_RKEY] =
+			err_s->res_tx_invalid_rkey;
+	stats->value[BNXT_RE_RES_TX_DOMAIN_ERR] =
+			err_s->res_tx_domain_err;
+	stats->value[BNXT_RE_RES_TX_NO_PERM] =
+			err_s->res_tx_no_perm;
+	stats->value[BNXT_RE_RES_TX_RANGE_ERR]  =
+			err_s->res_tx_range_err;
+	stats->value[BNXT_RE_RES_IRRQ_OFLOW] =
+			err_s->res_irrq_oflow;
+	stats->value[BNXT_RE_RES_UNSUP_OPCODE]  =
+			err_s->res_unsup_opcode;
+	stats->value[BNXT_RE_RES_UNALIGNED_ATOMIC] =
+			err_s->res_unaligned_atomic;
+	stats->value[BNXT_RE_RES_REM_INV_ERR]   =
+			err_s->res_rem_inv_err;
+	stats->value[BNXT_RE_RES_MEM_ERROR] =
+			err_s->res_mem_error;
+	stats->value[BNXT_RE_RES_SRQ_ERR] =
+			err_s->res_srq_err;
+	stats->value[BNXT_RE_RES_CMP_ERR] =
+			err_s->res_cmp_err;
+	stats->value[BNXT_RE_RES_INVALID_DUP_RKEY] =
+			err_s->res_invalid_dup_rkey;
+	stats->value[BNXT_RE_RES_WQE_FORMAT_ERR] =
+			err_s->res_wqe_format_err;
+	stats->value[BNXT_RE_RES_CQ_LOAD_ERR]   =
+			err_s->res_cq_load_err;
+	stats->value[BNXT_RE_RES_SRQ_LOAD_ERR]  =
+			err_s->res_srq_load_err;
+	stats->value[BNXT_RE_RES_TX_PCI_ERR]    =
+			err_s->res_tx_pci_err;
+	stats->value[BNXT_RE_RES_RX_PCI_ERR]    =
+			err_s->res_rx_pci_err;
+	stats->value[BNXT_RE_OUT_OF_SEQ_ERR]    =
+			err_s->res_oos_drop_count;
+}
+
+int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
+			    struct rdma_hw_stats *stats,
+			    u32 port, int index)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct ctx_hw_stats *hw_stats = NULL;
+	struct bnxt_qplib_roce_stats *err_s = NULL;
+	int rc  = 0;
+
+	hw_stats = rdev->qplib_ctx.stats.dma;
+	if (!port || !stats)
+		return -EINVAL;
+
+	stats->value[BNXT_RE_ACTIVE_QP] = atomic_read(&rdev->qp_count);
+	stats->value[BNXT_RE_ACTIVE_SRQ] = atomic_read(&rdev->srq_count);
+	stats->value[BNXT_RE_ACTIVE_CQ] = atomic_read(&rdev->cq_count);
+	stats->value[BNXT_RE_ACTIVE_MR] = atomic_read(&rdev->mr_count);
+	stats->value[BNXT_RE_ACTIVE_MW] = atomic_read(&rdev->mw_count);
+	stats->value[BNXT_RE_ACTIVE_PD] = atomic_read(&rdev->pd_count);
+	stats->value[BNXT_RE_ACTIVE_AH] = atomic_read(&rdev->ah_count);
+
+	if (hw_stats) {
+		stats->value[BNXT_RE_RECOVERABLE_ERRORS] =
+			le64_to_cpu(hw_stats->tx_bcast_pkts);
+		stats->value[BNXT_RE_RX_ERRORS] =
+			le64_to_cpu(hw_stats->rx_error_pkts);
+		stats->value[BNXT_RE_RX_DISCARDS] =
+			le64_to_cpu(hw_stats->rx_discard_pkts);
+		stats->value[BNXT_RE_RX_PKTS] =
+			le64_to_cpu(hw_stats->rx_ucast_pkts);
+		stats->value[BNXT_RE_RX_BYTES] =
+			le64_to_cpu(hw_stats->rx_ucast_bytes);
+		stats->value[BNXT_RE_TX_PKTS] =
+			le64_to_cpu(hw_stats->tx_ucast_pkts);
+		stats->value[BNXT_RE_TX_BYTES] =
+			le64_to_cpu(hw_stats->tx_ucast_bytes);
+	}
+	err_s = &rdev->stats.rstat.errs;
+	if (test_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags)) {
+		rc = bnxt_qplib_get_roce_stats(&rdev->rcfw, err_s);
+		if (rc) {
+			clear_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS,
+				  &rdev->flags);
+			goto done;
+		}
+		if (_is_ext_stats_supported(rdev->dev_attr.dev_cap_flags) &&
+		    !rdev->is_virtfn) {
+			rc = bnxt_re_get_ext_stat(rdev, stats);
+			if (rc) {
+				clear_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS,
+					  &rdev->flags);
+				goto done;
+			}
+		}
+		bnxt_re_copy_err_stats(rdev, stats, err_s);
+	}
+
+done:
+	return bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
+		BNXT_RE_NUM_EXT_COUNTERS : BNXT_RE_NUM_STD_COUNTERS;
+}
+
+struct rdma_hw_stats *bnxt_re_ib_alloc_hw_port_stats(struct ib_device *ibdev,
+						     u32 port_num)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	int num_counters = 0;
+
+	if (bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx))
+		num_counters = BNXT_RE_NUM_EXT_COUNTERS;
+	else
+		num_counters = BNXT_RE_NUM_STD_COUNTERS;
+
+	return rdma_alloc_hw_stats_struct(bnxt_re_stat_descs, num_counters,
+					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.h b/drivers/infiniband/hw/bnxt_re/hw_counters.h
new file mode 100644
index 000000000..7943b2c39
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.h
@@ -0,0 +1,130 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Statistics (header)
+ *
+ */
+
+#ifndef __BNXT_RE_HW_STATS_H__
+#define __BNXT_RE_HW_STATS_H__
+
+enum bnxt_re_hw_stats {
+	BNXT_RE_ACTIVE_PD,
+	BNXT_RE_ACTIVE_AH,
+	BNXT_RE_ACTIVE_QP,
+	BNXT_RE_ACTIVE_SRQ,
+	BNXT_RE_ACTIVE_CQ,
+	BNXT_RE_ACTIVE_MR,
+	BNXT_RE_ACTIVE_MW,
+	BNXT_RE_RX_PKTS,
+	BNXT_RE_RX_BYTES,
+	BNXT_RE_TX_PKTS,
+	BNXT_RE_TX_BYTES,
+	BNXT_RE_RECOVERABLE_ERRORS,
+	BNXT_RE_RX_ERRORS,
+	BNXT_RE_RX_DISCARDS,
+	BNXT_RE_TO_RETRANSMITS,
+	BNXT_RE_SEQ_ERR_NAKS_RCVD,
+	BNXT_RE_MAX_RETRY_EXCEEDED,
+	BNXT_RE_RNR_NAKS_RCVD,
+	BNXT_RE_MISSING_RESP,
+	BNXT_RE_UNRECOVERABLE_ERR,
+	BNXT_RE_BAD_RESP_ERR,
+	BNXT_RE_LOCAL_QP_OP_ERR,
+	BNXT_RE_LOCAL_PROTECTION_ERR,
+	BNXT_RE_MEM_MGMT_OP_ERR,
+	BNXT_RE_REMOTE_INVALID_REQ_ERR,
+	BNXT_RE_REMOTE_ACCESS_ERR,
+	BNXT_RE_REMOTE_OP_ERR,
+	BNXT_RE_DUP_REQ,
+	BNXT_RE_RES_EXCEED_MAX,
+	BNXT_RE_RES_LENGTH_MISMATCH,
+	BNXT_RE_RES_EXCEEDS_WQE,
+	BNXT_RE_RES_OPCODE_ERR,
+	BNXT_RE_RES_RX_INVALID_RKEY,
+	BNXT_RE_RES_RX_DOMAIN_ERR,
+	BNXT_RE_RES_RX_NO_PERM,
+	BNXT_RE_RES_RX_RANGE_ERR,
+	BNXT_RE_RES_TX_INVALID_RKEY,
+	BNXT_RE_RES_TX_DOMAIN_ERR,
+	BNXT_RE_RES_TX_NO_PERM,
+	BNXT_RE_RES_TX_RANGE_ERR,
+	BNXT_RE_RES_IRRQ_OFLOW,
+	BNXT_RE_RES_UNSUP_OPCODE,
+	BNXT_RE_RES_UNALIGNED_ATOMIC,
+	BNXT_RE_RES_REM_INV_ERR,
+	BNXT_RE_RES_MEM_ERROR,
+	BNXT_RE_RES_SRQ_ERR,
+	BNXT_RE_RES_CMP_ERR,
+	BNXT_RE_RES_INVALID_DUP_RKEY,
+	BNXT_RE_RES_WQE_FORMAT_ERR,
+	BNXT_RE_RES_CQ_LOAD_ERR,
+	BNXT_RE_RES_SRQ_LOAD_ERR,
+	BNXT_RE_RES_TX_PCI_ERR,
+	BNXT_RE_RES_RX_PCI_ERR,
+	BNXT_RE_OUT_OF_SEQ_ERR,
+	BNXT_RE_TX_ATOMIC_REQ,
+	BNXT_RE_TX_READ_REQ,
+	BNXT_RE_TX_READ_RES,
+	BNXT_RE_TX_WRITE_REQ,
+	BNXT_RE_TX_SEND_REQ,
+	BNXT_RE_RX_ATOMIC_REQ,
+	BNXT_RE_RX_READ_REQ,
+	BNXT_RE_RX_READ_RESP,
+	BNXT_RE_RX_WRITE_REQ,
+	BNXT_RE_RX_SEND_REQ,
+	BNXT_RE_RX_ROCE_GOOD_PKTS,
+	BNXT_RE_RX_ROCE_GOOD_BYTES,
+	BNXT_RE_OOB,
+	BNXT_RE_NUM_EXT_COUNTERS
+};
+
+#define BNXT_RE_NUM_STD_COUNTERS (BNXT_RE_OUT_OF_SEQ_ERR + 1)
+
+struct bnxt_re_rstat {
+	struct bnxt_qplib_roce_stats    errs;
+	struct bnxt_qplib_ext_stat      ext_stat;
+};
+
+struct bnxt_re_stats {
+	struct bnxt_re_rstat            rstat;
+};
+
+struct rdma_hw_stats *bnxt_re_ib_alloc_hw_port_stats(struct ib_device *ibdev,
+						     u32 port_num);
+int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
+			    struct rdma_hw_stats *stats,
+			    u32 port, int index);
+#endif /* __BNXT_RE_HW_STATS_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
new file mode 100644
index 000000000..4ed8814ef
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -0,0 +1,3963 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: IB Verbs interpreter
+ */
+
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/if_ether.h>
+#include <net/addrconf.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_umem.h>
+#include <rdma/ib_addr.h>
+#include <rdma/ib_mad.h>
+#include <rdma/ib_cache.h>
+#include <rdma/uverbs_ioctl.h>
+
+#include "bnxt_ulp.h"
+
+#include "roce_hsi.h"
+#include "qplib_res.h"
+#include "qplib_sp.h"
+#include "qplib_fp.h"
+#include "qplib_rcfw.h"
+
+#include "bnxt_re.h"
+#include "ib_verbs.h"
+#include <rdma/bnxt_re-abi.h>
+
+static int __from_ib_access_flags(int iflags)
+{
+	int qflags = 0;
+
+	if (iflags & IB_ACCESS_LOCAL_WRITE)
+		qflags |= BNXT_QPLIB_ACCESS_LOCAL_WRITE;
+	if (iflags & IB_ACCESS_REMOTE_READ)
+		qflags |= BNXT_QPLIB_ACCESS_REMOTE_READ;
+	if (iflags & IB_ACCESS_REMOTE_WRITE)
+		qflags |= BNXT_QPLIB_ACCESS_REMOTE_WRITE;
+	if (iflags & IB_ACCESS_REMOTE_ATOMIC)
+		qflags |= BNXT_QPLIB_ACCESS_REMOTE_ATOMIC;
+	if (iflags & IB_ACCESS_MW_BIND)
+		qflags |= BNXT_QPLIB_ACCESS_MW_BIND;
+	if (iflags & IB_ZERO_BASED)
+		qflags |= BNXT_QPLIB_ACCESS_ZERO_BASED;
+	if (iflags & IB_ACCESS_ON_DEMAND)
+		qflags |= BNXT_QPLIB_ACCESS_ON_DEMAND;
+	return qflags;
+};
+
+static enum ib_access_flags __to_ib_access_flags(int qflags)
+{
+	enum ib_access_flags iflags = 0;
+
+	if (qflags & BNXT_QPLIB_ACCESS_LOCAL_WRITE)
+		iflags |= IB_ACCESS_LOCAL_WRITE;
+	if (qflags & BNXT_QPLIB_ACCESS_REMOTE_WRITE)
+		iflags |= IB_ACCESS_REMOTE_WRITE;
+	if (qflags & BNXT_QPLIB_ACCESS_REMOTE_READ)
+		iflags |= IB_ACCESS_REMOTE_READ;
+	if (qflags & BNXT_QPLIB_ACCESS_REMOTE_ATOMIC)
+		iflags |= IB_ACCESS_REMOTE_ATOMIC;
+	if (qflags & BNXT_QPLIB_ACCESS_MW_BIND)
+		iflags |= IB_ACCESS_MW_BIND;
+	if (qflags & BNXT_QPLIB_ACCESS_ZERO_BASED)
+		iflags |= IB_ZERO_BASED;
+	if (qflags & BNXT_QPLIB_ACCESS_ON_DEMAND)
+		iflags |= IB_ACCESS_ON_DEMAND;
+	return iflags;
+};
+
+static int bnxt_re_build_sgl(struct ib_sge *ib_sg_list,
+			     struct bnxt_qplib_sge *sg_list, int num)
+{
+	int i, total = 0;
+
+	for (i = 0; i < num; i++) {
+		sg_list[i].addr = ib_sg_list[i].addr;
+		sg_list[i].lkey = ib_sg_list[i].lkey;
+		sg_list[i].size = ib_sg_list[i].length;
+		total += sg_list[i].size;
+	}
+	return total;
+}
+
+/* Device */
+int bnxt_re_query_device(struct ib_device *ibdev,
+			 struct ib_device_attr *ib_attr,
+			 struct ib_udata *udata)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+
+	memset(ib_attr, 0, sizeof(*ib_attr));
+	memcpy(&ib_attr->fw_ver, dev_attr->fw_ver,
+	       min(sizeof(dev_attr->fw_ver),
+		   sizeof(ib_attr->fw_ver)));
+	addrconf_addr_eui48((u8 *)&ib_attr->sys_image_guid,
+			    rdev->netdev->dev_addr);
+	ib_attr->max_mr_size = BNXT_RE_MAX_MR_SIZE;
+	ib_attr->page_size_cap = BNXT_RE_PAGE_SIZE_SUPPORTED;
+
+	ib_attr->vendor_id = rdev->en_dev->pdev->vendor;
+	ib_attr->vendor_part_id = rdev->en_dev->pdev->device;
+	ib_attr->hw_ver = rdev->en_dev->pdev->subsystem_device;
+	ib_attr->max_qp = dev_attr->max_qp;
+	ib_attr->max_qp_wr = dev_attr->max_qp_wqes;
+	ib_attr->device_cap_flags =
+				    IB_DEVICE_CURR_QP_STATE_MOD
+				    | IB_DEVICE_RC_RNR_NAK_GEN
+				    | IB_DEVICE_SHUTDOWN_PORT
+				    | IB_DEVICE_SYS_IMAGE_GUID
+				    | IB_DEVICE_RESIZE_MAX_WR
+				    | IB_DEVICE_PORT_ACTIVE_EVENT
+				    | IB_DEVICE_N_NOTIFY_CQ
+				    | IB_DEVICE_MEM_WINDOW
+				    | IB_DEVICE_MEM_WINDOW_TYPE_2B
+				    | IB_DEVICE_MEM_MGT_EXTENSIONS;
+	ib_attr->kernel_cap_flags = IBK_LOCAL_DMA_LKEY;
+	ib_attr->max_send_sge = dev_attr->max_qp_sges;
+	ib_attr->max_recv_sge = dev_attr->max_qp_sges;
+	ib_attr->max_sge_rd = dev_attr->max_qp_sges;
+	ib_attr->max_cq = dev_attr->max_cq;
+	ib_attr->max_cqe = dev_attr->max_cq_wqes;
+	ib_attr->max_mr = dev_attr->max_mr;
+	ib_attr->max_pd = dev_attr->max_pd;
+	ib_attr->max_qp_rd_atom = dev_attr->max_qp_rd_atom;
+	ib_attr->max_qp_init_rd_atom = dev_attr->max_qp_init_rd_atom;
+	ib_attr->atomic_cap = IB_ATOMIC_NONE;
+	ib_attr->masked_atomic_cap = IB_ATOMIC_NONE;
+	if (dev_attr->is_atomic) {
+		ib_attr->atomic_cap = IB_ATOMIC_GLOB;
+		ib_attr->masked_atomic_cap = IB_ATOMIC_GLOB;
+	}
+
+	ib_attr->max_ee_rd_atom = 0;
+	ib_attr->max_res_rd_atom = 0;
+	ib_attr->max_ee_init_rd_atom = 0;
+	ib_attr->max_ee = 0;
+	ib_attr->max_rdd = 0;
+	ib_attr->max_mw = dev_attr->max_mw;
+	ib_attr->max_raw_ipv6_qp = 0;
+	ib_attr->max_raw_ethy_qp = dev_attr->max_raw_ethy_qp;
+	ib_attr->max_mcast_grp = 0;
+	ib_attr->max_mcast_qp_attach = 0;
+	ib_attr->max_total_mcast_qp_attach = 0;
+	ib_attr->max_ah = dev_attr->max_ah;
+
+	ib_attr->max_srq = dev_attr->max_srq;
+	ib_attr->max_srq_wr = dev_attr->max_srq_wqes;
+	ib_attr->max_srq_sge = dev_attr->max_srq_sges;
+
+	ib_attr->max_fast_reg_page_list_len = MAX_PBL_LVL_1_PGS;
+
+	ib_attr->max_pkeys = 1;
+	ib_attr->local_ca_ack_delay = BNXT_RE_DEFAULT_ACK_DELAY;
+	return 0;
+}
+
+/* Port */
+int bnxt_re_query_port(struct ib_device *ibdev, u32 port_num,
+		       struct ib_port_attr *port_attr)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+
+	memset(port_attr, 0, sizeof(*port_attr));
+
+	if (netif_running(rdev->netdev) && netif_carrier_ok(rdev->netdev)) {
+		port_attr->state = IB_PORT_ACTIVE;
+		port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
+	} else {
+		port_attr->state = IB_PORT_DOWN;
+		port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
+	}
+	port_attr->max_mtu = IB_MTU_4096;
+	port_attr->active_mtu = iboe_get_mtu(rdev->netdev->mtu);
+	port_attr->gid_tbl_len = dev_attr->max_sgid;
+	port_attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_REINIT_SUP |
+				    IB_PORT_DEVICE_MGMT_SUP |
+				    IB_PORT_VENDOR_CLASS_SUP;
+	port_attr->ip_gids = true;
+
+	port_attr->max_msg_sz = (u32)BNXT_RE_MAX_MR_SIZE_LOW;
+	port_attr->bad_pkey_cntr = 0;
+	port_attr->qkey_viol_cntr = 0;
+	port_attr->pkey_tbl_len = dev_attr->max_pkey;
+	port_attr->lid = 0;
+	port_attr->sm_lid = 0;
+	port_attr->lmc = 0;
+	port_attr->max_vl_num = 4;
+	port_attr->sm_sl = 0;
+	port_attr->subnet_timeout = 0;
+	port_attr->init_type_reply = 0;
+	port_attr->active_speed = rdev->active_speed;
+	port_attr->active_width = rdev->active_width;
+
+	return 0;
+}
+
+int bnxt_re_get_port_immutable(struct ib_device *ibdev, u32 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr port_attr;
+
+	if (bnxt_re_query_port(ibdev, port_num, &port_attr))
+		return -EINVAL;
+
+	immutable->pkey_tbl_len = port_attr.pkey_tbl_len;
+	immutable->gid_tbl_len = port_attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+	immutable->core_cap_flags |= RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+	return 0;
+}
+
+void bnxt_re_query_fw_str(struct ib_device *ibdev, char *str)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d.%d",
+		 rdev->dev_attr.fw_ver[0], rdev->dev_attr.fw_ver[1],
+		 rdev->dev_attr.fw_ver[2], rdev->dev_attr.fw_ver[3]);
+}
+
+int bnxt_re_query_pkey(struct ib_device *ibdev, u32 port_num,
+		       u16 index, u16 *pkey)
+{
+	if (index > 0)
+		return -EINVAL;
+
+	*pkey = IB_DEFAULT_PKEY_FULL;
+
+	return 0;
+}
+
+int bnxt_re_query_gid(struct ib_device *ibdev, u32 port_num,
+		      int index, union ib_gid *gid)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	int rc = 0;
+
+	/* Ignore port_num */
+	memset(gid, 0, sizeof(*gid));
+	rc = bnxt_qplib_get_sgid(&rdev->qplib_res,
+				 &rdev->qplib_res.sgid_tbl, index,
+				 (struct bnxt_qplib_gid *)gid);
+	return rc;
+}
+
+int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context)
+{
+	int rc = 0;
+	struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(attr->device, ibdev);
+	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+	struct bnxt_qplib_gid *gid_to_del;
+	u16 vlan_id = 0xFFFF;
+
+	/* Delete the entry from the hardware */
+	ctx = *context;
+	if (!ctx)
+		return -EINVAL;
+
+	if (sgid_tbl && sgid_tbl->active) {
+		if (ctx->idx >= sgid_tbl->max)
+			return -EINVAL;
+		gid_to_del = &sgid_tbl->tbl[ctx->idx].gid;
+		vlan_id = sgid_tbl->tbl[ctx->idx].vlan_id;
+		/* DEL_GID is called in WQ context(netdevice_event_work_handler)
+		 * or via the ib_unregister_device path. In the former case QP1
+		 * may not be destroyed yet, in which case just return as FW
+		 * needs that entry to be present and will fail it's deletion.
+		 * We could get invoked again after QP1 is destroyed OR get an
+		 * ADD_GID call with a different GID value for the same index
+		 * where we issue MODIFY_GID cmd to update the GID entry -- TBD
+		 */
+		if (ctx->idx == 0 &&
+		    rdma_link_local_addr((struct in6_addr *)gid_to_del) &&
+		    ctx->refcnt == 1 && rdev->gsi_ctx.gsi_sqp) {
+			ibdev_dbg(&rdev->ibdev,
+				  "Trying to delete GID0 while QP1 is alive\n");
+			return -EFAULT;
+		}
+		ctx->refcnt--;
+		if (!ctx->refcnt) {
+			rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del,
+						 vlan_id,  true);
+			if (rc) {
+				ibdev_err(&rdev->ibdev,
+					  "Failed to remove GID: %#x", rc);
+			} else {
+				ctx_tbl = sgid_tbl->ctx;
+				ctx_tbl[ctx->idx] = NULL;
+				kfree(ctx);
+			}
+		}
+	} else {
+		return -EINVAL;
+	}
+	return rc;
+}
+
+int bnxt_re_add_gid(const struct ib_gid_attr *attr, void **context)
+{
+	int rc;
+	u32 tbl_idx = 0;
+	u16 vlan_id = 0xFFFF;
+	struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(attr->device, ibdev);
+	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+
+	rc = rdma_read_gid_l2_fields(attr, &vlan_id, NULL);
+	if (rc)
+		return rc;
+
+	rc = bnxt_qplib_add_sgid(sgid_tbl, (struct bnxt_qplib_gid *)&attr->gid,
+				 rdev->qplib_res.netdev->dev_addr,
+				 vlan_id, true, &tbl_idx);
+	if (rc == -EALREADY) {
+		ctx_tbl = sgid_tbl->ctx;
+		ctx_tbl[tbl_idx]->refcnt++;
+		*context = ctx_tbl[tbl_idx];
+		return 0;
+	}
+
+	if (rc < 0) {
+		ibdev_err(&rdev->ibdev, "Failed to add GID: %#x", rc);
+		return rc;
+	}
+
+	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	ctx_tbl = sgid_tbl->ctx;
+	ctx->idx = tbl_idx;
+	ctx->refcnt = 1;
+	ctx_tbl[tbl_idx] = ctx;
+	*context = ctx;
+
+	return rc;
+}
+
+enum rdma_link_layer bnxt_re_get_link_layer(struct ib_device *ibdev,
+					    u32 port_num)
+{
+	return IB_LINK_LAYER_ETHERNET;
+}
+
+#define	BNXT_RE_FENCE_PBL_SIZE	DIV_ROUND_UP(BNXT_RE_FENCE_BYTES, PAGE_SIZE)
+
+static void bnxt_re_create_fence_wqe(struct bnxt_re_pd *pd)
+{
+	struct bnxt_re_fence_data *fence = &pd->fence;
+	struct ib_mr *ib_mr = &fence->mr->ib_mr;
+	struct bnxt_qplib_swqe *wqe = &fence->bind_wqe;
+
+	memset(wqe, 0, sizeof(*wqe));
+	wqe->type = BNXT_QPLIB_SWQE_TYPE_BIND_MW;
+	wqe->wr_id = BNXT_QPLIB_FENCE_WRID;
+	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
+	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+	wqe->bind.zero_based = false;
+	wqe->bind.parent_l_key = ib_mr->lkey;
+	wqe->bind.va = (u64)(unsigned long)fence->va;
+	wqe->bind.length = fence->size;
+	wqe->bind.access_cntl = __from_ib_access_flags(IB_ACCESS_REMOTE_READ);
+	wqe->bind.mw_type = SQ_BIND_MW_TYPE_TYPE1;
+
+	/* Save the initial rkey in fence structure for now;
+	 * wqe->bind.r_key will be set at (re)bind time.
+	 */
+	fence->bind_rkey = ib_inc_rkey(fence->mw->rkey);
+}
+
+static int bnxt_re_bind_fence_mw(struct bnxt_qplib_qp *qplib_qp)
+{
+	struct bnxt_re_qp *qp = container_of(qplib_qp, struct bnxt_re_qp,
+					     qplib_qp);
+	struct ib_pd *ib_pd = qp->ib_qp.pd;
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_fence_data *fence = &pd->fence;
+	struct bnxt_qplib_swqe *fence_wqe = &fence->bind_wqe;
+	struct bnxt_qplib_swqe wqe;
+	int rc;
+
+	memcpy(&wqe, fence_wqe, sizeof(wqe));
+	wqe.bind.r_key = fence->bind_rkey;
+	fence->bind_rkey = ib_inc_rkey(fence->bind_rkey);
+
+	ibdev_dbg(&qp->rdev->ibdev,
+		  "Posting bind fence-WQE: rkey: %#x QP: %d PD: %p\n",
+		wqe.bind.r_key, qp->qplib_qp.id, pd);
+	rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe);
+	if (rc) {
+		ibdev_err(&qp->rdev->ibdev, "Failed to bind fence-WQE\n");
+		return rc;
+	}
+	bnxt_qplib_post_send_db(&qp->qplib_qp);
+
+	return rc;
+}
+
+static void bnxt_re_destroy_fence_mr(struct bnxt_re_pd *pd)
+{
+	struct bnxt_re_fence_data *fence = &pd->fence;
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct device *dev = &rdev->en_dev->pdev->dev;
+	struct bnxt_re_mr *mr = fence->mr;
+
+	if (fence->mw) {
+		bnxt_re_dealloc_mw(fence->mw);
+		fence->mw = NULL;
+	}
+	if (mr) {
+		if (mr->ib_mr.rkey)
+			bnxt_qplib_dereg_mrw(&rdev->qplib_res, &mr->qplib_mr,
+					     true);
+		if (mr->ib_mr.lkey)
+			bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+		kfree(mr);
+		fence->mr = NULL;
+	}
+	if (fence->dma_addr) {
+		dma_unmap_single(dev, fence->dma_addr, BNXT_RE_FENCE_BYTES,
+				 DMA_BIDIRECTIONAL);
+		fence->dma_addr = 0;
+	}
+}
+
+static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd)
+{
+	int mr_access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_MW_BIND;
+	struct bnxt_re_fence_data *fence = &pd->fence;
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct device *dev = &rdev->en_dev->pdev->dev;
+	struct bnxt_re_mr *mr = NULL;
+	dma_addr_t dma_addr = 0;
+	struct ib_mw *mw;
+	int rc;
+
+	dma_addr = dma_map_single(dev, fence->va, BNXT_RE_FENCE_BYTES,
+				  DMA_BIDIRECTIONAL);
+	rc = dma_mapping_error(dev, dma_addr);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to dma-map fence-MR-mem\n");
+		rc = -EIO;
+		fence->dma_addr = 0;
+		goto fail;
+	}
+	fence->dma_addr = dma_addr;
+
+	/* Allocate a MR */
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr) {
+		rc = -ENOMEM;
+		goto fail;
+	}
+	fence->mr = mr;
+	mr->rdev = rdev;
+	mr->qplib_mr.pd = &pd->qplib_pd;
+	mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR;
+	mr->qplib_mr.flags = __from_ib_access_flags(mr_access_flags);
+	rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to alloc fence-HW-MR\n");
+		goto fail;
+	}
+
+	/* Register MR */
+	mr->ib_mr.lkey = mr->qplib_mr.lkey;
+	mr->qplib_mr.va = (u64)(unsigned long)fence->va;
+	mr->qplib_mr.total_size = BNXT_RE_FENCE_BYTES;
+	rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, NULL,
+			       BNXT_RE_FENCE_PBL_SIZE, PAGE_SIZE);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to register fence-MR\n");
+		goto fail;
+	}
+	mr->ib_mr.rkey = mr->qplib_mr.rkey;
+
+	/* Create a fence MW only for kernel consumers */
+	mw = bnxt_re_alloc_mw(&pd->ib_pd, IB_MW_TYPE_1, NULL);
+	if (IS_ERR(mw)) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to create fence-MW for PD: %p\n", pd);
+		rc = PTR_ERR(mw);
+		goto fail;
+	}
+	fence->mw = mw;
+
+	bnxt_re_create_fence_wqe(pd);
+	return 0;
+
+fail:
+	bnxt_re_destroy_fence_mr(pd);
+	return rc;
+}
+
+/* Protection Domains */
+int bnxt_re_dealloc_pd(struct ib_pd *ib_pd, struct ib_udata *udata)
+{
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_dev *rdev = pd->rdev;
+
+	bnxt_re_destroy_fence_mr(pd);
+
+	if (pd->qplib_pd.id) {
+		if (!bnxt_qplib_dealloc_pd(&rdev->qplib_res,
+					   &rdev->qplib_res.pd_tbl,
+					   &pd->qplib_pd))
+			atomic_dec(&rdev->pd_count);
+	}
+	return 0;
+}
+
+int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+{
+	struct ib_device *ibdev = ibpd->device;
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct bnxt_re_ucontext *ucntx = rdma_udata_to_drv_context(
+		udata, struct bnxt_re_ucontext, ib_uctx);
+	struct bnxt_re_pd *pd = container_of(ibpd, struct bnxt_re_pd, ib_pd);
+	int rc;
+
+	pd->rdev = rdev;
+	if (bnxt_qplib_alloc_pd(&rdev->qplib_res.pd_tbl, &pd->qplib_pd)) {
+		ibdev_err(&rdev->ibdev, "Failed to allocate HW PD");
+		rc = -ENOMEM;
+		goto fail;
+	}
+
+	if (udata) {
+		struct bnxt_re_pd_resp resp;
+
+		if (!ucntx->dpi.dbr) {
+			/* Allocate DPI in alloc_pd to avoid failing of
+			 * ibv_devinfo and family of application when DPIs
+			 * are depleted.
+			 */
+			if (bnxt_qplib_alloc_dpi(&rdev->qplib_res.dpi_tbl,
+						 &ucntx->dpi, ucntx)) {
+				rc = -ENOMEM;
+				goto dbfail;
+			}
+		}
+
+		resp.pdid = pd->qplib_pd.id;
+		/* Still allow mapping this DBR to the new user PD. */
+		resp.dpi = ucntx->dpi.dpi;
+		resp.dbr = (u64)ucntx->dpi.umdbr;
+
+		rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (rc) {
+			ibdev_err(&rdev->ibdev,
+				  "Failed to copy user response\n");
+			goto dbfail;
+		}
+	}
+
+	if (!udata)
+		if (bnxt_re_create_fence_mr(pd))
+			ibdev_warn(&rdev->ibdev,
+				   "Failed to create Fence-MR\n");
+	atomic_inc(&rdev->pd_count);
+
+	return 0;
+dbfail:
+	bnxt_qplib_dealloc_pd(&rdev->qplib_res, &rdev->qplib_res.pd_tbl,
+			      &pd->qplib_pd);
+fail:
+	return rc;
+}
+
+/* Address Handles */
+int bnxt_re_destroy_ah(struct ib_ah *ib_ah, u32 flags)
+{
+	struct bnxt_re_ah *ah = container_of(ib_ah, struct bnxt_re_ah, ib_ah);
+	struct bnxt_re_dev *rdev = ah->rdev;
+
+	bnxt_qplib_destroy_ah(&rdev->qplib_res, &ah->qplib_ah,
+			      !(flags & RDMA_DESTROY_AH_SLEEPABLE));
+	atomic_dec(&rdev->ah_count);
+
+	return 0;
+}
+
+static u8 bnxt_re_stack_to_dev_nw_type(enum rdma_network_type ntype)
+{
+	u8 nw_type;
+
+	switch (ntype) {
+	case RDMA_NETWORK_IPV4:
+		nw_type = CMDQ_CREATE_AH_TYPE_V2IPV4;
+		break;
+	case RDMA_NETWORK_IPV6:
+		nw_type = CMDQ_CREATE_AH_TYPE_V2IPV6;
+		break;
+	default:
+		nw_type = CMDQ_CREATE_AH_TYPE_V1;
+		break;
+	}
+	return nw_type;
+}
+
+int bnxt_re_create_ah(struct ib_ah *ib_ah, struct rdma_ah_init_attr *init_attr,
+		      struct ib_udata *udata)
+{
+	struct ib_pd *ib_pd = ib_ah->pd;
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct rdma_ah_attr *ah_attr = init_attr->ah_attr;
+	const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr);
+	struct bnxt_re_dev *rdev = pd->rdev;
+	const struct ib_gid_attr *sgid_attr;
+	struct bnxt_re_gid_ctx *ctx;
+	struct bnxt_re_ah *ah = container_of(ib_ah, struct bnxt_re_ah, ib_ah);
+	u8 nw_type;
+	int rc;
+
+	if (!(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH)) {
+		ibdev_err(&rdev->ibdev, "Failed to alloc AH: GRH not set");
+		return -EINVAL;
+	}
+
+	ah->rdev = rdev;
+	ah->qplib_ah.pd = &pd->qplib_pd;
+
+	/* Supply the configuration for the HW */
+	memcpy(ah->qplib_ah.dgid.data, grh->dgid.raw,
+	       sizeof(union ib_gid));
+	sgid_attr = grh->sgid_attr;
+	/* Get the HW context of the GID. The reference
+	 * of GID table entry is already taken by the caller.
+	 */
+	ctx = rdma_read_gid_hw_context(sgid_attr);
+	ah->qplib_ah.sgid_index = ctx->idx;
+	ah->qplib_ah.host_sgid_index = grh->sgid_index;
+	ah->qplib_ah.traffic_class = grh->traffic_class;
+	ah->qplib_ah.flow_label = grh->flow_label;
+	ah->qplib_ah.hop_limit = grh->hop_limit;
+	ah->qplib_ah.sl = rdma_ah_get_sl(ah_attr);
+
+	/* Get network header type for this GID */
+	nw_type = rdma_gid_attr_network_type(sgid_attr);
+	ah->qplib_ah.nw_type = bnxt_re_stack_to_dev_nw_type(nw_type);
+
+	memcpy(ah->qplib_ah.dmac, ah_attr->roce.dmac, ETH_ALEN);
+	rc = bnxt_qplib_create_ah(&rdev->qplib_res, &ah->qplib_ah,
+				  !(init_attr->flags &
+				    RDMA_CREATE_AH_SLEEPABLE));
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to allocate HW AH");
+		return rc;
+	}
+
+	/* Write AVID to shared page. */
+	if (udata) {
+		struct bnxt_re_ucontext *uctx = rdma_udata_to_drv_context(
+			udata, struct bnxt_re_ucontext, ib_uctx);
+		unsigned long flag;
+		u32 *wrptr;
+
+		spin_lock_irqsave(&uctx->sh_lock, flag);
+		wrptr = (u32 *)(uctx->shpg + BNXT_RE_AVID_OFFT);
+		*wrptr = ah->qplib_ah.id;
+		wmb(); /* make sure cache is updated. */
+		spin_unlock_irqrestore(&uctx->sh_lock, flag);
+	}
+	atomic_inc(&rdev->ah_count);
+
+	return 0;
+}
+
+int bnxt_re_query_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr)
+{
+	struct bnxt_re_ah *ah = container_of(ib_ah, struct bnxt_re_ah, ib_ah);
+
+	ah_attr->type = ib_ah->type;
+	rdma_ah_set_sl(ah_attr, ah->qplib_ah.sl);
+	memcpy(ah_attr->roce.dmac, ah->qplib_ah.dmac, ETH_ALEN);
+	rdma_ah_set_grh(ah_attr, NULL, 0,
+			ah->qplib_ah.host_sgid_index,
+			0, ah->qplib_ah.traffic_class);
+	rdma_ah_set_dgid_raw(ah_attr, ah->qplib_ah.dgid.data);
+	rdma_ah_set_port_num(ah_attr, 1);
+	rdma_ah_set_static_rate(ah_attr, 0);
+	return 0;
+}
+
+unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp)
+	__acquires(&qp->scq->cq_lock) __acquires(&qp->rcq->cq_lock)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->scq->cq_lock, flags);
+	if (qp->rcq != qp->scq)
+		spin_lock(&qp->rcq->cq_lock);
+	else
+		__acquire(&qp->rcq->cq_lock);
+
+	return flags;
+}
+
+void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp,
+			unsigned long flags)
+	__releases(&qp->scq->cq_lock) __releases(&qp->rcq->cq_lock)
+{
+	if (qp->rcq != qp->scq)
+		spin_unlock(&qp->rcq->cq_lock);
+	else
+		__release(&qp->rcq->cq_lock);
+	spin_unlock_irqrestore(&qp->scq->cq_lock, flags);
+}
+
+static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
+{
+	struct bnxt_re_qp *gsi_sqp;
+	struct bnxt_re_ah *gsi_sah;
+	struct bnxt_re_dev *rdev;
+	int rc = 0;
+
+	rdev = qp->rdev;
+	gsi_sqp = rdev->gsi_ctx.gsi_sqp;
+	gsi_sah = rdev->gsi_ctx.gsi_sah;
+
+	ibdev_dbg(&rdev->ibdev, "Destroy the shadow AH\n");
+	bnxt_qplib_destroy_ah(&rdev->qplib_res,
+			      &gsi_sah->qplib_ah,
+			      true);
+	atomic_dec(&rdev->ah_count);
+	bnxt_qplib_clean_qp(&qp->qplib_qp);
+
+	ibdev_dbg(&rdev->ibdev, "Destroy the shadow QP\n");
+	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &gsi_sqp->qplib_qp);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Destroy Shadow QP failed");
+		goto fail;
+	}
+	bnxt_qplib_free_qp_res(&rdev->qplib_res, &gsi_sqp->qplib_qp);
+
+	/* remove from active qp list */
+	mutex_lock(&rdev->qp_lock);
+	list_del(&gsi_sqp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
+	kfree(rdev->gsi_ctx.sqp_tbl);
+	kfree(gsi_sah);
+	kfree(gsi_sqp);
+	rdev->gsi_ctx.gsi_sqp = NULL;
+	rdev->gsi_ctx.gsi_sah = NULL;
+	rdev->gsi_ctx.sqp_tbl = NULL;
+
+	return 0;
+fail:
+	return rc;
+}
+
+/* Queue Pairs */
+int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
+{
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
+	struct bnxt_qplib_qp *qplib_qp = &qp->qplib_qp;
+	struct bnxt_re_dev *rdev = qp->rdev;
+	struct bnxt_qplib_nq *scq_nq = NULL;
+	struct bnxt_qplib_nq *rcq_nq = NULL;
+	unsigned int flags;
+	int rc;
+
+	bnxt_qplib_flush_cqn_wq(&qp->qplib_qp);
+
+	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to destroy HW QP");
+		return rc;
+	}
+
+	if (rdma_is_kernel_res(&qp->ib_qp.res)) {
+		flags = bnxt_re_lock_cqs(qp);
+		bnxt_qplib_clean_qp(&qp->qplib_qp);
+		bnxt_re_unlock_cqs(qp, flags);
+	}
+
+	bnxt_qplib_free_qp_res(&rdev->qplib_res, &qp->qplib_qp);
+
+	if (ib_qp->qp_type == IB_QPT_GSI && rdev->gsi_ctx.gsi_sqp) {
+		rc = bnxt_re_destroy_gsi_sqp(qp);
+		if (rc)
+			return rc;
+	}
+
+	mutex_lock(&rdev->qp_lock);
+	list_del(&qp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
+	ib_umem_release(qp->rumem);
+	ib_umem_release(qp->sumem);
+
+	/* Flush all the entries of notification queue associated with
+	 * given qp.
+	 */
+	scq_nq = qplib_qp->scq->nq;
+	rcq_nq = qplib_qp->rcq->nq;
+	bnxt_re_synchronize_nq(scq_nq);
+	if (scq_nq != rcq_nq)
+		bnxt_re_synchronize_nq(rcq_nq);
+
+	return 0;
+}
+
+static u8 __from_ib_qp_type(enum ib_qp_type type)
+{
+	switch (type) {
+	case IB_QPT_GSI:
+		return CMDQ_CREATE_QP1_TYPE_GSI;
+	case IB_QPT_RC:
+		return CMDQ_CREATE_QP_TYPE_RC;
+	case IB_QPT_UD:
+		return CMDQ_CREATE_QP_TYPE_UD;
+	default:
+		return IB_QPT_MAX;
+	}
+}
+
+static u16 bnxt_re_setup_rwqe_size(struct bnxt_qplib_qp *qplqp,
+				   int rsge, int max)
+{
+	if (qplqp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC)
+		rsge = max;
+	return bnxt_re_get_rwqe_size(rsge);
+}
+
+static u16 bnxt_re_get_wqe_size(int ilsize, int nsge)
+{
+	u16 wqe_size, calc_ils;
+
+	wqe_size = bnxt_re_get_swqe_size(nsge);
+	if (ilsize) {
+		calc_ils = sizeof(struct sq_send_hdr) + ilsize;
+		wqe_size = max_t(u16, calc_ils, wqe_size);
+		wqe_size = ALIGN(wqe_size, sizeof(struct sq_send_hdr));
+	}
+	return wqe_size;
+}
+
+static int bnxt_re_setup_swqe_size(struct bnxt_re_qp *qp,
+				   struct ib_qp_init_attr *init_attr)
+{
+	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_qplib_qp *qplqp;
+	struct bnxt_re_dev *rdev;
+	struct bnxt_qplib_q *sq;
+	int align, ilsize;
+
+	rdev = qp->rdev;
+	qplqp = &qp->qplib_qp;
+	sq = &qplqp->sq;
+	dev_attr = &rdev->dev_attr;
+
+	align = sizeof(struct sq_send_hdr);
+	ilsize = ALIGN(init_attr->cap.max_inline_data, align);
+
+	sq->wqe_size = bnxt_re_get_wqe_size(ilsize, sq->max_sge);
+	if (sq->wqe_size > bnxt_re_get_swqe_size(dev_attr->max_qp_sges))
+		return -EINVAL;
+	/* For gen p4 and gen p5 backward compatibility mode
+	 * wqe size is fixed to 128 bytes
+	 */
+	if (sq->wqe_size < bnxt_re_get_swqe_size(dev_attr->max_qp_sges) &&
+			qplqp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC)
+		sq->wqe_size = bnxt_re_get_swqe_size(dev_attr->max_qp_sges);
+
+	if (init_attr->cap.max_inline_data) {
+		qplqp->max_inline_data = sq->wqe_size -
+			sizeof(struct sq_send_hdr);
+		init_attr->cap.max_inline_data = qplqp->max_inline_data;
+		if (qplqp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC)
+			sq->max_sge = qplqp->max_inline_data /
+				sizeof(struct sq_sge);
+	}
+
+	return 0;
+}
+
+static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd,
+				struct bnxt_re_qp *qp, struct ib_udata *udata)
+{
+	struct bnxt_qplib_qp *qplib_qp;
+	struct bnxt_re_ucontext *cntx;
+	struct bnxt_re_qp_req ureq;
+	int bytes = 0, psn_sz;
+	struct ib_umem *umem;
+	int psn_nume;
+
+	qplib_qp = &qp->qplib_qp;
+	cntx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext,
+					 ib_uctx);
+	if (ib_copy_from_udata(&ureq, udata, sizeof(ureq)))
+		return -EFAULT;
+
+	bytes = (qplib_qp->sq.max_wqe * qplib_qp->sq.wqe_size);
+	/* Consider mapping PSN search memory only for RC QPs. */
+	if (qplib_qp->type == CMDQ_CREATE_QP_TYPE_RC) {
+		psn_sz = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
+						   sizeof(struct sq_psn_search_ext) :
+						   sizeof(struct sq_psn_search);
+		psn_nume = (qplib_qp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) ?
+			    qplib_qp->sq.max_wqe :
+			    ((qplib_qp->sq.max_wqe * qplib_qp->sq.wqe_size) /
+			      sizeof(struct bnxt_qplib_sge));
+		bytes += (psn_nume * psn_sz);
+	}
+
+	bytes = PAGE_ALIGN(bytes);
+	umem = ib_umem_get(&rdev->ibdev, ureq.qpsva, bytes,
+			   IB_ACCESS_LOCAL_WRITE);
+	if (IS_ERR(umem))
+		return PTR_ERR(umem);
+
+	qp->sumem = umem;
+	qplib_qp->sq.sg_info.umem = umem;
+	qplib_qp->sq.sg_info.pgsize = PAGE_SIZE;
+	qplib_qp->sq.sg_info.pgshft = PAGE_SHIFT;
+	qplib_qp->qp_handle = ureq.qp_handle;
+
+	if (!qp->qplib_qp.srq) {
+		bytes = (qplib_qp->rq.max_wqe * qplib_qp->rq.wqe_size);
+		bytes = PAGE_ALIGN(bytes);
+		umem = ib_umem_get(&rdev->ibdev, ureq.qprva, bytes,
+				   IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(umem))
+			goto rqfail;
+		qp->rumem = umem;
+		qplib_qp->rq.sg_info.umem = umem;
+		qplib_qp->rq.sg_info.pgsize = PAGE_SIZE;
+		qplib_qp->rq.sg_info.pgshft = PAGE_SHIFT;
+	}
+
+	qplib_qp->dpi = &cntx->dpi;
+	return 0;
+rqfail:
+	ib_umem_release(qp->sumem);
+	qp->sumem = NULL;
+	memset(&qplib_qp->sq.sg_info, 0, sizeof(qplib_qp->sq.sg_info));
+
+	return PTR_ERR(umem);
+}
+
+static struct bnxt_re_ah *bnxt_re_create_shadow_qp_ah
+				(struct bnxt_re_pd *pd,
+				 struct bnxt_qplib_res *qp1_res,
+				 struct bnxt_qplib_qp *qp1_qp)
+{
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct bnxt_re_ah *ah;
+	union ib_gid sgid;
+	int rc;
+
+	ah = kzalloc(sizeof(*ah), GFP_KERNEL);
+	if (!ah)
+		return NULL;
+
+	ah->rdev = rdev;
+	ah->qplib_ah.pd = &pd->qplib_pd;
+
+	rc = bnxt_re_query_gid(&rdev->ibdev, 1, 0, &sgid);
+	if (rc)
+		goto fail;
+
+	/* supply the dgid data same as sgid */
+	memcpy(ah->qplib_ah.dgid.data, &sgid.raw,
+	       sizeof(union ib_gid));
+	ah->qplib_ah.sgid_index = 0;
+
+	ah->qplib_ah.traffic_class = 0;
+	ah->qplib_ah.flow_label = 0;
+	ah->qplib_ah.hop_limit = 1;
+	ah->qplib_ah.sl = 0;
+	/* Have DMAC same as SMAC */
+	ether_addr_copy(ah->qplib_ah.dmac, rdev->netdev->dev_addr);
+
+	rc = bnxt_qplib_create_ah(&rdev->qplib_res, &ah->qplib_ah, false);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to allocate HW AH for Shadow QP");
+		goto fail;
+	}
+	atomic_inc(&rdev->ah_count);
+
+	return ah;
+
+fail:
+	kfree(ah);
+	return NULL;
+}
+
+static struct bnxt_re_qp *bnxt_re_create_shadow_qp
+				(struct bnxt_re_pd *pd,
+				 struct bnxt_qplib_res *qp1_res,
+				 struct bnxt_qplib_qp *qp1_qp)
+{
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct bnxt_re_qp *qp;
+	int rc;
+
+	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+	if (!qp)
+		return NULL;
+
+	qp->rdev = rdev;
+
+	/* Initialize the shadow QP structure from the QP1 values */
+	ether_addr_copy(qp->qplib_qp.smac, rdev->netdev->dev_addr);
+
+	qp->qplib_qp.pd = &pd->qplib_pd;
+	qp->qplib_qp.qp_handle = (u64)(unsigned long)(&qp->qplib_qp);
+	qp->qplib_qp.type = IB_QPT_UD;
+
+	qp->qplib_qp.max_inline_data = 0;
+	qp->qplib_qp.sig_type = true;
+
+	/* Shadow QP SQ depth should be same as QP1 RQ depth */
+	qp->qplib_qp.sq.wqe_size = bnxt_re_get_wqe_size(0, 6);
+	qp->qplib_qp.sq.max_wqe = qp1_qp->rq.max_wqe;
+	qp->qplib_qp.sq.max_sge = 2;
+	/* Q full delta can be 1 since it is internal QP */
+	qp->qplib_qp.sq.q_full_delta = 1;
+	qp->qplib_qp.sq.sg_info.pgsize = PAGE_SIZE;
+	qp->qplib_qp.sq.sg_info.pgshft = PAGE_SHIFT;
+
+	qp->qplib_qp.scq = qp1_qp->scq;
+	qp->qplib_qp.rcq = qp1_qp->rcq;
+
+	qp->qplib_qp.rq.wqe_size = bnxt_re_get_rwqe_size(6);
+	qp->qplib_qp.rq.max_wqe = qp1_qp->rq.max_wqe;
+	qp->qplib_qp.rq.max_sge = qp1_qp->rq.max_sge;
+	/* Q full delta can be 1 since it is internal QP */
+	qp->qplib_qp.rq.q_full_delta = 1;
+	qp->qplib_qp.rq.sg_info.pgsize = PAGE_SIZE;
+	qp->qplib_qp.rq.sg_info.pgshft = PAGE_SHIFT;
+
+	qp->qplib_qp.mtu = qp1_qp->mtu;
+
+	qp->qplib_qp.sq_hdr_buf_size = 0;
+	qp->qplib_qp.rq_hdr_buf_size = BNXT_QPLIB_MAX_GRH_HDR_SIZE_IPV6;
+	qp->qplib_qp.dpi = &rdev->dpi_privileged;
+
+	rc = bnxt_qplib_create_qp(qp1_res, &qp->qplib_qp);
+	if (rc)
+		goto fail;
+
+	spin_lock_init(&qp->sq_lock);
+	INIT_LIST_HEAD(&qp->list);
+	mutex_lock(&rdev->qp_lock);
+	list_add_tail(&qp->list, &rdev->qp_list);
+	atomic_inc(&rdev->qp_count);
+	mutex_unlock(&rdev->qp_lock);
+	return qp;
+fail:
+	kfree(qp);
+	return NULL;
+}
+
+static int bnxt_re_init_rq_attr(struct bnxt_re_qp *qp,
+				struct ib_qp_init_attr *init_attr)
+{
+	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_qplib_qp *qplqp;
+	struct bnxt_re_dev *rdev;
+	struct bnxt_qplib_q *rq;
+	int entries;
+
+	rdev = qp->rdev;
+	qplqp = &qp->qplib_qp;
+	rq = &qplqp->rq;
+	dev_attr = &rdev->dev_attr;
+
+	if (init_attr->srq) {
+		struct bnxt_re_srq *srq;
+
+		srq = container_of(init_attr->srq, struct bnxt_re_srq, ib_srq);
+		qplqp->srq = &srq->qplib_srq;
+		rq->max_wqe = 0;
+	} else {
+		rq->max_sge = init_attr->cap.max_recv_sge;
+		if (rq->max_sge > dev_attr->max_qp_sges)
+			rq->max_sge = dev_attr->max_qp_sges;
+		init_attr->cap.max_recv_sge = rq->max_sge;
+		rq->wqe_size = bnxt_re_setup_rwqe_size(qplqp, rq->max_sge,
+						       dev_attr->max_qp_sges);
+		/* Allocate 1 more than what's provided so posting max doesn't
+		 * mean empty.
+		 */
+		entries = roundup_pow_of_two(init_attr->cap.max_recv_wr + 1);
+		rq->max_wqe = min_t(u32, entries, dev_attr->max_qp_wqes + 1);
+		rq->q_full_delta = 0;
+		rq->sg_info.pgsize = PAGE_SIZE;
+		rq->sg_info.pgshft = PAGE_SHIFT;
+	}
+
+	return 0;
+}
+
+static void bnxt_re_adjust_gsi_rq_attr(struct bnxt_re_qp *qp)
+{
+	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_qplib_qp *qplqp;
+	struct bnxt_re_dev *rdev;
+
+	rdev = qp->rdev;
+	qplqp = &qp->qplib_qp;
+	dev_attr = &rdev->dev_attr;
+
+	if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) {
+		qplqp->rq.max_sge = dev_attr->max_qp_sges;
+		if (qplqp->rq.max_sge > dev_attr->max_qp_sges)
+			qplqp->rq.max_sge = dev_attr->max_qp_sges;
+		qplqp->rq.max_sge = 6;
+	}
+}
+
+static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
+				struct ib_qp_init_attr *init_attr,
+				struct ib_udata *udata)
+{
+	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_qplib_qp *qplqp;
+	struct bnxt_re_dev *rdev;
+	struct bnxt_qplib_q *sq;
+	int entries;
+	int diff;
+	int rc;
+
+	rdev = qp->rdev;
+	qplqp = &qp->qplib_qp;
+	sq = &qplqp->sq;
+	dev_attr = &rdev->dev_attr;
+
+	sq->max_sge = init_attr->cap.max_send_sge;
+	if (sq->max_sge > dev_attr->max_qp_sges) {
+		sq->max_sge = dev_attr->max_qp_sges;
+		init_attr->cap.max_send_sge = sq->max_sge;
+	}
+
+	rc = bnxt_re_setup_swqe_size(qp, init_attr);
+	if (rc)
+		return rc;
+
+	entries = init_attr->cap.max_send_wr;
+	/* Allocate 128 + 1 more than what's provided */
+	diff = (qplqp->wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE) ?
+		0 : BNXT_QPLIB_RESERVED_QP_WRS;
+	entries = roundup_pow_of_two(entries + diff + 1);
+	sq->max_wqe = min_t(u32, entries, dev_attr->max_qp_wqes + diff + 1);
+	sq->q_full_delta = diff + 1;
+	/*
+	 * Reserving one slot for Phantom WQE. Application can
+	 * post one extra entry in this case. But allowing this to avoid
+	 * unexpected Queue full condition
+	 */
+	qplqp->sq.q_full_delta -= 1;
+	qplqp->sq.sg_info.pgsize = PAGE_SIZE;
+	qplqp->sq.sg_info.pgshft = PAGE_SHIFT;
+
+	return 0;
+}
+
+static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp,
+				       struct ib_qp_init_attr *init_attr)
+{
+	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_qplib_qp *qplqp;
+	struct bnxt_re_dev *rdev;
+	int entries;
+
+	rdev = qp->rdev;
+	qplqp = &qp->qplib_qp;
+	dev_attr = &rdev->dev_attr;
+
+	if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) {
+		entries = roundup_pow_of_two(init_attr->cap.max_send_wr + 1);
+		qplqp->sq.max_wqe = min_t(u32, entries,
+					  dev_attr->max_qp_wqes + 1);
+		qplqp->sq.q_full_delta = qplqp->sq.max_wqe -
+			init_attr->cap.max_send_wr;
+		qplqp->sq.max_sge++; /* Need one extra sge to put UD header */
+		if (qplqp->sq.max_sge > dev_attr->max_qp_sges)
+			qplqp->sq.max_sge = dev_attr->max_qp_sges;
+	}
+}
+
+static int bnxt_re_init_qp_type(struct bnxt_re_dev *rdev,
+				struct ib_qp_init_attr *init_attr)
+{
+	struct bnxt_qplib_chip_ctx *chip_ctx;
+	int qptype;
+
+	chip_ctx = rdev->chip_ctx;
+
+	qptype = __from_ib_qp_type(init_attr->qp_type);
+	if (qptype == IB_QPT_MAX) {
+		ibdev_err(&rdev->ibdev, "QP type 0x%x not supported", qptype);
+		qptype = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (bnxt_qplib_is_chip_gen_p5(chip_ctx) &&
+	    init_attr->qp_type == IB_QPT_GSI)
+		qptype = CMDQ_CREATE_QP_TYPE_GSI;
+out:
+	return qptype;
+}
+
+static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
+				struct ib_qp_init_attr *init_attr,
+				struct ib_udata *udata)
+{
+	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_qplib_qp *qplqp;
+	struct bnxt_re_dev *rdev;
+	struct bnxt_re_cq *cq;
+	int rc = 0, qptype;
+
+	rdev = qp->rdev;
+	qplqp = &qp->qplib_qp;
+	dev_attr = &rdev->dev_attr;
+
+	/* Setup misc params */
+	ether_addr_copy(qplqp->smac, rdev->netdev->dev_addr);
+	qplqp->pd = &pd->qplib_pd;
+	qplqp->qp_handle = (u64)qplqp;
+	qplqp->max_inline_data = init_attr->cap.max_inline_data;
+	qplqp->sig_type = ((init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) ?
+			    true : false);
+	qptype = bnxt_re_init_qp_type(rdev, init_attr);
+	if (qptype < 0) {
+		rc = qptype;
+		goto out;
+	}
+	qplqp->type = (u8)qptype;
+	qplqp->wqe_mode = rdev->chip_ctx->modes.wqe_mode;
+
+	if (init_attr->qp_type == IB_QPT_RC) {
+		qplqp->max_rd_atomic = dev_attr->max_qp_rd_atom;
+		qplqp->max_dest_rd_atomic = dev_attr->max_qp_init_rd_atom;
+	}
+	qplqp->mtu = ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
+	qplqp->dpi = &rdev->dpi_privileged; /* Doorbell page */
+	if (init_attr->create_flags) {
+		ibdev_dbg(&rdev->ibdev,
+			  "QP create flags 0x%x not supported",
+			  init_attr->create_flags);
+		return -EOPNOTSUPP;
+	}
+
+	/* Setup CQs */
+	if (init_attr->send_cq) {
+		cq = container_of(init_attr->send_cq, struct bnxt_re_cq, ib_cq);
+		qplqp->scq = &cq->qplib_cq;
+		qp->scq = cq;
+	}
+
+	if (init_attr->recv_cq) {
+		cq = container_of(init_attr->recv_cq, struct bnxt_re_cq, ib_cq);
+		qplqp->rcq = &cq->qplib_cq;
+		qp->rcq = cq;
+	}
+
+	/* Setup RQ/SRQ */
+	rc = bnxt_re_init_rq_attr(qp, init_attr);
+	if (rc)
+		goto out;
+	if (init_attr->qp_type == IB_QPT_GSI)
+		bnxt_re_adjust_gsi_rq_attr(qp);
+
+	/* Setup SQ */
+	rc = bnxt_re_init_sq_attr(qp, init_attr, udata);
+	if (rc)
+		goto out;
+	if (init_attr->qp_type == IB_QPT_GSI)
+		bnxt_re_adjust_gsi_sq_attr(qp, init_attr);
+
+	if (udata) /* This will update DPI and qp_handle */
+		rc = bnxt_re_init_user_qp(rdev, pd, qp, udata);
+out:
+	return rc;
+}
+
+static int bnxt_re_create_shadow_gsi(struct bnxt_re_qp *qp,
+				     struct bnxt_re_pd *pd)
+{
+	struct bnxt_re_sqp_entries *sqp_tbl;
+	struct bnxt_re_dev *rdev;
+	struct bnxt_re_qp *sqp;
+	struct bnxt_re_ah *sah;
+	int rc = 0;
+
+	rdev = qp->rdev;
+	/* Create a shadow QP to handle the QP1 traffic */
+	sqp_tbl = kcalloc(BNXT_RE_MAX_GSI_SQP_ENTRIES, sizeof(*sqp_tbl),
+			  GFP_KERNEL);
+	if (!sqp_tbl)
+		return -ENOMEM;
+	rdev->gsi_ctx.sqp_tbl = sqp_tbl;
+
+	sqp = bnxt_re_create_shadow_qp(pd, &rdev->qplib_res, &qp->qplib_qp);
+	if (!sqp) {
+		rc = -ENODEV;
+		ibdev_err(&rdev->ibdev, "Failed to create Shadow QP for QP1");
+		goto out;
+	}
+	rdev->gsi_ctx.gsi_sqp = sqp;
+
+	sqp->rcq = qp->rcq;
+	sqp->scq = qp->scq;
+	sah = bnxt_re_create_shadow_qp_ah(pd, &rdev->qplib_res,
+					  &qp->qplib_qp);
+	if (!sah) {
+		bnxt_qplib_destroy_qp(&rdev->qplib_res,
+				      &sqp->qplib_qp);
+		rc = -ENODEV;
+		ibdev_err(&rdev->ibdev,
+			  "Failed to create AH entry for ShadowQP");
+		goto out;
+	}
+	rdev->gsi_ctx.gsi_sah = sah;
+
+	return 0;
+out:
+	kfree(sqp_tbl);
+	return rc;
+}
+
+static int bnxt_re_create_gsi_qp(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
+				 struct ib_qp_init_attr *init_attr)
+{
+	struct bnxt_re_dev *rdev;
+	struct bnxt_qplib_qp *qplqp;
+	int rc = 0;
+
+	rdev = qp->rdev;
+	qplqp = &qp->qplib_qp;
+
+	qplqp->rq_hdr_buf_size = BNXT_QPLIB_MAX_QP1_RQ_HDR_SIZE_V2;
+	qplqp->sq_hdr_buf_size = BNXT_QPLIB_MAX_QP1_SQ_HDR_SIZE_V2;
+
+	rc = bnxt_qplib_create_qp1(&rdev->qplib_res, qplqp);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "create HW QP1 failed!");
+		goto out;
+	}
+
+	rc = bnxt_re_create_shadow_gsi(qp, pd);
+out:
+	return rc;
+}
+
+static bool bnxt_re_test_qp_limits(struct bnxt_re_dev *rdev,
+				   struct ib_qp_init_attr *init_attr,
+				   struct bnxt_qplib_dev_attr *dev_attr)
+{
+	bool rc = true;
+
+	if (init_attr->cap.max_send_wr > dev_attr->max_qp_wqes ||
+	    init_attr->cap.max_recv_wr > dev_attr->max_qp_wqes ||
+	    init_attr->cap.max_send_sge > dev_attr->max_qp_sges ||
+	    init_attr->cap.max_recv_sge > dev_attr->max_qp_sges ||
+	    init_attr->cap.max_inline_data > dev_attr->max_inline_data) {
+		ibdev_err(&rdev->ibdev,
+			  "Create QP failed - max exceeded! 0x%x/0x%x 0x%x/0x%x 0x%x/0x%x 0x%x/0x%x 0x%x/0x%x",
+			  init_attr->cap.max_send_wr, dev_attr->max_qp_wqes,
+			  init_attr->cap.max_recv_wr, dev_attr->max_qp_wqes,
+			  init_attr->cap.max_send_sge, dev_attr->max_qp_sges,
+			  init_attr->cap.max_recv_sge, dev_attr->max_qp_sges,
+			  init_attr->cap.max_inline_data,
+			  dev_attr->max_inline_data);
+		rc = false;
+	}
+	return rc;
+}
+
+int bnxt_re_create_qp(struct ib_qp *ib_qp, struct ib_qp_init_attr *qp_init_attr,
+		      struct ib_udata *udata)
+{
+	struct ib_pd *ib_pd = ib_qp->pd;
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
+	int rc;
+
+	rc = bnxt_re_test_qp_limits(rdev, qp_init_attr, dev_attr);
+	if (!rc) {
+		rc = -EINVAL;
+		goto fail;
+	}
+
+	qp->rdev = rdev;
+	rc = bnxt_re_init_qp_attr(qp, pd, qp_init_attr, udata);
+	if (rc)
+		goto fail;
+
+	if (qp_init_attr->qp_type == IB_QPT_GSI &&
+	    !(bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx))) {
+		rc = bnxt_re_create_gsi_qp(qp, pd, qp_init_attr);
+		if (rc == -ENODEV)
+			goto qp_destroy;
+		if (rc)
+			goto fail;
+	} else {
+		rc = bnxt_qplib_create_qp(&rdev->qplib_res, &qp->qplib_qp);
+		if (rc) {
+			ibdev_err(&rdev->ibdev, "Failed to create HW QP");
+			goto free_umem;
+		}
+		if (udata) {
+			struct bnxt_re_qp_resp resp;
+
+			resp.qpid = qp->qplib_qp.id;
+			resp.rsvd = 0;
+			rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+			if (rc) {
+				ibdev_err(&rdev->ibdev, "Failed to copy QP udata");
+				goto qp_destroy;
+			}
+		}
+	}
+
+	qp->ib_qp.qp_num = qp->qplib_qp.id;
+	if (qp_init_attr->qp_type == IB_QPT_GSI)
+		rdev->gsi_ctx.gsi_qp = qp;
+	spin_lock_init(&qp->sq_lock);
+	spin_lock_init(&qp->rq_lock);
+	INIT_LIST_HEAD(&qp->list);
+	mutex_lock(&rdev->qp_lock);
+	list_add_tail(&qp->list, &rdev->qp_list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_inc(&rdev->qp_count);
+
+	return 0;
+qp_destroy:
+	bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
+free_umem:
+	ib_umem_release(qp->rumem);
+	ib_umem_release(qp->sumem);
+fail:
+	return rc;
+}
+
+static u8 __from_ib_qp_state(enum ib_qp_state state)
+{
+	switch (state) {
+	case IB_QPS_RESET:
+		return CMDQ_MODIFY_QP_NEW_STATE_RESET;
+	case IB_QPS_INIT:
+		return CMDQ_MODIFY_QP_NEW_STATE_INIT;
+	case IB_QPS_RTR:
+		return CMDQ_MODIFY_QP_NEW_STATE_RTR;
+	case IB_QPS_RTS:
+		return CMDQ_MODIFY_QP_NEW_STATE_RTS;
+	case IB_QPS_SQD:
+		return CMDQ_MODIFY_QP_NEW_STATE_SQD;
+	case IB_QPS_SQE:
+		return CMDQ_MODIFY_QP_NEW_STATE_SQE;
+	case IB_QPS_ERR:
+	default:
+		return CMDQ_MODIFY_QP_NEW_STATE_ERR;
+	}
+}
+
+static enum ib_qp_state __to_ib_qp_state(u8 state)
+{
+	switch (state) {
+	case CMDQ_MODIFY_QP_NEW_STATE_RESET:
+		return IB_QPS_RESET;
+	case CMDQ_MODIFY_QP_NEW_STATE_INIT:
+		return IB_QPS_INIT;
+	case CMDQ_MODIFY_QP_NEW_STATE_RTR:
+		return IB_QPS_RTR;
+	case CMDQ_MODIFY_QP_NEW_STATE_RTS:
+		return IB_QPS_RTS;
+	case CMDQ_MODIFY_QP_NEW_STATE_SQD:
+		return IB_QPS_SQD;
+	case CMDQ_MODIFY_QP_NEW_STATE_SQE:
+		return IB_QPS_SQE;
+	case CMDQ_MODIFY_QP_NEW_STATE_ERR:
+	default:
+		return IB_QPS_ERR;
+	}
+}
+
+static u32 __from_ib_mtu(enum ib_mtu mtu)
+{
+	switch (mtu) {
+	case IB_MTU_256:
+		return CMDQ_MODIFY_QP_PATH_MTU_MTU_256;
+	case IB_MTU_512:
+		return CMDQ_MODIFY_QP_PATH_MTU_MTU_512;
+	case IB_MTU_1024:
+		return CMDQ_MODIFY_QP_PATH_MTU_MTU_1024;
+	case IB_MTU_2048:
+		return CMDQ_MODIFY_QP_PATH_MTU_MTU_2048;
+	case IB_MTU_4096:
+		return CMDQ_MODIFY_QP_PATH_MTU_MTU_4096;
+	default:
+		return CMDQ_MODIFY_QP_PATH_MTU_MTU_2048;
+	}
+}
+
+static enum ib_mtu __to_ib_mtu(u32 mtu)
+{
+	switch (mtu & CREQ_QUERY_QP_RESP_SB_PATH_MTU_MASK) {
+	case CMDQ_MODIFY_QP_PATH_MTU_MTU_256:
+		return IB_MTU_256;
+	case CMDQ_MODIFY_QP_PATH_MTU_MTU_512:
+		return IB_MTU_512;
+	case CMDQ_MODIFY_QP_PATH_MTU_MTU_1024:
+		return IB_MTU_1024;
+	case CMDQ_MODIFY_QP_PATH_MTU_MTU_2048:
+		return IB_MTU_2048;
+	case CMDQ_MODIFY_QP_PATH_MTU_MTU_4096:
+		return IB_MTU_4096;
+	default:
+		return IB_MTU_2048;
+	}
+}
+
+/* Shared Receive Queues */
+int bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
+{
+	struct bnxt_re_srq *srq = container_of(ib_srq, struct bnxt_re_srq,
+					       ib_srq);
+	struct bnxt_re_dev *rdev = srq->rdev;
+	struct bnxt_qplib_srq *qplib_srq = &srq->qplib_srq;
+	struct bnxt_qplib_nq *nq = NULL;
+
+	if (qplib_srq->cq)
+		nq = qplib_srq->cq->nq;
+	bnxt_qplib_destroy_srq(&rdev->qplib_res, qplib_srq);
+	ib_umem_release(srq->umem);
+	atomic_dec(&rdev->srq_count);
+	if (nq)
+		nq->budget--;
+	return 0;
+}
+
+static int bnxt_re_init_user_srq(struct bnxt_re_dev *rdev,
+				 struct bnxt_re_pd *pd,
+				 struct bnxt_re_srq *srq,
+				 struct ib_udata *udata)
+{
+	struct bnxt_re_srq_req ureq;
+	struct bnxt_qplib_srq *qplib_srq = &srq->qplib_srq;
+	struct ib_umem *umem;
+	int bytes = 0;
+	struct bnxt_re_ucontext *cntx = rdma_udata_to_drv_context(
+		udata, struct bnxt_re_ucontext, ib_uctx);
+
+	if (ib_copy_from_udata(&ureq, udata, sizeof(ureq)))
+		return -EFAULT;
+
+	bytes = (qplib_srq->max_wqe * qplib_srq->wqe_size);
+	bytes = PAGE_ALIGN(bytes);
+	umem = ib_umem_get(&rdev->ibdev, ureq.srqva, bytes,
+			   IB_ACCESS_LOCAL_WRITE);
+	if (IS_ERR(umem))
+		return PTR_ERR(umem);
+
+	srq->umem = umem;
+	qplib_srq->sg_info.umem = umem;
+	qplib_srq->sg_info.pgsize = PAGE_SIZE;
+	qplib_srq->sg_info.pgshft = PAGE_SHIFT;
+	qplib_srq->srq_handle = ureq.srq_handle;
+	qplib_srq->dpi = &cntx->dpi;
+
+	return 0;
+}
+
+int bnxt_re_create_srq(struct ib_srq *ib_srq,
+		       struct ib_srq_init_attr *srq_init_attr,
+		       struct ib_udata *udata)
+{
+	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_qplib_nq *nq = NULL;
+	struct bnxt_re_dev *rdev;
+	struct bnxt_re_srq *srq;
+	struct bnxt_re_pd *pd;
+	struct ib_pd *ib_pd;
+	int rc, entries;
+
+	ib_pd = ib_srq->pd;
+	pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	rdev = pd->rdev;
+	dev_attr = &rdev->dev_attr;
+	srq = container_of(ib_srq, struct bnxt_re_srq, ib_srq);
+
+	if (srq_init_attr->attr.max_wr >= dev_attr->max_srq_wqes) {
+		ibdev_err(&rdev->ibdev, "Create CQ failed - max exceeded");
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	if (srq_init_attr->srq_type != IB_SRQT_BASIC) {
+		rc = -EOPNOTSUPP;
+		goto exit;
+	}
+
+	srq->rdev = rdev;
+	srq->qplib_srq.pd = &pd->qplib_pd;
+	srq->qplib_srq.dpi = &rdev->dpi_privileged;
+	/* Allocate 1 more than what's provided so posting max doesn't
+	 * mean empty
+	 */
+	entries = roundup_pow_of_two(srq_init_attr->attr.max_wr + 1);
+	if (entries > dev_attr->max_srq_wqes + 1)
+		entries = dev_attr->max_srq_wqes + 1;
+	srq->qplib_srq.max_wqe = entries;
+
+	srq->qplib_srq.max_sge = srq_init_attr->attr.max_sge;
+	 /* 128 byte wqe size for SRQ . So use max sges */
+	srq->qplib_srq.wqe_size = bnxt_re_get_rwqe_size(dev_attr->max_srq_sges);
+	srq->qplib_srq.threshold = srq_init_attr->attr.srq_limit;
+	srq->srq_limit = srq_init_attr->attr.srq_limit;
+	srq->qplib_srq.eventq_hw_ring_id = rdev->nq[0].ring_id;
+	nq = &rdev->nq[0];
+
+	if (udata) {
+		rc = bnxt_re_init_user_srq(rdev, pd, srq, udata);
+		if (rc)
+			goto fail;
+	}
+
+	rc = bnxt_qplib_create_srq(&rdev->qplib_res, &srq->qplib_srq);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Create HW SRQ failed!");
+		goto fail;
+	}
+
+	if (udata) {
+		struct bnxt_re_srq_resp resp;
+
+		resp.srqid = srq->qplib_srq.id;
+		rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (rc) {
+			ibdev_err(&rdev->ibdev, "SRQ copy to udata failed!");
+			bnxt_qplib_destroy_srq(&rdev->qplib_res,
+					       &srq->qplib_srq);
+			goto fail;
+		}
+	}
+	if (nq)
+		nq->budget++;
+	atomic_inc(&rdev->srq_count);
+	spin_lock_init(&srq->lock);
+
+	return 0;
+
+fail:
+	ib_umem_release(srq->umem);
+exit:
+	return rc;
+}
+
+int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr,
+		       enum ib_srq_attr_mask srq_attr_mask,
+		       struct ib_udata *udata)
+{
+	struct bnxt_re_srq *srq = container_of(ib_srq, struct bnxt_re_srq,
+					       ib_srq);
+	struct bnxt_re_dev *rdev = srq->rdev;
+	int rc;
+
+	switch (srq_attr_mask) {
+	case IB_SRQ_MAX_WR:
+		/* SRQ resize is not supported */
+		break;
+	case IB_SRQ_LIMIT:
+		/* Change the SRQ threshold */
+		if (srq_attr->srq_limit > srq->qplib_srq.max_wqe)
+			return -EINVAL;
+
+		srq->qplib_srq.threshold = srq_attr->srq_limit;
+		rc = bnxt_qplib_modify_srq(&rdev->qplib_res, &srq->qplib_srq);
+		if (rc) {
+			ibdev_err(&rdev->ibdev, "Modify HW SRQ failed!");
+			return rc;
+		}
+		/* On success, update the shadow */
+		srq->srq_limit = srq_attr->srq_limit;
+		/* No need to Build and send response back to udata */
+		break;
+	default:
+		ibdev_err(&rdev->ibdev,
+			  "Unsupported srq_attr_mask 0x%x", srq_attr_mask);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr)
+{
+	struct bnxt_re_srq *srq = container_of(ib_srq, struct bnxt_re_srq,
+					       ib_srq);
+	struct bnxt_re_srq tsrq;
+	struct bnxt_re_dev *rdev = srq->rdev;
+	int rc;
+
+	/* Get live SRQ attr */
+	tsrq.qplib_srq.id = srq->qplib_srq.id;
+	rc = bnxt_qplib_query_srq(&rdev->qplib_res, &tsrq.qplib_srq);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Query HW SRQ failed!");
+		return rc;
+	}
+	srq_attr->max_wr = srq->qplib_srq.max_wqe;
+	srq_attr->max_sge = srq->qplib_srq.max_sge;
+	srq_attr->srq_limit = tsrq.qplib_srq.threshold;
+
+	return 0;
+}
+
+int bnxt_re_post_srq_recv(struct ib_srq *ib_srq, const struct ib_recv_wr *wr,
+			  const struct ib_recv_wr **bad_wr)
+{
+	struct bnxt_re_srq *srq = container_of(ib_srq, struct bnxt_re_srq,
+					       ib_srq);
+	struct bnxt_qplib_swqe wqe;
+	unsigned long flags;
+	int rc = 0;
+
+	spin_lock_irqsave(&srq->lock, flags);
+	while (wr) {
+		/* Transcribe each ib_recv_wr to qplib_swqe */
+		wqe.num_sge = wr->num_sge;
+		bnxt_re_build_sgl(wr->sg_list, wqe.sg_list, wr->num_sge);
+		wqe.wr_id = wr->wr_id;
+		wqe.type = BNXT_QPLIB_SWQE_TYPE_RECV;
+
+		rc = bnxt_qplib_post_srq_recv(&srq->qplib_srq, &wqe);
+		if (rc) {
+			*bad_wr = wr;
+			break;
+		}
+		wr = wr->next;
+	}
+	spin_unlock_irqrestore(&srq->lock, flags);
+
+	return rc;
+}
+static int bnxt_re_modify_shadow_qp(struct bnxt_re_dev *rdev,
+				    struct bnxt_re_qp *qp1_qp,
+				    int qp_attr_mask)
+{
+	struct bnxt_re_qp *qp = rdev->gsi_ctx.gsi_sqp;
+	int rc = 0;
+
+	if (qp_attr_mask & IB_QP_STATE) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_STATE;
+		qp->qplib_qp.state = qp1_qp->qplib_qp.state;
+	}
+	if (qp_attr_mask & IB_QP_PKEY_INDEX) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PKEY;
+		qp->qplib_qp.pkey_index = qp1_qp->qplib_qp.pkey_index;
+	}
+
+	if (qp_attr_mask & IB_QP_QKEY) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_QKEY;
+		/* Using a Random  QKEY */
+		qp->qplib_qp.qkey = 0x81818181;
+	}
+	if (qp_attr_mask & IB_QP_SQ_PSN) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_SQ_PSN;
+		qp->qplib_qp.sq.psn = qp1_qp->qplib_qp.sq.psn;
+	}
+
+	rc = bnxt_qplib_modify_qp(&rdev->qplib_res, &qp->qplib_qp);
+	if (rc)
+		ibdev_err(&rdev->ibdev, "Failed to modify Shadow QP for QP1");
+	return rc;
+}
+
+int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
+		      int qp_attr_mask, struct ib_udata *udata)
+{
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
+	struct bnxt_re_dev *rdev = qp->rdev;
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	enum ib_qp_state curr_qp_state, new_qp_state;
+	int rc, entries;
+	unsigned int flags;
+	u8 nw_type;
+
+	if (qp_attr_mask & ~IB_QP_ATTR_STANDARD_BITS)
+		return -EOPNOTSUPP;
+
+	qp->qplib_qp.modify_flags = 0;
+	if (qp_attr_mask & IB_QP_STATE) {
+		curr_qp_state = __to_ib_qp_state(qp->qplib_qp.cur_qp_state);
+		new_qp_state = qp_attr->qp_state;
+		if (!ib_modify_qp_is_ok(curr_qp_state, new_qp_state,
+					ib_qp->qp_type, qp_attr_mask)) {
+			ibdev_err(&rdev->ibdev,
+				  "Invalid attribute mask: %#x specified ",
+				  qp_attr_mask);
+			ibdev_err(&rdev->ibdev,
+				  "for qpn: %#x type: %#x",
+				  ib_qp->qp_num, ib_qp->qp_type);
+			ibdev_err(&rdev->ibdev,
+				  "curr_qp_state=0x%x, new_qp_state=0x%x\n",
+				  curr_qp_state, new_qp_state);
+			return -EINVAL;
+		}
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_STATE;
+		qp->qplib_qp.state = __from_ib_qp_state(qp_attr->qp_state);
+
+		if (!qp->sumem &&
+		    qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+			ibdev_dbg(&rdev->ibdev,
+				  "Move QP = %p to flush list\n", qp);
+			flags = bnxt_re_lock_cqs(qp);
+			bnxt_qplib_add_flush_qp(&qp->qplib_qp);
+			bnxt_re_unlock_cqs(qp, flags);
+		}
+		if (!qp->sumem &&
+		    qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_RESET) {
+			ibdev_dbg(&rdev->ibdev,
+				  "Move QP = %p out of flush list\n", qp);
+			flags = bnxt_re_lock_cqs(qp);
+			bnxt_qplib_clean_qp(&qp->qplib_qp);
+			bnxt_re_unlock_cqs(qp, flags);
+		}
+	}
+	if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_EN_SQD_ASYNC_NOTIFY;
+		qp->qplib_qp.en_sqd_async_notify = true;
+	}
+	if (qp_attr_mask & IB_QP_ACCESS_FLAGS) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS;
+		qp->qplib_qp.access =
+			__from_ib_access_flags(qp_attr->qp_access_flags);
+		/* LOCAL_WRITE access must be set to allow RC receive */
+		qp->qplib_qp.access |= BNXT_QPLIB_ACCESS_LOCAL_WRITE;
+		/* Temp: Set all params on QP as of now */
+		qp->qplib_qp.access |= CMDQ_MODIFY_QP_ACCESS_REMOTE_WRITE;
+		qp->qplib_qp.access |= CMDQ_MODIFY_QP_ACCESS_REMOTE_READ;
+	}
+	if (qp_attr_mask & IB_QP_PKEY_INDEX) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PKEY;
+		qp->qplib_qp.pkey_index = qp_attr->pkey_index;
+	}
+	if (qp_attr_mask & IB_QP_QKEY) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_QKEY;
+		qp->qplib_qp.qkey = qp_attr->qkey;
+	}
+	if (qp_attr_mask & IB_QP_AV) {
+		const struct ib_global_route *grh =
+			rdma_ah_read_grh(&qp_attr->ah_attr);
+		const struct ib_gid_attr *sgid_attr;
+		struct bnxt_re_gid_ctx *ctx;
+
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_DGID |
+				     CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL |
+				     CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX |
+				     CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT |
+				     CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS |
+				     CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC |
+				     CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID;
+		memcpy(qp->qplib_qp.ah.dgid.data, grh->dgid.raw,
+		       sizeof(qp->qplib_qp.ah.dgid.data));
+		qp->qplib_qp.ah.flow_label = grh->flow_label;
+		sgid_attr = grh->sgid_attr;
+		/* Get the HW context of the GID. The reference
+		 * of GID table entry is already taken by the caller.
+		 */
+		ctx = rdma_read_gid_hw_context(sgid_attr);
+		qp->qplib_qp.ah.sgid_index = ctx->idx;
+		qp->qplib_qp.ah.host_sgid_index = grh->sgid_index;
+		qp->qplib_qp.ah.hop_limit = grh->hop_limit;
+		qp->qplib_qp.ah.traffic_class = grh->traffic_class;
+		qp->qplib_qp.ah.sl = rdma_ah_get_sl(&qp_attr->ah_attr);
+		ether_addr_copy(qp->qplib_qp.ah.dmac,
+				qp_attr->ah_attr.roce.dmac);
+
+		rc = rdma_read_gid_l2_fields(sgid_attr, NULL,
+					     &qp->qplib_qp.smac[0]);
+		if (rc)
+			return rc;
+
+		nw_type = rdma_gid_attr_network_type(sgid_attr);
+		switch (nw_type) {
+		case RDMA_NETWORK_IPV4:
+			qp->qplib_qp.nw_type =
+				CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV4;
+			break;
+		case RDMA_NETWORK_IPV6:
+			qp->qplib_qp.nw_type =
+				CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV6;
+			break;
+		default:
+			qp->qplib_qp.nw_type =
+				CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV1;
+			break;
+		}
+	}
+
+	if (qp_attr_mask & IB_QP_PATH_MTU) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
+		qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu);
+		qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu);
+	} else if (qp_attr->qp_state == IB_QPS_RTR) {
+		qp->qplib_qp.modify_flags |=
+			CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
+		qp->qplib_qp.path_mtu =
+			__from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu));
+		qp->qplib_qp.mtu =
+			ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
+	}
+
+	if (qp_attr_mask & IB_QP_TIMEOUT) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_TIMEOUT;
+		qp->qplib_qp.timeout = qp_attr->timeout;
+	}
+	if (qp_attr_mask & IB_QP_RETRY_CNT) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_RETRY_CNT;
+		qp->qplib_qp.retry_cnt = qp_attr->retry_cnt;
+	}
+	if (qp_attr_mask & IB_QP_RNR_RETRY) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_RNR_RETRY;
+		qp->qplib_qp.rnr_retry = qp_attr->rnr_retry;
+	}
+	if (qp_attr_mask & IB_QP_MIN_RNR_TIMER) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER;
+		qp->qplib_qp.min_rnr_timer = qp_attr->min_rnr_timer;
+	}
+	if (qp_attr_mask & IB_QP_RQ_PSN) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN;
+		qp->qplib_qp.rq.psn = qp_attr->rq_psn;
+	}
+	if (qp_attr_mask & IB_QP_MAX_QP_RD_ATOMIC) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_MAX_RD_ATOMIC;
+		/* Cap the max_rd_atomic to device max */
+		qp->qplib_qp.max_rd_atomic = min_t(u32, qp_attr->max_rd_atomic,
+						   dev_attr->max_qp_rd_atom);
+	}
+	if (qp_attr_mask & IB_QP_SQ_PSN) {
+		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_SQ_PSN;
+		qp->qplib_qp.sq.psn = qp_attr->sq_psn;
+	}
+	if (qp_attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) {
+		if (qp_attr->max_dest_rd_atomic >
+		    dev_attr->max_qp_init_rd_atom) {
+			ibdev_err(&rdev->ibdev,
+				  "max_dest_rd_atomic requested%d is > dev_max%d",
+				  qp_attr->max_dest_rd_atomic,
+				  dev_attr->max_qp_init_rd_atom);
+			return -EINVAL;
+		}
+
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC;
+		qp->qplib_qp.max_dest_rd_atomic = qp_attr->max_dest_rd_atomic;
+	}
+	if (qp_attr_mask & IB_QP_CAP) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SIZE |
+				CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SIZE |
+				CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SGE |
+				CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SGE |
+				CMDQ_MODIFY_QP_MODIFY_MASK_MAX_INLINE_DATA;
+		if ((qp_attr->cap.max_send_wr >= dev_attr->max_qp_wqes) ||
+		    (qp_attr->cap.max_recv_wr >= dev_attr->max_qp_wqes) ||
+		    (qp_attr->cap.max_send_sge >= dev_attr->max_qp_sges) ||
+		    (qp_attr->cap.max_recv_sge >= dev_attr->max_qp_sges) ||
+		    (qp_attr->cap.max_inline_data >=
+						dev_attr->max_inline_data)) {
+			ibdev_err(&rdev->ibdev,
+				  "Create QP failed - max exceeded");
+			return -EINVAL;
+		}
+		entries = roundup_pow_of_two(qp_attr->cap.max_send_wr);
+		qp->qplib_qp.sq.max_wqe = min_t(u32, entries,
+						dev_attr->max_qp_wqes + 1);
+		qp->qplib_qp.sq.q_full_delta = qp->qplib_qp.sq.max_wqe -
+						qp_attr->cap.max_send_wr;
+		/*
+		 * Reserving one slot for Phantom WQE. Some application can
+		 * post one extra entry in this case. Allowing this to avoid
+		 * unexpected Queue full condition
+		 */
+		qp->qplib_qp.sq.q_full_delta -= 1;
+		qp->qplib_qp.sq.max_sge = qp_attr->cap.max_send_sge;
+		if (qp->qplib_qp.rq.max_wqe) {
+			entries = roundup_pow_of_two(qp_attr->cap.max_recv_wr);
+			qp->qplib_qp.rq.max_wqe =
+				min_t(u32, entries, dev_attr->max_qp_wqes + 1);
+			qp->qplib_qp.rq.q_full_delta = qp->qplib_qp.rq.max_wqe -
+						       qp_attr->cap.max_recv_wr;
+			qp->qplib_qp.rq.max_sge = qp_attr->cap.max_recv_sge;
+		} else {
+			/* SRQ was used prior, just ignore the RQ caps */
+		}
+	}
+	if (qp_attr_mask & IB_QP_DEST_QPN) {
+		qp->qplib_qp.modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID;
+		qp->qplib_qp.dest_qpn = qp_attr->dest_qp_num;
+	}
+	rc = bnxt_qplib_modify_qp(&rdev->qplib_res, &qp->qplib_qp);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to modify HW QP");
+		return rc;
+	}
+	if (ib_qp->qp_type == IB_QPT_GSI && rdev->gsi_ctx.gsi_sqp)
+		rc = bnxt_re_modify_shadow_qp(rdev, qp, qp_attr_mask);
+	return rc;
+}
+
+int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
+		     int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr)
+{
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
+	struct bnxt_re_dev *rdev = qp->rdev;
+	struct bnxt_qplib_qp *qplib_qp;
+	int rc;
+
+	qplib_qp = kzalloc(sizeof(*qplib_qp), GFP_KERNEL);
+	if (!qplib_qp)
+		return -ENOMEM;
+
+	qplib_qp->id = qp->qplib_qp.id;
+	qplib_qp->ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
+
+	rc = bnxt_qplib_query_qp(&rdev->qplib_res, qplib_qp);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to query HW QP");
+		goto out;
+	}
+	qp_attr->qp_state = __to_ib_qp_state(qplib_qp->state);
+	qp_attr->cur_qp_state = __to_ib_qp_state(qplib_qp->cur_qp_state);
+	qp_attr->en_sqd_async_notify = qplib_qp->en_sqd_async_notify ? 1 : 0;
+	qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp->access);
+	qp_attr->pkey_index = qplib_qp->pkey_index;
+	qp_attr->qkey = qplib_qp->qkey;
+	qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
+	rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp->ah.flow_label,
+			qplib_qp->ah.host_sgid_index,
+			qplib_qp->ah.hop_limit,
+			qplib_qp->ah.traffic_class);
+	rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp->ah.dgid.data);
+	rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp->ah.sl);
+	ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp->ah.dmac);
+	qp_attr->path_mtu = __to_ib_mtu(qplib_qp->path_mtu);
+	qp_attr->timeout = qplib_qp->timeout;
+	qp_attr->retry_cnt = qplib_qp->retry_cnt;
+	qp_attr->rnr_retry = qplib_qp->rnr_retry;
+	qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer;
+	qp_attr->rq_psn = qplib_qp->rq.psn;
+	qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic;
+	qp_attr->sq_psn = qplib_qp->sq.psn;
+	qp_attr->max_dest_rd_atomic = qplib_qp->max_dest_rd_atomic;
+	qp_init_attr->sq_sig_type = qplib_qp->sig_type ? IB_SIGNAL_ALL_WR :
+							 IB_SIGNAL_REQ_WR;
+	qp_attr->dest_qp_num = qplib_qp->dest_qpn;
+
+	qp_attr->cap.max_send_wr = qp->qplib_qp.sq.max_wqe;
+	qp_attr->cap.max_send_sge = qp->qplib_qp.sq.max_sge;
+	qp_attr->cap.max_recv_wr = qp->qplib_qp.rq.max_wqe;
+	qp_attr->cap.max_recv_sge = qp->qplib_qp.rq.max_sge;
+	qp_attr->cap.max_inline_data = qp->qplib_qp.max_inline_data;
+	qp_init_attr->cap = qp_attr->cap;
+
+out:
+	kfree(qplib_qp);
+	return rc;
+}
+
+/* Routine for sending QP1 packets for RoCE V1 an V2
+ */
+static int bnxt_re_build_qp1_send_v2(struct bnxt_re_qp *qp,
+				     const struct ib_send_wr *wr,
+				     struct bnxt_qplib_swqe *wqe,
+				     int payload_size)
+{
+	struct bnxt_re_ah *ah = container_of(ud_wr(wr)->ah, struct bnxt_re_ah,
+					     ib_ah);
+	struct bnxt_qplib_ah *qplib_ah = &ah->qplib_ah;
+	const struct ib_gid_attr *sgid_attr = ah->ib_ah.sgid_attr;
+	struct bnxt_qplib_sge sge;
+	u8 nw_type;
+	u16 ether_type;
+	union ib_gid dgid;
+	bool is_eth = false;
+	bool is_vlan = false;
+	bool is_grh = false;
+	bool is_udp = false;
+	u8 ip_version = 0;
+	u16 vlan_id = 0xFFFF;
+	void *buf;
+	int i, rc = 0;
+
+	memset(&qp->qp1_hdr, 0, sizeof(qp->qp1_hdr));
+
+	rc = rdma_read_gid_l2_fields(sgid_attr, &vlan_id, NULL);
+	if (rc)
+		return rc;
+
+	/* Get network header type for this GID */
+	nw_type = rdma_gid_attr_network_type(sgid_attr);
+	switch (nw_type) {
+	case RDMA_NETWORK_IPV4:
+		nw_type = BNXT_RE_ROCEV2_IPV4_PACKET;
+		break;
+	case RDMA_NETWORK_IPV6:
+		nw_type = BNXT_RE_ROCEV2_IPV6_PACKET;
+		break;
+	default:
+		nw_type = BNXT_RE_ROCE_V1_PACKET;
+		break;
+	}
+	memcpy(&dgid.raw, &qplib_ah->dgid, 16);
+	is_udp = sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP;
+	if (is_udp) {
+		if (ipv6_addr_v4mapped((struct in6_addr *)&sgid_attr->gid)) {
+			ip_version = 4;
+			ether_type = ETH_P_IP;
+		} else {
+			ip_version = 6;
+			ether_type = ETH_P_IPV6;
+		}
+		is_grh = false;
+	} else {
+		ether_type = ETH_P_IBOE;
+		is_grh = true;
+	}
+
+	is_eth = true;
+	is_vlan = (vlan_id && (vlan_id < 0x1000)) ? true : false;
+
+	ib_ud_header_init(payload_size, !is_eth, is_eth, is_vlan, is_grh,
+			  ip_version, is_udp, 0, &qp->qp1_hdr);
+
+	/* ETH */
+	ether_addr_copy(qp->qp1_hdr.eth.dmac_h, ah->qplib_ah.dmac);
+	ether_addr_copy(qp->qp1_hdr.eth.smac_h, qp->qplib_qp.smac);
+
+	/* For vlan, check the sgid for vlan existence */
+
+	if (!is_vlan) {
+		qp->qp1_hdr.eth.type = cpu_to_be16(ether_type);
+	} else {
+		qp->qp1_hdr.vlan.type = cpu_to_be16(ether_type);
+		qp->qp1_hdr.vlan.tag = cpu_to_be16(vlan_id);
+	}
+
+	if (is_grh || (ip_version == 6)) {
+		memcpy(qp->qp1_hdr.grh.source_gid.raw, sgid_attr->gid.raw,
+		       sizeof(sgid_attr->gid));
+		memcpy(qp->qp1_hdr.grh.destination_gid.raw, qplib_ah->dgid.data,
+		       sizeof(sgid_attr->gid));
+		qp->qp1_hdr.grh.hop_limit     = qplib_ah->hop_limit;
+	}
+
+	if (ip_version == 4) {
+		qp->qp1_hdr.ip4.tos = 0;
+		qp->qp1_hdr.ip4.id = 0;
+		qp->qp1_hdr.ip4.frag_off = htons(IP_DF);
+		qp->qp1_hdr.ip4.ttl = qplib_ah->hop_limit;
+
+		memcpy(&qp->qp1_hdr.ip4.saddr, sgid_attr->gid.raw + 12, 4);
+		memcpy(&qp->qp1_hdr.ip4.daddr, qplib_ah->dgid.data + 12, 4);
+		qp->qp1_hdr.ip4.check = ib_ud_ip4_csum(&qp->qp1_hdr);
+	}
+
+	if (is_udp) {
+		qp->qp1_hdr.udp.dport = htons(ROCE_V2_UDP_DPORT);
+		qp->qp1_hdr.udp.sport = htons(0x8CD1);
+		qp->qp1_hdr.udp.csum = 0;
+	}
+
+	/* BTH */
+	if (wr->opcode == IB_WR_SEND_WITH_IMM) {
+		qp->qp1_hdr.bth.opcode = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE;
+		qp->qp1_hdr.immediate_present = 1;
+	} else {
+		qp->qp1_hdr.bth.opcode = IB_OPCODE_UD_SEND_ONLY;
+	}
+	if (wr->send_flags & IB_SEND_SOLICITED)
+		qp->qp1_hdr.bth.solicited_event = 1;
+	/* pad_count */
+	qp->qp1_hdr.bth.pad_count = (4 - payload_size) & 3;
+
+	/* P_key for QP1 is for all members */
+	qp->qp1_hdr.bth.pkey = cpu_to_be16(0xFFFF);
+	qp->qp1_hdr.bth.destination_qpn = IB_QP1;
+	qp->qp1_hdr.bth.ack_req = 0;
+	qp->send_psn++;
+	qp->send_psn &= BTH_PSN_MASK;
+	qp->qp1_hdr.bth.psn = cpu_to_be32(qp->send_psn);
+	/* DETH */
+	/* Use the priviledged Q_Key for QP1 */
+	qp->qp1_hdr.deth.qkey = cpu_to_be32(IB_QP1_QKEY);
+	qp->qp1_hdr.deth.source_qpn = IB_QP1;
+
+	/* Pack the QP1 to the transmit buffer */
+	buf = bnxt_qplib_get_qp1_sq_buf(&qp->qplib_qp, &sge);
+	if (buf) {
+		ib_ud_header_pack(&qp->qp1_hdr, buf);
+		for (i = wqe->num_sge; i; i--) {
+			wqe->sg_list[i].addr = wqe->sg_list[i - 1].addr;
+			wqe->sg_list[i].lkey = wqe->sg_list[i - 1].lkey;
+			wqe->sg_list[i].size = wqe->sg_list[i - 1].size;
+		}
+
+		/*
+		 * Max Header buf size for IPV6 RoCE V2 is 86,
+		 * which is same as the QP1 SQ header buffer.
+		 * Header buf size for IPV4 RoCE V2 can be 66.
+		 * ETH(14) + VLAN(4)+ IP(20) + UDP (8) + BTH(20).
+		 * Subtract 20 bytes from QP1 SQ header buf size
+		 */
+		if (is_udp && ip_version == 4)
+			sge.size -= 20;
+		/*
+		 * Max Header buf size for RoCE V1 is 78.
+		 * ETH(14) + VLAN(4) + GRH(40) + BTH(20).
+		 * Subtract 8 bytes from QP1 SQ header buf size
+		 */
+		if (!is_udp)
+			sge.size -= 8;
+
+		/* Subtract 4 bytes for non vlan packets */
+		if (!is_vlan)
+			sge.size -= 4;
+
+		wqe->sg_list[0].addr = sge.addr;
+		wqe->sg_list[0].lkey = sge.lkey;
+		wqe->sg_list[0].size = sge.size;
+		wqe->num_sge++;
+
+	} else {
+		ibdev_err(&qp->rdev->ibdev, "QP1 buffer is empty!");
+		rc = -ENOMEM;
+	}
+	return rc;
+}
+
+/* For the MAD layer, it only provides the recv SGE the size of
+ * ib_grh + MAD datagram.  No Ethernet headers, Ethertype, BTH, DETH,
+ * nor RoCE iCRC.  The Cu+ solution must provide buffer for the entire
+ * receive packet (334 bytes) with no VLAN and then copy the GRH
+ * and the MAD datagram out to the provided SGE.
+ */
+static int bnxt_re_build_qp1_shadow_qp_recv(struct bnxt_re_qp *qp,
+					    const struct ib_recv_wr *wr,
+					    struct bnxt_qplib_swqe *wqe,
+					    int payload_size)
+{
+	struct bnxt_re_sqp_entries *sqp_entry;
+	struct bnxt_qplib_sge ref, sge;
+	struct bnxt_re_dev *rdev;
+	u32 rq_prod_index;
+
+	rdev = qp->rdev;
+
+	rq_prod_index = bnxt_qplib_get_rq_prod_index(&qp->qplib_qp);
+
+	if (!bnxt_qplib_get_qp1_rq_buf(&qp->qplib_qp, &sge))
+		return -ENOMEM;
+
+	/* Create 1 SGE to receive the entire
+	 * ethernet packet
+	 */
+	/* Save the reference from ULP */
+	ref.addr = wqe->sg_list[0].addr;
+	ref.lkey = wqe->sg_list[0].lkey;
+	ref.size = wqe->sg_list[0].size;
+
+	sqp_entry = &rdev->gsi_ctx.sqp_tbl[rq_prod_index];
+
+	/* SGE 1 */
+	wqe->sg_list[0].addr = sge.addr;
+	wqe->sg_list[0].lkey = sge.lkey;
+	wqe->sg_list[0].size = BNXT_QPLIB_MAX_QP1_RQ_HDR_SIZE_V2;
+	sge.size -= wqe->sg_list[0].size;
+
+	sqp_entry->sge.addr = ref.addr;
+	sqp_entry->sge.lkey = ref.lkey;
+	sqp_entry->sge.size = ref.size;
+	/* Store the wrid for reporting completion */
+	sqp_entry->wrid = wqe->wr_id;
+	/* change the wqe->wrid to table index */
+	wqe->wr_id = rq_prod_index;
+	return 0;
+}
+
+static int is_ud_qp(struct bnxt_re_qp *qp)
+{
+	return (qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_UD ||
+		qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_GSI);
+}
+
+static int bnxt_re_build_send_wqe(struct bnxt_re_qp *qp,
+				  const struct ib_send_wr *wr,
+				  struct bnxt_qplib_swqe *wqe)
+{
+	struct bnxt_re_ah *ah = NULL;
+
+	if (is_ud_qp(qp)) {
+		ah = container_of(ud_wr(wr)->ah, struct bnxt_re_ah, ib_ah);
+		wqe->send.q_key = ud_wr(wr)->remote_qkey;
+		wqe->send.dst_qp = ud_wr(wr)->remote_qpn;
+		wqe->send.avid = ah->qplib_ah.id;
+	}
+	switch (wr->opcode) {
+	case IB_WR_SEND:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_SEND;
+		break;
+	case IB_WR_SEND_WITH_IMM:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM;
+		wqe->send.imm_data = wr->ex.imm_data;
+		break;
+	case IB_WR_SEND_WITH_INV:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV;
+		wqe->send.inv_key = wr->ex.invalidate_rkey;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (wr->send_flags & IB_SEND_SIGNALED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
+	if (wr->send_flags & IB_SEND_FENCE)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+	if (wr->send_flags & IB_SEND_SOLICITED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT;
+	if (wr->send_flags & IB_SEND_INLINE)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_INLINE;
+
+	return 0;
+}
+
+static int bnxt_re_build_rdma_wqe(const struct ib_send_wr *wr,
+				  struct bnxt_qplib_swqe *wqe)
+{
+	switch (wr->opcode) {
+	case IB_WR_RDMA_WRITE:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE;
+		break;
+	case IB_WR_RDMA_WRITE_WITH_IMM:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE_WITH_IMM;
+		wqe->rdma.imm_data = wr->ex.imm_data;
+		break;
+	case IB_WR_RDMA_READ:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_RDMA_READ;
+		wqe->rdma.inv_key = wr->ex.invalidate_rkey;
+		break;
+	default:
+		return -EINVAL;
+	}
+	wqe->rdma.remote_va = rdma_wr(wr)->remote_addr;
+	wqe->rdma.r_key = rdma_wr(wr)->rkey;
+	if (wr->send_flags & IB_SEND_SIGNALED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
+	if (wr->send_flags & IB_SEND_FENCE)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+	if (wr->send_flags & IB_SEND_SOLICITED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT;
+	if (wr->send_flags & IB_SEND_INLINE)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_INLINE;
+
+	return 0;
+}
+
+static int bnxt_re_build_atomic_wqe(const struct ib_send_wr *wr,
+				    struct bnxt_qplib_swqe *wqe)
+{
+	switch (wr->opcode) {
+	case IB_WR_ATOMIC_CMP_AND_SWP:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP;
+		wqe->atomic.cmp_data = atomic_wr(wr)->compare_add;
+		wqe->atomic.swap_data = atomic_wr(wr)->swap;
+		break;
+	case IB_WR_ATOMIC_FETCH_AND_ADD:
+		wqe->type = BNXT_QPLIB_SWQE_TYPE_ATOMIC_FETCH_AND_ADD;
+		wqe->atomic.cmp_data = atomic_wr(wr)->compare_add;
+		break;
+	default:
+		return -EINVAL;
+	}
+	wqe->atomic.remote_va = atomic_wr(wr)->remote_addr;
+	wqe->atomic.r_key = atomic_wr(wr)->rkey;
+	if (wr->send_flags & IB_SEND_SIGNALED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
+	if (wr->send_flags & IB_SEND_FENCE)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+	if (wr->send_flags & IB_SEND_SOLICITED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT;
+	return 0;
+}
+
+static int bnxt_re_build_inv_wqe(const struct ib_send_wr *wr,
+				 struct bnxt_qplib_swqe *wqe)
+{
+	wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV;
+	wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey;
+
+	/* Need unconditional fence for local invalidate
+	 * opcode to work as expected.
+	 */
+	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+
+	if (wr->send_flags & IB_SEND_SIGNALED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
+	if (wr->send_flags & IB_SEND_SOLICITED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT;
+
+	return 0;
+}
+
+static int bnxt_re_build_reg_wqe(const struct ib_reg_wr *wr,
+				 struct bnxt_qplib_swqe *wqe)
+{
+	struct bnxt_re_mr *mr = container_of(wr->mr, struct bnxt_re_mr, ib_mr);
+	struct bnxt_qplib_frpl *qplib_frpl = &mr->qplib_frpl;
+	int access = wr->access;
+
+	wqe->frmr.pbl_ptr = (__le64 *)qplib_frpl->hwq.pbl_ptr[0];
+	wqe->frmr.pbl_dma_ptr = qplib_frpl->hwq.pbl_dma_ptr[0];
+	wqe->frmr.page_list = mr->pages;
+	wqe->frmr.page_list_len = mr->npages;
+	wqe->frmr.levels = qplib_frpl->hwq.level;
+	wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR;
+
+	/* Need unconditional fence for reg_mr
+	 * opcode to function as expected.
+	 */
+
+	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+
+	if (wr->wr.send_flags & IB_SEND_SIGNALED)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
+
+	if (access & IB_ACCESS_LOCAL_WRITE)
+		wqe->frmr.access_cntl |= SQ_FR_PMR_ACCESS_CNTL_LOCAL_WRITE;
+	if (access & IB_ACCESS_REMOTE_READ)
+		wqe->frmr.access_cntl |= SQ_FR_PMR_ACCESS_CNTL_REMOTE_READ;
+	if (access & IB_ACCESS_REMOTE_WRITE)
+		wqe->frmr.access_cntl |= SQ_FR_PMR_ACCESS_CNTL_REMOTE_WRITE;
+	if (access & IB_ACCESS_REMOTE_ATOMIC)
+		wqe->frmr.access_cntl |= SQ_FR_PMR_ACCESS_CNTL_REMOTE_ATOMIC;
+	if (access & IB_ACCESS_MW_BIND)
+		wqe->frmr.access_cntl |= SQ_FR_PMR_ACCESS_CNTL_WINDOW_BIND;
+
+	wqe->frmr.l_key = wr->key;
+	wqe->frmr.length = wr->mr->length;
+	wqe->frmr.pbl_pg_sz_log = ilog2(PAGE_SIZE >> PAGE_SHIFT_4K);
+	wqe->frmr.pg_sz_log = ilog2(wr->mr->page_size >> PAGE_SHIFT_4K);
+	wqe->frmr.va = wr->mr->iova;
+	return 0;
+}
+
+static int bnxt_re_copy_inline_data(struct bnxt_re_dev *rdev,
+				    const struct ib_send_wr *wr,
+				    struct bnxt_qplib_swqe *wqe)
+{
+	/*  Copy the inline data to the data  field */
+	u8 *in_data;
+	u32 i, sge_len;
+	void *sge_addr;
+
+	in_data = wqe->inline_data;
+	for (i = 0; i < wr->num_sge; i++) {
+		sge_addr = (void *)(unsigned long)
+				wr->sg_list[i].addr;
+		sge_len = wr->sg_list[i].length;
+
+		if ((sge_len + wqe->inline_len) >
+		    BNXT_QPLIB_SWQE_MAX_INLINE_LENGTH) {
+			ibdev_err(&rdev->ibdev,
+				  "Inline data size requested > supported value");
+			return -EINVAL;
+		}
+		sge_len = wr->sg_list[i].length;
+
+		memcpy(in_data, sge_addr, sge_len);
+		in_data += wr->sg_list[i].length;
+		wqe->inline_len += wr->sg_list[i].length;
+	}
+	return wqe->inline_len;
+}
+
+static int bnxt_re_copy_wr_payload(struct bnxt_re_dev *rdev,
+				   const struct ib_send_wr *wr,
+				   struct bnxt_qplib_swqe *wqe)
+{
+	int payload_sz = 0;
+
+	if (wr->send_flags & IB_SEND_INLINE)
+		payload_sz = bnxt_re_copy_inline_data(rdev, wr, wqe);
+	else
+		payload_sz = bnxt_re_build_sgl(wr->sg_list, wqe->sg_list,
+					       wqe->num_sge);
+
+	return payload_sz;
+}
+
+static void bnxt_ud_qp_hw_stall_workaround(struct bnxt_re_qp *qp)
+{
+	if ((qp->ib_qp.qp_type == IB_QPT_UD ||
+	     qp->ib_qp.qp_type == IB_QPT_GSI ||
+	     qp->ib_qp.qp_type == IB_QPT_RAW_ETHERTYPE) &&
+	     qp->qplib_qp.wqe_cnt == BNXT_RE_UD_QP_HW_STALL) {
+		int qp_attr_mask;
+		struct ib_qp_attr qp_attr;
+
+		qp_attr_mask = IB_QP_STATE;
+		qp_attr.qp_state = IB_QPS_RTS;
+		bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, qp_attr_mask, NULL);
+		qp->qplib_qp.wqe_cnt = 0;
+	}
+}
+
+static int bnxt_re_post_send_shadow_qp(struct bnxt_re_dev *rdev,
+				       struct bnxt_re_qp *qp,
+				       const struct ib_send_wr *wr)
+{
+	int rc = 0, payload_sz = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->sq_lock, flags);
+	while (wr) {
+		struct bnxt_qplib_swqe wqe = {};
+
+		/* Common */
+		wqe.num_sge = wr->num_sge;
+		if (wr->num_sge > qp->qplib_qp.sq.max_sge) {
+			ibdev_err(&rdev->ibdev,
+				  "Limit exceeded for Send SGEs");
+			rc = -EINVAL;
+			goto bad;
+		}
+
+		payload_sz = bnxt_re_copy_wr_payload(qp->rdev, wr, &wqe);
+		if (payload_sz < 0) {
+			rc = -EINVAL;
+			goto bad;
+		}
+		wqe.wr_id = wr->wr_id;
+
+		wqe.type = BNXT_QPLIB_SWQE_TYPE_SEND;
+
+		rc = bnxt_re_build_send_wqe(qp, wr, &wqe);
+		if (!rc)
+			rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe);
+bad:
+		if (rc) {
+			ibdev_err(&rdev->ibdev,
+				  "Post send failed opcode = %#x rc = %d",
+				  wr->opcode, rc);
+			break;
+		}
+		wr = wr->next;
+	}
+	bnxt_qplib_post_send_db(&qp->qplib_qp);
+	bnxt_ud_qp_hw_stall_workaround(qp);
+	spin_unlock_irqrestore(&qp->sq_lock, flags);
+	return rc;
+}
+
+int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr,
+		      const struct ib_send_wr **bad_wr)
+{
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
+	struct bnxt_qplib_swqe wqe;
+	int rc = 0, payload_sz = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->sq_lock, flags);
+	while (wr) {
+		/* House keeping */
+		memset(&wqe, 0, sizeof(wqe));
+
+		/* Common */
+		wqe.num_sge = wr->num_sge;
+		if (wr->num_sge > qp->qplib_qp.sq.max_sge) {
+			ibdev_err(&qp->rdev->ibdev,
+				  "Limit exceeded for Send SGEs");
+			rc = -EINVAL;
+			goto bad;
+		}
+
+		payload_sz = bnxt_re_copy_wr_payload(qp->rdev, wr, &wqe);
+		if (payload_sz < 0) {
+			rc = -EINVAL;
+			goto bad;
+		}
+		wqe.wr_id = wr->wr_id;
+
+		switch (wr->opcode) {
+		case IB_WR_SEND:
+		case IB_WR_SEND_WITH_IMM:
+			if (qp->qplib_qp.type == CMDQ_CREATE_QP1_TYPE_GSI) {
+				rc = bnxt_re_build_qp1_send_v2(qp, wr, &wqe,
+							       payload_sz);
+				if (rc)
+					goto bad;
+				wqe.rawqp1.lflags |=
+					SQ_SEND_RAWETH_QP1_LFLAGS_ROCE_CRC;
+			}
+			switch (wr->send_flags) {
+			case IB_SEND_IP_CSUM:
+				wqe.rawqp1.lflags |=
+					SQ_SEND_RAWETH_QP1_LFLAGS_IP_CHKSUM;
+				break;
+			default:
+				break;
+			}
+			fallthrough;
+		case IB_WR_SEND_WITH_INV:
+			rc = bnxt_re_build_send_wqe(qp, wr, &wqe);
+			break;
+		case IB_WR_RDMA_WRITE:
+		case IB_WR_RDMA_WRITE_WITH_IMM:
+		case IB_WR_RDMA_READ:
+			rc = bnxt_re_build_rdma_wqe(wr, &wqe);
+			break;
+		case IB_WR_ATOMIC_CMP_AND_SWP:
+		case IB_WR_ATOMIC_FETCH_AND_ADD:
+			rc = bnxt_re_build_atomic_wqe(wr, &wqe);
+			break;
+		case IB_WR_RDMA_READ_WITH_INV:
+			ibdev_err(&qp->rdev->ibdev,
+				  "RDMA Read with Invalidate is not supported");
+			rc = -EINVAL;
+			goto bad;
+		case IB_WR_LOCAL_INV:
+			rc = bnxt_re_build_inv_wqe(wr, &wqe);
+			break;
+		case IB_WR_REG_MR:
+			rc = bnxt_re_build_reg_wqe(reg_wr(wr), &wqe);
+			break;
+		default:
+			/* Unsupported WRs */
+			ibdev_err(&qp->rdev->ibdev,
+				  "WR (%#x) is not supported", wr->opcode);
+			rc = -EINVAL;
+			goto bad;
+		}
+		if (!rc)
+			rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe);
+bad:
+		if (rc) {
+			ibdev_err(&qp->rdev->ibdev,
+				  "post_send failed op:%#x qps = %#x rc = %d\n",
+				  wr->opcode, qp->qplib_qp.state, rc);
+			*bad_wr = wr;
+			break;
+		}
+		wr = wr->next;
+	}
+	bnxt_qplib_post_send_db(&qp->qplib_qp);
+	bnxt_ud_qp_hw_stall_workaround(qp);
+	spin_unlock_irqrestore(&qp->sq_lock, flags);
+
+	return rc;
+}
+
+static int bnxt_re_post_recv_shadow_qp(struct bnxt_re_dev *rdev,
+				       struct bnxt_re_qp *qp,
+				       const struct ib_recv_wr *wr)
+{
+	struct bnxt_qplib_swqe wqe;
+	int rc = 0;
+
+	memset(&wqe, 0, sizeof(wqe));
+	while (wr) {
+		/* House keeping */
+		memset(&wqe, 0, sizeof(wqe));
+
+		/* Common */
+		wqe.num_sge = wr->num_sge;
+		if (wr->num_sge > qp->qplib_qp.rq.max_sge) {
+			ibdev_err(&rdev->ibdev,
+				  "Limit exceeded for Receive SGEs");
+			rc = -EINVAL;
+			break;
+		}
+		bnxt_re_build_sgl(wr->sg_list, wqe.sg_list, wr->num_sge);
+		wqe.wr_id = wr->wr_id;
+		wqe.type = BNXT_QPLIB_SWQE_TYPE_RECV;
+
+		rc = bnxt_qplib_post_recv(&qp->qplib_qp, &wqe);
+		if (rc)
+			break;
+
+		wr = wr->next;
+	}
+	if (!rc)
+		bnxt_qplib_post_recv_db(&qp->qplib_qp);
+	return rc;
+}
+
+int bnxt_re_post_recv(struct ib_qp *ib_qp, const struct ib_recv_wr *wr,
+		      const struct ib_recv_wr **bad_wr)
+{
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
+	struct bnxt_qplib_swqe wqe;
+	int rc = 0, payload_sz = 0;
+	unsigned long flags;
+	u32 count = 0;
+
+	spin_lock_irqsave(&qp->rq_lock, flags);
+	while (wr) {
+		/* House keeping */
+		memset(&wqe, 0, sizeof(wqe));
+
+		/* Common */
+		wqe.num_sge = wr->num_sge;
+		if (wr->num_sge > qp->qplib_qp.rq.max_sge) {
+			ibdev_err(&qp->rdev->ibdev,
+				  "Limit exceeded for Receive SGEs");
+			rc = -EINVAL;
+			*bad_wr = wr;
+			break;
+		}
+
+		payload_sz = bnxt_re_build_sgl(wr->sg_list, wqe.sg_list,
+					       wr->num_sge);
+		wqe.wr_id = wr->wr_id;
+		wqe.type = BNXT_QPLIB_SWQE_TYPE_RECV;
+
+		if (ib_qp->qp_type == IB_QPT_GSI &&
+		    qp->qplib_qp.type != CMDQ_CREATE_QP_TYPE_GSI)
+			rc = bnxt_re_build_qp1_shadow_qp_recv(qp, wr, &wqe,
+							      payload_sz);
+		if (!rc)
+			rc = bnxt_qplib_post_recv(&qp->qplib_qp, &wqe);
+		if (rc) {
+			*bad_wr = wr;
+			break;
+		}
+
+		/* Ring DB if the RQEs posted reaches a threshold value */
+		if (++count >= BNXT_RE_RQ_WQE_THRESHOLD) {
+			bnxt_qplib_post_recv_db(&qp->qplib_qp);
+			count = 0;
+		}
+
+		wr = wr->next;
+	}
+
+	if (count)
+		bnxt_qplib_post_recv_db(&qp->qplib_qp);
+
+	spin_unlock_irqrestore(&qp->rq_lock, flags);
+
+	return rc;
+}
+
+/* Completion Queues */
+int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
+{
+	struct bnxt_re_cq *cq;
+	struct bnxt_qplib_nq *nq;
+	struct bnxt_re_dev *rdev;
+
+	cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
+	rdev = cq->rdev;
+	nq = cq->qplib_cq.nq;
+
+	bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
+	ib_umem_release(cq->umem);
+
+	atomic_dec(&rdev->cq_count);
+	nq->budget--;
+	kfree(cq->cql);
+	return 0;
+}
+
+int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+		      struct ib_udata *udata)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibcq->device, ibdev);
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_re_cq *cq = container_of(ibcq, struct bnxt_re_cq, ib_cq);
+	int rc, entries;
+	int cqe = attr->cqe;
+	struct bnxt_qplib_nq *nq = NULL;
+	unsigned int nq_alloc_cnt;
+
+	if (attr->flags)
+		return -EOPNOTSUPP;
+
+	/* Validate CQ fields */
+	if (cqe < 1 || cqe > dev_attr->max_cq_wqes) {
+		ibdev_err(&rdev->ibdev, "Failed to create CQ -max exceeded");
+		return -EINVAL;
+	}
+
+	cq->rdev = rdev;
+	cq->qplib_cq.cq_handle = (u64)(unsigned long)(&cq->qplib_cq);
+
+	entries = roundup_pow_of_two(cqe + 1);
+	if (entries > dev_attr->max_cq_wqes + 1)
+		entries = dev_attr->max_cq_wqes + 1;
+
+	cq->qplib_cq.sg_info.pgsize = PAGE_SIZE;
+	cq->qplib_cq.sg_info.pgshft = PAGE_SHIFT;
+	if (udata) {
+		struct bnxt_re_cq_req req;
+		struct bnxt_re_ucontext *uctx = rdma_udata_to_drv_context(
+			udata, struct bnxt_re_ucontext, ib_uctx);
+		if (ib_copy_from_udata(&req, udata, sizeof(req))) {
+			rc = -EFAULT;
+			goto fail;
+		}
+
+		cq->umem = ib_umem_get(&rdev->ibdev, req.cq_va,
+				       entries * sizeof(struct cq_base),
+				       IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(cq->umem)) {
+			rc = PTR_ERR(cq->umem);
+			goto fail;
+		}
+		cq->qplib_cq.sg_info.umem = cq->umem;
+		cq->qplib_cq.dpi = &uctx->dpi;
+	} else {
+		cq->max_cql = min_t(u32, entries, MAX_CQL_PER_POLL);
+		cq->cql = kcalloc(cq->max_cql, sizeof(struct bnxt_qplib_cqe),
+				  GFP_KERNEL);
+		if (!cq->cql) {
+			rc = -ENOMEM;
+			goto fail;
+		}
+
+		cq->qplib_cq.dpi = &rdev->dpi_privileged;
+	}
+	/*
+	 * Allocating the NQ in a round robin fashion. nq_alloc_cnt is a
+	 * used for getting the NQ index.
+	 */
+	nq_alloc_cnt = atomic_inc_return(&rdev->nq_alloc_cnt);
+	nq = &rdev->nq[nq_alloc_cnt % (rdev->num_msix - 1)];
+	cq->qplib_cq.max_wqe = entries;
+	cq->qplib_cq.cnq_hw_ring_id = nq->ring_id;
+	cq->qplib_cq.nq	= nq;
+
+	rc = bnxt_qplib_create_cq(&rdev->qplib_res, &cq->qplib_cq);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to create HW CQ");
+		goto fail;
+	}
+
+	cq->ib_cq.cqe = entries;
+	cq->cq_period = cq->qplib_cq.period;
+	nq->budget++;
+
+	atomic_inc(&rdev->cq_count);
+	spin_lock_init(&cq->cq_lock);
+
+	if (udata) {
+		struct bnxt_re_cq_resp resp;
+
+		resp.cqid = cq->qplib_cq.id;
+		resp.tail = cq->qplib_cq.hwq.cons;
+		resp.phase = cq->qplib_cq.period;
+		resp.rsvd = 0;
+		rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (rc) {
+			ibdev_err(&rdev->ibdev, "Failed to copy CQ udata");
+			bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
+			goto c2fail;
+		}
+	}
+
+	return 0;
+
+c2fail:
+	ib_umem_release(cq->umem);
+fail:
+	kfree(cq->cql);
+	return rc;
+}
+
+static u8 __req_to_ib_wc_status(u8 qstatus)
+{
+	switch (qstatus) {
+	case CQ_REQ_STATUS_OK:
+		return IB_WC_SUCCESS;
+	case CQ_REQ_STATUS_BAD_RESPONSE_ERR:
+		return IB_WC_BAD_RESP_ERR;
+	case CQ_REQ_STATUS_LOCAL_LENGTH_ERR:
+		return IB_WC_LOC_LEN_ERR;
+	case CQ_REQ_STATUS_LOCAL_QP_OPERATION_ERR:
+		return IB_WC_LOC_QP_OP_ERR;
+	case CQ_REQ_STATUS_LOCAL_PROTECTION_ERR:
+		return IB_WC_LOC_PROT_ERR;
+	case CQ_REQ_STATUS_MEMORY_MGT_OPERATION_ERR:
+		return IB_WC_GENERAL_ERR;
+	case CQ_REQ_STATUS_REMOTE_INVALID_REQUEST_ERR:
+		return IB_WC_REM_INV_REQ_ERR;
+	case CQ_REQ_STATUS_REMOTE_ACCESS_ERR:
+		return IB_WC_REM_ACCESS_ERR;
+	case CQ_REQ_STATUS_REMOTE_OPERATION_ERR:
+		return IB_WC_REM_OP_ERR;
+	case CQ_REQ_STATUS_RNR_NAK_RETRY_CNT_ERR:
+		return IB_WC_RNR_RETRY_EXC_ERR;
+	case CQ_REQ_STATUS_TRANSPORT_RETRY_CNT_ERR:
+		return IB_WC_RETRY_EXC_ERR;
+	case CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR:
+		return IB_WC_WR_FLUSH_ERR;
+	default:
+		return IB_WC_GENERAL_ERR;
+	}
+	return 0;
+}
+
+static u8 __rawqp1_to_ib_wc_status(u8 qstatus)
+{
+	switch (qstatus) {
+	case CQ_RES_RAWETH_QP1_STATUS_OK:
+		return IB_WC_SUCCESS;
+	case CQ_RES_RAWETH_QP1_STATUS_LOCAL_ACCESS_ERROR:
+		return IB_WC_LOC_ACCESS_ERR;
+	case CQ_RES_RAWETH_QP1_STATUS_HW_LOCAL_LENGTH_ERR:
+		return IB_WC_LOC_LEN_ERR;
+	case CQ_RES_RAWETH_QP1_STATUS_LOCAL_PROTECTION_ERR:
+		return IB_WC_LOC_PROT_ERR;
+	case CQ_RES_RAWETH_QP1_STATUS_LOCAL_QP_OPERATION_ERR:
+		return IB_WC_LOC_QP_OP_ERR;
+	case CQ_RES_RAWETH_QP1_STATUS_MEMORY_MGT_OPERATION_ERR:
+		return IB_WC_GENERAL_ERR;
+	case CQ_RES_RAWETH_QP1_STATUS_WORK_REQUEST_FLUSHED_ERR:
+		return IB_WC_WR_FLUSH_ERR;
+	case CQ_RES_RAWETH_QP1_STATUS_HW_FLUSH_ERR:
+		return IB_WC_WR_FLUSH_ERR;
+	default:
+		return IB_WC_GENERAL_ERR;
+	}
+}
+
+static u8 __rc_to_ib_wc_status(u8 qstatus)
+{
+	switch (qstatus) {
+	case CQ_RES_RC_STATUS_OK:
+		return IB_WC_SUCCESS;
+	case CQ_RES_RC_STATUS_LOCAL_ACCESS_ERROR:
+		return IB_WC_LOC_ACCESS_ERR;
+	case CQ_RES_RC_STATUS_LOCAL_LENGTH_ERR:
+		return IB_WC_LOC_LEN_ERR;
+	case CQ_RES_RC_STATUS_LOCAL_PROTECTION_ERR:
+		return IB_WC_LOC_PROT_ERR;
+	case CQ_RES_RC_STATUS_LOCAL_QP_OPERATION_ERR:
+		return IB_WC_LOC_QP_OP_ERR;
+	case CQ_RES_RC_STATUS_MEMORY_MGT_OPERATION_ERR:
+		return IB_WC_GENERAL_ERR;
+	case CQ_RES_RC_STATUS_REMOTE_INVALID_REQUEST_ERR:
+		return IB_WC_REM_INV_REQ_ERR;
+	case CQ_RES_RC_STATUS_WORK_REQUEST_FLUSHED_ERR:
+		return IB_WC_WR_FLUSH_ERR;
+	case CQ_RES_RC_STATUS_HW_FLUSH_ERR:
+		return IB_WC_WR_FLUSH_ERR;
+	default:
+		return IB_WC_GENERAL_ERR;
+	}
+}
+
+static void bnxt_re_process_req_wc(struct ib_wc *wc, struct bnxt_qplib_cqe *cqe)
+{
+	switch (cqe->type) {
+	case BNXT_QPLIB_SWQE_TYPE_SEND:
+		wc->opcode = IB_WC_SEND;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM:
+		wc->opcode = IB_WC_SEND;
+		wc->wc_flags |= IB_WC_WITH_IMM;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV:
+		wc->opcode = IB_WC_SEND;
+		wc->wc_flags |= IB_WC_WITH_INVALIDATE;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE:
+		wc->opcode = IB_WC_RDMA_WRITE;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE_WITH_IMM:
+		wc->opcode = IB_WC_RDMA_WRITE;
+		wc->wc_flags |= IB_WC_WITH_IMM;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_RDMA_READ:
+		wc->opcode = IB_WC_RDMA_READ;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP:
+		wc->opcode = IB_WC_COMP_SWAP;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_ATOMIC_FETCH_AND_ADD:
+		wc->opcode = IB_WC_FETCH_ADD;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_LOCAL_INV:
+		wc->opcode = IB_WC_LOCAL_INV;
+		break;
+	case BNXT_QPLIB_SWQE_TYPE_REG_MR:
+		wc->opcode = IB_WC_REG_MR;
+		break;
+	default:
+		wc->opcode = IB_WC_SEND;
+		break;
+	}
+
+	wc->status = __req_to_ib_wc_status(cqe->status);
+}
+
+static int bnxt_re_check_packet_type(u16 raweth_qp1_flags,
+				     u16 raweth_qp1_flags2)
+{
+	bool is_ipv6 = false, is_ipv4 = false;
+
+	/* raweth_qp1_flags Bit 9-6 indicates itype */
+	if ((raweth_qp1_flags & CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ROCE)
+	    != CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ROCE)
+		return -1;
+
+	if (raweth_qp1_flags2 &
+	    CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_CS_CALC &&
+	    raweth_qp1_flags2 &
+	    CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_L4_CS_CALC) {
+		/* raweth_qp1_flags2 Bit 8 indicates ip_type. 0-v4 1 - v6 */
+		(raweth_qp1_flags2 &
+		 CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_TYPE) ?
+			(is_ipv6 = true) : (is_ipv4 = true);
+		return ((is_ipv6) ?
+			 BNXT_RE_ROCEV2_IPV6_PACKET :
+			 BNXT_RE_ROCEV2_IPV4_PACKET);
+	} else {
+		return BNXT_RE_ROCE_V1_PACKET;
+	}
+}
+
+static int bnxt_re_to_ib_nw_type(int nw_type)
+{
+	u8 nw_hdr_type = 0xFF;
+
+	switch (nw_type) {
+	case BNXT_RE_ROCE_V1_PACKET:
+		nw_hdr_type = RDMA_NETWORK_ROCE_V1;
+		break;
+	case BNXT_RE_ROCEV2_IPV4_PACKET:
+		nw_hdr_type = RDMA_NETWORK_IPV4;
+		break;
+	case BNXT_RE_ROCEV2_IPV6_PACKET:
+		nw_hdr_type = RDMA_NETWORK_IPV6;
+		break;
+	}
+	return nw_hdr_type;
+}
+
+static bool bnxt_re_is_loopback_packet(struct bnxt_re_dev *rdev,
+				       void *rq_hdr_buf)
+{
+	u8 *tmp_buf = NULL;
+	struct ethhdr *eth_hdr;
+	u16 eth_type;
+	bool rc = false;
+
+	tmp_buf = (u8 *)rq_hdr_buf;
+	/*
+	 * If dest mac is not same as I/F mac, this could be a
+	 * loopback address or multicast address, check whether
+	 * it is a loopback packet
+	 */
+	if (!ether_addr_equal(tmp_buf, rdev->netdev->dev_addr)) {
+		tmp_buf += 4;
+		/* Check the  ether type */
+		eth_hdr = (struct ethhdr *)tmp_buf;
+		eth_type = ntohs(eth_hdr->h_proto);
+		switch (eth_type) {
+		case ETH_P_IBOE:
+			rc = true;
+			break;
+		case ETH_P_IP:
+		case ETH_P_IPV6: {
+			u32 len;
+			struct udphdr *udp_hdr;
+
+			len = (eth_type == ETH_P_IP ? sizeof(struct iphdr) :
+						      sizeof(struct ipv6hdr));
+			tmp_buf += sizeof(struct ethhdr) + len;
+			udp_hdr = (struct udphdr *)tmp_buf;
+			if (ntohs(udp_hdr->dest) ==
+				    ROCE_V2_UDP_DPORT)
+				rc = true;
+			break;
+			}
+		default:
+			break;
+		}
+	}
+
+	return rc;
+}
+
+static int bnxt_re_process_raw_qp_pkt_rx(struct bnxt_re_qp *gsi_qp,
+					 struct bnxt_qplib_cqe *cqe)
+{
+	struct bnxt_re_dev *rdev = gsi_qp->rdev;
+	struct bnxt_re_sqp_entries *sqp_entry = NULL;
+	struct bnxt_re_qp *gsi_sqp = rdev->gsi_ctx.gsi_sqp;
+	struct bnxt_re_ah *gsi_sah;
+	struct ib_send_wr *swr;
+	struct ib_ud_wr udwr;
+	struct ib_recv_wr rwr;
+	int pkt_type = 0;
+	u32 tbl_idx;
+	void *rq_hdr_buf;
+	dma_addr_t rq_hdr_buf_map;
+	dma_addr_t shrq_hdr_buf_map;
+	u32 offset = 0;
+	u32 skip_bytes = 0;
+	struct ib_sge s_sge[2];
+	struct ib_sge r_sge[2];
+	int rc;
+
+	memset(&udwr, 0, sizeof(udwr));
+	memset(&rwr, 0, sizeof(rwr));
+	memset(&s_sge, 0, sizeof(s_sge));
+	memset(&r_sge, 0, sizeof(r_sge));
+
+	swr = &udwr.wr;
+	tbl_idx = cqe->wr_id;
+
+	rq_hdr_buf = gsi_qp->qplib_qp.rq_hdr_buf +
+			(tbl_idx * gsi_qp->qplib_qp.rq_hdr_buf_size);
+	rq_hdr_buf_map = bnxt_qplib_get_qp_buf_from_index(&gsi_qp->qplib_qp,
+							  tbl_idx);
+
+	/* Shadow QP header buffer */
+	shrq_hdr_buf_map = bnxt_qplib_get_qp_buf_from_index(&gsi_qp->qplib_qp,
+							    tbl_idx);
+	sqp_entry = &rdev->gsi_ctx.sqp_tbl[tbl_idx];
+
+	/* Store this cqe */
+	memcpy(&sqp_entry->cqe, cqe, sizeof(struct bnxt_qplib_cqe));
+	sqp_entry->qp1_qp = gsi_qp;
+
+	/* Find packet type from the cqe */
+
+	pkt_type = bnxt_re_check_packet_type(cqe->raweth_qp1_flags,
+					     cqe->raweth_qp1_flags2);
+	if (pkt_type < 0) {
+		ibdev_err(&rdev->ibdev, "Invalid packet\n");
+		return -EINVAL;
+	}
+
+	/* Adjust the offset for the user buffer and post in the rq */
+
+	if (pkt_type == BNXT_RE_ROCEV2_IPV4_PACKET)
+		offset = 20;
+
+	/*
+	 * QP1 loopback packet has 4 bytes of internal header before
+	 * ether header. Skip these four bytes.
+	 */
+	if (bnxt_re_is_loopback_packet(rdev, rq_hdr_buf))
+		skip_bytes = 4;
+
+	/* First send SGE . Skip the ether header*/
+	s_sge[0].addr = rq_hdr_buf_map + BNXT_QPLIB_MAX_QP1_RQ_ETH_HDR_SIZE
+			+ skip_bytes;
+	s_sge[0].lkey = 0xFFFFFFFF;
+	s_sge[0].length = offset ? BNXT_QPLIB_MAX_GRH_HDR_SIZE_IPV4 :
+				BNXT_QPLIB_MAX_GRH_HDR_SIZE_IPV6;
+
+	/* Second Send SGE */
+	s_sge[1].addr = s_sge[0].addr + s_sge[0].length +
+			BNXT_QPLIB_MAX_QP1_RQ_BDETH_HDR_SIZE;
+	if (pkt_type != BNXT_RE_ROCE_V1_PACKET)
+		s_sge[1].addr += 8;
+	s_sge[1].lkey = 0xFFFFFFFF;
+	s_sge[1].length = 256;
+
+	/* First recv SGE */
+
+	r_sge[0].addr = shrq_hdr_buf_map;
+	r_sge[0].lkey = 0xFFFFFFFF;
+	r_sge[0].length = 40;
+
+	r_sge[1].addr = sqp_entry->sge.addr + offset;
+	r_sge[1].lkey = sqp_entry->sge.lkey;
+	r_sge[1].length = BNXT_QPLIB_MAX_GRH_HDR_SIZE_IPV6 + 256 - offset;
+
+	/* Create receive work request */
+	rwr.num_sge = 2;
+	rwr.sg_list = r_sge;
+	rwr.wr_id = tbl_idx;
+	rwr.next = NULL;
+
+	rc = bnxt_re_post_recv_shadow_qp(rdev, gsi_sqp, &rwr);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to post Rx buffers to shadow QP");
+		return -ENOMEM;
+	}
+
+	swr->num_sge = 2;
+	swr->sg_list = s_sge;
+	swr->wr_id = tbl_idx;
+	swr->opcode = IB_WR_SEND;
+	swr->next = NULL;
+	gsi_sah = rdev->gsi_ctx.gsi_sah;
+	udwr.ah = &gsi_sah->ib_ah;
+	udwr.remote_qpn = gsi_sqp->qplib_qp.id;
+	udwr.remote_qkey = gsi_sqp->qplib_qp.qkey;
+
+	/* post data received  in the send queue */
+	return bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr);
+}
+
+static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc,
+					  struct bnxt_qplib_cqe *cqe)
+{
+	wc->opcode = IB_WC_RECV;
+	wc->status = __rawqp1_to_ib_wc_status(cqe->status);
+	wc->wc_flags |= IB_WC_GRH;
+}
+
+static bool bnxt_re_check_if_vlan_valid(struct bnxt_re_dev *rdev,
+					u16 vlan_id)
+{
+	/*
+	 * Check if the vlan is configured in the host.  If not configured, it
+	 * can be a transparent VLAN. So dont report the vlan id.
+	 */
+	if (!__vlan_find_dev_deep_rcu(rdev->netdev,
+				      htons(ETH_P_8021Q), vlan_id))
+		return false;
+	return true;
+}
+
+static bool bnxt_re_is_vlan_pkt(struct bnxt_qplib_cqe *orig_cqe,
+				u16 *vid, u8 *sl)
+{
+	bool ret = false;
+	u32 metadata;
+	u16 tpid;
+
+	metadata = orig_cqe->raweth_qp1_metadata;
+	if (orig_cqe->raweth_qp1_flags2 &
+		CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_VLAN) {
+		tpid = ((metadata &
+			 CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_MASK) >>
+			 CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_SFT);
+		if (tpid == ETH_P_8021Q) {
+			*vid = metadata &
+			       CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_VID_MASK;
+			*sl = (metadata &
+			       CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_MASK) >>
+			       CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_SFT;
+			ret = true;
+		}
+	}
+
+	return ret;
+}
+
+static void bnxt_re_process_res_rc_wc(struct ib_wc *wc,
+				      struct bnxt_qplib_cqe *cqe)
+{
+	wc->opcode = IB_WC_RECV;
+	wc->status = __rc_to_ib_wc_status(cqe->status);
+
+	if (cqe->flags & CQ_RES_RC_FLAGS_IMM)
+		wc->wc_flags |= IB_WC_WITH_IMM;
+	if (cqe->flags & CQ_RES_RC_FLAGS_INV)
+		wc->wc_flags |= IB_WC_WITH_INVALIDATE;
+	if ((cqe->flags & (CQ_RES_RC_FLAGS_RDMA | CQ_RES_RC_FLAGS_IMM)) ==
+	    (CQ_RES_RC_FLAGS_RDMA | CQ_RES_RC_FLAGS_IMM))
+		wc->opcode = IB_WC_RECV_RDMA_WITH_IMM;
+}
+
+static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp,
+					     struct ib_wc *wc,
+					     struct bnxt_qplib_cqe *cqe)
+{
+	struct bnxt_re_dev *rdev = gsi_sqp->rdev;
+	struct bnxt_re_qp *gsi_qp = NULL;
+	struct bnxt_qplib_cqe *orig_cqe = NULL;
+	struct bnxt_re_sqp_entries *sqp_entry = NULL;
+	int nw_type;
+	u32 tbl_idx;
+	u16 vlan_id;
+	u8 sl;
+
+	tbl_idx = cqe->wr_id;
+
+	sqp_entry = &rdev->gsi_ctx.sqp_tbl[tbl_idx];
+	gsi_qp = sqp_entry->qp1_qp;
+	orig_cqe = &sqp_entry->cqe;
+
+	wc->wr_id = sqp_entry->wrid;
+	wc->byte_len = orig_cqe->length;
+	wc->qp = &gsi_qp->ib_qp;
+
+	wc->ex.imm_data = orig_cqe->immdata;
+	wc->src_qp = orig_cqe->src_qp;
+	memcpy(wc->smac, orig_cqe->smac, ETH_ALEN);
+	if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) {
+		if (bnxt_re_check_if_vlan_valid(rdev, vlan_id)) {
+			wc->vlan_id = vlan_id;
+			wc->sl = sl;
+			wc->wc_flags |= IB_WC_WITH_VLAN;
+		}
+	}
+	wc->port_num = 1;
+	wc->vendor_err = orig_cqe->status;
+
+	wc->opcode = IB_WC_RECV;
+	wc->status = __rawqp1_to_ib_wc_status(orig_cqe->status);
+	wc->wc_flags |= IB_WC_GRH;
+
+	nw_type = bnxt_re_check_packet_type(orig_cqe->raweth_qp1_flags,
+					    orig_cqe->raweth_qp1_flags2);
+	if (nw_type >= 0) {
+		wc->network_hdr_type = bnxt_re_to_ib_nw_type(nw_type);
+		wc->wc_flags |= IB_WC_WITH_NETWORK_HDR_TYPE;
+	}
+}
+
+static void bnxt_re_process_res_ud_wc(struct bnxt_re_qp *qp,
+				      struct ib_wc *wc,
+				      struct bnxt_qplib_cqe *cqe)
+{
+	struct bnxt_re_dev *rdev;
+	u16 vlan_id = 0;
+	u8 nw_type;
+
+	rdev = qp->rdev;
+	wc->opcode = IB_WC_RECV;
+	wc->status = __rc_to_ib_wc_status(cqe->status);
+
+	if (cqe->flags & CQ_RES_UD_FLAGS_IMM)
+		wc->wc_flags |= IB_WC_WITH_IMM;
+	/* report only on GSI QP for Thor */
+	if (qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_GSI) {
+		wc->wc_flags |= IB_WC_GRH;
+		memcpy(wc->smac, cqe->smac, ETH_ALEN);
+		wc->wc_flags |= IB_WC_WITH_SMAC;
+		if (cqe->flags & CQ_RES_UD_FLAGS_META_FORMAT_VLAN) {
+			vlan_id = (cqe->cfa_meta & 0xFFF);
+		}
+		/* Mark only if vlan_id is non zero */
+		if (vlan_id && bnxt_re_check_if_vlan_valid(rdev, vlan_id)) {
+			wc->vlan_id = vlan_id;
+			wc->wc_flags |= IB_WC_WITH_VLAN;
+		}
+		nw_type = (cqe->flags & CQ_RES_UD_FLAGS_ROCE_IP_VER_MASK) >>
+			   CQ_RES_UD_FLAGS_ROCE_IP_VER_SFT;
+		wc->network_hdr_type = bnxt_re_to_ib_nw_type(nw_type);
+		wc->wc_flags |= IB_WC_WITH_NETWORK_HDR_TYPE;
+	}
+
+}
+
+static int send_phantom_wqe(struct bnxt_re_qp *qp)
+{
+	struct bnxt_qplib_qp *lib_qp = &qp->qplib_qp;
+	unsigned long flags;
+	int rc = 0;
+
+	spin_lock_irqsave(&qp->sq_lock, flags);
+
+	rc = bnxt_re_bind_fence_mw(lib_qp);
+	if (!rc) {
+		lib_qp->sq.phantom_wqe_cnt++;
+		ibdev_dbg(&qp->rdev->ibdev,
+			  "qp %#x sq->prod %#x sw_prod %#x phantom_wqe_cnt %d\n",
+			  lib_qp->id, lib_qp->sq.hwq.prod,
+			  HWQ_CMP(lib_qp->sq.hwq.prod, &lib_qp->sq.hwq),
+			  lib_qp->sq.phantom_wqe_cnt);
+	}
+
+	spin_unlock_irqrestore(&qp->sq_lock, flags);
+	return rc;
+}
+
+int bnxt_re_poll_cq(struct ib_cq *ib_cq, int num_entries, struct ib_wc *wc)
+{
+	struct bnxt_re_cq *cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
+	struct bnxt_re_qp *qp, *sh_qp;
+	struct bnxt_qplib_cqe *cqe;
+	int i, ncqe, budget;
+	struct bnxt_qplib_q *sq;
+	struct bnxt_qplib_qp *lib_qp;
+	u32 tbl_idx;
+	struct bnxt_re_sqp_entries *sqp_entry = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cq->cq_lock, flags);
+	budget = min_t(u32, num_entries, cq->max_cql);
+	num_entries = budget;
+	if (!cq->cql) {
+		ibdev_err(&cq->rdev->ibdev, "POLL CQ : no CQL to use");
+		goto exit;
+	}
+	cqe = &cq->cql[0];
+	while (budget) {
+		lib_qp = NULL;
+		ncqe = bnxt_qplib_poll_cq(&cq->qplib_cq, cqe, budget, &lib_qp);
+		if (lib_qp) {
+			sq = &lib_qp->sq;
+			if (sq->send_phantom) {
+				qp = container_of(lib_qp,
+						  struct bnxt_re_qp, qplib_qp);
+				if (send_phantom_wqe(qp) == -ENOMEM)
+					ibdev_err(&cq->rdev->ibdev,
+						  "Phantom failed! Scheduled to send again\n");
+				else
+					sq->send_phantom = false;
+			}
+		}
+		if (ncqe < budget)
+			ncqe += bnxt_qplib_process_flush_list(&cq->qplib_cq,
+							      cqe + ncqe,
+							      budget - ncqe);
+
+		if (!ncqe)
+			break;
+
+		for (i = 0; i < ncqe; i++, cqe++) {
+			/* Transcribe each qplib_wqe back to ib_wc */
+			memset(wc, 0, sizeof(*wc));
+
+			wc->wr_id = cqe->wr_id;
+			wc->byte_len = cqe->length;
+			qp = container_of
+				((struct bnxt_qplib_qp *)
+				 (unsigned long)(cqe->qp_handle),
+				 struct bnxt_re_qp, qplib_qp);
+			wc->qp = &qp->ib_qp;
+			wc->ex.imm_data = cqe->immdata;
+			wc->src_qp = cqe->src_qp;
+			memcpy(wc->smac, cqe->smac, ETH_ALEN);
+			wc->port_num = 1;
+			wc->vendor_err = cqe->status;
+
+			switch (cqe->opcode) {
+			case CQ_BASE_CQE_TYPE_REQ:
+				sh_qp = qp->rdev->gsi_ctx.gsi_sqp;
+				if (sh_qp &&
+				    qp->qplib_qp.id == sh_qp->qplib_qp.id) {
+					/* Handle this completion with
+					 * the stored completion
+					 */
+					memset(wc, 0, sizeof(*wc));
+					continue;
+				}
+				bnxt_re_process_req_wc(wc, cqe);
+				break;
+			case CQ_BASE_CQE_TYPE_RES_RAWETH_QP1:
+				if (!cqe->status) {
+					int rc = 0;
+
+					rc = bnxt_re_process_raw_qp_pkt_rx
+								(qp, cqe);
+					if (!rc) {
+						memset(wc, 0, sizeof(*wc));
+						continue;
+					}
+					cqe->status = -1;
+				}
+				/* Errors need not be looped back.
+				 * But change the wr_id to the one
+				 * stored in the table
+				 */
+				tbl_idx = cqe->wr_id;
+				sqp_entry = &cq->rdev->gsi_ctx.sqp_tbl[tbl_idx];
+				wc->wr_id = sqp_entry->wrid;
+				bnxt_re_process_res_rawqp1_wc(wc, cqe);
+				break;
+			case CQ_BASE_CQE_TYPE_RES_RC:
+				bnxt_re_process_res_rc_wc(wc, cqe);
+				break;
+			case CQ_BASE_CQE_TYPE_RES_UD:
+				sh_qp = qp->rdev->gsi_ctx.gsi_sqp;
+				if (sh_qp &&
+				    qp->qplib_qp.id == sh_qp->qplib_qp.id) {
+					/* Handle this completion with
+					 * the stored completion
+					 */
+					if (cqe->status) {
+						continue;
+					} else {
+						bnxt_re_process_res_shadow_qp_wc
+								(qp, wc, cqe);
+						break;
+					}
+				}
+				bnxt_re_process_res_ud_wc(qp, wc, cqe);
+				break;
+			default:
+				ibdev_err(&cq->rdev->ibdev,
+					  "POLL CQ : type 0x%x not handled",
+					  cqe->opcode);
+				continue;
+			}
+			wc++;
+			budget--;
+		}
+	}
+exit:
+	spin_unlock_irqrestore(&cq->cq_lock, flags);
+	return num_entries - budget;
+}
+
+int bnxt_re_req_notify_cq(struct ib_cq *ib_cq,
+			  enum ib_cq_notify_flags ib_cqn_flags)
+{
+	struct bnxt_re_cq *cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
+	int type = 0, rc = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cq->cq_lock, flags);
+	/* Trigger on the very next completion */
+	if (ib_cqn_flags & IB_CQ_NEXT_COMP)
+		type = DBC_DBC_TYPE_CQ_ARMALL;
+	/* Trigger on the next solicited completion */
+	else if (ib_cqn_flags & IB_CQ_SOLICITED)
+		type = DBC_DBC_TYPE_CQ_ARMSE;
+
+	/* Poll to see if there are missed events */
+	if ((ib_cqn_flags & IB_CQ_REPORT_MISSED_EVENTS) &&
+	    !(bnxt_qplib_is_cq_empty(&cq->qplib_cq))) {
+		rc = 1;
+		goto exit;
+	}
+	bnxt_qplib_req_notify_cq(&cq->qplib_cq, type);
+
+exit:
+	spin_unlock_irqrestore(&cq->cq_lock, flags);
+	return rc;
+}
+
+/* Memory Regions */
+struct ib_mr *bnxt_re_get_dma_mr(struct ib_pd *ib_pd, int mr_access_flags)
+{
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct bnxt_re_mr *mr;
+	int rc;
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	mr->rdev = rdev;
+	mr->qplib_mr.pd = &pd->qplib_pd;
+	mr->qplib_mr.flags = __from_ib_access_flags(mr_access_flags);
+	mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR;
+
+	/* Allocate and register 0 as the address */
+	rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr);
+	if (rc)
+		goto fail;
+
+	mr->qplib_mr.hwq.level = PBL_LVL_MAX;
+	mr->qplib_mr.total_size = -1; /* Infinte length */
+	rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, NULL, 0,
+			       PAGE_SIZE);
+	if (rc)
+		goto fail_mr;
+
+	mr->ib_mr.lkey = mr->qplib_mr.lkey;
+	if (mr_access_flags & (IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ |
+			       IB_ACCESS_REMOTE_ATOMIC))
+		mr->ib_mr.rkey = mr->ib_mr.lkey;
+	atomic_inc(&rdev->mr_count);
+
+	return &mr->ib_mr;
+
+fail_mr:
+	bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+fail:
+	kfree(mr);
+	return ERR_PTR(rc);
+}
+
+int bnxt_re_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
+{
+	struct bnxt_re_mr *mr = container_of(ib_mr, struct bnxt_re_mr, ib_mr);
+	struct bnxt_re_dev *rdev = mr->rdev;
+	int rc;
+
+	rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Dereg MR failed: %#x\n", rc);
+		return rc;
+	}
+
+	if (mr->pages) {
+		rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
+							&mr->qplib_frpl);
+		kfree(mr->pages);
+		mr->npages = 0;
+		mr->pages = NULL;
+	}
+	ib_umem_release(mr->ib_umem);
+
+	kfree(mr);
+	atomic_dec(&rdev->mr_count);
+	return rc;
+}
+
+static int bnxt_re_set_page(struct ib_mr *ib_mr, u64 addr)
+{
+	struct bnxt_re_mr *mr = container_of(ib_mr, struct bnxt_re_mr, ib_mr);
+
+	if (unlikely(mr->npages == mr->qplib_frpl.max_pg_ptrs))
+		return -ENOMEM;
+
+	mr->pages[mr->npages++] = addr;
+	return 0;
+}
+
+int bnxt_re_map_mr_sg(struct ib_mr *ib_mr, struct scatterlist *sg, int sg_nents,
+		      unsigned int *sg_offset)
+{
+	struct bnxt_re_mr *mr = container_of(ib_mr, struct bnxt_re_mr, ib_mr);
+
+	mr->npages = 0;
+	return ib_sg_to_pages(ib_mr, sg, sg_nents, sg_offset, bnxt_re_set_page);
+}
+
+struct ib_mr *bnxt_re_alloc_mr(struct ib_pd *ib_pd, enum ib_mr_type type,
+			       u32 max_num_sg)
+{
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct bnxt_re_mr *mr = NULL;
+	int rc;
+
+	if (type != IB_MR_TYPE_MEM_REG) {
+		ibdev_dbg(&rdev->ibdev, "MR type 0x%x not supported", type);
+		return ERR_PTR(-EINVAL);
+	}
+	if (max_num_sg > MAX_PBL_LVL_1_PGS)
+		return ERR_PTR(-EINVAL);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	mr->rdev = rdev;
+	mr->qplib_mr.pd = &pd->qplib_pd;
+	mr->qplib_mr.flags = BNXT_QPLIB_FR_PMR;
+	mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR;
+
+	rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr);
+	if (rc)
+		goto bail;
+
+	mr->ib_mr.lkey = mr->qplib_mr.lkey;
+	mr->ib_mr.rkey = mr->ib_mr.lkey;
+
+	mr->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL);
+	if (!mr->pages) {
+		rc = -ENOMEM;
+		goto fail;
+	}
+	rc = bnxt_qplib_alloc_fast_reg_page_list(&rdev->qplib_res,
+						 &mr->qplib_frpl, max_num_sg);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to allocate HW FR page list");
+		goto fail_mr;
+	}
+
+	atomic_inc(&rdev->mr_count);
+	return &mr->ib_mr;
+
+fail_mr:
+	kfree(mr->pages);
+fail:
+	bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+bail:
+	kfree(mr);
+	return ERR_PTR(rc);
+}
+
+struct ib_mw *bnxt_re_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
+			       struct ib_udata *udata)
+{
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct bnxt_re_mw *mw;
+	int rc;
+
+	mw = kzalloc(sizeof(*mw), GFP_KERNEL);
+	if (!mw)
+		return ERR_PTR(-ENOMEM);
+	mw->rdev = rdev;
+	mw->qplib_mw.pd = &pd->qplib_pd;
+
+	mw->qplib_mw.type = (type == IB_MW_TYPE_1 ?
+			       CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE1 :
+			       CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B);
+	rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mw->qplib_mw);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Allocate MW failed!");
+		goto fail;
+	}
+	mw->ib_mw.rkey = mw->qplib_mw.rkey;
+
+	atomic_inc(&rdev->mw_count);
+	return &mw->ib_mw;
+
+fail:
+	kfree(mw);
+	return ERR_PTR(rc);
+}
+
+int bnxt_re_dealloc_mw(struct ib_mw *ib_mw)
+{
+	struct bnxt_re_mw *mw = container_of(ib_mw, struct bnxt_re_mw, ib_mw);
+	struct bnxt_re_dev *rdev = mw->rdev;
+	int rc;
+
+	rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &mw->qplib_mw);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Free MW failed: %#x\n", rc);
+		return rc;
+	}
+
+	kfree(mw);
+	atomic_dec(&rdev->mw_count);
+	return rc;
+}
+
+/* uverbs */
+struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length,
+				  u64 virt_addr, int mr_access_flags,
+				  struct ib_udata *udata)
+{
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_dev *rdev = pd->rdev;
+	struct bnxt_re_mr *mr;
+	struct ib_umem *umem;
+	unsigned long page_size;
+	int umem_pgs, rc;
+
+	if (length > BNXT_RE_MAX_MR_SIZE) {
+		ibdev_err(&rdev->ibdev, "MR Size: %lld > Max supported:%lld\n",
+			  length, BNXT_RE_MAX_MR_SIZE);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	mr->rdev = rdev;
+	mr->qplib_mr.pd = &pd->qplib_pd;
+	mr->qplib_mr.flags = __from_ib_access_flags(mr_access_flags);
+	mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_MR;
+
+	rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to allocate MR");
+		goto free_mr;
+	}
+	/* The fixed portion of the rkey is the same as the lkey */
+	mr->ib_mr.rkey = mr->qplib_mr.rkey;
+
+	umem = ib_umem_get(&rdev->ibdev, start, length, mr_access_flags);
+	if (IS_ERR(umem)) {
+		ibdev_err(&rdev->ibdev, "Failed to get umem");
+		rc = -EFAULT;
+		goto free_mrw;
+	}
+	mr->ib_umem = umem;
+
+	mr->qplib_mr.va = virt_addr;
+	page_size = ib_umem_find_best_pgsz(
+		umem, BNXT_RE_PAGE_SIZE_SUPPORTED, virt_addr);
+	if (!page_size) {
+		ibdev_err(&rdev->ibdev, "umem page size unsupported!");
+		rc = -EFAULT;
+		goto free_umem;
+	}
+	mr->qplib_mr.total_size = length;
+
+	umem_pgs = ib_umem_num_dma_blocks(umem, page_size);
+	rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, umem,
+			       umem_pgs, page_size);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to register user MR");
+		goto free_umem;
+	}
+
+	mr->ib_mr.lkey = mr->qplib_mr.lkey;
+	mr->ib_mr.rkey = mr->qplib_mr.lkey;
+	atomic_inc(&rdev->mr_count);
+
+	return &mr->ib_mr;
+free_umem:
+	ib_umem_release(umem);
+free_mrw:
+	bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+free_mr:
+	kfree(mr);
+	return ERR_PTR(rc);
+}
+
+int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
+{
+	struct ib_device *ibdev = ctx->device;
+	struct bnxt_re_ucontext *uctx =
+		container_of(ctx, struct bnxt_re_ucontext, ib_uctx);
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_re_uctx_resp resp = {};
+	u32 chip_met_rev_num = 0;
+	int rc;
+
+	ibdev_dbg(ibdev, "ABI version requested %u", ibdev->ops.uverbs_abi_ver);
+
+	if (ibdev->ops.uverbs_abi_ver != BNXT_RE_ABI_VERSION) {
+		ibdev_dbg(ibdev, " is different from the device %d ",
+			  BNXT_RE_ABI_VERSION);
+		return -EPERM;
+	}
+
+	uctx->rdev = rdev;
+
+	uctx->shpg = (void *)__get_free_page(GFP_KERNEL);
+	if (!uctx->shpg) {
+		rc = -ENOMEM;
+		goto fail;
+	}
+	spin_lock_init(&uctx->sh_lock);
+
+	resp.comp_mask = BNXT_RE_UCNTX_CMASK_HAVE_CCTX;
+	chip_met_rev_num = rdev->chip_ctx->chip_num;
+	chip_met_rev_num |= ((u32)rdev->chip_ctx->chip_rev & 0xFF) <<
+			     BNXT_RE_CHIP_ID0_CHIP_REV_SFT;
+	chip_met_rev_num |= ((u32)rdev->chip_ctx->chip_metal & 0xFF) <<
+			     BNXT_RE_CHIP_ID0_CHIP_MET_SFT;
+	resp.chip_id0 = chip_met_rev_num;
+	/*Temp, Use xa_alloc instead */
+	resp.dev_id = rdev->en_dev->pdev->devfn;
+	resp.max_qp = rdev->qplib_ctx.qpc_count;
+	resp.pg_size = PAGE_SIZE;
+	resp.cqe_sz = sizeof(struct cq_base);
+	resp.max_cqd = dev_attr->max_cq_wqes;
+
+	resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE;
+	resp.mode = rdev->chip_ctx->modes.wqe_mode;
+
+	rc = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
+	if (rc) {
+		ibdev_err(ibdev, "Failed to copy user context");
+		rc = -EFAULT;
+		goto cfail;
+	}
+
+	return 0;
+cfail:
+	free_page((unsigned long)uctx->shpg);
+	uctx->shpg = NULL;
+fail:
+	return rc;
+}
+
+void bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
+{
+	struct bnxt_re_ucontext *uctx = container_of(ib_uctx,
+						   struct bnxt_re_ucontext,
+						   ib_uctx);
+
+	struct bnxt_re_dev *rdev = uctx->rdev;
+
+	if (uctx->shpg)
+		free_page((unsigned long)uctx->shpg);
+
+	if (uctx->dpi.dbr) {
+		/* Free DPI only if this is the first PD allocated by the
+		 * application and mark the context dpi as NULL
+		 */
+		bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
+				       &rdev->qplib_res.dpi_tbl, &uctx->dpi);
+		uctx->dpi.dbr = NULL;
+	}
+}
+
+/* Helper function to mmap the virtual memory from user app */
+int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
+{
+	struct bnxt_re_ucontext *uctx = container_of(ib_uctx,
+						   struct bnxt_re_ucontext,
+						   ib_uctx);
+	struct bnxt_re_dev *rdev = uctx->rdev;
+	u64 pfn;
+
+	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+		return -EINVAL;
+
+	if (vma->vm_pgoff) {
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+		if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				       PAGE_SIZE, vma->vm_page_prot)) {
+			ibdev_err(&rdev->ibdev, "Failed to map DPI");
+			return -EAGAIN;
+		}
+	} else {
+		pfn = virt_to_phys(uctx->shpg) >> PAGE_SHIFT;
+		if (remap_pfn_range(vma, vma->vm_start,
+				    pfn, PAGE_SIZE, vma->vm_page_prot)) {
+			ibdev_err(&rdev->ibdev, "Failed to map shared page");
+			return -EAGAIN;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
new file mode 100644
index 000000000..94326267f
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -0,0 +1,216 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: IB Verbs interpreter (header)
+ */
+
+#ifndef __BNXT_RE_IB_VERBS_H__
+#define __BNXT_RE_IB_VERBS_H__
+
+struct bnxt_re_gid_ctx {
+	u32			idx;
+	u32			refcnt;
+};
+
+#define BNXT_RE_FENCE_BYTES	64
+struct bnxt_re_fence_data {
+	u32 size;
+	u8 va[BNXT_RE_FENCE_BYTES];
+	dma_addr_t dma_addr;
+	struct bnxt_re_mr *mr;
+	struct ib_mw *mw;
+	struct bnxt_qplib_swqe bind_wqe;
+	u32 bind_rkey;
+};
+
+struct bnxt_re_pd {
+	struct ib_pd            ib_pd;
+	struct bnxt_re_dev	*rdev;
+	struct bnxt_qplib_pd	qplib_pd;
+	struct bnxt_re_fence_data fence;
+};
+
+struct bnxt_re_ah {
+	struct ib_ah		ib_ah;
+	struct bnxt_re_dev	*rdev;
+	struct bnxt_qplib_ah	qplib_ah;
+};
+
+struct bnxt_re_srq {
+	struct ib_srq		ib_srq;
+	struct bnxt_re_dev	*rdev;
+	u32			srq_limit;
+	struct bnxt_qplib_srq	qplib_srq;
+	struct ib_umem		*umem;
+	spinlock_t		lock;		/* protect srq */
+};
+
+struct bnxt_re_qp {
+	struct ib_qp		ib_qp;
+	struct list_head	list;
+	struct bnxt_re_dev	*rdev;
+	spinlock_t		sq_lock;	/* protect sq */
+	spinlock_t		rq_lock;	/* protect rq */
+	struct bnxt_qplib_qp	qplib_qp;
+	struct ib_umem		*sumem;
+	struct ib_umem		*rumem;
+	/* QP1 */
+	u32			send_psn;
+	struct ib_ud_header	qp1_hdr;
+	struct bnxt_re_cq	*scq;
+	struct bnxt_re_cq	*rcq;
+};
+
+struct bnxt_re_cq {
+	struct ib_cq		ib_cq;
+	struct bnxt_re_dev	*rdev;
+	spinlock_t              cq_lock;	/* protect cq */
+	u16			cq_count;
+	u16			cq_period;
+	struct bnxt_qplib_cq	qplib_cq;
+	struct bnxt_qplib_cqe	*cql;
+#define MAX_CQL_PER_POLL	1024
+	u32			max_cql;
+	struct ib_umem		*umem;
+};
+
+struct bnxt_re_mr {
+	struct bnxt_re_dev	*rdev;
+	struct ib_mr		ib_mr;
+	struct ib_umem		*ib_umem;
+	struct bnxt_qplib_mrw	qplib_mr;
+	u32			npages;
+	u64			*pages;
+	struct bnxt_qplib_frpl	qplib_frpl;
+};
+
+struct bnxt_re_frpl {
+	struct bnxt_re_dev		*rdev;
+	struct bnxt_qplib_frpl		qplib_frpl;
+	u64				*page_list;
+};
+
+struct bnxt_re_mw {
+	struct bnxt_re_dev	*rdev;
+	struct ib_mw		ib_mw;
+	struct bnxt_qplib_mrw	qplib_mw;
+};
+
+struct bnxt_re_ucontext {
+	struct ib_ucontext      ib_uctx;
+	struct bnxt_re_dev	*rdev;
+	struct bnxt_qplib_dpi	dpi;
+	void			*shpg;
+	spinlock_t		sh_lock;	/* protect shpg */
+};
+
+static inline u16 bnxt_re_get_swqe_size(int nsge)
+{
+	return sizeof(struct sq_send_hdr) + nsge * sizeof(struct sq_sge);
+}
+
+static inline u16 bnxt_re_get_rwqe_size(int nsge)
+{
+	return sizeof(struct rq_wqe_hdr) + (nsge * sizeof(struct sq_sge));
+}
+
+int bnxt_re_query_device(struct ib_device *ibdev,
+			 struct ib_device_attr *ib_attr,
+			 struct ib_udata *udata);
+int bnxt_re_query_port(struct ib_device *ibdev, u32 port_num,
+		       struct ib_port_attr *port_attr);
+int bnxt_re_get_port_immutable(struct ib_device *ibdev, u32 port_num,
+			       struct ib_port_immutable *immutable);
+void bnxt_re_query_fw_str(struct ib_device *ibdev, char *str);
+int bnxt_re_query_pkey(struct ib_device *ibdev, u32 port_num,
+		       u16 index, u16 *pkey);
+int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context);
+int bnxt_re_add_gid(const struct ib_gid_attr *attr, void **context);
+int bnxt_re_query_gid(struct ib_device *ibdev, u32 port_num,
+		      int index, union ib_gid *gid);
+enum rdma_link_layer bnxt_re_get_link_layer(struct ib_device *ibdev,
+					    u32 port_num);
+int bnxt_re_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int bnxt_re_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int bnxt_re_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
+		      struct ib_udata *udata);
+int bnxt_re_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
+int bnxt_re_destroy_ah(struct ib_ah *ah, u32 flags);
+int bnxt_re_create_srq(struct ib_srq *srq,
+		       struct ib_srq_init_attr *srq_init_attr,
+		       struct ib_udata *udata);
+int bnxt_re_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr,
+		       enum ib_srq_attr_mask srq_attr_mask,
+		       struct ib_udata *udata);
+int bnxt_re_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
+int bnxt_re_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
+int bnxt_re_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr,
+			  const struct ib_recv_wr **bad_recv_wr);
+int bnxt_re_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr,
+		      struct ib_udata *udata);
+int bnxt_re_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
+		      int qp_attr_mask, struct ib_udata *udata);
+int bnxt_re_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
+		     int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
+int bnxt_re_destroy_qp(struct ib_qp *qp, struct ib_udata *udata);
+int bnxt_re_post_send(struct ib_qp *qp, const struct ib_send_wr *send_wr,
+		      const struct ib_send_wr **bad_send_wr);
+int bnxt_re_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr,
+		      const struct ib_recv_wr **bad_recv_wr);
+int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+		      struct ib_udata *udata);
+int bnxt_re_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int bnxt_re_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc);
+int bnxt_re_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
+struct ib_mr *bnxt_re_get_dma_mr(struct ib_pd *pd, int mr_access_flags);
+
+int bnxt_re_map_mr_sg(struct ib_mr *ib_mr, struct scatterlist *sg, int sg_nents,
+		      unsigned int *sg_offset);
+struct ib_mr *bnxt_re_alloc_mr(struct ib_pd *ib_pd, enum ib_mr_type mr_type,
+			       u32 max_num_sg);
+int bnxt_re_dereg_mr(struct ib_mr *mr, struct ib_udata *udata);
+struct ib_mw *bnxt_re_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
+			       struct ib_udata *udata);
+int bnxt_re_dealloc_mw(struct ib_mw *mw);
+struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
+				  u64 virt_addr, int mr_access_flags,
+				  struct ib_udata *udata);
+int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata);
+void bnxt_re_dealloc_ucontext(struct ib_ucontext *context);
+int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
+
+unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp);
+void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags);
+#endif /* __BNXT_RE_IB_VERBS_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
new file mode 100644
index 000000000..43d396a7d
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -0,0 +1,1799 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Main component of the bnxt_re driver
+ */
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <net/dcbnl.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#include <linux/if_ether.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_umem.h>
+#include <rdma/ib_addr.h>
+
+#include "bnxt_ulp.h"
+#include "roce_hsi.h"
+#include "qplib_res.h"
+#include "qplib_sp.h"
+#include "qplib_fp.h"
+#include "qplib_rcfw.h"
+#include "bnxt_re.h"
+#include "ib_verbs.h"
+#include <rdma/bnxt_re-abi.h>
+#include "bnxt.h"
+#include "hw_counters.h"
+
+static char version[] =
+		BNXT_RE_DESC "\n";
+
+MODULE_AUTHOR("Eddie Wai <eddie.wai@broadcom.com>");
+MODULE_DESCRIPTION(BNXT_RE_DESC);
+MODULE_LICENSE("Dual BSD/GPL");
+
+/* globals */
+static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list);
+/* Mutex to protect the list of bnxt_re devices added */
+static DEFINE_MUTEX(bnxt_re_dev_lock);
+static struct workqueue_struct *bnxt_re_wq;
+static void bnxt_re_remove_device(struct bnxt_re_dev *rdev);
+static void bnxt_re_dealloc_driver(struct ib_device *ib_dev);
+static void bnxt_re_stop_irq(void *handle);
+static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev);
+
+static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
+{
+	struct bnxt_qplib_chip_ctx *cctx;
+
+	cctx = rdev->chip_ctx;
+	cctx->modes.wqe_mode = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
+			       mode : BNXT_QPLIB_WQE_MODE_STATIC;
+}
+
+static void bnxt_re_destroy_chip_ctx(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_qplib_chip_ctx *chip_ctx;
+
+	if (!rdev->chip_ctx)
+		return;
+	chip_ctx = rdev->chip_ctx;
+	rdev->chip_ctx = NULL;
+	rdev->rcfw.res = NULL;
+	rdev->qplib_res.cctx = NULL;
+	rdev->qplib_res.pdev = NULL;
+	rdev->qplib_res.netdev = NULL;
+	kfree(chip_ctx);
+}
+
+static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode)
+{
+	struct bnxt_qplib_chip_ctx *chip_ctx;
+	struct bnxt_en_dev *en_dev;
+	struct bnxt *bp;
+
+	en_dev = rdev->en_dev;
+	bp = netdev_priv(en_dev->net);
+
+	chip_ctx = kzalloc(sizeof(*chip_ctx), GFP_KERNEL);
+	if (!chip_ctx)
+		return -ENOMEM;
+	chip_ctx->chip_num = bp->chip_num;
+	chip_ctx->hw_stats_size = bp->hw_ring_stats_size;
+
+	rdev->chip_ctx = chip_ctx;
+	/* rest members to follow eventually */
+
+	rdev->qplib_res.cctx = rdev->chip_ctx;
+	rdev->rcfw.res = &rdev->qplib_res;
+	rdev->qplib_res.dattr = &rdev->dev_attr;
+	rdev->qplib_res.is_vf = BNXT_VF(bp);
+
+	bnxt_re_set_drv_mode(rdev, wqe_mode);
+	if (bnxt_qplib_determine_atomics(en_dev->pdev))
+		ibdev_info(&rdev->ibdev,
+			   "platform doesn't support global atomics.");
+	return 0;
+}
+
+/* SR-IOV helper functions */
+
+static void bnxt_re_get_sriov_func_type(struct bnxt_re_dev *rdev)
+{
+	struct bnxt *bp;
+
+	bp = netdev_priv(rdev->en_dev->net);
+	if (BNXT_VF(bp))
+		rdev->is_virtfn = 1;
+}
+
+/* Set the maximum number of each resource that the driver actually wants
+ * to allocate. This may be up to the maximum number the firmware has
+ * reserved for the function. The driver may choose to allocate fewer
+ * resources than the firmware maximum.
+ */
+static void bnxt_re_limit_pf_res(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_qplib_dev_attr *attr;
+	struct bnxt_qplib_ctx *ctx;
+	int i;
+
+	attr = &rdev->dev_attr;
+	ctx = &rdev->qplib_ctx;
+
+	ctx->qpc_count = min_t(u32, BNXT_RE_MAX_QPC_COUNT,
+			       attr->max_qp);
+	ctx->mrw_count = BNXT_RE_MAX_MRW_COUNT_256K;
+	/* Use max_mr from fw since max_mrw does not get set */
+	ctx->mrw_count = min_t(u32, ctx->mrw_count, attr->max_mr);
+	ctx->srqc_count = min_t(u32, BNXT_RE_MAX_SRQC_COUNT,
+				attr->max_srq);
+	ctx->cq_count = min_t(u32, BNXT_RE_MAX_CQ_COUNT, attr->max_cq);
+	if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx))
+		for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
+			rdev->qplib_ctx.tqm_ctx.qcount[i] =
+			rdev->dev_attr.tqm_alloc_reqs[i];
+}
+
+static void bnxt_re_limit_vf_res(struct bnxt_qplib_ctx *qplib_ctx, u32 num_vf)
+{
+	struct bnxt_qplib_vf_res *vf_res;
+	u32 mrws = 0;
+	u32 vf_pct;
+	u32 nvfs;
+
+	vf_res = &qplib_ctx->vf_res;
+	/*
+	 * Reserve a set of resources for the PF. Divide the remaining
+	 * resources among the VFs
+	 */
+	vf_pct = 100 - BNXT_RE_PCT_RSVD_FOR_PF;
+	nvfs = num_vf;
+	num_vf = 100 * num_vf;
+	vf_res->max_qp_per_vf = (qplib_ctx->qpc_count * vf_pct) / num_vf;
+	vf_res->max_srq_per_vf = (qplib_ctx->srqc_count * vf_pct) / num_vf;
+	vf_res->max_cq_per_vf = (qplib_ctx->cq_count * vf_pct) / num_vf;
+	/*
+	 * The driver allows many more MRs than other resources. If the
+	 * firmware does also, then reserve a fixed amount for the PF and
+	 * divide the rest among VFs. VFs may use many MRs for NFS
+	 * mounts, ISER, NVME applications, etc. If the firmware severely
+	 * restricts the number of MRs, then let PF have half and divide
+	 * the rest among VFs, as for the other resource types.
+	 */
+	if (qplib_ctx->mrw_count < BNXT_RE_MAX_MRW_COUNT_64K) {
+		mrws = qplib_ctx->mrw_count * vf_pct;
+		nvfs = num_vf;
+	} else {
+		mrws = qplib_ctx->mrw_count - BNXT_RE_RESVD_MR_FOR_PF;
+	}
+	vf_res->max_mrw_per_vf = (mrws / nvfs);
+	vf_res->max_gid_per_vf = BNXT_RE_MAX_GID_PER_VF;
+}
+
+static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
+{
+	u32 num_vfs;
+
+	memset(&rdev->qplib_ctx.vf_res, 0, sizeof(struct bnxt_qplib_vf_res));
+	bnxt_re_limit_pf_res(rdev);
+
+	num_vfs =  bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
+			BNXT_RE_GEN_P5_MAX_VF : rdev->num_vfs;
+	if (num_vfs)
+		bnxt_re_limit_vf_res(&rdev->qplib_ctx, num_vfs);
+}
+
+/* for handling bnxt_en callbacks later */
+static void bnxt_re_stop(void *p)
+{
+	struct bnxt_re_dev *rdev = p;
+	struct bnxt *bp;
+
+	if (!rdev)
+		return;
+	ASSERT_RTNL();
+
+	/* L2 driver invokes this callback during device error/crash or device
+	 * reset. Current RoCE driver doesn't recover the device in case of
+	 * error. Handle the error by dispatching fatal events to all qps
+	 * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as
+	 * L2 driver want to modify the MSIx table.
+	 */
+	bp = netdev_priv(rdev->netdev);
+
+	ibdev_info(&rdev->ibdev, "Handle device stop call from L2 driver");
+	/* Check the current device state from L2 structure and move the
+	 * device to detached state if FW_FATAL_COND is set.
+	 * This prevents more commands to HW during clean-up,
+	 * in case the device is already in error.
+	 */
+	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+		set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags);
+
+	bnxt_re_dev_stop(rdev);
+	bnxt_re_stop_irq(rdev);
+	/* Move the device states to detached and  avoid sending any more
+	 * commands to HW
+	 */
+	set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags);
+	set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags);
+}
+
+static void bnxt_re_start(void *p)
+{
+}
+
+static void bnxt_re_sriov_config(void *p, int num_vfs)
+{
+	struct bnxt_re_dev *rdev = p;
+
+	if (!rdev)
+		return;
+
+	if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
+		return;
+	rdev->num_vfs = num_vfs;
+	if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) {
+		bnxt_re_set_resource_limits(rdev);
+		bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw,
+					      &rdev->qplib_ctx);
+	}
+}
+
+static void bnxt_re_shutdown(void *p)
+{
+	struct bnxt_re_dev *rdev = p;
+
+	if (!rdev)
+		return;
+	ASSERT_RTNL();
+	/* Release the MSIx vectors before queuing unregister */
+	bnxt_re_stop_irq(rdev);
+	ib_unregister_device_queued(&rdev->ibdev);
+}
+
+static void bnxt_re_stop_irq(void *handle)
+{
+	struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+	struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw;
+	struct bnxt_qplib_nq *nq;
+	int indx;
+
+	for (indx = BNXT_RE_NQ_IDX; indx < rdev->num_msix; indx++) {
+		nq = &rdev->nq[indx - 1];
+		bnxt_qplib_nq_stop_irq(nq, false);
+	}
+
+	bnxt_qplib_rcfw_stop_irq(rcfw, false);
+}
+
+static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
+{
+	struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+	struct bnxt_msix_entry *msix_ent = rdev->msix_entries;
+	struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw;
+	struct bnxt_qplib_nq *nq;
+	int indx, rc;
+
+	if (!ent) {
+		/* Not setting the f/w timeout bit in rcfw.
+		 * During the driver unload the first command
+		 * to f/w will timeout and that will set the
+		 * timeout bit.
+		 */
+		ibdev_err(&rdev->ibdev, "Failed to re-start IRQs\n");
+		return;
+	}
+
+	/* Vectors may change after restart, so update with new vectors
+	 * in device sctructure.
+	 */
+	for (indx = 0; indx < rdev->num_msix; indx++)
+		rdev->msix_entries[indx].vector = ent[indx].vector;
+
+	rc = bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector,
+				       false);
+	if (rc) {
+		ibdev_warn(&rdev->ibdev, "Failed to reinit CREQ\n");
+		return;
+	}
+	for (indx = BNXT_RE_NQ_IDX ; indx < rdev->num_msix; indx++) {
+		nq = &rdev->nq[indx - 1];
+		rc = bnxt_qplib_nq_start_irq(nq, indx - 1,
+					     msix_ent[indx].vector, false);
+		if (rc) {
+			ibdev_warn(&rdev->ibdev, "Failed to reinit NQ index %d\n",
+				   indx - 1);
+			return;
+		}
+	}
+}
+
+static struct bnxt_ulp_ops bnxt_re_ulp_ops = {
+	.ulp_async_notifier = NULL,
+	.ulp_stop = bnxt_re_stop,
+	.ulp_start = bnxt_re_start,
+	.ulp_sriov_config = bnxt_re_sriov_config,
+	.ulp_shutdown = bnxt_re_shutdown,
+	.ulp_irq_stop = bnxt_re_stop_irq,
+	.ulp_irq_restart = bnxt_re_start_irq
+};
+
+/* RoCE -> Net driver */
+
+/* Driver registration routines used to let the networking driver (bnxt_en)
+ * to know that the RoCE driver is now installed
+ */
+static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_en_dev *en_dev;
+	int rc;
+
+	if (!rdev)
+		return -EINVAL;
+
+	en_dev = rdev->en_dev;
+
+	rc = en_dev->en_ops->bnxt_unregister_device(rdev->en_dev,
+						    BNXT_ROCE_ULP);
+	return rc;
+}
+
+static int bnxt_re_register_netdev(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_en_dev *en_dev;
+	int rc = 0;
+
+	if (!rdev)
+		return -EINVAL;
+
+	en_dev = rdev->en_dev;
+
+	rc = en_dev->en_ops->bnxt_register_device(en_dev, BNXT_ROCE_ULP,
+						  &bnxt_re_ulp_ops, rdev);
+	rdev->qplib_res.pdev = rdev->en_dev->pdev;
+	return rc;
+}
+
+static int bnxt_re_free_msix(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_en_dev *en_dev;
+	int rc;
+
+	if (!rdev)
+		return -EINVAL;
+
+	en_dev = rdev->en_dev;
+
+
+	rc = en_dev->en_ops->bnxt_free_msix(rdev->en_dev, BNXT_ROCE_ULP);
+
+	return rc;
+}
+
+static int bnxt_re_request_msix(struct bnxt_re_dev *rdev)
+{
+	int rc = 0, num_msix_want = BNXT_RE_MAX_MSIX, num_msix_got;
+	struct bnxt_en_dev *en_dev;
+
+	if (!rdev)
+		return -EINVAL;
+
+	en_dev = rdev->en_dev;
+
+	num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus());
+
+	num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP,
+							 rdev->msix_entries,
+							 num_msix_want);
+	if (num_msix_got < BNXT_RE_MIN_MSIX) {
+		rc = -EINVAL;
+		goto done;
+	}
+	if (num_msix_got != num_msix_want) {
+		ibdev_warn(&rdev->ibdev,
+			   "Requested %d MSI-X vectors, got %d\n",
+			   num_msix_want, num_msix_got);
+	}
+	rdev->num_msix = num_msix_got;
+done:
+	return rc;
+}
+
+static void bnxt_re_init_hwrm_hdr(struct bnxt_re_dev *rdev, struct input *hdr,
+				  u16 opcd, u16 crid, u16 trid)
+{
+	hdr->req_type = cpu_to_le16(opcd);
+	hdr->cmpl_ring = cpu_to_le16(crid);
+	hdr->target_id = cpu_to_le16(trid);
+}
+
+static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg,
+				int msg_len, void *resp, int resp_max_len,
+				int timeout)
+{
+	fw_msg->msg = msg;
+	fw_msg->msg_len = msg_len;
+	fw_msg->resp = resp;
+	fw_msg->resp_max_len = resp_max_len;
+	fw_msg->timeout = timeout;
+}
+
+static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
+				 u16 fw_ring_id, int type)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct hwrm_ring_free_input req = {0};
+	struct hwrm_ring_free_output resp;
+	struct bnxt_fw_msg fw_msg;
+	int rc = -EINVAL;
+
+	if (!en_dev)
+		return rc;
+
+	if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
+		return 0;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_FREE, -1, -1);
+	req.ring_type = type;
+	req.ring_id = cpu_to_le16(fw_ring_id);
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
+	if (rc)
+		ibdev_err(&rdev->ibdev, "Failed to free HW ring:%d :%#x",
+			  req.ring_id, rc);
+	return rc;
+}
+
+static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev,
+				  struct bnxt_re_ring_attr *ring_attr,
+				  u16 *fw_ring_id)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct hwrm_ring_alloc_input req = {0};
+	struct hwrm_ring_alloc_output resp;
+	struct bnxt_fw_msg fw_msg;
+	int rc = -EINVAL;
+
+	if (!en_dev)
+		return rc;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_ALLOC, -1, -1);
+	req.enables = 0;
+	req.page_tbl_addr =  cpu_to_le64(ring_attr->dma_arr[0]);
+	if (ring_attr->pages > 1) {
+		/* Page size is in log2 units */
+		req.page_size = BNXT_PAGE_SHIFT;
+		req.page_tbl_depth = 1;
+	}
+	req.fbo = 0;
+	/* Association of ring index with doorbell index and MSIX number */
+	req.logical_id = cpu_to_le16(ring_attr->lrid);
+	req.length = cpu_to_le32(ring_attr->depth + 1);
+	req.ring_type = ring_attr->type;
+	req.int_mode = ring_attr->mode;
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
+	if (!rc)
+		*fw_ring_id = le16_to_cpu(resp.ring_id);
+
+	return rc;
+}
+
+static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev,
+				      u32 fw_stats_ctx_id)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct hwrm_stat_ctx_free_input req = {};
+	struct hwrm_stat_ctx_free_output resp = {};
+	struct bnxt_fw_msg fw_msg;
+	int rc = -EINVAL;
+
+	if (!en_dev)
+		return rc;
+
+	if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
+		return 0;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_FREE, -1, -1);
+	req.stat_ctx_id = cpu_to_le32(fw_stats_ctx_id);
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
+	if (rc)
+		ibdev_err(&rdev->ibdev, "Failed to free HW stats context %#x",
+			  rc);
+
+	return rc;
+}
+
+static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
+				       dma_addr_t dma_map,
+				       u32 *fw_stats_ctx_id)
+{
+	struct bnxt_qplib_chip_ctx *chip_ctx = rdev->chip_ctx;
+	struct hwrm_stat_ctx_alloc_output resp = {0};
+	struct hwrm_stat_ctx_alloc_input req = {0};
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct bnxt_fw_msg fw_msg;
+	int rc = -EINVAL;
+
+	*fw_stats_ctx_id = INVALID_STATS_CTX_ID;
+
+	if (!en_dev)
+		return rc;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1);
+	req.update_period_ms = cpu_to_le32(1000);
+	req.stats_dma_addr = cpu_to_le64(dma_map);
+	req.stats_dma_length = cpu_to_le16(chip_ctx->hw_stats_size);
+	req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE;
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
+	if (!rc)
+		*fw_stats_ctx_id = le32_to_cpu(resp.stat_ctx_id);
+
+	return rc;
+}
+
+/* Device */
+
+static bool is_bnxt_re_dev(struct net_device *netdev)
+{
+	struct ethtool_drvinfo drvinfo;
+
+	if (netdev->ethtool_ops && netdev->ethtool_ops->get_drvinfo) {
+		memset(&drvinfo, 0, sizeof(drvinfo));
+		netdev->ethtool_ops->get_drvinfo(netdev, &drvinfo);
+
+		if (strcmp(drvinfo.driver, "bnxt_en"))
+			return false;
+		return true;
+	}
+	return false;
+}
+
+static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev)
+{
+	struct ib_device *ibdev =
+		ib_device_get_by_netdev(netdev, RDMA_DRIVER_BNXT_RE);
+	if (!ibdev)
+		return NULL;
+
+	return container_of(ibdev, struct bnxt_re_dev, ibdev);
+}
+
+static struct bnxt_en_dev *bnxt_re_dev_probe(struct net_device *netdev)
+{
+	struct bnxt_en_dev *en_dev;
+	struct pci_dev *pdev;
+
+	en_dev = bnxt_ulp_probe(netdev);
+	if (IS_ERR(en_dev))
+		return en_dev;
+
+	pdev = en_dev->pdev;
+	if (!pdev)
+		return ERR_PTR(-EINVAL);
+
+	if (!(en_dev->flags & BNXT_EN_FLAG_ROCE_CAP)) {
+		dev_info(&pdev->dev,
+			"%s: probe error: RoCE is not supported on this device",
+			ROCE_DRV_MODULE_NAME);
+		return ERR_PTR(-ENODEV);
+	}
+
+	dev_hold(netdev);
+
+	return en_dev;
+}
+
+static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr,
+			   char *buf)
+{
+	struct bnxt_re_dev *rdev =
+		rdma_device_to_drv_device(device, struct bnxt_re_dev, ibdev);
+
+	return sysfs_emit(buf, "0x%x\n", rdev->en_dev->pdev->vendor);
+}
+static DEVICE_ATTR_RO(hw_rev);
+
+static ssize_t hca_type_show(struct device *device,
+			     struct device_attribute *attr, char *buf)
+{
+	struct bnxt_re_dev *rdev =
+		rdma_device_to_drv_device(device, struct bnxt_re_dev, ibdev);
+
+	return sysfs_emit(buf, "%s\n", rdev->ibdev.node_desc);
+}
+static DEVICE_ATTR_RO(hca_type);
+
+static struct attribute *bnxt_re_attributes[] = {
+	&dev_attr_hw_rev.attr,
+	&dev_attr_hca_type.attr,
+	NULL
+};
+
+static const struct attribute_group bnxt_re_dev_attr_group = {
+	.attrs = bnxt_re_attributes,
+};
+
+static const struct ib_device_ops bnxt_re_dev_ops = {
+	.owner = THIS_MODULE,
+	.driver_id = RDMA_DRIVER_BNXT_RE,
+	.uverbs_abi_ver = BNXT_RE_ABI_VERSION,
+
+	.add_gid = bnxt_re_add_gid,
+	.alloc_hw_port_stats = bnxt_re_ib_alloc_hw_port_stats,
+	.alloc_mr = bnxt_re_alloc_mr,
+	.alloc_pd = bnxt_re_alloc_pd,
+	.alloc_ucontext = bnxt_re_alloc_ucontext,
+	.create_ah = bnxt_re_create_ah,
+	.create_cq = bnxt_re_create_cq,
+	.create_qp = bnxt_re_create_qp,
+	.create_srq = bnxt_re_create_srq,
+	.create_user_ah = bnxt_re_create_ah,
+	.dealloc_driver = bnxt_re_dealloc_driver,
+	.dealloc_pd = bnxt_re_dealloc_pd,
+	.dealloc_ucontext = bnxt_re_dealloc_ucontext,
+	.del_gid = bnxt_re_del_gid,
+	.dereg_mr = bnxt_re_dereg_mr,
+	.destroy_ah = bnxt_re_destroy_ah,
+	.destroy_cq = bnxt_re_destroy_cq,
+	.destroy_qp = bnxt_re_destroy_qp,
+	.destroy_srq = bnxt_re_destroy_srq,
+	.device_group = &bnxt_re_dev_attr_group,
+	.get_dev_fw_str = bnxt_re_query_fw_str,
+	.get_dma_mr = bnxt_re_get_dma_mr,
+	.get_hw_stats = bnxt_re_ib_get_hw_stats,
+	.get_link_layer = bnxt_re_get_link_layer,
+	.get_port_immutable = bnxt_re_get_port_immutable,
+	.map_mr_sg = bnxt_re_map_mr_sg,
+	.mmap = bnxt_re_mmap,
+	.modify_qp = bnxt_re_modify_qp,
+	.modify_srq = bnxt_re_modify_srq,
+	.poll_cq = bnxt_re_poll_cq,
+	.post_recv = bnxt_re_post_recv,
+	.post_send = bnxt_re_post_send,
+	.post_srq_recv = bnxt_re_post_srq_recv,
+	.query_ah = bnxt_re_query_ah,
+	.query_device = bnxt_re_query_device,
+	.query_pkey = bnxt_re_query_pkey,
+	.query_port = bnxt_re_query_port,
+	.query_qp = bnxt_re_query_qp,
+	.query_srq = bnxt_re_query_srq,
+	.reg_user_mr = bnxt_re_reg_user_mr,
+	.req_notify_cq = bnxt_re_req_notify_cq,
+	INIT_RDMA_OBJ_SIZE(ib_ah, bnxt_re_ah, ib_ah),
+	INIT_RDMA_OBJ_SIZE(ib_cq, bnxt_re_cq, ib_cq),
+	INIT_RDMA_OBJ_SIZE(ib_pd, bnxt_re_pd, ib_pd),
+	INIT_RDMA_OBJ_SIZE(ib_qp, bnxt_re_qp, ib_qp),
+	INIT_RDMA_OBJ_SIZE(ib_srq, bnxt_re_srq, ib_srq),
+	INIT_RDMA_OBJ_SIZE(ib_ucontext, bnxt_re_ucontext, ib_uctx),
+};
+
+static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
+{
+	struct ib_device *ibdev = &rdev->ibdev;
+	int ret;
+
+	/* ib device init */
+	ibdev->node_type = RDMA_NODE_IB_CA;
+	strscpy(ibdev->node_desc, BNXT_RE_DESC " HCA",
+		strlen(BNXT_RE_DESC) + 5);
+	ibdev->phys_port_cnt = 1;
+
+	addrconf_addr_eui48((u8 *)&ibdev->node_guid, rdev->netdev->dev_addr);
+
+	ibdev->num_comp_vectors	= rdev->num_msix - 1;
+	ibdev->dev.parent = &rdev->en_dev->pdev->dev;
+	ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;
+
+	ib_set_device_ops(ibdev, &bnxt_re_dev_ops);
+	ret = ib_device_set_netdev(&rdev->ibdev, rdev->netdev, 1);
+	if (ret)
+		return ret;
+
+	dma_set_max_seg_size(&rdev->en_dev->pdev->dev, UINT_MAX);
+	return ib_register_device(ibdev, "bnxt_re%d", &rdev->en_dev->pdev->dev);
+}
+
+static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev)
+{
+	dev_put(rdev->netdev);
+	rdev->netdev = NULL;
+	mutex_lock(&bnxt_re_dev_lock);
+	list_del_rcu(&rdev->list);
+	mutex_unlock(&bnxt_re_dev_lock);
+
+	synchronize_rcu();
+}
+
+static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev,
+					   struct bnxt_en_dev *en_dev)
+{
+	struct bnxt_re_dev *rdev;
+
+	/* Allocate bnxt_re_dev instance here */
+	rdev = ib_alloc_device(bnxt_re_dev, ibdev);
+	if (!rdev) {
+		ibdev_err(NULL, "%s: bnxt_re_dev allocation failure!",
+			  ROCE_DRV_MODULE_NAME);
+		return NULL;
+	}
+	/* Default values */
+	rdev->netdev = netdev;
+	dev_hold(rdev->netdev);
+	rdev->en_dev = en_dev;
+	rdev->id = rdev->en_dev->pdev->devfn;
+	INIT_LIST_HEAD(&rdev->qp_list);
+	mutex_init(&rdev->qp_lock);
+	atomic_set(&rdev->qp_count, 0);
+	atomic_set(&rdev->cq_count, 0);
+	atomic_set(&rdev->srq_count, 0);
+	atomic_set(&rdev->mr_count, 0);
+	atomic_set(&rdev->mw_count, 0);
+	atomic_set(&rdev->ah_count, 0);
+	atomic_set(&rdev->pd_count, 0);
+	rdev->cosq[0] = 0xFFFF;
+	rdev->cosq[1] = 0xFFFF;
+
+	mutex_lock(&bnxt_re_dev_lock);
+	list_add_tail_rcu(&rdev->list, &bnxt_re_dev_list);
+	mutex_unlock(&bnxt_re_dev_lock);
+	return rdev;
+}
+
+static int bnxt_re_handle_unaffi_async_event(struct creq_func_event
+					     *unaffi_async)
+{
+	switch (unaffi_async->event) {
+	case CREQ_FUNC_EVENT_EVENT_TX_WQE_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_TX_DATA_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_RX_WQE_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_RX_DATA_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CQ_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_TQM_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCQ_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCS_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCC_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCM_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_TIM_ERROR:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event,
+					 struct bnxt_re_qp *qp)
+{
+	struct ib_event event;
+	unsigned int flags;
+
+	if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR &&
+	    rdma_is_kernel_res(&qp->ib_qp.res)) {
+		flags = bnxt_re_lock_cqs(qp);
+		bnxt_qplib_add_flush_qp(&qp->qplib_qp);
+		bnxt_re_unlock_cqs(qp, flags);
+	}
+
+	memset(&event, 0, sizeof(event));
+	if (qp->qplib_qp.srq) {
+		event.device = &qp->rdev->ibdev;
+		event.element.qp = &qp->ib_qp;
+		event.event = IB_EVENT_QP_LAST_WQE_REACHED;
+	}
+
+	if (event.device && qp->ib_qp.event_handler)
+		qp->ib_qp.event_handler(&event, qp->ib_qp.qp_context);
+
+	return 0;
+}
+
+static int bnxt_re_handle_affi_async_event(struct creq_qp_event *affi_async,
+					   void *obj)
+{
+	int rc = 0;
+	u8 event;
+
+	if (!obj)
+		return rc; /* QP was already dead, still return success */
+
+	event = affi_async->event;
+	if (event == CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION) {
+		struct bnxt_qplib_qp *lib_qp = obj;
+		struct bnxt_re_qp *qp = container_of(lib_qp, struct bnxt_re_qp,
+						     qplib_qp);
+		rc = bnxt_re_handle_qp_async_event(affi_async, qp);
+	}
+	return rc;
+}
+
+static int bnxt_re_aeq_handler(struct bnxt_qplib_rcfw *rcfw,
+			       void *aeqe, void *obj)
+{
+	struct creq_qp_event *affi_async;
+	struct creq_func_event *unaffi_async;
+	u8 type;
+	int rc;
+
+	type = ((struct creq_base *)aeqe)->type;
+	if (type == CREQ_BASE_TYPE_FUNC_EVENT) {
+		unaffi_async = aeqe;
+		rc = bnxt_re_handle_unaffi_async_event(unaffi_async);
+	} else {
+		affi_async = aeqe;
+		rc = bnxt_re_handle_affi_async_event(affi_async, obj);
+	}
+
+	return rc;
+}
+
+static int bnxt_re_srqn_handler(struct bnxt_qplib_nq *nq,
+				struct bnxt_qplib_srq *handle, u8 event)
+{
+	struct bnxt_re_srq *srq = container_of(handle, struct bnxt_re_srq,
+					       qplib_srq);
+	struct ib_event ib_event;
+
+	ib_event.device = &srq->rdev->ibdev;
+	ib_event.element.srq = &srq->ib_srq;
+	if (event == NQ_SRQ_EVENT_EVENT_SRQ_THRESHOLD_EVENT)
+		ib_event.event = IB_EVENT_SRQ_LIMIT_REACHED;
+	else
+		ib_event.event = IB_EVENT_SRQ_ERR;
+
+	if (srq->ib_srq.event_handler) {
+		/* Lock event_handler? */
+		(*srq->ib_srq.event_handler)(&ib_event,
+					     srq->ib_srq.srq_context);
+	}
+	return 0;
+}
+
+static int bnxt_re_cqn_handler(struct bnxt_qplib_nq *nq,
+			       struct bnxt_qplib_cq *handle)
+{
+	struct bnxt_re_cq *cq = container_of(handle, struct bnxt_re_cq,
+					     qplib_cq);
+
+	if (cq->ib_cq.comp_handler) {
+		/* Lock comp_handler? */
+		(*cq->ib_cq.comp_handler)(&cq->ib_cq, cq->ib_cq.cq_context);
+	}
+
+	return 0;
+}
+
+#define BNXT_RE_GEN_P5_PF_NQ_DB		0x10000
+#define BNXT_RE_GEN_P5_VF_NQ_DB		0x4000
+static u32 bnxt_re_get_nqdb_offset(struct bnxt_re_dev *rdev, u16 indx)
+{
+	return bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
+		(rdev->is_virtfn ? BNXT_RE_GEN_P5_VF_NQ_DB :
+				   BNXT_RE_GEN_P5_PF_NQ_DB) :
+				   rdev->msix_entries[indx].db_offset;
+}
+
+static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
+{
+	int i;
+
+	for (i = 1; i < rdev->num_msix; i++)
+		bnxt_qplib_disable_nq(&rdev->nq[i - 1]);
+
+	if (rdev->qplib_res.rcfw)
+		bnxt_qplib_cleanup_res(&rdev->qplib_res);
+}
+
+static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
+{
+	int num_vec_enabled = 0;
+	int rc = 0, i;
+	u32 db_offt;
+
+	bnxt_qplib_init_res(&rdev->qplib_res);
+
+	for (i = 1; i < rdev->num_msix ; i++) {
+		db_offt = bnxt_re_get_nqdb_offset(rdev, i);
+		rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1],
+					  i - 1, rdev->msix_entries[i].vector,
+					  db_offt, &bnxt_re_cqn_handler,
+					  &bnxt_re_srqn_handler);
+		if (rc) {
+			ibdev_err(&rdev->ibdev,
+				  "Failed to enable NQ with rc = 0x%x", rc);
+			goto fail;
+		}
+		num_vec_enabled++;
+	}
+	return 0;
+fail:
+	for (i = num_vec_enabled; i >= 0; i--)
+		bnxt_qplib_disable_nq(&rdev->nq[i]);
+	return rc;
+}
+
+static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev)
+{
+	u8 type;
+	int i;
+
+	for (i = 0; i < rdev->num_msix - 1; i++) {
+		type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
+		bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, type);
+		bnxt_qplib_free_nq(&rdev->nq[i]);
+		rdev->nq[i].res = NULL;
+	}
+}
+
+static void bnxt_re_free_res(struct bnxt_re_dev *rdev)
+{
+	bnxt_re_free_nq_res(rdev);
+
+	if (rdev->qplib_res.dpi_tbl.max) {
+		bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
+				       &rdev->qplib_res.dpi_tbl,
+				       &rdev->dpi_privileged);
+	}
+	if (rdev->qplib_res.rcfw) {
+		bnxt_qplib_free_res(&rdev->qplib_res);
+		rdev->qplib_res.rcfw = NULL;
+	}
+}
+
+static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_re_ring_attr rattr = {};
+	int num_vec_created = 0;
+	int rc = 0, i;
+	u8 type;
+
+	/* Configure and allocate resources for qplib */
+	rdev->qplib_res.rcfw = &rdev->rcfw;
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr,
+				     rdev->is_virtfn);
+	if (rc)
+		goto fail;
+
+	rc = bnxt_qplib_alloc_res(&rdev->qplib_res, rdev->en_dev->pdev,
+				  rdev->netdev, &rdev->dev_attr);
+	if (rc)
+		goto fail;
+
+	rc = bnxt_qplib_alloc_dpi(&rdev->qplib_res.dpi_tbl,
+				  &rdev->dpi_privileged,
+				  rdev);
+	if (rc)
+		goto dealloc_res;
+
+	for (i = 0; i < rdev->num_msix - 1; i++) {
+		struct bnxt_qplib_nq *nq;
+
+		nq = &rdev->nq[i];
+		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;
+		rc = bnxt_qplib_alloc_nq(&rdev->qplib_res, &rdev->nq[i]);
+		if (rc) {
+			ibdev_err(&rdev->ibdev, "Alloc Failed NQ%d rc:%#x",
+				  i, rc);
+			goto free_nq;
+		}
+		type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
+		rattr.dma_arr = nq->hwq.pbl[PBL_LVL_0].pg_map_arr;
+		rattr.pages = nq->hwq.pbl[rdev->nq[i].hwq.level].pg_count;
+		rattr.type = type;
+		rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX;
+		rattr.depth = BNXT_QPLIB_NQE_MAX_CNT - 1;
+		rattr.lrid = rdev->msix_entries[i + 1].ring_idx;
+		rc = bnxt_re_net_ring_alloc(rdev, &rattr, &nq->ring_id);
+		if (rc) {
+			ibdev_err(&rdev->ibdev,
+				  "Failed to allocate NQ fw id with rc = 0x%x",
+				  rc);
+			bnxt_qplib_free_nq(&rdev->nq[i]);
+			goto free_nq;
+		}
+		num_vec_created++;
+	}
+	return 0;
+free_nq:
+	for (i = num_vec_created - 1; i >= 0; i--) {
+		type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
+		bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, type);
+		bnxt_qplib_free_nq(&rdev->nq[i]);
+	}
+	bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
+			       &rdev->qplib_res.dpi_tbl,
+			       &rdev->dpi_privileged);
+dealloc_res:
+	bnxt_qplib_free_res(&rdev->qplib_res);
+
+fail:
+	rdev->qplib_res.rcfw = NULL;
+	return rc;
+}
+
+static void bnxt_re_dispatch_event(struct ib_device *ibdev, struct ib_qp *qp,
+				   u8 port_num, enum ib_event_type event)
+{
+	struct ib_event ib_event;
+
+	ib_event.device = ibdev;
+	if (qp) {
+		ib_event.element.qp = qp;
+		ib_event.event = event;
+		if (qp->event_handler)
+			qp->event_handler(&ib_event, qp->qp_context);
+
+	} else {
+		ib_event.element.port_num = port_num;
+		ib_event.event = event;
+		ib_dispatch_event(&ib_event);
+	}
+}
+
+#define HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN      0x02
+static int bnxt_re_query_hwrm_pri2cos(struct bnxt_re_dev *rdev, u8 dir,
+				      u64 *cid_map)
+{
+	struct hwrm_queue_pri2cos_qcfg_input req = {0};
+	struct bnxt *bp = netdev_priv(rdev->netdev);
+	struct hwrm_queue_pri2cos_qcfg_output resp;
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct bnxt_fw_msg fw_msg;
+	u32 flags = 0;
+	u8 *qcfgmap, *tmp_map;
+	int rc = 0, i;
+
+	if (!cid_map)
+		return -EINVAL;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
+			      HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
+	flags |= (dir & 0x01);
+	flags |= HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN;
+	req.flags = cpu_to_le32(flags);
+	req.port_id = bp->pf.port_id;
+
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
+	if (rc)
+		return rc;
+
+	if (resp.queue_cfg_info) {
+		ibdev_warn(&rdev->ibdev,
+			   "Asymmetric cos queue configuration detected");
+		ibdev_warn(&rdev->ibdev,
+			   " on device, QoS may not be fully functional\n");
+	}
+	qcfgmap = &resp.pri0_cos_queue_id;
+	tmp_map = (u8 *)cid_map;
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		tmp_map[i] = qcfgmap[i];
+
+	return rc;
+}
+
+static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev,
+					struct bnxt_re_qp *qp)
+{
+	return (qp->ib_qp.qp_type == IB_QPT_GSI) ||
+	       (qp == rdev->gsi_ctx.gsi_sqp);
+}
+
+static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev)
+{
+	int mask = IB_QP_STATE;
+	struct ib_qp_attr qp_attr;
+	struct bnxt_re_qp *qp;
+
+	qp_attr.qp_state = IB_QPS_ERR;
+	mutex_lock(&rdev->qp_lock);
+	list_for_each_entry(qp, &rdev->qp_list, list) {
+		/* Modify the state of all QPs except QP1/Shadow QP */
+		if (!bnxt_re_is_qp1_or_shadow_qp(rdev, qp)) {
+			if (qp->qplib_qp.state !=
+			    CMDQ_MODIFY_QP_NEW_STATE_RESET &&
+			    qp->qplib_qp.state !=
+			    CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+				bnxt_re_dispatch_event(&rdev->ibdev, &qp->ib_qp,
+						       1, IB_EVENT_QP_FATAL);
+				bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, mask,
+						  NULL);
+			}
+		}
+	}
+	mutex_unlock(&rdev->qp_lock);
+}
+
+static int bnxt_re_update_gid(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+	struct bnxt_qplib_gid gid;
+	u16 gid_idx, index;
+	int rc = 0;
+
+	if (!ib_device_try_get(&rdev->ibdev))
+		return 0;
+
+	for (index = 0; index < sgid_tbl->active; index++) {
+		gid_idx = sgid_tbl->hw_id[index];
+
+		if (!memcmp(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero,
+			    sizeof(bnxt_qplib_gid_zero)))
+			continue;
+		/* need to modify the VLAN enable setting of non VLAN GID only
+		 * as setting is done for VLAN GID while adding GID
+		 */
+		if (sgid_tbl->vlan[index])
+			continue;
+
+		memcpy(&gid, &sgid_tbl->tbl[index], sizeof(gid));
+
+		rc = bnxt_qplib_update_sgid(sgid_tbl, &gid, gid_idx,
+					    rdev->qplib_res.netdev->dev_addr);
+	}
+
+	ib_device_put(&rdev->ibdev);
+	return rc;
+}
+
+static u32 bnxt_re_get_priority_mask(struct bnxt_re_dev *rdev)
+{
+	u32 prio_map = 0, tmp_map = 0;
+	struct net_device *netdev;
+	struct dcb_app app;
+
+	netdev = rdev->netdev;
+
+	memset(&app, 0, sizeof(app));
+	app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE;
+	app.protocol = ETH_P_IBOE;
+	tmp_map = dcb_ieee_getapp_mask(netdev, &app);
+	prio_map = tmp_map;
+
+	app.selector = IEEE_8021QAZ_APP_SEL_DGRAM;
+	app.protocol = ROCE_V2_UDP_DPORT;
+	tmp_map = dcb_ieee_getapp_mask(netdev, &app);
+	prio_map |= tmp_map;
+
+	return prio_map;
+}
+
+static void bnxt_re_parse_cid_map(u8 prio_map, u8 *cid_map, u16 *cosq)
+{
+	u16 prio;
+	u8 id;
+
+	for (prio = 0, id = 0; prio < 8; prio++) {
+		if (prio_map & (1 << prio)) {
+			cosq[id] = cid_map[prio];
+			id++;
+			if (id == 2) /* Max 2 tcs supported */
+				break;
+		}
+	}
+}
+
+static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev)
+{
+	u8 prio_map = 0;
+	u64 cid_map;
+	int rc;
+
+	/* Get priority for roce */
+	prio_map = bnxt_re_get_priority_mask(rdev);
+
+	if (prio_map == rdev->cur_prio_map)
+		return 0;
+	rdev->cur_prio_map = prio_map;
+	/* Get cosq id for this priority */
+	rc = bnxt_re_query_hwrm_pri2cos(rdev, 0, &cid_map);
+	if (rc) {
+		ibdev_warn(&rdev->ibdev, "no cos for p_mask %x\n", prio_map);
+		return rc;
+	}
+	/* Parse CoS IDs for app priority */
+	bnxt_re_parse_cid_map(prio_map, (u8 *)&cid_map, rdev->cosq);
+
+	/* Config BONO. */
+	rc = bnxt_qplib_map_tc2cos(&rdev->qplib_res, rdev->cosq);
+	if (rc) {
+		ibdev_warn(&rdev->ibdev, "no tc for cos{%x, %x}\n",
+			   rdev->cosq[0], rdev->cosq[1]);
+		return rc;
+	}
+
+	/* Actual priorities are not programmed as they are already
+	 * done by L2 driver; just enable or disable priority vlan tagging
+	 */
+	if ((prio_map == 0 && rdev->qplib_res.prio) ||
+	    (prio_map != 0 && !rdev->qplib_res.prio)) {
+		rdev->qplib_res.prio = prio_map ? true : false;
+
+		bnxt_re_update_gid(rdev);
+	}
+
+	return 0;
+}
+
+static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct hwrm_ver_get_output resp = {0};
+	struct hwrm_ver_get_input req = {0};
+	struct bnxt_fw_msg fw_msg;
+	int rc = 0;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
+			      HWRM_VER_GET, -1, -1);
+	req.hwrm_intf_maj = HWRM_VERSION_MAJOR;
+	req.hwrm_intf_min = HWRM_VERSION_MINOR;
+	req.hwrm_intf_upd = HWRM_VERSION_UPDATE;
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to query HW version, rc = 0x%x",
+			  rc);
+		return;
+	}
+	rdev->qplib_ctx.hwrm_intf_ver =
+		(u64)le16_to_cpu(resp.hwrm_intf_major) << 48 |
+		(u64)le16_to_cpu(resp.hwrm_intf_minor) << 32 |
+		(u64)le16_to_cpu(resp.hwrm_intf_build) << 16 |
+		le16_to_cpu(resp.hwrm_intf_patch);
+}
+
+static int bnxt_re_ib_init(struct bnxt_re_dev *rdev)
+{
+	int rc = 0;
+	u32 event;
+
+	/* Register ib dev */
+	rc = bnxt_re_register_ib(rdev);
+	if (rc) {
+		pr_err("Failed to register with IB: %#x\n", rc);
+		return rc;
+	}
+	dev_info(rdev_to_dev(rdev), "Device registered successfully");
+	ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+			 &rdev->active_width);
+	set_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags);
+
+	event = netif_running(rdev->netdev) && netif_carrier_ok(rdev->netdev) ?
+		IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
+
+	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, event);
+
+	return rc;
+}
+
+static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev)
+{
+	u8 type;
+	int rc;
+
+	if (test_and_clear_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags))
+		cancel_delayed_work_sync(&rdev->worker);
+
+	if (test_and_clear_bit(BNXT_RE_FLAG_RESOURCES_INITIALIZED,
+			       &rdev->flags))
+		bnxt_re_cleanup_res(rdev);
+	if (test_and_clear_bit(BNXT_RE_FLAG_RESOURCES_ALLOCATED, &rdev->flags))
+		bnxt_re_free_res(rdev);
+
+	if (test_and_clear_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags)) {
+		rc = bnxt_qplib_deinit_rcfw(&rdev->rcfw);
+		if (rc)
+			ibdev_warn(&rdev->ibdev,
+				   "Failed to deinitialize RCFW: %#x", rc);
+		bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id);
+		bnxt_qplib_free_ctx(&rdev->qplib_res, &rdev->qplib_ctx);
+		bnxt_qplib_disable_rcfw_channel(&rdev->rcfw);
+		type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
+		bnxt_re_net_ring_free(rdev, rdev->rcfw.creq.ring_id, type);
+		bnxt_qplib_free_rcfw_channel(&rdev->rcfw);
+	}
+	if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) {
+		rc = bnxt_re_free_msix(rdev);
+		if (rc)
+			ibdev_warn(&rdev->ibdev,
+				   "Failed to free MSI-X vectors: %#x", rc);
+	}
+
+	bnxt_re_destroy_chip_ctx(rdev);
+	if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) {
+		rc = bnxt_re_unregister_netdev(rdev);
+		if (rc)
+			ibdev_warn(&rdev->ibdev,
+				   "Failed to unregister with netdev: %#x", rc);
+	}
+}
+
+/* worker thread for polling periodic events. Now used for QoS programming*/
+static void bnxt_re_worker(struct work_struct *work)
+{
+	struct bnxt_re_dev *rdev = container_of(work, struct bnxt_re_dev,
+						worker.work);
+
+	bnxt_re_setup_qos(rdev);
+	schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000));
+}
+
+static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode)
+{
+	struct bnxt_qplib_creq_ctx *creq;
+	struct bnxt_re_ring_attr rattr;
+	u32 db_offt;
+	int vid;
+	u8 type;
+	int rc;
+
+	/* Registered a new RoCE device instance to netdev */
+	memset(&rattr, 0, sizeof(rattr));
+	rc = bnxt_re_register_netdev(rdev);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to register with netedev: %#x\n", rc);
+		return -EINVAL;
+	}
+	set_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
+
+	rc = bnxt_re_setup_chip_ctx(rdev, wqe_mode);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to get chip context\n");
+		return -EINVAL;
+	}
+
+	/* Check whether VF or PF */
+	bnxt_re_get_sriov_func_type(rdev);
+
+	rc = bnxt_re_request_msix(rdev);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to get MSI-X vectors: %#x\n", rc);
+		rc = -EINVAL;
+		goto fail;
+	}
+	set_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags);
+
+	bnxt_re_query_hwrm_intf_version(rdev);
+
+	/* Establish RCFW Communication Channel to initialize the context
+	 * memory for the function and all child VFs
+	 */
+	rc = bnxt_qplib_alloc_rcfw_channel(&rdev->qplib_res, &rdev->rcfw,
+					   &rdev->qplib_ctx,
+					   BNXT_RE_MAX_QPC_COUNT);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to allocate RCFW Channel: %#x\n", rc);
+		goto fail;
+	}
+
+	type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
+	creq = &rdev->rcfw.creq;
+	rattr.dma_arr = creq->hwq.pbl[PBL_LVL_0].pg_map_arr;
+	rattr.pages = creq->hwq.pbl[creq->hwq.level].pg_count;
+	rattr.type = type;
+	rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX;
+	rattr.depth = BNXT_QPLIB_CREQE_MAX_CNT - 1;
+	rattr.lrid = rdev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx;
+	rc = bnxt_re_net_ring_alloc(rdev, &rattr, &creq->ring_id);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to allocate CREQ: %#x\n", rc);
+		goto free_rcfw;
+	}
+	db_offt = bnxt_re_get_nqdb_offset(rdev, BNXT_RE_AEQ_IDX);
+	vid = rdev->msix_entries[BNXT_RE_AEQ_IDX].vector;
+	rc = bnxt_qplib_enable_rcfw_channel(&rdev->rcfw,
+					    vid, db_offt, rdev->is_virtfn,
+					    &bnxt_re_aeq_handler);
+	if (rc) {
+		ibdev_err(&rdev->ibdev, "Failed to enable RCFW channel: %#x\n",
+			  rc);
+		goto free_ring;
+	}
+
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr,
+				     rdev->is_virtfn);
+	if (rc)
+		goto disable_rcfw;
+
+	bnxt_re_set_resource_limits(rdev);
+
+	rc = bnxt_qplib_alloc_ctx(&rdev->qplib_res, &rdev->qplib_ctx, 0,
+				  bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx));
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to allocate QPLIB context: %#x\n", rc);
+		goto disable_rcfw;
+	}
+	rc = bnxt_re_net_stats_ctx_alloc(rdev,
+					 rdev->qplib_ctx.stats.dma_map,
+					 &rdev->qplib_ctx.stats.fw_id);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to allocate stats context: %#x\n", rc);
+		goto free_ctx;
+	}
+
+	rc = bnxt_qplib_init_rcfw(&rdev->rcfw, &rdev->qplib_ctx,
+				  rdev->is_virtfn);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to initialize RCFW: %#x\n", rc);
+		goto free_sctx;
+	}
+	set_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags);
+
+	/* Resources based on the 'new' device caps */
+	rc = bnxt_re_alloc_res(rdev);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to allocate resources: %#x\n", rc);
+		goto fail;
+	}
+	set_bit(BNXT_RE_FLAG_RESOURCES_ALLOCATED, &rdev->flags);
+	rc = bnxt_re_init_res(rdev);
+	if (rc) {
+		ibdev_err(&rdev->ibdev,
+			  "Failed to initialize resources: %#x\n", rc);
+		goto fail;
+	}
+
+	set_bit(BNXT_RE_FLAG_RESOURCES_INITIALIZED, &rdev->flags);
+
+	if (!rdev->is_virtfn) {
+		rc = bnxt_re_setup_qos(rdev);
+		if (rc)
+			ibdev_info(&rdev->ibdev,
+				   "RoCE priority not yet configured\n");
+
+		INIT_DELAYED_WORK(&rdev->worker, bnxt_re_worker);
+		set_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags);
+		schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000));
+	}
+
+	return 0;
+free_sctx:
+	bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id);
+free_ctx:
+	bnxt_qplib_free_ctx(&rdev->qplib_res, &rdev->qplib_ctx);
+disable_rcfw:
+	bnxt_qplib_disable_rcfw_channel(&rdev->rcfw);
+free_ring:
+	type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
+	bnxt_re_net_ring_free(rdev, rdev->rcfw.creq.ring_id, type);
+free_rcfw:
+	bnxt_qplib_free_rcfw_channel(&rdev->rcfw);
+fail:
+	bnxt_re_dev_uninit(rdev);
+
+	return rc;
+}
+
+static void bnxt_re_dev_unreg(struct bnxt_re_dev *rdev)
+{
+	struct net_device *netdev = rdev->netdev;
+
+	bnxt_re_dev_remove(rdev);
+
+	if (netdev)
+		dev_put(netdev);
+}
+
+static int bnxt_re_dev_reg(struct bnxt_re_dev **rdev, struct net_device *netdev)
+{
+	struct bnxt_en_dev *en_dev;
+	int rc = 0;
+
+	if (!is_bnxt_re_dev(netdev))
+		return -ENODEV;
+
+	en_dev = bnxt_re_dev_probe(netdev);
+	if (IS_ERR(en_dev)) {
+		if (en_dev != ERR_PTR(-ENODEV))
+			ibdev_err(&(*rdev)->ibdev, "%s: Failed to probe\n",
+				  ROCE_DRV_MODULE_NAME);
+		rc = PTR_ERR(en_dev);
+		goto exit;
+	}
+	*rdev = bnxt_re_dev_add(netdev, en_dev);
+	if (!*rdev) {
+		rc = -ENOMEM;
+		dev_put(netdev);
+		goto exit;
+	}
+exit:
+	return rc;
+}
+
+static void bnxt_re_remove_device(struct bnxt_re_dev *rdev)
+{
+	bnxt_re_dev_uninit(rdev);
+	pci_dev_put(rdev->en_dev->pdev);
+	bnxt_re_dev_unreg(rdev);
+}
+
+static int bnxt_re_add_device(struct bnxt_re_dev **rdev,
+			      struct net_device *netdev, u8 wqe_mode)
+{
+	int rc;
+
+	rc = bnxt_re_dev_reg(rdev, netdev);
+	if (rc == -ENODEV)
+		return rc;
+	if (rc) {
+		pr_err("Failed to register with the device %s: %#x\n",
+		       netdev->name, rc);
+		return rc;
+	}
+
+	pci_dev_get((*rdev)->en_dev->pdev);
+	rc = bnxt_re_dev_init(*rdev, wqe_mode);
+	if (rc) {
+		pci_dev_put((*rdev)->en_dev->pdev);
+		bnxt_re_dev_unreg(*rdev);
+	}
+
+	return rc;
+}
+
+static void bnxt_re_dealloc_driver(struct ib_device *ib_dev)
+{
+	struct bnxt_re_dev *rdev =
+		container_of(ib_dev, struct bnxt_re_dev, ibdev);
+
+	dev_info(rdev_to_dev(rdev), "Unregistering Device");
+
+	rtnl_lock();
+	bnxt_re_remove_device(rdev);
+	rtnl_unlock();
+}
+
+/* Handle all deferred netevents tasks */
+static void bnxt_re_task(struct work_struct *work)
+{
+	struct bnxt_re_work *re_work;
+	struct bnxt_re_dev *rdev;
+	int rc = 0;
+
+	re_work = container_of(work, struct bnxt_re_work, work);
+	rdev = re_work->rdev;
+
+	if (re_work->event == NETDEV_REGISTER) {
+		rc = bnxt_re_ib_init(rdev);
+		if (rc) {
+			ibdev_err(&rdev->ibdev,
+				  "Failed to register with IB: %#x", rc);
+			rtnl_lock();
+			bnxt_re_remove_device(rdev);
+			rtnl_unlock();
+			goto exit;
+		}
+		goto exit;
+	}
+
+	if (!ib_device_try_get(&rdev->ibdev))
+		goto exit;
+
+	switch (re_work->event) {
+	case NETDEV_UP:
+		bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
+				       IB_EVENT_PORT_ACTIVE);
+		break;
+	case NETDEV_DOWN:
+		bnxt_re_dev_stop(rdev);
+		break;
+	case NETDEV_CHANGE:
+		if (!netif_carrier_ok(rdev->netdev))
+			bnxt_re_dev_stop(rdev);
+		else if (netif_carrier_ok(rdev->netdev))
+			bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
+					       IB_EVENT_PORT_ACTIVE);
+		ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+				 &rdev->active_width);
+		break;
+	default:
+		break;
+	}
+	ib_device_put(&rdev->ibdev);
+exit:
+	put_device(&rdev->ibdev.dev);
+	kfree(re_work);
+}
+
+/*
+ * "Notifier chain callback can be invoked for the same chain from
+ * different CPUs at the same time".
+ *
+ * For cases when the netdev is already present, our call to the
+ * register_netdevice_notifier() will actually get the rtnl_lock()
+ * before sending NETDEV_REGISTER and (if up) NETDEV_UP
+ * events.
+ *
+ * But for cases when the netdev is not already present, the notifier
+ * chain is subjected to be invoked from different CPUs simultaneously.
+ *
+ * This is protected by the netdev_mutex.
+ */
+static int bnxt_re_netdev_event(struct notifier_block *notifier,
+				unsigned long event, void *ptr)
+{
+	struct net_device *real_dev, *netdev = netdev_notifier_info_to_dev(ptr);
+	struct bnxt_re_work *re_work;
+	struct bnxt_re_dev *rdev;
+	int rc = 0;
+	bool sch_work = false;
+	bool release = true;
+
+	real_dev = rdma_vlan_dev_real_dev(netdev);
+	if (!real_dev)
+		real_dev = netdev;
+
+	rdev = bnxt_re_from_netdev(real_dev);
+	if (!rdev && event != NETDEV_REGISTER)
+		return NOTIFY_OK;
+
+	if (real_dev != netdev)
+		goto exit;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		if (rdev)
+			break;
+		rc = bnxt_re_add_device(&rdev, real_dev,
+					BNXT_QPLIB_WQE_MODE_STATIC);
+		if (!rc)
+			sch_work = true;
+		release = false;
+		break;
+
+	case NETDEV_UNREGISTER:
+		ib_unregister_device_queued(&rdev->ibdev);
+		break;
+
+	default:
+		sch_work = true;
+		break;
+	}
+	if (sch_work) {
+		/* Allocate for the deferred task */
+		re_work = kzalloc(sizeof(*re_work), GFP_KERNEL);
+		if (re_work) {
+			get_device(&rdev->ibdev.dev);
+			re_work->rdev = rdev;
+			re_work->event = event;
+			re_work->vlan_dev = (real_dev == netdev ?
+					     NULL : netdev);
+			INIT_WORK(&re_work->work, bnxt_re_task);
+			queue_work(bnxt_re_wq, &re_work->work);
+		}
+	}
+
+exit:
+	if (rdev && release)
+		ib_device_put(&rdev->ibdev);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block bnxt_re_netdev_notifier = {
+	.notifier_call = bnxt_re_netdev_event
+};
+
+static int __init bnxt_re_mod_init(void)
+{
+	int rc = 0;
+
+	pr_info("%s: %s", ROCE_DRV_MODULE_NAME, version);
+
+	bnxt_re_wq = create_singlethread_workqueue("bnxt_re");
+	if (!bnxt_re_wq)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&bnxt_re_dev_list);
+
+	rc = register_netdevice_notifier(&bnxt_re_netdev_notifier);
+	if (rc) {
+		pr_err("%s: Cannot register to netdevice_notifier",
+		       ROCE_DRV_MODULE_NAME);
+		goto err_netdev;
+	}
+	return 0;
+
+err_netdev:
+	destroy_workqueue(bnxt_re_wq);
+
+	return rc;
+}
+
+static void __exit bnxt_re_mod_exit(void)
+{
+	struct bnxt_re_dev *rdev;
+
+	unregister_netdevice_notifier(&bnxt_re_netdev_notifier);
+	if (bnxt_re_wq)
+		destroy_workqueue(bnxt_re_wq);
+	list_for_each_entry(rdev, &bnxt_re_dev_list, list) {
+		/* VF device removal should be called before the removal
+		 * of PF device. Queue VFs unregister first, so that VFs
+		 * shall be removed before the PF during the call of
+		 * ib_unregister_driver.
+		 */
+		if (rdev->is_virtfn)
+			ib_unregister_device(&rdev->ibdev);
+	}
+	ib_unregister_driver(RDMA_DRIVER_BNXT_RE);
+}
+
+module_init(bnxt_re_mod_init);
+module_exit(bnxt_re_mod_exit);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
new file mode 100644
index 000000000..101129354
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -0,0 +1,2976 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Fast Path Operators
+ */
+
+#define dev_fmt(fmt) "QPLIB: " fmt
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/prefetch.h>
+#include <linux/if_ether.h>
+#include <rdma/ib_mad.h>
+
+#include "roce_hsi.h"
+
+#include "qplib_res.h"
+#include "qplib_rcfw.h"
+#include "qplib_sp.h"
+#include "qplib_fp.h"
+
+static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp);
+
+static void bnxt_qplib_cancel_phantom_processing(struct bnxt_qplib_qp *qp)
+{
+	qp->sq.condition = false;
+	qp->sq.send_phantom = false;
+	qp->sq.single = false;
+}
+
+/* Flush list */
+static void __bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_cq *scq, *rcq;
+
+	scq = qp->scq;
+	rcq = qp->rcq;
+
+	if (!qp->sq.flushed) {
+		dev_dbg(&scq->hwq.pdev->dev,
+			"FP: Adding to SQ Flush list = %p\n", qp);
+		bnxt_qplib_cancel_phantom_processing(qp);
+		list_add_tail(&qp->sq_flush, &scq->sqf_head);
+		qp->sq.flushed = true;
+	}
+	if (!qp->srq) {
+		if (!qp->rq.flushed) {
+			dev_dbg(&rcq->hwq.pdev->dev,
+				"FP: Adding to RQ Flush list = %p\n", qp);
+			list_add_tail(&qp->rq_flush, &rcq->rqf_head);
+			qp->rq.flushed = true;
+		}
+	}
+}
+
+static void bnxt_qplib_acquire_cq_flush_locks(struct bnxt_qplib_qp *qp,
+				       unsigned long *flags)
+	__acquires(&qp->scq->flush_lock) __acquires(&qp->rcq->flush_lock)
+{
+	spin_lock_irqsave(&qp->scq->flush_lock, *flags);
+	if (qp->scq == qp->rcq)
+		__acquire(&qp->rcq->flush_lock);
+	else
+		spin_lock(&qp->rcq->flush_lock);
+}
+
+static void bnxt_qplib_release_cq_flush_locks(struct bnxt_qplib_qp *qp,
+				       unsigned long *flags)
+	__releases(&qp->scq->flush_lock) __releases(&qp->rcq->flush_lock)
+{
+	if (qp->scq == qp->rcq)
+		__release(&qp->rcq->flush_lock);
+	else
+		spin_unlock(&qp->rcq->flush_lock);
+	spin_unlock_irqrestore(&qp->scq->flush_lock, *flags);
+}
+
+void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp)
+{
+	unsigned long flags;
+
+	bnxt_qplib_acquire_cq_flush_locks(qp, &flags);
+	__bnxt_qplib_add_flush_qp(qp);
+	bnxt_qplib_release_cq_flush_locks(qp, &flags);
+}
+
+static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp)
+{
+	if (qp->sq.flushed) {
+		qp->sq.flushed = false;
+		list_del(&qp->sq_flush);
+	}
+	if (!qp->srq) {
+		if (qp->rq.flushed) {
+			qp->rq.flushed = false;
+			list_del(&qp->rq_flush);
+		}
+	}
+}
+
+void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp)
+{
+	unsigned long flags;
+
+	bnxt_qplib_acquire_cq_flush_locks(qp, &flags);
+	__clean_cq(qp->scq, (u64)(unsigned long)qp);
+	qp->sq.hwq.prod = 0;
+	qp->sq.hwq.cons = 0;
+	__clean_cq(qp->rcq, (u64)(unsigned long)qp);
+	qp->rq.hwq.prod = 0;
+	qp->rq.hwq.cons = 0;
+
+	__bnxt_qplib_del_flush_qp(qp);
+	bnxt_qplib_release_cq_flush_locks(qp, &flags);
+}
+
+static void bnxt_qpn_cqn_sched_task(struct work_struct *work)
+{
+	struct bnxt_qplib_nq_work *nq_work =
+			container_of(work, struct bnxt_qplib_nq_work, work);
+
+	struct bnxt_qplib_cq *cq = nq_work->cq;
+	struct bnxt_qplib_nq *nq = nq_work->nq;
+
+	if (cq && nq) {
+		spin_lock_bh(&cq->compl_lock);
+		if (atomic_read(&cq->arm_state) && nq->cqn_handler) {
+			dev_dbg(&nq->pdev->dev,
+				"%s:Trigger cq  = %p event nq = %p\n",
+				__func__, cq, nq);
+			nq->cqn_handler(nq, cq);
+		}
+		spin_unlock_bh(&cq->compl_lock);
+	}
+	kfree(nq_work);
+}
+
+static void bnxt_qplib_free_qp_hdr_buf(struct bnxt_qplib_res *res,
+				       struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct bnxt_qplib_q *sq = &qp->sq;
+
+	if (qp->rq_hdr_buf)
+		dma_free_coherent(&res->pdev->dev,
+				  rq->max_wqe * qp->rq_hdr_buf_size,
+				  qp->rq_hdr_buf, qp->rq_hdr_buf_map);
+	if (qp->sq_hdr_buf)
+		dma_free_coherent(&res->pdev->dev,
+				  sq->max_wqe * qp->sq_hdr_buf_size,
+				  qp->sq_hdr_buf, qp->sq_hdr_buf_map);
+	qp->rq_hdr_buf = NULL;
+	qp->sq_hdr_buf = NULL;
+	qp->rq_hdr_buf_map = 0;
+	qp->sq_hdr_buf_map = 0;
+	qp->sq_hdr_buf_size = 0;
+	qp->rq_hdr_buf_size = 0;
+}
+
+static int bnxt_qplib_alloc_qp_hdr_buf(struct bnxt_qplib_res *res,
+				       struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct bnxt_qplib_q *sq = &qp->sq;
+	int rc = 0;
+
+	if (qp->sq_hdr_buf_size && sq->max_wqe) {
+		qp->sq_hdr_buf = dma_alloc_coherent(&res->pdev->dev,
+					sq->max_wqe * qp->sq_hdr_buf_size,
+					&qp->sq_hdr_buf_map, GFP_KERNEL);
+		if (!qp->sq_hdr_buf) {
+			rc = -ENOMEM;
+			dev_err(&res->pdev->dev,
+				"Failed to create sq_hdr_buf\n");
+			goto fail;
+		}
+	}
+
+	if (qp->rq_hdr_buf_size && rq->max_wqe) {
+		qp->rq_hdr_buf = dma_alloc_coherent(&res->pdev->dev,
+						    rq->max_wqe *
+						    qp->rq_hdr_buf_size,
+						    &qp->rq_hdr_buf_map,
+						    GFP_KERNEL);
+		if (!qp->rq_hdr_buf) {
+			rc = -ENOMEM;
+			dev_err(&res->pdev->dev,
+				"Failed to create rq_hdr_buf\n");
+			goto fail;
+		}
+	}
+	return 0;
+
+fail:
+	bnxt_qplib_free_qp_hdr_buf(res, qp);
+	return rc;
+}
+
+static void clean_nq(struct bnxt_qplib_nq *nq, struct bnxt_qplib_cq *cq)
+{
+	struct bnxt_qplib_hwq *hwq = &nq->hwq;
+	struct nq_base *nqe, **nq_ptr;
+	int budget = nq->budget;
+	u32 sw_cons, raw_cons;
+	uintptr_t q_handle;
+	u16 type;
+
+	spin_lock_bh(&hwq->lock);
+	/* Service the NQ until empty */
+	raw_cons = hwq->cons;
+	while (budget--) {
+		sw_cons = HWQ_CMP(raw_cons, hwq);
+		nq_ptr = (struct nq_base **)hwq->pbl_ptr;
+		nqe = &nq_ptr[NQE_PG(sw_cons)][NQE_IDX(sw_cons)];
+		if (!NQE_CMP_VALID(nqe, raw_cons, hwq->max_elements))
+			break;
+
+		/*
+		 * The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
+
+		type = le16_to_cpu(nqe->info10_type) & NQ_BASE_TYPE_MASK;
+		switch (type) {
+		case NQ_BASE_TYPE_CQ_NOTIFICATION:
+		{
+			struct nq_cn *nqcne = (struct nq_cn *)nqe;
+
+			q_handle = le32_to_cpu(nqcne->cq_handle_low);
+			q_handle |= (u64)le32_to_cpu(nqcne->cq_handle_high)
+						     << 32;
+			if ((unsigned long)cq == q_handle) {
+				nqcne->cq_handle_low = 0;
+				nqcne->cq_handle_high = 0;
+				cq->cnq_events++;
+			}
+			break;
+		}
+		default:
+			break;
+		}
+		raw_cons++;
+	}
+	spin_unlock_bh(&hwq->lock);
+}
+
+/* Wait for receiving all NQEs for this CQ and clean the NQEs associated with
+ * this CQ.
+ */
+static void __wait_for_all_nqes(struct bnxt_qplib_cq *cq, u16 cnq_events)
+{
+	u32 retry_cnt = 100;
+
+	while (retry_cnt--) {
+		if (cnq_events == cq->cnq_events)
+			return;
+		usleep_range(50, 100);
+		clean_nq(cq->nq, cq);
+	}
+}
+
+static void bnxt_qplib_service_nq(struct tasklet_struct *t)
+{
+	struct bnxt_qplib_nq *nq = from_tasklet(nq, t, nq_tasklet);
+	struct bnxt_qplib_hwq *hwq = &nq->hwq;
+	int num_srqne_processed = 0;
+	int num_cqne_processed = 0;
+	struct bnxt_qplib_cq *cq;
+	int budget = nq->budget;
+	u32 sw_cons, raw_cons;
+	struct nq_base *nqe;
+	uintptr_t q_handle;
+	u16 type;
+
+	spin_lock_bh(&hwq->lock);
+	/* Service the NQ until empty */
+	raw_cons = hwq->cons;
+	while (budget--) {
+		sw_cons = HWQ_CMP(raw_cons, hwq);
+		nqe = bnxt_qplib_get_qe(hwq, sw_cons, NULL);
+		if (!NQE_CMP_VALID(nqe, raw_cons, hwq->max_elements))
+			break;
+
+		/*
+		 * The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
+
+		type = le16_to_cpu(nqe->info10_type) & NQ_BASE_TYPE_MASK;
+		switch (type) {
+		case NQ_BASE_TYPE_CQ_NOTIFICATION:
+		{
+			struct nq_cn *nqcne = (struct nq_cn *)nqe;
+
+			q_handle = le32_to_cpu(nqcne->cq_handle_low);
+			q_handle |= (u64)le32_to_cpu(nqcne->cq_handle_high)
+						     << 32;
+			cq = (struct bnxt_qplib_cq *)(unsigned long)q_handle;
+			if (!cq)
+				break;
+			bnxt_qplib_armen_db(&cq->dbinfo,
+					    DBC_DBC_TYPE_CQ_ARMENA);
+			spin_lock_bh(&cq->compl_lock);
+			atomic_set(&cq->arm_state, 0);
+			if (!nq->cqn_handler(nq, (cq)))
+				num_cqne_processed++;
+			else
+				dev_warn(&nq->pdev->dev,
+					 "cqn - type 0x%x not handled\n", type);
+			cq->cnq_events++;
+			spin_unlock_bh(&cq->compl_lock);
+			break;
+		}
+		case NQ_BASE_TYPE_SRQ_EVENT:
+		{
+			struct bnxt_qplib_srq *srq;
+			struct nq_srq_event *nqsrqe =
+						(struct nq_srq_event *)nqe;
+
+			q_handle = le32_to_cpu(nqsrqe->srq_handle_low);
+			q_handle |= (u64)le32_to_cpu(nqsrqe->srq_handle_high)
+				     << 32;
+			srq = (struct bnxt_qplib_srq *)q_handle;
+			bnxt_qplib_armen_db(&srq->dbinfo,
+					    DBC_DBC_TYPE_SRQ_ARMENA);
+			if (!nq->srqn_handler(nq,
+					      (struct bnxt_qplib_srq *)q_handle,
+					      nqsrqe->event))
+				num_srqne_processed++;
+			else
+				dev_warn(&nq->pdev->dev,
+					 "SRQ event 0x%x not handled\n",
+					 nqsrqe->event);
+			break;
+		}
+		case NQ_BASE_TYPE_DBQ_EVENT:
+			break;
+		default:
+			dev_warn(&nq->pdev->dev,
+				 "nqe with type = 0x%x not handled\n", type);
+			break;
+		}
+		raw_cons++;
+	}
+	if (hwq->cons != raw_cons) {
+		hwq->cons = raw_cons;
+		bnxt_qplib_ring_nq_db(&nq->nq_db.dbinfo, nq->res->cctx, true);
+	}
+	spin_unlock_bh(&hwq->lock);
+}
+
+/* bnxt_re_synchronize_nq - self polling notification queue.
+ * @nq      -     notification queue pointer
+ *
+ * This function will start polling entries of a given notification queue
+ * for all pending  entries.
+ * This function is useful to synchronize notification entries while resources
+ * are going away.
+ */
+
+void bnxt_re_synchronize_nq(struct bnxt_qplib_nq *nq)
+{
+	int budget = nq->budget;
+
+	nq->budget = nq->hwq.max_elements;
+	bnxt_qplib_service_nq(&nq->nq_tasklet);
+	nq->budget = budget;
+}
+
+static irqreturn_t bnxt_qplib_nq_irq(int irq, void *dev_instance)
+{
+	struct bnxt_qplib_nq *nq = dev_instance;
+	struct bnxt_qplib_hwq *hwq = &nq->hwq;
+	u32 sw_cons;
+
+	/* Prefetch the NQ element */
+	sw_cons = HWQ_CMP(hwq->cons, hwq);
+	prefetch(bnxt_qplib_get_qe(hwq, sw_cons, NULL));
+
+	/* Fan out to CPU affinitized kthreads? */
+	tasklet_schedule(&nq->nq_tasklet);
+
+	return IRQ_HANDLED;
+}
+
+void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill)
+{
+	if (!nq->requested)
+		return;
+
+	tasklet_disable(&nq->nq_tasklet);
+	/* Mask h/w interrupt */
+	bnxt_qplib_ring_nq_db(&nq->nq_db.dbinfo, nq->res->cctx, false);
+	/* Sync with last running IRQ handler */
+	synchronize_irq(nq->msix_vec);
+	if (kill)
+		tasklet_kill(&nq->nq_tasklet);
+
+	irq_set_affinity_hint(nq->msix_vec, NULL);
+	free_irq(nq->msix_vec, nq);
+	kfree(nq->name);
+	nq->name = NULL;
+	nq->requested = false;
+}
+
+void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
+{
+	if (nq->cqn_wq) {
+		destroy_workqueue(nq->cqn_wq);
+		nq->cqn_wq = NULL;
+	}
+
+	/* Make sure the HW is stopped! */
+	bnxt_qplib_nq_stop_irq(nq, true);
+
+	if (nq->nq_db.reg.bar_reg) {
+		iounmap(nq->nq_db.reg.bar_reg);
+		nq->nq_db.reg.bar_reg = NULL;
+	}
+
+	nq->cqn_handler = NULL;
+	nq->srqn_handler = NULL;
+	nq->msix_vec = 0;
+}
+
+int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx,
+			    int msix_vector, bool need_init)
+{
+	struct bnxt_qplib_res *res = nq->res;
+	int rc;
+
+	if (nq->requested)
+		return -EFAULT;
+
+	nq->msix_vec = msix_vector;
+	if (need_init)
+		tasklet_setup(&nq->nq_tasklet, bnxt_qplib_service_nq);
+	else
+		tasklet_enable(&nq->nq_tasklet);
+
+	nq->name = kasprintf(GFP_KERNEL, "bnxt_re-nq-%d@pci:%s",
+			     nq_indx, pci_name(res->pdev));
+	if (!nq->name)
+		return -ENOMEM;
+	rc = request_irq(nq->msix_vec, bnxt_qplib_nq_irq, 0, nq->name, nq);
+	if (rc) {
+		kfree(nq->name);
+		nq->name = NULL;
+		tasklet_disable(&nq->nq_tasklet);
+		return rc;
+	}
+
+	cpumask_clear(&nq->mask);
+	cpumask_set_cpu(nq_indx, &nq->mask);
+	rc = irq_set_affinity_hint(nq->msix_vec, &nq->mask);
+	if (rc) {
+		dev_warn(&nq->pdev->dev,
+			 "set affinity failed; vector: %d nq_idx: %d\n",
+			 nq->msix_vec, nq_indx);
+	}
+	nq->requested = true;
+	bnxt_qplib_ring_nq_db(&nq->nq_db.dbinfo, res->cctx, true);
+
+	return rc;
+}
+
+static int bnxt_qplib_map_nq_db(struct bnxt_qplib_nq *nq,  u32 reg_offt)
+{
+	resource_size_t reg_base;
+	struct bnxt_qplib_nq_db *nq_db;
+	struct pci_dev *pdev;
+	int rc = 0;
+
+	pdev = nq->pdev;
+	nq_db = &nq->nq_db;
+
+	nq_db->reg.bar_id = NQ_CONS_PCI_BAR_REGION;
+	nq_db->reg.bar_base = pci_resource_start(pdev, nq_db->reg.bar_id);
+	if (!nq_db->reg.bar_base) {
+		dev_err(&pdev->dev, "QPLIB: NQ BAR region %d resc start is 0!",
+			nq_db->reg.bar_id);
+		rc = -ENOMEM;
+		goto fail;
+	}
+
+	reg_base = nq_db->reg.bar_base + reg_offt;
+	/* Unconditionally map 8 bytes to support 57500 series */
+	nq_db->reg.len = 8;
+	nq_db->reg.bar_reg = ioremap(reg_base, nq_db->reg.len);
+	if (!nq_db->reg.bar_reg) {
+		dev_err(&pdev->dev, "QPLIB: NQ BAR region %d mapping failed",
+			nq_db->reg.bar_id);
+		rc = -ENOMEM;
+		goto fail;
+	}
+
+	nq_db->dbinfo.db = nq_db->reg.bar_reg;
+	nq_db->dbinfo.hwq = &nq->hwq;
+	nq_db->dbinfo.xid = nq->ring_id;
+fail:
+	return rc;
+}
+
+int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
+			 int nq_idx, int msix_vector, int bar_reg_offset,
+			 cqn_handler_t cqn_handler,
+			 srqn_handler_t srqn_handler)
+{
+	int rc = -1;
+
+	nq->pdev = pdev;
+	nq->cqn_handler = cqn_handler;
+	nq->srqn_handler = srqn_handler;
+
+	/* Have a task to schedule CQ notifiers in post send case */
+	nq->cqn_wq  = create_singlethread_workqueue("bnxt_qplib_nq");
+	if (!nq->cqn_wq)
+		return -ENOMEM;
+
+	rc = bnxt_qplib_map_nq_db(nq, bar_reg_offset);
+	if (rc)
+		goto fail;
+
+	rc = bnxt_qplib_nq_start_irq(nq, nq_idx, msix_vector, true);
+	if (rc) {
+		dev_err(&nq->pdev->dev,
+			"Failed to request irq for nq-idx %d\n", nq_idx);
+		goto fail;
+	}
+
+	return 0;
+fail:
+	bnxt_qplib_disable_nq(nq);
+	return rc;
+}
+
+void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq)
+{
+	if (nq->hwq.max_elements) {
+		bnxt_qplib_free_hwq(nq->res, &nq->hwq);
+		nq->hwq.max_elements = 0;
+	}
+}
+
+int bnxt_qplib_alloc_nq(struct bnxt_qplib_res *res, struct bnxt_qplib_nq *nq)
+{
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_sg_info sginfo = {};
+
+	nq->pdev = res->pdev;
+	nq->res = res;
+	if (!nq->hwq.max_elements ||
+	    nq->hwq.max_elements > BNXT_QPLIB_NQE_MAX_CNT)
+		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;
+
+	sginfo.pgsize = PAGE_SIZE;
+	sginfo.pgshft = PAGE_SHIFT;
+	hwq_attr.res = res;
+	hwq_attr.sginfo = &sginfo;
+	hwq_attr.depth = nq->hwq.max_elements;
+	hwq_attr.stride = sizeof(struct nq_base);
+	hwq_attr.type = bnxt_qplib_get_hwq_type(nq->res);
+	if (bnxt_qplib_alloc_init_hwq(&nq->hwq, &hwq_attr)) {
+		dev_err(&nq->pdev->dev, "FP NQ allocation failed");
+		return -ENOMEM;
+	}
+	nq->budget = 8;
+	return 0;
+}
+
+/* SRQ */
+void bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res,
+			   struct bnxt_qplib_srq *srq)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_destroy_srq req;
+	struct creq_destroy_srq_resp resp;
+	u16 cmd_flags = 0;
+	int rc;
+
+	RCFW_CMD_PREP(req, DESTROY_SRQ, cmd_flags);
+
+	/* Configure the request */
+	req.srq_cid = cpu_to_le32(srq->id);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (struct cmdq_base *)&req,
+					  (struct creq_base *)&resp, NULL, 0);
+	kfree(srq->swq);
+	if (rc)
+		return;
+	bnxt_qplib_free_hwq(res, &srq->hwq);
+}
+
+int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
+			  struct bnxt_qplib_srq *srq)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct creq_create_srq_resp resp;
+	struct cmdq_create_srq req;
+	struct bnxt_qplib_pbl *pbl;
+	u16 cmd_flags = 0;
+	u16 pg_sz_lvl;
+	int rc, idx;
+
+	hwq_attr.res = res;
+	hwq_attr.sginfo = &srq->sg_info;
+	hwq_attr.depth = srq->max_wqe;
+	hwq_attr.stride = srq->wqe_size;
+	hwq_attr.type = HWQ_TYPE_QUEUE;
+	rc = bnxt_qplib_alloc_init_hwq(&srq->hwq, &hwq_attr);
+	if (rc)
+		goto exit;
+
+	srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq),
+			   GFP_KERNEL);
+	if (!srq->swq) {
+		rc = -ENOMEM;
+		goto fail;
+	}
+
+	RCFW_CMD_PREP(req, CREATE_SRQ, cmd_flags);
+
+	/* Configure the request */
+	req.dpi = cpu_to_le32(srq->dpi->dpi);
+	req.srq_handle = cpu_to_le64((uintptr_t)srq);
+
+	req.srq_size = cpu_to_le16((u16)srq->hwq.max_elements);
+	pbl = &srq->hwq.pbl[PBL_LVL_0];
+	pg_sz_lvl = ((u16)bnxt_qplib_base_pg_size(&srq->hwq) <<
+		     CMDQ_CREATE_SRQ_PG_SIZE_SFT);
+	pg_sz_lvl |= (srq->hwq.level & CMDQ_CREATE_SRQ_LVL_MASK) <<
+		      CMDQ_CREATE_SRQ_LVL_SFT;
+	req.pg_size_lvl = cpu_to_le16(pg_sz_lvl);
+	req.pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+	req.pd_id = cpu_to_le32(srq->pd->id);
+	req.eventq_id = cpu_to_le16(srq->eventq_hw_ring_id);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		goto fail;
+
+	spin_lock_init(&srq->lock);
+	srq->start_idx = 0;
+	srq->last_idx = srq->hwq.max_elements - 1;
+	for (idx = 0; idx < srq->hwq.max_elements; idx++)
+		srq->swq[idx].next_idx = idx + 1;
+	srq->swq[srq->last_idx].next_idx = -1;
+
+	srq->id = le32_to_cpu(resp.xid);
+	srq->dbinfo.hwq = &srq->hwq;
+	srq->dbinfo.xid = srq->id;
+	srq->dbinfo.db = srq->dpi->dbr;
+	srq->dbinfo.max_slot = 1;
+	srq->dbinfo.priv_db = res->dpi_tbl.dbr_bar_reg_iomem;
+	if (srq->threshold)
+		bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA);
+	srq->arm_req = false;
+
+	return 0;
+fail:
+	bnxt_qplib_free_hwq(res, &srq->hwq);
+	kfree(srq->swq);
+exit:
+	return rc;
+}
+
+int bnxt_qplib_modify_srq(struct bnxt_qplib_res *res,
+			  struct bnxt_qplib_srq *srq)
+{
+	struct bnxt_qplib_hwq *srq_hwq = &srq->hwq;
+	u32 sw_prod, sw_cons, count = 0;
+
+	sw_prod = HWQ_CMP(srq_hwq->prod, srq_hwq);
+	sw_cons = HWQ_CMP(srq_hwq->cons, srq_hwq);
+
+	count = sw_prod > sw_cons ? sw_prod - sw_cons :
+				    srq_hwq->max_elements - sw_cons + sw_prod;
+	if (count > srq->threshold) {
+		srq->arm_req = false;
+		bnxt_qplib_srq_arm_db(&srq->dbinfo, srq->threshold);
+	} else {
+		/* Deferred arming */
+		srq->arm_req = true;
+	}
+
+	return 0;
+}
+
+int bnxt_qplib_query_srq(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_srq *srq)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_query_srq req;
+	struct creq_query_srq_resp resp;
+	struct bnxt_qplib_rcfw_sbuf *sbuf;
+	struct creq_query_srq_resp_sb *sb;
+	u16 cmd_flags = 0;
+	int rc = 0;
+
+	RCFW_CMD_PREP(req, QUERY_SRQ, cmd_flags);
+
+	/* Configure the request */
+	sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb));
+	if (!sbuf)
+		return -ENOMEM;
+	req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS;
+	req.srq_cid = cpu_to_le32(srq->id);
+	sb = sbuf->sb;
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  (void *)sbuf, 0);
+	srq->threshold = le16_to_cpu(sb->srq_limit);
+	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
+
+	return rc;
+}
+
+int bnxt_qplib_post_srq_recv(struct bnxt_qplib_srq *srq,
+			     struct bnxt_qplib_swqe *wqe)
+{
+	struct bnxt_qplib_hwq *srq_hwq = &srq->hwq;
+	struct rq_wqe *srqe;
+	struct sq_sge *hw_sge;
+	u32 sw_prod, sw_cons, count = 0;
+	int i, rc = 0, next;
+
+	spin_lock(&srq_hwq->lock);
+	if (srq->start_idx == srq->last_idx) {
+		dev_err(&srq_hwq->pdev->dev,
+			"FP: SRQ (0x%x) is full!\n", srq->id);
+		rc = -EINVAL;
+		spin_unlock(&srq_hwq->lock);
+		goto done;
+	}
+	next = srq->start_idx;
+	srq->start_idx = srq->swq[next].next_idx;
+	spin_unlock(&srq_hwq->lock);
+
+	sw_prod = HWQ_CMP(srq_hwq->prod, srq_hwq);
+	srqe = bnxt_qplib_get_qe(srq_hwq, sw_prod, NULL);
+	memset(srqe, 0, srq->wqe_size);
+	/* Calculate wqe_size16 and data_len */
+	for (i = 0, hw_sge = (struct sq_sge *)srqe->data;
+	     i < wqe->num_sge; i++, hw_sge++) {
+		hw_sge->va_or_pa = cpu_to_le64(wqe->sg_list[i].addr);
+		hw_sge->l_key = cpu_to_le32(wqe->sg_list[i].lkey);
+		hw_sge->size = cpu_to_le32(wqe->sg_list[i].size);
+	}
+	srqe->wqe_type = wqe->type;
+	srqe->flags = wqe->flags;
+	srqe->wqe_size = wqe->num_sge +
+			((offsetof(typeof(*srqe), data) + 15) >> 4);
+	srqe->wr_id[0] = cpu_to_le32((u32)next);
+	srq->swq[next].wr_id = wqe->wr_id;
+
+	srq_hwq->prod++;
+
+	spin_lock(&srq_hwq->lock);
+	sw_prod = HWQ_CMP(srq_hwq->prod, srq_hwq);
+	/* retaining srq_hwq->cons for this logic
+	 * actually the lock is only required to
+	 * read srq_hwq->cons.
+	 */
+	sw_cons = HWQ_CMP(srq_hwq->cons, srq_hwq);
+	count = sw_prod > sw_cons ? sw_prod - sw_cons :
+				    srq_hwq->max_elements - sw_cons + sw_prod;
+	spin_unlock(&srq_hwq->lock);
+	/* Ring DB */
+	bnxt_qplib_ring_prod_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ);
+	if (srq->arm_req == true && count > srq->threshold) {
+		srq->arm_req = false;
+		bnxt_qplib_srq_arm_db(&srq->dbinfo, srq->threshold);
+	}
+done:
+	return rc;
+}
+
+/* QP */
+
+static int bnxt_qplib_alloc_init_swq(struct bnxt_qplib_q *que)
+{
+	int rc = 0;
+	int indx;
+
+	que->swq = kcalloc(que->max_wqe, sizeof(*que->swq), GFP_KERNEL);
+	if (!que->swq) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	que->swq_start = 0;
+	que->swq_last = que->max_wqe - 1;
+	for (indx = 0; indx < que->max_wqe; indx++)
+		que->swq[indx].next_idx = indx + 1;
+	que->swq[que->swq_last].next_idx = 0; /* Make it circular */
+	que->swq_last = 0;
+out:
+	return rc;
+}
+
+int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct creq_create_qp1_resp resp;
+	struct cmdq_create_qp1 req;
+	struct bnxt_qplib_pbl *pbl;
+	u16 cmd_flags = 0;
+	u32 qp_flags = 0;
+	u8 pg_sz_lvl;
+	u32 tbl_indx;
+	int rc;
+
+	RCFW_CMD_PREP(req, CREATE_QP1, cmd_flags);
+
+	/* General */
+	req.type = qp->type;
+	req.dpi = cpu_to_le32(qp->dpi->dpi);
+	req.qp_handle = cpu_to_le64(qp->qp_handle);
+
+	/* SQ */
+	hwq_attr.res = res;
+	hwq_attr.sginfo = &sq->sg_info;
+	hwq_attr.stride = sizeof(struct sq_sge);
+	hwq_attr.depth = bnxt_qplib_get_depth(sq);
+	hwq_attr.type = HWQ_TYPE_QUEUE;
+	rc = bnxt_qplib_alloc_init_hwq(&sq->hwq, &hwq_attr);
+	if (rc)
+		goto exit;
+
+	rc = bnxt_qplib_alloc_init_swq(sq);
+	if (rc)
+		goto fail_sq;
+
+	req.sq_size = cpu_to_le32(bnxt_qplib_set_sq_size(sq, qp->wqe_mode));
+	pbl = &sq->hwq.pbl[PBL_LVL_0];
+	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+	pg_sz_lvl = (bnxt_qplib_base_pg_size(&sq->hwq) <<
+		     CMDQ_CREATE_QP1_SQ_PG_SIZE_SFT);
+	pg_sz_lvl |= (sq->hwq.level & CMDQ_CREATE_QP1_SQ_LVL_MASK);
+	req.sq_pg_size_sq_lvl = pg_sz_lvl;
+	req.sq_fwo_sq_sge =
+		cpu_to_le16((sq->max_sge & CMDQ_CREATE_QP1_SQ_SGE_MASK) <<
+			     CMDQ_CREATE_QP1_SQ_SGE_SFT);
+	req.scq_cid = cpu_to_le32(qp->scq->id);
+
+	/* RQ */
+	if (rq->max_wqe) {
+		hwq_attr.res = res;
+		hwq_attr.sginfo = &rq->sg_info;
+		hwq_attr.stride = sizeof(struct sq_sge);
+		hwq_attr.depth = bnxt_qplib_get_depth(rq);
+		hwq_attr.type = HWQ_TYPE_QUEUE;
+		rc = bnxt_qplib_alloc_init_hwq(&rq->hwq, &hwq_attr);
+		if (rc)
+			goto sq_swq;
+		rc = bnxt_qplib_alloc_init_swq(rq);
+		if (rc)
+			goto fail_rq;
+		req.rq_size = cpu_to_le32(rq->max_wqe);
+		pbl = &rq->hwq.pbl[PBL_LVL_0];
+		req.rq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+		pg_sz_lvl = (bnxt_qplib_base_pg_size(&rq->hwq) <<
+			     CMDQ_CREATE_QP1_RQ_PG_SIZE_SFT);
+		pg_sz_lvl |= (rq->hwq.level & CMDQ_CREATE_QP1_RQ_LVL_MASK);
+		req.rq_pg_size_rq_lvl = pg_sz_lvl;
+		req.rq_fwo_rq_sge =
+			cpu_to_le16((rq->max_sge &
+				     CMDQ_CREATE_QP1_RQ_SGE_MASK) <<
+				    CMDQ_CREATE_QP1_RQ_SGE_SFT);
+	}
+	req.rcq_cid = cpu_to_le32(qp->rcq->id);
+	/* Header buffer - allow hdr_buf pass in */
+	rc = bnxt_qplib_alloc_qp_hdr_buf(res, qp);
+	if (rc) {
+		rc = -ENOMEM;
+		goto rq_rwq;
+	}
+	qp_flags |= CMDQ_CREATE_QP1_QP_FLAGS_RESERVED_LKEY_ENABLE;
+	req.qp_flags = cpu_to_le32(qp_flags);
+	req.pd_id = cpu_to_le32(qp->pd->id);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		goto fail;
+
+	qp->id = le32_to_cpu(resp.xid);
+	qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET;
+	qp->cctx = res->cctx;
+	sq->dbinfo.hwq = &sq->hwq;
+	sq->dbinfo.xid = qp->id;
+	sq->dbinfo.db = qp->dpi->dbr;
+	sq->dbinfo.max_slot = bnxt_qplib_set_sq_max_slot(qp->wqe_mode);
+	if (rq->max_wqe) {
+		rq->dbinfo.hwq = &rq->hwq;
+		rq->dbinfo.xid = qp->id;
+		rq->dbinfo.db = qp->dpi->dbr;
+		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
+	}
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
+
+	return 0;
+
+fail:
+	bnxt_qplib_free_qp_hdr_buf(res, qp);
+rq_rwq:
+	kfree(rq->swq);
+fail_rq:
+	bnxt_qplib_free_hwq(res, &rq->hwq);
+sq_swq:
+	kfree(sq->swq);
+fail_sq:
+	bnxt_qplib_free_hwq(res, &sq->hwq);
+exit:
+	return rc;
+}
+
+static void bnxt_qplib_init_psn_ptr(struct bnxt_qplib_qp *qp, int size)
+{
+	struct bnxt_qplib_hwq *hwq;
+	struct bnxt_qplib_q *sq;
+	u64 fpsne, psn_pg;
+	u16 indx_pad = 0;
+
+	sq = &qp->sq;
+	hwq = &sq->hwq;
+	/* First psn entry */
+	fpsne = (u64)bnxt_qplib_get_qe(hwq, hwq->depth, &psn_pg);
+	if (!IS_ALIGNED(fpsne, PAGE_SIZE))
+		indx_pad = (fpsne & ~PAGE_MASK) / size;
+	hwq->pad_pgofft = indx_pad;
+	hwq->pad_pg = (u64 *)psn_pg;
+	hwq->pad_stride = size;
+}
+
+int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_sg_info sginfo = {};
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct creq_create_qp_resp resp;
+	int rc, req_size, psn_sz = 0;
+	struct bnxt_qplib_hwq *xrrq;
+	struct bnxt_qplib_pbl *pbl;
+	struct cmdq_create_qp req;
+	u16 cmd_flags = 0;
+	u32 qp_flags = 0;
+	u8 pg_sz_lvl;
+	u32 tbl_indx;
+	u16 nsge;
+
+	RCFW_CMD_PREP(req, CREATE_QP, cmd_flags);
+
+	/* General */
+	req.type = qp->type;
+	req.dpi = cpu_to_le32(qp->dpi->dpi);
+	req.qp_handle = cpu_to_le64(qp->qp_handle);
+
+	/* SQ */
+	if (qp->type == CMDQ_CREATE_QP_TYPE_RC) {
+		psn_sz = bnxt_qplib_is_chip_gen_p5(res->cctx) ?
+			 sizeof(struct sq_psn_search_ext) :
+			 sizeof(struct sq_psn_search);
+	}
+
+	hwq_attr.res = res;
+	hwq_attr.sginfo = &sq->sg_info;
+	hwq_attr.stride = sizeof(struct sq_sge);
+	hwq_attr.depth = bnxt_qplib_get_depth(sq);
+	hwq_attr.aux_stride = psn_sz;
+	hwq_attr.aux_depth = bnxt_qplib_set_sq_size(sq, qp->wqe_mode);
+	hwq_attr.type = HWQ_TYPE_QUEUE;
+	rc = bnxt_qplib_alloc_init_hwq(&sq->hwq, &hwq_attr);
+	if (rc)
+		goto exit;
+
+	rc = bnxt_qplib_alloc_init_swq(sq);
+	if (rc)
+		goto fail_sq;
+
+	if (psn_sz)
+		bnxt_qplib_init_psn_ptr(qp, psn_sz);
+
+	req.sq_size = cpu_to_le32(bnxt_qplib_set_sq_size(sq, qp->wqe_mode));
+	pbl = &sq->hwq.pbl[PBL_LVL_0];
+	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+	pg_sz_lvl = (bnxt_qplib_base_pg_size(&sq->hwq) <<
+		     CMDQ_CREATE_QP_SQ_PG_SIZE_SFT);
+	pg_sz_lvl |= (sq->hwq.level & CMDQ_CREATE_QP_SQ_LVL_MASK);
+	req.sq_pg_size_sq_lvl = pg_sz_lvl;
+	req.sq_fwo_sq_sge =
+		cpu_to_le16(((sq->max_sge & CMDQ_CREATE_QP_SQ_SGE_MASK) <<
+			     CMDQ_CREATE_QP_SQ_SGE_SFT) | 0);
+	req.scq_cid = cpu_to_le32(qp->scq->id);
+
+	/* RQ */
+	if (!qp->srq) {
+		hwq_attr.res = res;
+		hwq_attr.sginfo = &rq->sg_info;
+		hwq_attr.stride = sizeof(struct sq_sge);
+		hwq_attr.depth = bnxt_qplib_get_depth(rq);
+		hwq_attr.aux_stride = 0;
+		hwq_attr.aux_depth = 0;
+		hwq_attr.type = HWQ_TYPE_QUEUE;
+		rc = bnxt_qplib_alloc_init_hwq(&rq->hwq, &hwq_attr);
+		if (rc)
+			goto sq_swq;
+		rc = bnxt_qplib_alloc_init_swq(rq);
+		if (rc)
+			goto fail_rq;
+
+		req.rq_size = cpu_to_le32(rq->max_wqe);
+		pbl = &rq->hwq.pbl[PBL_LVL_0];
+		req.rq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+		pg_sz_lvl = (bnxt_qplib_base_pg_size(&rq->hwq) <<
+			     CMDQ_CREATE_QP_RQ_PG_SIZE_SFT);
+		pg_sz_lvl |= (rq->hwq.level & CMDQ_CREATE_QP_RQ_LVL_MASK);
+		req.rq_pg_size_rq_lvl = pg_sz_lvl;
+		nsge = (qp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) ?
+			6 : rq->max_sge;
+		req.rq_fwo_rq_sge =
+			cpu_to_le16(((nsge &
+				      CMDQ_CREATE_QP_RQ_SGE_MASK) <<
+				     CMDQ_CREATE_QP_RQ_SGE_SFT) | 0);
+	} else {
+		/* SRQ */
+		qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_SRQ_USED;
+		req.srq_cid = cpu_to_le32(qp->srq->id);
+	}
+	req.rcq_cid = cpu_to_le32(qp->rcq->id);
+
+	qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_RESERVED_LKEY_ENABLE;
+	qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_FR_PMR_ENABLED;
+	if (qp->sig_type)
+		qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_FORCE_COMPLETION;
+	if (qp->wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE)
+		qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_VARIABLE_SIZED_WQE_ENABLED;
+	if (_is_ext_stats_supported(res->dattr->dev_cap_flags) && !res->is_vf)
+		qp_flags |= CMDQ_CREATE_QP_QP_FLAGS_EXT_STATS_ENABLED;
+
+	req.qp_flags = cpu_to_le32(qp_flags);
+
+	/* ORRQ and IRRQ */
+	if (psn_sz) {
+		xrrq = &qp->orrq;
+		xrrq->max_elements =
+			ORD_LIMIT_TO_ORRQ_SLOTS(qp->max_rd_atomic);
+		req_size = xrrq->max_elements *
+			   BNXT_QPLIB_MAX_ORRQE_ENTRY_SIZE + PAGE_SIZE - 1;
+		req_size &= ~(PAGE_SIZE - 1);
+		sginfo.pgsize = req_size;
+		sginfo.pgshft = PAGE_SHIFT;
+
+		hwq_attr.res = res;
+		hwq_attr.sginfo = &sginfo;
+		hwq_attr.depth = xrrq->max_elements;
+		hwq_attr.stride = BNXT_QPLIB_MAX_ORRQE_ENTRY_SIZE;
+		hwq_attr.aux_stride = 0;
+		hwq_attr.aux_depth = 0;
+		hwq_attr.type = HWQ_TYPE_CTX;
+		rc = bnxt_qplib_alloc_init_hwq(xrrq, &hwq_attr);
+		if (rc)
+			goto rq_swq;
+		pbl = &xrrq->pbl[PBL_LVL_0];
+		req.orrq_addr = cpu_to_le64(pbl->pg_map_arr[0]);
+
+		xrrq = &qp->irrq;
+		xrrq->max_elements = IRD_LIMIT_TO_IRRQ_SLOTS(
+						qp->max_dest_rd_atomic);
+		req_size = xrrq->max_elements *
+			   BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE + PAGE_SIZE - 1;
+		req_size &= ~(PAGE_SIZE - 1);
+		sginfo.pgsize = req_size;
+		hwq_attr.depth =  xrrq->max_elements;
+		hwq_attr.stride = BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE;
+		rc = bnxt_qplib_alloc_init_hwq(xrrq, &hwq_attr);
+		if (rc)
+			goto fail_orrq;
+
+		pbl = &xrrq->pbl[PBL_LVL_0];
+		req.irrq_addr = cpu_to_le64(pbl->pg_map_arr[0]);
+	}
+	req.pd_id = cpu_to_le32(qp->pd->id);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		goto fail;
+
+	qp->id = le32_to_cpu(resp.xid);
+	qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET;
+	INIT_LIST_HEAD(&qp->sq_flush);
+	INIT_LIST_HEAD(&qp->rq_flush);
+	qp->cctx = res->cctx;
+	sq->dbinfo.hwq = &sq->hwq;
+	sq->dbinfo.xid = qp->id;
+	sq->dbinfo.db = qp->dpi->dbr;
+	sq->dbinfo.max_slot = bnxt_qplib_set_sq_max_slot(qp->wqe_mode);
+	if (rq->max_wqe) {
+		rq->dbinfo.hwq = &rq->hwq;
+		rq->dbinfo.xid = qp->id;
+		rq->dbinfo.db = qp->dpi->dbr;
+		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
+	}
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
+
+	return 0;
+fail:
+	bnxt_qplib_free_hwq(res, &qp->irrq);
+fail_orrq:
+	bnxt_qplib_free_hwq(res, &qp->orrq);
+rq_swq:
+	kfree(rq->swq);
+fail_rq:
+	bnxt_qplib_free_hwq(res, &rq->hwq);
+sq_swq:
+	kfree(sq->swq);
+fail_sq:
+	bnxt_qplib_free_hwq(res, &sq->hwq);
+exit:
+	return rc;
+}
+
+static void __modify_flags_from_init_state(struct bnxt_qplib_qp *qp)
+{
+	switch (qp->state) {
+	case CMDQ_MODIFY_QP_NEW_STATE_RTR:
+		/* INIT->RTR, configure the path_mtu to the default
+		 * 2048 if not being requested
+		 */
+		if (!(qp->modify_flags &
+		    CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU)) {
+			qp->modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
+			qp->path_mtu =
+				CMDQ_MODIFY_QP_PATH_MTU_MTU_2048;
+		}
+		qp->modify_flags &=
+			~CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID;
+		/* Bono FW require the max_dest_rd_atomic to be >= 1 */
+		if (qp->max_dest_rd_atomic < 1)
+			qp->max_dest_rd_atomic = 1;
+		qp->modify_flags &= ~CMDQ_MODIFY_QP_MODIFY_MASK_SRC_MAC;
+		/* Bono FW 20.6.5 requires SGID_INDEX configuration */
+		if (!(qp->modify_flags &
+		    CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX)) {
+			qp->modify_flags |=
+				CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX;
+			qp->ah.sgid_index = 0;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void __modify_flags_from_rtr_state(struct bnxt_qplib_qp *qp)
+{
+	switch (qp->state) {
+	case CMDQ_MODIFY_QP_NEW_STATE_RTS:
+		/* Bono FW requires the max_rd_atomic to be >= 1 */
+		if (qp->max_rd_atomic < 1)
+			qp->max_rd_atomic = 1;
+		/* Bono FW does not allow PKEY_INDEX,
+		 * DGID, FLOW_LABEL, SGID_INDEX, HOP_LIMIT,
+		 * TRAFFIC_CLASS, DEST_MAC, PATH_MTU, RQ_PSN,
+		 * MIN_RNR_TIMER, MAX_DEST_RD_ATOMIC, DEST_QP_ID
+		 * modification
+		 */
+		qp->modify_flags &=
+			~(CMDQ_MODIFY_QP_MODIFY_MASK_PKEY |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_DGID |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC |
+			  CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID);
+		break;
+	default:
+		break;
+	}
+}
+
+static void __filter_modify_flags(struct bnxt_qplib_qp *qp)
+{
+	switch (qp->cur_qp_state) {
+	case CMDQ_MODIFY_QP_NEW_STATE_RESET:
+		break;
+	case CMDQ_MODIFY_QP_NEW_STATE_INIT:
+		__modify_flags_from_init_state(qp);
+		break;
+	case CMDQ_MODIFY_QP_NEW_STATE_RTR:
+		__modify_flags_from_rtr_state(qp);
+		break;
+	case CMDQ_MODIFY_QP_NEW_STATE_RTS:
+		break;
+	case CMDQ_MODIFY_QP_NEW_STATE_SQD:
+		break;
+	case CMDQ_MODIFY_QP_NEW_STATE_SQE:
+		break;
+	case CMDQ_MODIFY_QP_NEW_STATE_ERR:
+		break;
+	default:
+		break;
+	}
+}
+
+int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_modify_qp req;
+	struct creq_modify_qp_resp resp;
+	u16 cmd_flags = 0;
+	u32 temp32[4];
+	u32 bmask;
+	int rc;
+
+	RCFW_CMD_PREP(req, MODIFY_QP, cmd_flags);
+
+	/* Filter out the qp_attr_mask based on the state->new transition */
+	__filter_modify_flags(qp);
+	bmask = qp->modify_flags;
+	req.modify_mask = cpu_to_le32(qp->modify_flags);
+	req.qp_cid = cpu_to_le32(qp->id);
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_STATE) {
+		req.network_type_en_sqd_async_notify_new_state =
+				(qp->state & CMDQ_MODIFY_QP_NEW_STATE_MASK) |
+				(qp->en_sqd_async_notify ?
+					CMDQ_MODIFY_QP_EN_SQD_ASYNC_NOTIFY : 0);
+	}
+	req.network_type_en_sqd_async_notify_new_state |= qp->nw_type;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS)
+		req.access = qp->access;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_PKEY)
+		req.pkey = cpu_to_le16(IB_DEFAULT_PKEY_FULL);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_QKEY)
+		req.qkey = cpu_to_le32(qp->qkey);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_DGID) {
+		memcpy(temp32, qp->ah.dgid.data, sizeof(struct bnxt_qplib_gid));
+		req.dgid[0] = cpu_to_le32(temp32[0]);
+		req.dgid[1] = cpu_to_le32(temp32[1]);
+		req.dgid[2] = cpu_to_le32(temp32[2]);
+		req.dgid[3] = cpu_to_le32(temp32[3]);
+	}
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL)
+		req.flow_label = cpu_to_le32(qp->ah.flow_label);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX)
+		req.sgid_index = cpu_to_le16(res->sgid_tbl.hw_id
+					     [qp->ah.sgid_index]);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT)
+		req.hop_limit = qp->ah.hop_limit;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS)
+		req.traffic_class = qp->ah.traffic_class;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC)
+		memcpy(req.dest_mac, qp->ah.dmac, 6);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU)
+		req.path_mtu = qp->path_mtu;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_TIMEOUT)
+		req.timeout = qp->timeout;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_RETRY_CNT)
+		req.retry_cnt = qp->retry_cnt;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_RNR_RETRY)
+		req.rnr_retry = qp->rnr_retry;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER)
+		req.min_rnr_timer = qp->min_rnr_timer;
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN)
+		req.rq_psn = cpu_to_le32(qp->rq.psn);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_SQ_PSN)
+		req.sq_psn = cpu_to_le32(qp->sq.psn);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_MAX_RD_ATOMIC)
+		req.max_rd_atomic =
+			ORD_LIMIT_TO_ORRQ_SLOTS(qp->max_rd_atomic);
+
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC)
+		req.max_dest_rd_atomic =
+			IRD_LIMIT_TO_IRRQ_SLOTS(qp->max_dest_rd_atomic);
+
+	req.sq_size = cpu_to_le32(qp->sq.hwq.max_elements);
+	req.rq_size = cpu_to_le32(qp->rq.hwq.max_elements);
+	req.sq_sge = cpu_to_le16(qp->sq.max_sge);
+	req.rq_sge = cpu_to_le16(qp->rq.max_sge);
+	req.max_inline_data = cpu_to_le32(qp->max_inline_data);
+	if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID)
+		req.dest_qp_id = cpu_to_le32(qp->dest_qpn);
+
+	req.vlan_pcp_vlan_dei_vlan_id = cpu_to_le16(qp->vlan_id);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		return rc;
+	qp->cur_qp_state = qp->state;
+	return 0;
+}
+
+int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_query_qp req;
+	struct creq_query_qp_resp resp;
+	struct bnxt_qplib_rcfw_sbuf *sbuf;
+	struct creq_query_qp_resp_sb *sb;
+	u16 cmd_flags = 0;
+	u32 temp32[4];
+	int i, rc = 0;
+
+	RCFW_CMD_PREP(req, QUERY_QP, cmd_flags);
+
+	sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb));
+	if (!sbuf)
+		return -ENOMEM;
+	sb = sbuf->sb;
+
+	req.qp_cid = cpu_to_le32(qp->id);
+	req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS;
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  (void *)sbuf, 0);
+	if (rc)
+		goto bail;
+	/* Extract the context from the side buffer */
+	qp->state = sb->en_sqd_async_notify_state &
+			CREQ_QUERY_QP_RESP_SB_STATE_MASK;
+	qp->en_sqd_async_notify = sb->en_sqd_async_notify_state &
+				  CREQ_QUERY_QP_RESP_SB_EN_SQD_ASYNC_NOTIFY ?
+				  true : false;
+	qp->access = sb->access;
+	qp->pkey_index = le16_to_cpu(sb->pkey);
+	qp->qkey = le32_to_cpu(sb->qkey);
+
+	temp32[0] = le32_to_cpu(sb->dgid[0]);
+	temp32[1] = le32_to_cpu(sb->dgid[1]);
+	temp32[2] = le32_to_cpu(sb->dgid[2]);
+	temp32[3] = le32_to_cpu(sb->dgid[3]);
+	memcpy(qp->ah.dgid.data, temp32, sizeof(qp->ah.dgid.data));
+
+	qp->ah.flow_label = le32_to_cpu(sb->flow_label);
+
+	qp->ah.sgid_index = 0;
+	for (i = 0; i < res->sgid_tbl.max; i++) {
+		if (res->sgid_tbl.hw_id[i] == le16_to_cpu(sb->sgid_index)) {
+			qp->ah.sgid_index = i;
+			break;
+		}
+	}
+	if (i == res->sgid_tbl.max)
+		dev_warn(&res->pdev->dev, "SGID not found??\n");
+
+	qp->ah.hop_limit = sb->hop_limit;
+	qp->ah.traffic_class = sb->traffic_class;
+	memcpy(qp->ah.dmac, sb->dest_mac, 6);
+	qp->ah.vlan_id = (le16_to_cpu(sb->path_mtu_dest_vlan_id) &
+				CREQ_QUERY_QP_RESP_SB_VLAN_ID_MASK) >>
+				CREQ_QUERY_QP_RESP_SB_VLAN_ID_SFT;
+	qp->path_mtu = (le16_to_cpu(sb->path_mtu_dest_vlan_id) &
+				    CREQ_QUERY_QP_RESP_SB_PATH_MTU_MASK) >>
+				    CREQ_QUERY_QP_RESP_SB_PATH_MTU_SFT;
+	qp->timeout = sb->timeout;
+	qp->retry_cnt = sb->retry_cnt;
+	qp->rnr_retry = sb->rnr_retry;
+	qp->min_rnr_timer = sb->min_rnr_timer;
+	qp->rq.psn = le32_to_cpu(sb->rq_psn);
+	qp->max_rd_atomic = ORRQ_SLOTS_TO_ORD_LIMIT(sb->max_rd_atomic);
+	qp->sq.psn = le32_to_cpu(sb->sq_psn);
+	qp->max_dest_rd_atomic =
+			IRRQ_SLOTS_TO_IRD_LIMIT(sb->max_dest_rd_atomic);
+	qp->sq.max_wqe = qp->sq.hwq.max_elements;
+	qp->rq.max_wqe = qp->rq.hwq.max_elements;
+	qp->sq.max_sge = le16_to_cpu(sb->sq_sge);
+	qp->rq.max_sge = le16_to_cpu(sb->rq_sge);
+	qp->max_inline_data = le32_to_cpu(sb->max_inline_data);
+	qp->dest_qpn = le32_to_cpu(sb->dest_qp_id);
+	memcpy(qp->smac, sb->src_mac, 6);
+	qp->vlan_id = le16_to_cpu(sb->vlan_pcp_vlan_dei_vlan_id);
+bail:
+	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
+	return rc;
+}
+
+static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp)
+{
+	struct bnxt_qplib_hwq *cq_hwq = &cq->hwq;
+	struct cq_base *hw_cqe;
+	int i;
+
+	for (i = 0; i < cq_hwq->max_elements; i++) {
+		hw_cqe = bnxt_qplib_get_qe(cq_hwq, i, NULL);
+		if (!CQE_CMP_VALID(hw_cqe, i, cq_hwq->max_elements))
+			continue;
+		/*
+		 * The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
+		switch (hw_cqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK) {
+		case CQ_BASE_CQE_TYPE_REQ:
+		case CQ_BASE_CQE_TYPE_TERMINAL:
+		{
+			struct cq_req *cqe = (struct cq_req *)hw_cqe;
+
+			if (qp == le64_to_cpu(cqe->qp_handle))
+				cqe->qp_handle = 0;
+			break;
+		}
+		case CQ_BASE_CQE_TYPE_RES_RC:
+		case CQ_BASE_CQE_TYPE_RES_UD:
+		case CQ_BASE_CQE_TYPE_RES_RAWETH_QP1:
+		{
+			struct cq_res_rc *cqe = (struct cq_res_rc *)hw_cqe;
+
+			if (qp == le64_to_cpu(cqe->qp_handle))
+				cqe->qp_handle = 0;
+			break;
+		}
+		default:
+			break;
+		}
+	}
+}
+
+int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
+			  struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_destroy_qp req;
+	struct creq_destroy_qp_resp resp;
+	u16 cmd_flags = 0;
+	u32 tbl_indx;
+	int rc;
+
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID;
+	rcfw->qp_tbl[tbl_indx].qp_handle = NULL;
+
+	RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags);
+
+	req.qp_cid = cpu_to_le32(qp->id);
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc) {
+		rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+		rcfw->qp_tbl[tbl_indx].qp_handle = qp;
+		return rc;
+	}
+
+	return 0;
+}
+
+void bnxt_qplib_free_qp_res(struct bnxt_qplib_res *res,
+			    struct bnxt_qplib_qp *qp)
+{
+	bnxt_qplib_free_qp_hdr_buf(res, qp);
+	bnxt_qplib_free_hwq(res, &qp->sq.hwq);
+	kfree(qp->sq.swq);
+
+	bnxt_qplib_free_hwq(res, &qp->rq.hwq);
+	kfree(qp->rq.swq);
+
+	if (qp->irrq.max_elements)
+		bnxt_qplib_free_hwq(res, &qp->irrq);
+	if (qp->orrq.max_elements)
+		bnxt_qplib_free_hwq(res, &qp->orrq);
+
+}
+
+void *bnxt_qplib_get_qp1_sq_buf(struct bnxt_qplib_qp *qp,
+				struct bnxt_qplib_sge *sge)
+{
+	struct bnxt_qplib_q *sq = &qp->sq;
+	u32 sw_prod;
+
+	memset(sge, 0, sizeof(*sge));
+
+	if (qp->sq_hdr_buf) {
+		sw_prod = sq->swq_start;
+		sge->addr = (dma_addr_t)(qp->sq_hdr_buf_map +
+					 sw_prod * qp->sq_hdr_buf_size);
+		sge->lkey = 0xFFFFFFFF;
+		sge->size = qp->sq_hdr_buf_size;
+		return qp->sq_hdr_buf + sw_prod * sge->size;
+	}
+	return NULL;
+}
+
+u32 bnxt_qplib_get_rq_prod_index(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_q *rq = &qp->rq;
+
+	return rq->swq_start;
+}
+
+dma_addr_t bnxt_qplib_get_qp_buf_from_index(struct bnxt_qplib_qp *qp, u32 index)
+{
+	return (qp->rq_hdr_buf_map + index * qp->rq_hdr_buf_size);
+}
+
+void *bnxt_qplib_get_qp1_rq_buf(struct bnxt_qplib_qp *qp,
+				struct bnxt_qplib_sge *sge)
+{
+	struct bnxt_qplib_q *rq = &qp->rq;
+	u32 sw_prod;
+
+	memset(sge, 0, sizeof(*sge));
+
+	if (qp->rq_hdr_buf) {
+		sw_prod = rq->swq_start;
+		sge->addr = (dma_addr_t)(qp->rq_hdr_buf_map +
+					 sw_prod * qp->rq_hdr_buf_size);
+		sge->lkey = 0xFFFFFFFF;
+		sge->size = qp->rq_hdr_buf_size;
+		return qp->rq_hdr_buf + sw_prod * sge->size;
+	}
+	return NULL;
+}
+
+static void bnxt_qplib_fill_psn_search(struct bnxt_qplib_qp *qp,
+				       struct bnxt_qplib_swqe *wqe,
+				       struct bnxt_qplib_swq *swq)
+{
+	struct sq_psn_search_ext *psns_ext;
+	struct sq_psn_search *psns;
+	u32 flg_npsn;
+	u32 op_spsn;
+
+	if (!swq->psn_search)
+		return;
+	psns = swq->psn_search;
+	psns_ext = swq->psn_ext;
+
+	op_spsn = ((swq->start_psn << SQ_PSN_SEARCH_START_PSN_SFT) &
+		    SQ_PSN_SEARCH_START_PSN_MASK);
+	op_spsn |= ((wqe->type << SQ_PSN_SEARCH_OPCODE_SFT) &
+		     SQ_PSN_SEARCH_OPCODE_MASK);
+	flg_npsn = ((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) &
+		     SQ_PSN_SEARCH_NEXT_PSN_MASK);
+
+	if (bnxt_qplib_is_chip_gen_p5(qp->cctx)) {
+		psns_ext->opcode_start_psn = cpu_to_le32(op_spsn);
+		psns_ext->flags_next_psn = cpu_to_le32(flg_npsn);
+		psns_ext->start_slot_idx = cpu_to_le16(swq->slot_idx);
+	} else {
+		psns->opcode_start_psn = cpu_to_le32(op_spsn);
+		psns->flags_next_psn = cpu_to_le32(flg_npsn);
+	}
+}
+
+static int bnxt_qplib_put_inline(struct bnxt_qplib_qp *qp,
+				 struct bnxt_qplib_swqe *wqe,
+				 u16 *idx)
+{
+	struct bnxt_qplib_hwq *hwq;
+	int len, t_len, offt;
+	bool pull_dst = true;
+	void *il_dst = NULL;
+	void *il_src = NULL;
+	int t_cplen, cplen;
+	int indx;
+
+	hwq = &qp->sq.hwq;
+	t_len = 0;
+	for (indx = 0; indx < wqe->num_sge; indx++) {
+		len = wqe->sg_list[indx].size;
+		il_src = (void *)wqe->sg_list[indx].addr;
+		t_len += len;
+		if (t_len > qp->max_inline_data)
+			return -ENOMEM;
+		while (len) {
+			if (pull_dst) {
+				pull_dst = false;
+				il_dst = bnxt_qplib_get_prod_qe(hwq, *idx);
+				(*idx)++;
+				t_cplen = 0;
+				offt = 0;
+			}
+			cplen = min_t(int, len, sizeof(struct sq_sge));
+			cplen = min_t(int, cplen,
+					(sizeof(struct sq_sge) - offt));
+			memcpy(il_dst, il_src, cplen);
+			t_cplen += cplen;
+			il_src += cplen;
+			il_dst += cplen;
+			offt += cplen;
+			len -= cplen;
+			if (t_cplen == sizeof(struct sq_sge))
+				pull_dst = true;
+		}
+	}
+
+	return t_len;
+}
+
+static u32 bnxt_qplib_put_sges(struct bnxt_qplib_hwq *hwq,
+			       struct bnxt_qplib_sge *ssge,
+			       u16 nsge, u16 *idx)
+{
+	struct sq_sge *dsge;
+	int indx, len = 0;
+
+	for (indx = 0; indx < nsge; indx++, (*idx)++) {
+		dsge = bnxt_qplib_get_prod_qe(hwq, *idx);
+		dsge->va_or_pa = cpu_to_le64(ssge[indx].addr);
+		dsge->l_key = cpu_to_le32(ssge[indx].lkey);
+		dsge->size = cpu_to_le32(ssge[indx].size);
+		len += ssge[indx].size;
+	}
+
+	return len;
+}
+
+static u16 bnxt_qplib_required_slots(struct bnxt_qplib_qp *qp,
+				     struct bnxt_qplib_swqe *wqe,
+				     u16 *wqe_sz, u16 *qdf, u8 mode)
+{
+	u32 ilsize, bytes;
+	u16 nsge;
+	u16 slot;
+
+	nsge = wqe->num_sge;
+	/* Adding sq_send_hdr is a misnomer, for rq also hdr size is same. */
+	bytes = sizeof(struct sq_send_hdr) + nsge * sizeof(struct sq_sge);
+	if (wqe->flags & BNXT_QPLIB_SWQE_FLAGS_INLINE) {
+		ilsize = bnxt_qplib_calc_ilsize(wqe, qp->max_inline_data);
+		bytes = ALIGN(ilsize, sizeof(struct sq_sge));
+		bytes += sizeof(struct sq_send_hdr);
+	}
+
+	*qdf =  __xlate_qfd(qp->sq.q_full_delta, bytes);
+	slot = bytes >> 4;
+	*wqe_sz = slot;
+	if (mode == BNXT_QPLIB_WQE_MODE_STATIC)
+		slot = 8;
+	return slot;
+}
+
+static void bnxt_qplib_pull_psn_buff(struct bnxt_qplib_q *sq,
+				     struct bnxt_qplib_swq *swq)
+{
+	struct bnxt_qplib_hwq *hwq;
+	u32 pg_num, pg_indx;
+	void *buff;
+	u32 tail;
+
+	hwq = &sq->hwq;
+	if (!hwq->pad_pg)
+		return;
+	tail = swq->slot_idx / sq->dbinfo.max_slot;
+	pg_num = (tail + hwq->pad_pgofft) / (PAGE_SIZE / hwq->pad_stride);
+	pg_indx = (tail + hwq->pad_pgofft) % (PAGE_SIZE / hwq->pad_stride);
+	buff = (void *)(hwq->pad_pg[pg_num] + pg_indx * hwq->pad_stride);
+	swq->psn_ext = buff;
+	swq->psn_search = buff;
+}
+
+void bnxt_qplib_post_send_db(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_q *sq = &qp->sq;
+
+	bnxt_qplib_ring_prod_db(&sq->dbinfo, DBC_DBC_TYPE_SQ);
+}
+
+int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
+			 struct bnxt_qplib_swqe *wqe)
+{
+	struct bnxt_qplib_nq_work *nq_work = NULL;
+	int i, rc = 0, data_len = 0, pkt_num = 0;
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct bnxt_qplib_hwq *hwq;
+	struct bnxt_qplib_swq *swq;
+	bool sch_handler = false;
+	u16 wqe_sz, qdf = 0;
+	void *base_hdr;
+	void *ext_hdr;
+	__le32 temp32;
+	u32 wqe_idx;
+	u32 slots;
+	u16 idx;
+
+	hwq = &sq->hwq;
+	if (qp->state != CMDQ_MODIFY_QP_NEW_STATE_RTS &&
+	    qp->state != CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+		dev_err(&hwq->pdev->dev,
+			"QPLIB: FP: QP (0x%x) is in the 0x%x state",
+			qp->id, qp->state);
+		rc = -EINVAL;
+		goto done;
+	}
+
+	slots = bnxt_qplib_required_slots(qp, wqe, &wqe_sz, &qdf, qp->wqe_mode);
+	if (bnxt_qplib_queue_full(sq, slots + qdf)) {
+		dev_err(&hwq->pdev->dev,
+			"prod = %#x cons = %#x qdepth = %#x delta = %#x\n",
+			hwq->prod, hwq->cons, hwq->depth, sq->q_full_delta);
+		rc = -ENOMEM;
+		goto done;
+	}
+
+	swq = bnxt_qplib_get_swqe(sq, &wqe_idx);
+	bnxt_qplib_pull_psn_buff(sq, swq);
+
+	idx = 0;
+	swq->slot_idx = hwq->prod;
+	swq->slots = slots;
+	swq->wr_id = wqe->wr_id;
+	swq->type = wqe->type;
+	swq->flags = wqe->flags;
+	swq->start_psn = sq->psn & BTH_PSN_MASK;
+	if (qp->sig_type)
+		swq->flags |= SQ_SEND_FLAGS_SIGNAL_COMP;
+
+	if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+		sch_handler = true;
+		dev_dbg(&hwq->pdev->dev,
+			"%s Error QP. Scheduling for poll_cq\n", __func__);
+		goto queue_err;
+	}
+
+	base_hdr = bnxt_qplib_get_prod_qe(hwq, idx++);
+	ext_hdr = bnxt_qplib_get_prod_qe(hwq, idx++);
+	memset(base_hdr, 0, sizeof(struct sq_sge));
+	memset(ext_hdr, 0, sizeof(struct sq_sge));
+
+	if (wqe->flags & BNXT_QPLIB_SWQE_FLAGS_INLINE)
+		/* Copy the inline data */
+		data_len = bnxt_qplib_put_inline(qp, wqe, &idx);
+	else
+		data_len = bnxt_qplib_put_sges(hwq, wqe->sg_list, wqe->num_sge,
+					       &idx);
+	if (data_len < 0)
+		goto queue_err;
+	/* Specifics */
+	switch (wqe->type) {
+	case BNXT_QPLIB_SWQE_TYPE_SEND:
+		if (qp->type == CMDQ_CREATE_QP1_TYPE_GSI) {
+			struct sq_send_raweth_qp1_hdr *sqe = base_hdr;
+			struct sq_raw_ext_hdr *ext_sqe = ext_hdr;
+			/* Assemble info for Raw Ethertype QPs */
+
+			sqe->wqe_type = wqe->type;
+			sqe->flags = wqe->flags;
+			sqe->wqe_size = wqe_sz;
+			sqe->cfa_action = cpu_to_le16(wqe->rawqp1.cfa_action);
+			sqe->lflags = cpu_to_le16(wqe->rawqp1.lflags);
+			sqe->length = cpu_to_le32(data_len);
+			ext_sqe->cfa_meta = cpu_to_le32((wqe->rawqp1.cfa_meta &
+				SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_MASK) <<
+				SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_SFT);
+
+			break;
+		}
+		fallthrough;
+	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM:
+	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV:
+	{
+		struct sq_ud_ext_hdr *ext_sqe = ext_hdr;
+		struct sq_send_hdr *sqe = base_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->wqe_size = wqe_sz;
+		sqe->inv_key_or_imm_data = cpu_to_le32(wqe->send.inv_key);
+		if (qp->type == CMDQ_CREATE_QP_TYPE_UD ||
+		    qp->type == CMDQ_CREATE_QP_TYPE_GSI) {
+			sqe->q_key = cpu_to_le32(wqe->send.q_key);
+			sqe->length = cpu_to_le32(data_len);
+			sq->psn = (sq->psn + 1) & BTH_PSN_MASK;
+			ext_sqe->dst_qp = cpu_to_le32(wqe->send.dst_qp &
+						      SQ_SEND_DST_QP_MASK);
+			ext_sqe->avid = cpu_to_le32(wqe->send.avid &
+						    SQ_SEND_AVID_MASK);
+		} else {
+			sqe->length = cpu_to_le32(data_len);
+			if (qp->mtu)
+				pkt_num = (data_len + qp->mtu - 1) / qp->mtu;
+			if (!pkt_num)
+				pkt_num = 1;
+			sq->psn = (sq->psn + pkt_num) & BTH_PSN_MASK;
+		}
+		break;
+	}
+	case BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE:
+	case BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE_WITH_IMM:
+	case BNXT_QPLIB_SWQE_TYPE_RDMA_READ:
+	{
+		struct sq_rdma_ext_hdr *ext_sqe = ext_hdr;
+		struct sq_rdma_hdr *sqe = base_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->wqe_size = wqe_sz;
+		sqe->imm_data = cpu_to_le32(wqe->rdma.inv_key);
+		sqe->length = cpu_to_le32((u32)data_len);
+		ext_sqe->remote_va = cpu_to_le64(wqe->rdma.remote_va);
+		ext_sqe->remote_key = cpu_to_le32(wqe->rdma.r_key);
+		if (qp->mtu)
+			pkt_num = (data_len + qp->mtu - 1) / qp->mtu;
+		if (!pkt_num)
+			pkt_num = 1;
+		sq->psn = (sq->psn + pkt_num) & BTH_PSN_MASK;
+		break;
+	}
+	case BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP:
+	case BNXT_QPLIB_SWQE_TYPE_ATOMIC_FETCH_AND_ADD:
+	{
+		struct sq_atomic_ext_hdr *ext_sqe = ext_hdr;
+		struct sq_atomic_hdr *sqe = base_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->remote_key = cpu_to_le32(wqe->atomic.r_key);
+		sqe->remote_va = cpu_to_le64(wqe->atomic.remote_va);
+		ext_sqe->swap_data = cpu_to_le64(wqe->atomic.swap_data);
+		ext_sqe->cmp_data = cpu_to_le64(wqe->atomic.cmp_data);
+		if (qp->mtu)
+			pkt_num = (data_len + qp->mtu - 1) / qp->mtu;
+		if (!pkt_num)
+			pkt_num = 1;
+		sq->psn = (sq->psn + pkt_num) & BTH_PSN_MASK;
+		break;
+	}
+	case BNXT_QPLIB_SWQE_TYPE_LOCAL_INV:
+	{
+		struct sq_localinvalidate *sqe = base_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->inv_l_key = cpu_to_le32(wqe->local_inv.inv_l_key);
+
+		break;
+	}
+	case BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR:
+	{
+		struct sq_fr_pmr_ext_hdr *ext_sqe = ext_hdr;
+		struct sq_fr_pmr_hdr *sqe = base_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->access_cntl = wqe->frmr.access_cntl |
+				   SQ_FR_PMR_ACCESS_CNTL_LOCAL_WRITE;
+		sqe->zero_based_page_size_log =
+			(wqe->frmr.pg_sz_log & SQ_FR_PMR_PAGE_SIZE_LOG_MASK) <<
+			SQ_FR_PMR_PAGE_SIZE_LOG_SFT |
+			(wqe->frmr.zero_based ? SQ_FR_PMR_ZERO_BASED : 0);
+		sqe->l_key = cpu_to_le32(wqe->frmr.l_key);
+		temp32 = cpu_to_le32(wqe->frmr.length);
+		memcpy(sqe->length, &temp32, sizeof(wqe->frmr.length));
+		sqe->numlevels_pbl_page_size_log =
+			((wqe->frmr.pbl_pg_sz_log <<
+					SQ_FR_PMR_PBL_PAGE_SIZE_LOG_SFT) &
+					SQ_FR_PMR_PBL_PAGE_SIZE_LOG_MASK) |
+			((wqe->frmr.levels << SQ_FR_PMR_NUMLEVELS_SFT) &
+					SQ_FR_PMR_NUMLEVELS_MASK);
+
+		for (i = 0; i < wqe->frmr.page_list_len; i++)
+			wqe->frmr.pbl_ptr[i] = cpu_to_le64(
+						wqe->frmr.page_list[i] |
+						PTU_PTE_VALID);
+		ext_sqe->pblptr = cpu_to_le64(wqe->frmr.pbl_dma_ptr);
+		ext_sqe->va = cpu_to_le64(wqe->frmr.va);
+
+		break;
+	}
+	case BNXT_QPLIB_SWQE_TYPE_BIND_MW:
+	{
+		struct sq_bind_ext_hdr *ext_sqe = ext_hdr;
+		struct sq_bind_hdr *sqe = base_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->access_cntl = wqe->bind.access_cntl;
+		sqe->mw_type_zero_based = wqe->bind.mw_type |
+			(wqe->bind.zero_based ? SQ_BIND_ZERO_BASED : 0);
+		sqe->parent_l_key = cpu_to_le32(wqe->bind.parent_l_key);
+		sqe->l_key = cpu_to_le32(wqe->bind.r_key);
+		ext_sqe->va = cpu_to_le64(wqe->bind.va);
+		ext_sqe->length_lo = cpu_to_le32(wqe->bind.length);
+		break;
+	}
+	default:
+		/* Bad wqe, return error */
+		rc = -EINVAL;
+		goto done;
+	}
+	swq->next_psn = sq->psn & BTH_PSN_MASK;
+	bnxt_qplib_fill_psn_search(qp, wqe, swq);
+queue_err:
+	bnxt_qplib_swq_mod_start(sq, wqe_idx);
+	bnxt_qplib_hwq_incr_prod(hwq, swq->slots);
+	qp->wqe_cnt++;
+done:
+	if (sch_handler) {
+		nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC);
+		if (nq_work) {
+			nq_work->cq = qp->scq;
+			nq_work->nq = qp->scq->nq;
+			INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task);
+			queue_work(qp->scq->nq->cqn_wq, &nq_work->work);
+		} else {
+			dev_err(&hwq->pdev->dev,
+				"FP: Failed to allocate SQ nq_work!\n");
+			rc = -ENOMEM;
+		}
+	}
+	return rc;
+}
+
+void bnxt_qplib_post_recv_db(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_q *rq = &qp->rq;
+
+	bnxt_qplib_ring_prod_db(&rq->dbinfo, DBC_DBC_TYPE_RQ);
+}
+
+int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp,
+			 struct bnxt_qplib_swqe *wqe)
+{
+	struct bnxt_qplib_nq_work *nq_work = NULL;
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct rq_wqe_hdr *base_hdr;
+	struct rq_ext_hdr *ext_hdr;
+	struct bnxt_qplib_hwq *hwq;
+	struct bnxt_qplib_swq *swq;
+	bool sch_handler = false;
+	u16 wqe_sz, idx;
+	u32 wqe_idx;
+	int rc = 0;
+
+	hwq = &rq->hwq;
+	if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_RESET) {
+		dev_err(&hwq->pdev->dev,
+			"QPLIB: FP: QP (0x%x) is in the 0x%x state",
+			qp->id, qp->state);
+		rc = -EINVAL;
+		goto done;
+	}
+
+	if (bnxt_qplib_queue_full(rq, rq->dbinfo.max_slot)) {
+		dev_err(&hwq->pdev->dev,
+			"FP: QP (0x%x) RQ is full!\n", qp->id);
+		rc = -EINVAL;
+		goto done;
+	}
+
+	swq = bnxt_qplib_get_swqe(rq, &wqe_idx);
+	swq->wr_id = wqe->wr_id;
+	swq->slots = rq->dbinfo.max_slot;
+
+	if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+		sch_handler = true;
+		dev_dbg(&hwq->pdev->dev,
+			"%s: Error QP. Scheduling for poll_cq\n", __func__);
+		goto queue_err;
+	}
+
+	idx = 0;
+	base_hdr = bnxt_qplib_get_prod_qe(hwq, idx++);
+	ext_hdr = bnxt_qplib_get_prod_qe(hwq, idx++);
+	memset(base_hdr, 0, sizeof(struct sq_sge));
+	memset(ext_hdr, 0, sizeof(struct sq_sge));
+	wqe_sz = (sizeof(struct rq_wqe_hdr) +
+	wqe->num_sge * sizeof(struct sq_sge)) >> 4;
+	bnxt_qplib_put_sges(hwq, wqe->sg_list, wqe->num_sge, &idx);
+	if (!wqe->num_sge) {
+		struct sq_sge *sge;
+
+		sge = bnxt_qplib_get_prod_qe(hwq, idx++);
+		sge->size = 0;
+		wqe_sz++;
+	}
+	base_hdr->wqe_type = wqe->type;
+	base_hdr->flags = wqe->flags;
+	base_hdr->wqe_size = wqe_sz;
+	base_hdr->wr_id[0] = cpu_to_le32(wqe_idx);
+queue_err:
+	bnxt_qplib_swq_mod_start(rq, wqe_idx);
+	bnxt_qplib_hwq_incr_prod(hwq, swq->slots);
+done:
+	if (sch_handler) {
+		nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC);
+		if (nq_work) {
+			nq_work->cq = qp->rcq;
+			nq_work->nq = qp->rcq->nq;
+			INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task);
+			queue_work(qp->rcq->nq->cqn_wq, &nq_work->work);
+		} else {
+			dev_err(&hwq->pdev->dev,
+				"FP: Failed to allocate RQ nq_work!\n");
+			rc = -ENOMEM;
+		}
+	}
+
+	return rc;
+}
+
+/* CQ */
+int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct creq_create_cq_resp resp;
+	struct bnxt_qplib_pbl *pbl;
+	struct cmdq_create_cq req;
+	u16 cmd_flags = 0;
+	u32 pg_sz_lvl;
+	int rc;
+
+	if (!cq->dpi) {
+		dev_err(&rcfw->pdev->dev,
+			"FP: CREATE_CQ failed due to NULL DPI\n");
+		return -EINVAL;
+	}
+
+	hwq_attr.res = res;
+	hwq_attr.depth = cq->max_wqe;
+	hwq_attr.stride = sizeof(struct cq_base);
+	hwq_attr.type = HWQ_TYPE_QUEUE;
+	hwq_attr.sginfo = &cq->sg_info;
+	rc = bnxt_qplib_alloc_init_hwq(&cq->hwq, &hwq_attr);
+	if (rc)
+		return rc;
+
+	RCFW_CMD_PREP(req, CREATE_CQ, cmd_flags);
+
+	req.dpi = cpu_to_le32(cq->dpi->dpi);
+	req.cq_handle = cpu_to_le64(cq->cq_handle);
+	req.cq_size = cpu_to_le32(cq->hwq.max_elements);
+	pbl = &cq->hwq.pbl[PBL_LVL_0];
+	pg_sz_lvl = (bnxt_qplib_base_pg_size(&cq->hwq) <<
+		     CMDQ_CREATE_CQ_PG_SIZE_SFT);
+	pg_sz_lvl |= (cq->hwq.level & CMDQ_CREATE_CQ_LVL_MASK);
+	req.pg_size_lvl = cpu_to_le32(pg_sz_lvl);
+	req.pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+	req.cq_fco_cnq_id = cpu_to_le32(
+			(cq->cnq_hw_ring_id & CMDQ_CREATE_CQ_CNQ_ID_MASK) <<
+			 CMDQ_CREATE_CQ_CNQ_ID_SFT);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		goto fail;
+
+	cq->id = le32_to_cpu(resp.xid);
+	cq->period = BNXT_QPLIB_QUEUE_START_PERIOD;
+	init_waitqueue_head(&cq->waitq);
+	INIT_LIST_HEAD(&cq->sqf_head);
+	INIT_LIST_HEAD(&cq->rqf_head);
+	spin_lock_init(&cq->compl_lock);
+	spin_lock_init(&cq->flush_lock);
+
+	cq->dbinfo.hwq = &cq->hwq;
+	cq->dbinfo.xid = cq->id;
+	cq->dbinfo.db = cq->dpi->dbr;
+	cq->dbinfo.priv_db = res->dpi_tbl.dbr_bar_reg_iomem;
+
+	bnxt_qplib_armen_db(&cq->dbinfo, DBC_DBC_TYPE_CQ_ARMENA);
+
+	return 0;
+
+fail:
+	bnxt_qplib_free_hwq(res, &cq->hwq);
+	return rc;
+}
+
+int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_destroy_cq req;
+	struct creq_destroy_cq_resp resp;
+	u16 total_cnq_events;
+	u16 cmd_flags = 0;
+	int rc;
+
+	RCFW_CMD_PREP(req, DESTROY_CQ, cmd_flags);
+
+	req.cq_cid = cpu_to_le32(cq->id);
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		return rc;
+	total_cnq_events = le16_to_cpu(resp.total_cnq_events);
+	__wait_for_all_nqes(cq, total_cnq_events);
+	bnxt_qplib_free_hwq(res, &cq->hwq);
+	return 0;
+}
+
+static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp,
+		      struct bnxt_qplib_cqe **pcqe, int *budget)
+{
+	struct bnxt_qplib_cqe *cqe;
+	u32 start, last;
+	int rc = 0;
+
+	/* Now complete all outstanding SQEs with FLUSHED_ERR */
+	start = sq->swq_start;
+	cqe = *pcqe;
+	while (*budget) {
+		last = sq->swq_last;
+		if (start == last)
+			break;
+		/* Skip the FENCE WQE completions */
+		if (sq->swq[last].wr_id == BNXT_QPLIB_FENCE_WRID) {
+			bnxt_qplib_cancel_phantom_processing(qp);
+			goto skip_compl;
+		}
+		memset(cqe, 0, sizeof(*cqe));
+		cqe->status = CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR;
+		cqe->opcode = CQ_BASE_CQE_TYPE_REQ;
+		cqe->qp_handle = (u64)(unsigned long)qp;
+		cqe->wr_id = sq->swq[last].wr_id;
+		cqe->src_qp = qp->id;
+		cqe->type = sq->swq[last].type;
+		cqe++;
+		(*budget)--;
+skip_compl:
+		bnxt_qplib_hwq_incr_cons(&sq->hwq, sq->swq[last].slots);
+		sq->swq_last = sq->swq[last].next_idx;
+	}
+	*pcqe = cqe;
+	if (!(*budget) && sq->swq_last != start)
+		/* Out of budget */
+		rc = -EAGAIN;
+
+	return rc;
+}
+
+static int __flush_rq(struct bnxt_qplib_q *rq, struct bnxt_qplib_qp *qp,
+		      struct bnxt_qplib_cqe **pcqe, int *budget)
+{
+	struct bnxt_qplib_cqe *cqe;
+	u32 start, last;
+	int opcode = 0;
+	int rc = 0;
+
+	switch (qp->type) {
+	case CMDQ_CREATE_QP1_TYPE_GSI:
+		opcode = CQ_BASE_CQE_TYPE_RES_RAWETH_QP1;
+		break;
+	case CMDQ_CREATE_QP_TYPE_RC:
+		opcode = CQ_BASE_CQE_TYPE_RES_RC;
+		break;
+	case CMDQ_CREATE_QP_TYPE_UD:
+	case CMDQ_CREATE_QP_TYPE_GSI:
+		opcode = CQ_BASE_CQE_TYPE_RES_UD;
+		break;
+	}
+
+	/* Flush the rest of the RQ */
+	start = rq->swq_start;
+	cqe = *pcqe;
+	while (*budget) {
+		last = rq->swq_last;
+		if (last == start)
+			break;
+		memset(cqe, 0, sizeof(*cqe));
+		cqe->status =
+		    CQ_RES_RC_STATUS_WORK_REQUEST_FLUSHED_ERR;
+		cqe->opcode = opcode;
+		cqe->qp_handle = (unsigned long)qp;
+		cqe->wr_id = rq->swq[last].wr_id;
+		cqe++;
+		(*budget)--;
+		bnxt_qplib_hwq_incr_cons(&rq->hwq, rq->swq[last].slots);
+		rq->swq_last = rq->swq[last].next_idx;
+	}
+	*pcqe = cqe;
+	if (!*budget && rq->swq_last != start)
+		/* Out of budget */
+		rc = -EAGAIN;
+
+	return rc;
+}
+
+void bnxt_qplib_mark_qp_error(void *qp_handle)
+{
+	struct bnxt_qplib_qp *qp = qp_handle;
+
+	if (!qp)
+		return;
+
+	/* Must block new posting of SQ and RQ */
+	qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
+	bnxt_qplib_cancel_phantom_processing(qp);
+}
+
+/* Note: SQE is valid from sw_sq_cons up to cqe_sq_cons (exclusive)
+ *       CQE is track from sw_cq_cons to max_element but valid only if VALID=1
+ */
+static int do_wa9060(struct bnxt_qplib_qp *qp, struct bnxt_qplib_cq *cq,
+		     u32 cq_cons, u32 swq_last, u32 cqe_sq_cons)
+{
+	u32 peek_sw_cq_cons, peek_raw_cq_cons, peek_sq_cons_idx;
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct cq_req *peek_req_hwcqe;
+	struct bnxt_qplib_qp *peek_qp;
+	struct bnxt_qplib_q *peek_sq;
+	struct bnxt_qplib_swq *swq;
+	struct cq_base *peek_hwcqe;
+	int i, rc = 0;
+
+	/* Normal mode */
+	/* Check for the psn_search marking before completing */
+	swq = &sq->swq[swq_last];
+	if (swq->psn_search &&
+	    le32_to_cpu(swq->psn_search->flags_next_psn) & 0x80000000) {
+		/* Unmark */
+		swq->psn_search->flags_next_psn = cpu_to_le32
+			(le32_to_cpu(swq->psn_search->flags_next_psn)
+				     & ~0x80000000);
+		dev_dbg(&cq->hwq.pdev->dev,
+			"FP: Process Req cq_cons=0x%x qp=0x%x sq cons sw=0x%x cqe=0x%x marked!\n",
+			cq_cons, qp->id, swq_last, cqe_sq_cons);
+		sq->condition = true;
+		sq->send_phantom = true;
+
+		/* TODO: Only ARM if the previous SQE is ARMALL */
+		bnxt_qplib_ring_db(&cq->dbinfo, DBC_DBC_TYPE_CQ_ARMALL);
+		rc = -EAGAIN;
+		goto out;
+	}
+	if (sq->condition) {
+		/* Peek at the completions */
+		peek_raw_cq_cons = cq->hwq.cons;
+		peek_sw_cq_cons = cq_cons;
+		i = cq->hwq.max_elements;
+		while (i--) {
+			peek_sw_cq_cons = HWQ_CMP((peek_sw_cq_cons), &cq->hwq);
+			peek_hwcqe = bnxt_qplib_get_qe(&cq->hwq,
+						       peek_sw_cq_cons, NULL);
+			/* If the next hwcqe is VALID */
+			if (CQE_CMP_VALID(peek_hwcqe, peek_raw_cq_cons,
+					  cq->hwq.max_elements)) {
+			/*
+			 * The valid test of the entry must be done first before
+			 * reading any further.
+			 */
+				dma_rmb();
+				/* If the next hwcqe is a REQ */
+				if ((peek_hwcqe->cqe_type_toggle &
+				    CQ_BASE_CQE_TYPE_MASK) ==
+				    CQ_BASE_CQE_TYPE_REQ) {
+					peek_req_hwcqe = (struct cq_req *)
+							 peek_hwcqe;
+					peek_qp = (struct bnxt_qplib_qp *)
+						((unsigned long)
+						 le64_to_cpu
+						 (peek_req_hwcqe->qp_handle));
+					peek_sq = &peek_qp->sq;
+					peek_sq_cons_idx =
+						((le16_to_cpu(
+						  peek_req_hwcqe->sq_cons_idx)
+						  - 1) % sq->max_wqe);
+					/* If the hwcqe's sq's wr_id matches */
+					if (peek_sq == sq &&
+					    sq->swq[peek_sq_cons_idx].wr_id ==
+					    BNXT_QPLIB_FENCE_WRID) {
+						/*
+						 *  Unbreak only if the phantom
+						 *  comes back
+						 */
+						dev_dbg(&cq->hwq.pdev->dev,
+							"FP: Got Phantom CQE\n");
+						sq->condition = false;
+						sq->single = true;
+						rc = 0;
+						goto out;
+					}
+				}
+				/* Valid but not the phantom, so keep looping */
+			} else {
+				/* Not valid yet, just exit and wait */
+				rc = -EINVAL;
+				goto out;
+			}
+			peek_sw_cq_cons++;
+			peek_raw_cq_cons++;
+		}
+		dev_err(&cq->hwq.pdev->dev,
+			"Should not have come here! cq_cons=0x%x qp=0x%x sq cons sw=0x%x hw=0x%x\n",
+			cq_cons, qp->id, swq_last, cqe_sq_cons);
+		rc = -EINVAL;
+	}
+out:
+	return rc;
+}
+
+static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
+				     struct cq_req *hwcqe,
+				     struct bnxt_qplib_cqe **pcqe, int *budget,
+				     u32 cq_cons, struct bnxt_qplib_qp **lib_qp)
+{
+	struct bnxt_qplib_swq *swq;
+	struct bnxt_qplib_cqe *cqe;
+	struct bnxt_qplib_qp *qp;
+	struct bnxt_qplib_q *sq;
+	u32 cqe_sq_cons;
+	int rc = 0;
+
+	qp = (struct bnxt_qplib_qp *)((unsigned long)
+				      le64_to_cpu(hwcqe->qp_handle));
+	if (!qp) {
+		dev_err(&cq->hwq.pdev->dev,
+			"FP: Process Req qp is NULL\n");
+		return -EINVAL;
+	}
+	sq = &qp->sq;
+
+	cqe_sq_cons = le16_to_cpu(hwcqe->sq_cons_idx) % sq->max_wqe;
+	if (qp->sq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
+	/* Require to walk the sq's swq to fabricate CQEs for all previously
+	 * signaled SWQEs due to CQE aggregation from the current sq cons
+	 * to the cqe_sq_cons
+	 */
+	cqe = *pcqe;
+	while (*budget) {
+		if (sq->swq_last == cqe_sq_cons)
+			/* Done */
+			break;
+
+		swq = &sq->swq[sq->swq_last];
+		memset(cqe, 0, sizeof(*cqe));
+		cqe->opcode = CQ_BASE_CQE_TYPE_REQ;
+		cqe->qp_handle = (u64)(unsigned long)qp;
+		cqe->src_qp = qp->id;
+		cqe->wr_id = swq->wr_id;
+		if (cqe->wr_id == BNXT_QPLIB_FENCE_WRID)
+			goto skip;
+		cqe->type = swq->type;
+
+		/* For the last CQE, check for status.  For errors, regardless
+		 * of the request being signaled or not, it must complete with
+		 * the hwcqe error status
+		 */
+		if (swq->next_idx == cqe_sq_cons &&
+		    hwcqe->status != CQ_REQ_STATUS_OK) {
+			cqe->status = hwcqe->status;
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: CQ Processed Req wr_id[%d] = 0x%llx with status 0x%x\n",
+				sq->swq_last, cqe->wr_id, cqe->status);
+			cqe++;
+			(*budget)--;
+			bnxt_qplib_mark_qp_error(qp);
+			/* Add qp to flush list of the CQ */
+			bnxt_qplib_add_flush_qp(qp);
+		} else {
+			/* Before we complete, do WA 9060 */
+			if (do_wa9060(qp, cq, cq_cons, sq->swq_last,
+				      cqe_sq_cons)) {
+				*lib_qp = qp;
+				goto out;
+			}
+			if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
+				cqe->status = CQ_REQ_STATUS_OK;
+				cqe++;
+				(*budget)--;
+			}
+		}
+skip:
+		bnxt_qplib_hwq_incr_cons(&sq->hwq, swq->slots);
+		sq->swq_last = swq->next_idx;
+		if (sq->single)
+			break;
+	}
+out:
+	*pcqe = cqe;
+	if (sq->swq_last != cqe_sq_cons) {
+		/* Out of budget */
+		rc = -EAGAIN;
+		goto done;
+	}
+	/*
+	 * Back to normal completion mode only after it has completed all of
+	 * the WC for this CQE
+	 */
+	sq->single = false;
+done:
+	return rc;
+}
+
+static void bnxt_qplib_release_srqe(struct bnxt_qplib_srq *srq, u32 tag)
+{
+	spin_lock(&srq->hwq.lock);
+	srq->swq[srq->last_idx].next_idx = (int)tag;
+	srq->last_idx = (int)tag;
+	srq->swq[srq->last_idx].next_idx = -1;
+	srq->hwq.cons++; /* Support for SRQE counter */
+	spin_unlock(&srq->hwq.lock);
+}
+
+static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq,
+					struct cq_res_rc *hwcqe,
+					struct bnxt_qplib_cqe **pcqe,
+					int *budget)
+{
+	struct bnxt_qplib_srq *srq;
+	struct bnxt_qplib_cqe *cqe;
+	struct bnxt_qplib_qp *qp;
+	struct bnxt_qplib_q *rq;
+	u32 wr_id_idx;
+	int rc = 0;
+
+	qp = (struct bnxt_qplib_qp *)((unsigned long)
+				      le64_to_cpu(hwcqe->qp_handle));
+	if (!qp) {
+		dev_err(&cq->hwq.pdev->dev, "process_cq RC qp is NULL\n");
+		return -EINVAL;
+	}
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
+
+	cqe = *pcqe;
+	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
+	cqe->length = le32_to_cpu(hwcqe->length);
+	cqe->invrkey = le32_to_cpu(hwcqe->imm_data_or_inv_r_key);
+	cqe->mr_handle = le64_to_cpu(hwcqe->mr_handle);
+	cqe->flags = le16_to_cpu(hwcqe->flags);
+	cqe->status = hwcqe->status;
+	cqe->qp_handle = (u64)(unsigned long)qp;
+
+	wr_id_idx = le32_to_cpu(hwcqe->srq_or_rq_wr_id) &
+				CQ_RES_RC_SRQ_OR_RQ_WR_ID_MASK;
+	if (cqe->flags & CQ_RES_RC_FLAGS_SRQ_SRQ) {
+		srq = qp->srq;
+		if (!srq)
+			return -EINVAL;
+		if (wr_id_idx >= srq->hwq.max_elements) {
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: CQ Process RC wr_id idx 0x%x exceeded SRQ max 0x%x\n",
+				wr_id_idx, srq->hwq.max_elements);
+			return -EINVAL;
+		}
+		cqe->wr_id = srq->swq[wr_id_idx].wr_id;
+		bnxt_qplib_release_srqe(srq, wr_id_idx);
+		cqe++;
+		(*budget)--;
+		*pcqe = cqe;
+	} else {
+		struct bnxt_qplib_swq *swq;
+
+		rq = &qp->rq;
+		if (wr_id_idx > (rq->max_wqe - 1)) {
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: CQ Process RC wr_id idx 0x%x exceeded RQ max 0x%x\n",
+				wr_id_idx, rq->max_wqe);
+			return -EINVAL;
+		}
+		if (wr_id_idx != rq->swq_last)
+			return -EINVAL;
+		swq = &rq->swq[rq->swq_last];
+		cqe->wr_id = swq->wr_id;
+		cqe++;
+		(*budget)--;
+		bnxt_qplib_hwq_incr_cons(&rq->hwq, swq->slots);
+		rq->swq_last = swq->next_idx;
+		*pcqe = cqe;
+
+		if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
+			qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
+			/* Add qp to flush list of the CQ */
+			bnxt_qplib_add_flush_qp(qp);
+		}
+	}
+
+done:
+	return rc;
+}
+
+static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq,
+					struct cq_res_ud *hwcqe,
+					struct bnxt_qplib_cqe **pcqe,
+					int *budget)
+{
+	struct bnxt_qplib_srq *srq;
+	struct bnxt_qplib_cqe *cqe;
+	struct bnxt_qplib_qp *qp;
+	struct bnxt_qplib_q *rq;
+	u32 wr_id_idx;
+	int rc = 0;
+
+	qp = (struct bnxt_qplib_qp *)((unsigned long)
+				      le64_to_cpu(hwcqe->qp_handle));
+	if (!qp) {
+		dev_err(&cq->hwq.pdev->dev, "process_cq UD qp is NULL\n");
+		return -EINVAL;
+	}
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
+	cqe = *pcqe;
+	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
+	cqe->length = le16_to_cpu(hwcqe->length) & CQ_RES_UD_LENGTH_MASK;
+	cqe->cfa_meta = le16_to_cpu(hwcqe->cfa_metadata);
+	cqe->invrkey = le32_to_cpu(hwcqe->imm_data);
+	cqe->flags = le16_to_cpu(hwcqe->flags);
+	cqe->status = hwcqe->status;
+	cqe->qp_handle = (u64)(unsigned long)qp;
+	/*FIXME: Endianness fix needed for smace */
+	memcpy(cqe->smac, hwcqe->src_mac, ETH_ALEN);
+	wr_id_idx = le32_to_cpu(hwcqe->src_qp_high_srq_or_rq_wr_id)
+				& CQ_RES_UD_SRQ_OR_RQ_WR_ID_MASK;
+	cqe->src_qp = le16_to_cpu(hwcqe->src_qp_low) |
+				  ((le32_to_cpu(
+				  hwcqe->src_qp_high_srq_or_rq_wr_id) &
+				 CQ_RES_UD_SRC_QP_HIGH_MASK) >> 8);
+
+	if (cqe->flags & CQ_RES_RC_FLAGS_SRQ_SRQ) {
+		srq = qp->srq;
+		if (!srq)
+			return -EINVAL;
+
+		if (wr_id_idx >= srq->hwq.max_elements) {
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: CQ Process UD wr_id idx 0x%x exceeded SRQ max 0x%x\n",
+				wr_id_idx, srq->hwq.max_elements);
+			return -EINVAL;
+		}
+		cqe->wr_id = srq->swq[wr_id_idx].wr_id;
+		bnxt_qplib_release_srqe(srq, wr_id_idx);
+		cqe++;
+		(*budget)--;
+		*pcqe = cqe;
+	} else {
+		struct bnxt_qplib_swq *swq;
+
+		rq = &qp->rq;
+		if (wr_id_idx > (rq->max_wqe - 1)) {
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: CQ Process UD wr_id idx 0x%x exceeded RQ max 0x%x\n",
+				wr_id_idx, rq->max_wqe);
+			return -EINVAL;
+		}
+
+		if (rq->swq_last != wr_id_idx)
+			return -EINVAL;
+		swq = &rq->swq[rq->swq_last];
+		cqe->wr_id = swq->wr_id;
+		cqe++;
+		(*budget)--;
+		bnxt_qplib_hwq_incr_cons(&rq->hwq, swq->slots);
+		rq->swq_last = swq->next_idx;
+		*pcqe = cqe;
+
+		if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
+			qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
+			/* Add qp to flush list of the CQ */
+			bnxt_qplib_add_flush_qp(qp);
+		}
+	}
+done:
+	return rc;
+}
+
+bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq)
+{
+	struct cq_base *hw_cqe;
+	u32 sw_cons, raw_cons;
+	bool rc = true;
+
+	raw_cons = cq->hwq.cons;
+	sw_cons = HWQ_CMP(raw_cons, &cq->hwq);
+	hw_cqe = bnxt_qplib_get_qe(&cq->hwq, sw_cons, NULL);
+	 /* Check for Valid bit. If the CQE is valid, return false */
+	rc = !CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements);
+	return rc;
+}
+
+static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq,
+						struct cq_res_raweth_qp1 *hwcqe,
+						struct bnxt_qplib_cqe **pcqe,
+						int *budget)
+{
+	struct bnxt_qplib_qp *qp;
+	struct bnxt_qplib_q *rq;
+	struct bnxt_qplib_srq *srq;
+	struct bnxt_qplib_cqe *cqe;
+	u32 wr_id_idx;
+	int rc = 0;
+
+	qp = (struct bnxt_qplib_qp *)((unsigned long)
+				      le64_to_cpu(hwcqe->qp_handle));
+	if (!qp) {
+		dev_err(&cq->hwq.pdev->dev, "process_cq Raw/QP1 qp is NULL\n");
+		return -EINVAL;
+	}
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
+	cqe = *pcqe;
+	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
+	cqe->flags = le16_to_cpu(hwcqe->flags);
+	cqe->qp_handle = (u64)(unsigned long)qp;
+
+	wr_id_idx =
+		le32_to_cpu(hwcqe->raweth_qp1_payload_offset_srq_or_rq_wr_id)
+				& CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_MASK;
+	cqe->src_qp = qp->id;
+	if (qp->id == 1 && !cqe->length) {
+		/* Add workaround for the length misdetection */
+		cqe->length = 296;
+	} else {
+		cqe->length = le16_to_cpu(hwcqe->length);
+	}
+	cqe->pkey_index = qp->pkey_index;
+	memcpy(cqe->smac, qp->smac, 6);
+
+	cqe->raweth_qp1_flags = le16_to_cpu(hwcqe->raweth_qp1_flags);
+	cqe->raweth_qp1_flags2 = le32_to_cpu(hwcqe->raweth_qp1_flags2);
+	cqe->raweth_qp1_metadata = le32_to_cpu(hwcqe->raweth_qp1_metadata);
+
+	if (cqe->flags & CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ) {
+		srq = qp->srq;
+		if (!srq) {
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: SRQ used but not defined??\n");
+			return -EINVAL;
+		}
+		if (wr_id_idx >= srq->hwq.max_elements) {
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: CQ Process Raw/QP1 wr_id idx 0x%x exceeded SRQ max 0x%x\n",
+				wr_id_idx, srq->hwq.max_elements);
+			return -EINVAL;
+		}
+		cqe->wr_id = srq->swq[wr_id_idx].wr_id;
+		bnxt_qplib_release_srqe(srq, wr_id_idx);
+		cqe++;
+		(*budget)--;
+		*pcqe = cqe;
+	} else {
+		struct bnxt_qplib_swq *swq;
+
+		rq = &qp->rq;
+		if (wr_id_idx > (rq->max_wqe - 1)) {
+			dev_err(&cq->hwq.pdev->dev,
+				"FP: CQ Process Raw/QP1 RQ wr_id idx 0x%x exceeded RQ max 0x%x\n",
+				wr_id_idx, rq->max_wqe);
+			return -EINVAL;
+		}
+		if (rq->swq_last != wr_id_idx)
+			return -EINVAL;
+		swq = &rq->swq[rq->swq_last];
+		cqe->wr_id = swq->wr_id;
+		cqe++;
+		(*budget)--;
+		bnxt_qplib_hwq_incr_cons(&rq->hwq, swq->slots);
+		rq->swq_last = swq->next_idx;
+		*pcqe = cqe;
+
+		if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
+			qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
+			/* Add qp to flush list of the CQ */
+			bnxt_qplib_add_flush_qp(qp);
+		}
+	}
+
+done:
+	return rc;
+}
+
+static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq,
+					  struct cq_terminal *hwcqe,
+					  struct bnxt_qplib_cqe **pcqe,
+					  int *budget)
+{
+	struct bnxt_qplib_qp *qp;
+	struct bnxt_qplib_q *sq, *rq;
+	struct bnxt_qplib_cqe *cqe;
+	u32 swq_last = 0, cqe_cons;
+	int rc = 0;
+
+	/* Check the Status */
+	if (hwcqe->status != CQ_TERMINAL_STATUS_OK)
+		dev_warn(&cq->hwq.pdev->dev,
+			 "FP: CQ Process Terminal Error status = 0x%x\n",
+			 hwcqe->status);
+
+	qp = (struct bnxt_qplib_qp *)((unsigned long)
+				      le64_to_cpu(hwcqe->qp_handle));
+	if (!qp)
+		return -EINVAL;
+
+	/* Must block new posting of SQ and RQ */
+	qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
+
+	sq = &qp->sq;
+	rq = &qp->rq;
+
+	cqe_cons = le16_to_cpu(hwcqe->sq_cons_idx);
+	if (cqe_cons == 0xFFFF)
+		goto do_rq;
+	cqe_cons %= sq->max_wqe;
+
+	if (qp->sq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QP in Flush QP = %p\n", __func__, qp);
+		goto sq_done;
+	}
+
+	/* Terminal CQE can also include aggregated successful CQEs prior.
+	 * So we must complete all CQEs from the current sq's cons to the
+	 * cq_cons with status OK
+	 */
+	cqe = *pcqe;
+	while (*budget) {
+		swq_last = sq->swq_last;
+		if (swq_last == cqe_cons)
+			break;
+		if (sq->swq[swq_last].flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
+			memset(cqe, 0, sizeof(*cqe));
+			cqe->status = CQ_REQ_STATUS_OK;
+			cqe->opcode = CQ_BASE_CQE_TYPE_REQ;
+			cqe->qp_handle = (u64)(unsigned long)qp;
+			cqe->src_qp = qp->id;
+			cqe->wr_id = sq->swq[swq_last].wr_id;
+			cqe->type = sq->swq[swq_last].type;
+			cqe++;
+			(*budget)--;
+		}
+		bnxt_qplib_hwq_incr_cons(&sq->hwq, sq->swq[swq_last].slots);
+		sq->swq_last = sq->swq[swq_last].next_idx;
+	}
+	*pcqe = cqe;
+	if (!(*budget) && swq_last != cqe_cons) {
+		/* Out of budget */
+		rc = -EAGAIN;
+		goto sq_done;
+	}
+sq_done:
+	if (rc)
+		return rc;
+do_rq:
+	cqe_cons = le16_to_cpu(hwcqe->rq_cons_idx);
+	if (cqe_cons == 0xFFFF) {
+		goto done;
+	} else if (cqe_cons > rq->max_wqe - 1) {
+		dev_err(&cq->hwq.pdev->dev,
+			"FP: CQ Processed terminal reported rq_cons_idx 0x%x exceeds max 0x%x\n",
+			cqe_cons, rq->max_wqe);
+		rc = -EINVAL;
+		goto done;
+	}
+
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QP in Flush QP = %p\n", __func__, qp);
+		rc = 0;
+		goto done;
+	}
+
+	/* Terminal CQE requires all posted RQEs to complete with FLUSHED_ERR
+	 * from the current rq->cons to the rq->prod regardless what the
+	 * rq->cons the terminal CQE indicates
+	 */
+
+	/* Add qp to flush list of the CQ */
+	bnxt_qplib_add_flush_qp(qp);
+done:
+	return rc;
+}
+
+static int bnxt_qplib_cq_process_cutoff(struct bnxt_qplib_cq *cq,
+					struct cq_cutoff *hwcqe)
+{
+	/* Check the Status */
+	if (hwcqe->status != CQ_CUTOFF_STATUS_OK) {
+		dev_err(&cq->hwq.pdev->dev,
+			"FP: CQ Process Cutoff Error status = 0x%x\n",
+			hwcqe->status);
+		return -EINVAL;
+	}
+	clear_bit(CQ_FLAGS_RESIZE_IN_PROG, &cq->flags);
+	wake_up_interruptible(&cq->waitq);
+
+	return 0;
+}
+
+int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq,
+				  struct bnxt_qplib_cqe *cqe,
+				  int num_cqes)
+{
+	struct bnxt_qplib_qp *qp = NULL;
+	u32 budget = num_cqes;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cq->flush_lock, flags);
+	list_for_each_entry(qp, &cq->sqf_head, sq_flush) {
+		dev_dbg(&cq->hwq.pdev->dev, "FP: Flushing SQ QP= %p\n", qp);
+		__flush_sq(&qp->sq, qp, &cqe, &budget);
+	}
+
+	list_for_each_entry(qp, &cq->rqf_head, rq_flush) {
+		dev_dbg(&cq->hwq.pdev->dev, "FP: Flushing RQ QP= %p\n", qp);
+		__flush_rq(&qp->rq, qp, &cqe, &budget);
+	}
+	spin_unlock_irqrestore(&cq->flush_lock, flags);
+
+	return num_cqes - budget;
+}
+
+int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe,
+		       int num_cqes, struct bnxt_qplib_qp **lib_qp)
+{
+	struct cq_base *hw_cqe;
+	u32 sw_cons, raw_cons;
+	int budget, rc = 0;
+	u8 type;
+
+	raw_cons = cq->hwq.cons;
+	budget = num_cqes;
+
+	while (budget) {
+		sw_cons = HWQ_CMP(raw_cons, &cq->hwq);
+		hw_cqe = bnxt_qplib_get_qe(&cq->hwq, sw_cons, NULL);
+
+		/* Check for Valid bit */
+		if (!CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements))
+			break;
+
+		/*
+		 * The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
+		/* From the device's respective CQE format to qplib_wc*/
+		type = hw_cqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
+		switch (type) {
+		case CQ_BASE_CQE_TYPE_REQ:
+			rc = bnxt_qplib_cq_process_req(cq,
+						       (struct cq_req *)hw_cqe,
+						       &cqe, &budget,
+						       sw_cons, lib_qp);
+			break;
+		case CQ_BASE_CQE_TYPE_RES_RC:
+			rc = bnxt_qplib_cq_process_res_rc(cq,
+							  (struct cq_res_rc *)
+							  hw_cqe, &cqe,
+							  &budget);
+			break;
+		case CQ_BASE_CQE_TYPE_RES_UD:
+			rc = bnxt_qplib_cq_process_res_ud
+					(cq, (struct cq_res_ud *)hw_cqe, &cqe,
+					 &budget);
+			break;
+		case CQ_BASE_CQE_TYPE_RES_RAWETH_QP1:
+			rc = bnxt_qplib_cq_process_res_raweth_qp1
+					(cq, (struct cq_res_raweth_qp1 *)
+					 hw_cqe, &cqe, &budget);
+			break;
+		case CQ_BASE_CQE_TYPE_TERMINAL:
+			rc = bnxt_qplib_cq_process_terminal
+					(cq, (struct cq_terminal *)hw_cqe,
+					 &cqe, &budget);
+			break;
+		case CQ_BASE_CQE_TYPE_CUT_OFF:
+			bnxt_qplib_cq_process_cutoff
+					(cq, (struct cq_cutoff *)hw_cqe);
+			/* Done processing this CQ */
+			goto exit;
+		default:
+			dev_err(&cq->hwq.pdev->dev,
+				"process_cq unknown type 0x%lx\n",
+				hw_cqe->cqe_type_toggle &
+				CQ_BASE_CQE_TYPE_MASK);
+			rc = -EINVAL;
+			break;
+		}
+		if (rc < 0) {
+			if (rc == -EAGAIN)
+				break;
+			/* Error while processing the CQE, just skip to the
+			 * next one
+			 */
+			if (type != CQ_BASE_CQE_TYPE_TERMINAL)
+				dev_err(&cq->hwq.pdev->dev,
+					"process_cqe error rc = 0x%x\n", rc);
+		}
+		raw_cons++;
+	}
+	if (cq->hwq.cons != raw_cons) {
+		cq->hwq.cons = raw_cons;
+		bnxt_qplib_ring_db(&cq->dbinfo, DBC_DBC_TYPE_CQ);
+	}
+exit:
+	return num_cqes - budget;
+}
+
+void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type)
+{
+	if (arm_type)
+		bnxt_qplib_ring_db(&cq->dbinfo, arm_type);
+	/* Using cq->arm_state variable to track whether to issue cq handler */
+	atomic_set(&cq->arm_state, 1);
+}
+
+void bnxt_qplib_flush_cqn_wq(struct bnxt_qplib_qp *qp)
+{
+	flush_workqueue(qp->scq->nq->cqn_wq);
+	if (qp->scq != qp->rcq)
+		flush_workqueue(qp->rcq->nq->cqn_wq);
+}
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
new file mode 100644
index 000000000..49d89c080
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -0,0 +1,612 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Fast Path Operators (header)
+ */
+
+#ifndef __BNXT_QPLIB_FP_H__
+#define __BNXT_QPLIB_FP_H__
+
+#include <rdma/bnxt_re-abi.h>
+
+/* Few helper structures temporarily defined here
+ * should get rid of these when roce_hsi.h is updated
+ * in original code base
+ */
+struct sq_ud_ext_hdr {
+	__le32 dst_qp;
+	__le32 avid;
+	__le64 rsvd;
+};
+
+struct sq_raw_ext_hdr {
+	__le32 cfa_meta;
+	__le32 rsvd0;
+	__le64 rsvd1;
+};
+
+struct sq_rdma_ext_hdr {
+	__le64 remote_va;
+	__le32 remote_key;
+	__le32 rsvd;
+};
+
+struct sq_atomic_ext_hdr {
+	__le64 swap_data;
+	__le64 cmp_data;
+};
+
+struct sq_fr_pmr_ext_hdr {
+	__le64 pblptr;
+	__le64 va;
+};
+
+struct sq_bind_ext_hdr {
+	__le64 va;
+	__le32 length_lo;
+	__le32 length_hi;
+};
+
+struct rq_ext_hdr {
+	__le64 rsvd1;
+	__le64 rsvd2;
+};
+
+/* Helper structures end */
+
+struct bnxt_qplib_srq {
+	struct bnxt_qplib_pd		*pd;
+	struct bnxt_qplib_dpi		*dpi;
+	struct bnxt_qplib_db_info	dbinfo;
+	u64				srq_handle;
+	u32				id;
+	u16				wqe_size;
+	u32				max_wqe;
+	u32				max_sge;
+	u32				threshold;
+	bool				arm_req;
+	struct bnxt_qplib_cq		*cq;
+	struct bnxt_qplib_hwq		hwq;
+	struct bnxt_qplib_swq		*swq;
+	int				start_idx;
+	int				last_idx;
+	struct bnxt_qplib_sg_info	sg_info;
+	u16				eventq_hw_ring_id;
+	spinlock_t			lock; /* protect SRQE link list */
+};
+
+struct bnxt_qplib_sge {
+	u64				addr;
+	u32				lkey;
+	u32				size;
+};
+
+#define BNXT_QPLIB_QP_MAX_SGL	6
+struct bnxt_qplib_swq {
+	u64				wr_id;
+	int				next_idx;
+	u8				type;
+	u8				flags;
+	u32				start_psn;
+	u32				next_psn;
+	u32				slot_idx;
+	u8				slots;
+	struct sq_psn_search		*psn_search;
+	struct sq_psn_search_ext	*psn_ext;
+};
+
+struct bnxt_qplib_swqe {
+	/* General */
+#define	BNXT_QPLIB_FENCE_WRID	0x46454E43	/* "FENC" */
+	u64				wr_id;
+	u8				reqs_type;
+	u8				type;
+#define BNXT_QPLIB_SWQE_TYPE_SEND			0
+#define BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM		1
+#define BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV		2
+#define BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE			4
+#define BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE_WITH_IMM	5
+#define BNXT_QPLIB_SWQE_TYPE_RDMA_READ			6
+#define BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP		8
+#define BNXT_QPLIB_SWQE_TYPE_ATOMIC_FETCH_AND_ADD	11
+#define BNXT_QPLIB_SWQE_TYPE_LOCAL_INV			12
+#define BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR		13
+#define BNXT_QPLIB_SWQE_TYPE_REG_MR			13
+#define BNXT_QPLIB_SWQE_TYPE_BIND_MW			14
+#define BNXT_QPLIB_SWQE_TYPE_RECV			128
+#define BNXT_QPLIB_SWQE_TYPE_RECV_RDMA_IMM		129
+	u8				flags;
+#define BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP		BIT(0)
+#define BNXT_QPLIB_SWQE_FLAGS_RD_ATOMIC_FENCE		BIT(1)
+#define BNXT_QPLIB_SWQE_FLAGS_UC_FENCE			BIT(2)
+#define BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT		BIT(3)
+#define BNXT_QPLIB_SWQE_FLAGS_INLINE			BIT(4)
+	struct bnxt_qplib_sge		sg_list[BNXT_QPLIB_QP_MAX_SGL];
+	int				num_sge;
+	/* Max inline data is 96 bytes */
+	u32				inline_len;
+#define BNXT_QPLIB_SWQE_MAX_INLINE_LENGTH		96
+	u8		inline_data[BNXT_QPLIB_SWQE_MAX_INLINE_LENGTH];
+
+	union {
+		/* Send, with imm, inval key */
+		struct {
+			union {
+				__be32	imm_data;
+				u32	inv_key;
+			};
+			u32		q_key;
+			u32		dst_qp;
+			u16		avid;
+		} send;
+
+		/* Send Raw Ethernet and QP1 */
+		struct {
+			u16		lflags;
+			u16		cfa_action;
+			u32		cfa_meta;
+		} rawqp1;
+
+		/* RDMA write, with imm, read */
+		struct {
+			union {
+				__be32	imm_data;
+				u32	inv_key;
+			};
+			u64		remote_va;
+			u32		r_key;
+		} rdma;
+
+		/* Atomic cmp/swap, fetch/add */
+		struct {
+			u64		remote_va;
+			u32		r_key;
+			u64		swap_data;
+			u64		cmp_data;
+		} atomic;
+
+		/* Local Invalidate */
+		struct {
+			u32		inv_l_key;
+		} local_inv;
+
+		/* FR-PMR */
+		struct {
+			u8		access_cntl;
+			u8		pg_sz_log;
+			bool		zero_based;
+			u32		l_key;
+			u32		length;
+			u8		pbl_pg_sz_log;
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_4K			0
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_8K			1
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_64K			4
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_256K			6
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_1M			8
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_2M			9
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_4M			10
+#define BNXT_QPLIB_SWQE_PAGE_SIZE_1G			18
+			u8		levels;
+#define PAGE_SHIFT_4K	12
+			__le64		*pbl_ptr;
+			dma_addr_t	pbl_dma_ptr;
+			u64		*page_list;
+			u16		page_list_len;
+			u64		va;
+		} frmr;
+
+		/* Bind */
+		struct {
+			u8		access_cntl;
+#define BNXT_QPLIB_BIND_SWQE_ACCESS_LOCAL_WRITE		BIT(0)
+#define BNXT_QPLIB_BIND_SWQE_ACCESS_REMOTE_READ		BIT(1)
+#define BNXT_QPLIB_BIND_SWQE_ACCESS_REMOTE_WRITE	BIT(2)
+#define BNXT_QPLIB_BIND_SWQE_ACCESS_REMOTE_ATOMIC	BIT(3)
+#define BNXT_QPLIB_BIND_SWQE_ACCESS_WINDOW_BIND		BIT(4)
+			bool		zero_based;
+			u8		mw_type;
+			u32		parent_l_key;
+			u32		r_key;
+			u64		va;
+			u32		length;
+		} bind;
+	};
+};
+
+struct bnxt_qplib_q {
+	struct bnxt_qplib_hwq		hwq;
+	struct bnxt_qplib_swq		*swq;
+	struct bnxt_qplib_db_info	dbinfo;
+	struct bnxt_qplib_sg_info	sg_info;
+	u32				max_wqe;
+	u16				wqe_size;
+	u16				q_full_delta;
+	u16				max_sge;
+	u32				psn;
+	bool				condition;
+	bool				single;
+	bool				send_phantom;
+	u32				phantom_wqe_cnt;
+	u32				phantom_cqe_cnt;
+	u32				next_cq_cons;
+	bool				flushed;
+	u32				swq_start;
+	u32				swq_last;
+};
+
+struct bnxt_qplib_qp {
+	struct bnxt_qplib_pd		*pd;
+	struct bnxt_qplib_dpi		*dpi;
+	struct bnxt_qplib_chip_ctx	*cctx;
+	u64				qp_handle;
+#define BNXT_QPLIB_QP_ID_INVALID        0xFFFFFFFF
+	u32				id;
+	u8				type;
+	u8				sig_type;
+	u8				wqe_mode;
+	u8				state;
+	u8				cur_qp_state;
+	u64				modify_flags;
+	u32				max_inline_data;
+	u32				mtu;
+	u8				path_mtu;
+	bool				en_sqd_async_notify;
+	u16				pkey_index;
+	u32				qkey;
+	u32				dest_qp_id;
+	u8				access;
+	u8				timeout;
+	u8				retry_cnt;
+	u8				rnr_retry;
+	u64				wqe_cnt;
+	u32				min_rnr_timer;
+	u32				max_rd_atomic;
+	u32				max_dest_rd_atomic;
+	u32				dest_qpn;
+	u8				smac[6];
+	u16				vlan_id;
+	u8				nw_type;
+	struct bnxt_qplib_ah		ah;
+
+#define BTH_PSN_MASK			((1 << 24) - 1)
+	/* SQ */
+	struct bnxt_qplib_q		sq;
+	/* RQ */
+	struct bnxt_qplib_q		rq;
+	/* SRQ */
+	struct bnxt_qplib_srq		*srq;
+	/* CQ */
+	struct bnxt_qplib_cq		*scq;
+	struct bnxt_qplib_cq		*rcq;
+	/* IRRQ and ORRQ */
+	struct bnxt_qplib_hwq		irrq;
+	struct bnxt_qplib_hwq		orrq;
+	/* Header buffer for QP1 */
+	int				sq_hdr_buf_size;
+	int				rq_hdr_buf_size;
+/*
+ * Buffer space for ETH(14), IP or GRH(40), UDP header(8)
+ * and ib_bth + ib_deth (20).
+ * Max required is 82 when RoCE V2 is enabled
+ */
+#define BNXT_QPLIB_MAX_QP1_SQ_HDR_SIZE_V2	86
+	/* Ethernet header	=  14 */
+	/* ib_grh		=  40 (provided by MAD) */
+	/* ib_bth + ib_deth	=  20 */
+	/* MAD			= 256 (provided by MAD) */
+	/* iCRC			=   4 */
+#define BNXT_QPLIB_MAX_QP1_RQ_ETH_HDR_SIZE	14
+#define BNXT_QPLIB_MAX_QP1_RQ_HDR_SIZE_V2	512
+#define BNXT_QPLIB_MAX_GRH_HDR_SIZE_IPV4	20
+#define BNXT_QPLIB_MAX_GRH_HDR_SIZE_IPV6	40
+#define BNXT_QPLIB_MAX_QP1_RQ_BDETH_HDR_SIZE	20
+	void				*sq_hdr_buf;
+	dma_addr_t			sq_hdr_buf_map;
+	void				*rq_hdr_buf;
+	dma_addr_t			rq_hdr_buf_map;
+	struct list_head		sq_flush;
+	struct list_head		rq_flush;
+};
+
+#define BNXT_QPLIB_MAX_CQE_ENTRY_SIZE	sizeof(struct cq_base)
+
+#define CQE_CNT_PER_PG		(PAGE_SIZE / BNXT_QPLIB_MAX_CQE_ENTRY_SIZE)
+#define CQE_MAX_IDX_PER_PG	(CQE_CNT_PER_PG - 1)
+#define CQE_PG(x)		(((x) & ~CQE_MAX_IDX_PER_PG) / CQE_CNT_PER_PG)
+#define CQE_IDX(x)		((x) & CQE_MAX_IDX_PER_PG)
+
+#define ROCE_CQE_CMP_V			0
+#define CQE_CMP_VALID(hdr, raw_cons, cp_bit)			\
+	(!!((hdr)->cqe_type_toggle & CQ_BASE_TOGGLE) ==		\
+	   !((raw_cons) & (cp_bit)))
+
+static inline bool bnxt_qplib_queue_full(struct bnxt_qplib_q *que,
+					 u8 slots)
+{
+	struct bnxt_qplib_hwq *hwq;
+	int avail;
+
+	hwq = &que->hwq;
+	/* False full is possible, retrying post-send makes sense */
+	avail = hwq->cons - hwq->prod;
+	if (hwq->cons <= hwq->prod)
+		avail += hwq->depth;
+	return avail <= slots;
+}
+
+struct bnxt_qplib_cqe {
+	u8				status;
+	u8				type;
+	u8				opcode;
+	u32				length;
+	u16				cfa_meta;
+	u64				wr_id;
+	union {
+		__be32			immdata;
+		u32			invrkey;
+	};
+	u64				qp_handle;
+	u64				mr_handle;
+	u16				flags;
+	u8				smac[6];
+	u32				src_qp;
+	u16				raweth_qp1_flags;
+	u16				raweth_qp1_errors;
+	u16				raweth_qp1_cfa_code;
+	u32				raweth_qp1_flags2;
+	u32				raweth_qp1_metadata;
+	u8				raweth_qp1_payload_offset;
+	u16				pkey_index;
+};
+
+#define BNXT_QPLIB_QUEUE_START_PERIOD		0x01
+struct bnxt_qplib_cq {
+	struct bnxt_qplib_dpi		*dpi;
+	struct bnxt_qplib_db_info	dbinfo;
+	u32				max_wqe;
+	u32				id;
+	u16				count;
+	u16				period;
+	struct bnxt_qplib_hwq		hwq;
+	u32				cnq_hw_ring_id;
+	struct bnxt_qplib_nq		*nq;
+	bool				resize_in_progress;
+	struct bnxt_qplib_sg_info	sg_info;
+	u64				cq_handle;
+
+#define CQ_RESIZE_WAIT_TIME_MS		500
+	unsigned long			flags;
+#define CQ_FLAGS_RESIZE_IN_PROG		1
+	wait_queue_head_t		waitq;
+	struct list_head		sqf_head, rqf_head;
+	atomic_t			arm_state;
+	spinlock_t			compl_lock; /* synch CQ handlers */
+/* Locking Notes:
+ * QP can move to error state from modify_qp, async error event or error
+ * CQE as part of poll_cq. When QP is moved to error state, it gets added
+ * to two flush lists, one each for SQ and RQ.
+ * Each flush list is protected by qplib_cq->flush_lock. Both scq and rcq
+ * flush_locks should be acquired when QP is moved to error. The control path
+ * operations(modify_qp and async error events) are synchronized with poll_cq
+ * using upper level CQ locks (bnxt_re_cq->cq_lock) of both SCQ and RCQ.
+ * The qplib_cq->flush_lock is required to synchronize two instances of poll_cq
+ * of the same QP while manipulating the flush list.
+ */
+	spinlock_t			flush_lock; /* QP flush management */
+	u16				cnq_events;
+};
+
+#define BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE	sizeof(struct xrrq_irrq)
+#define BNXT_QPLIB_MAX_ORRQE_ENTRY_SIZE	sizeof(struct xrrq_orrq)
+#define IRD_LIMIT_TO_IRRQ_SLOTS(x)	(2 * (x) + 2)
+#define IRRQ_SLOTS_TO_IRD_LIMIT(s)	(((s) >> 1) - 1)
+#define ORD_LIMIT_TO_ORRQ_SLOTS(x)	((x) + 1)
+#define ORRQ_SLOTS_TO_ORD_LIMIT(s)	((s) - 1)
+
+#define BNXT_QPLIB_MAX_NQE_ENTRY_SIZE	sizeof(struct nq_base)
+
+#define NQE_CNT_PER_PG		(PAGE_SIZE / BNXT_QPLIB_MAX_NQE_ENTRY_SIZE)
+#define NQE_MAX_IDX_PER_PG	(NQE_CNT_PER_PG - 1)
+#define NQE_PG(x)		(((x) & ~NQE_MAX_IDX_PER_PG) / NQE_CNT_PER_PG)
+#define NQE_IDX(x)		((x) & NQE_MAX_IDX_PER_PG)
+
+#define NQE_CMP_VALID(hdr, raw_cons, cp_bit)			\
+	(!!(le32_to_cpu((hdr)->info63_v[0]) & NQ_BASE_V) ==	\
+	   !((raw_cons) & (cp_bit)))
+
+#define BNXT_QPLIB_NQE_MAX_CNT		(128 * 1024)
+
+#define NQ_CONS_PCI_BAR_REGION		2
+#define NQ_DB_KEY_CP			(0x2 << CMPL_DOORBELL_KEY_SFT)
+#define NQ_DB_IDX_VALID			CMPL_DOORBELL_IDX_VALID
+#define NQ_DB_IRQ_DIS			CMPL_DOORBELL_MASK
+#define NQ_DB_CP_FLAGS_REARM		(NQ_DB_KEY_CP |		\
+					 NQ_DB_IDX_VALID)
+#define NQ_DB_CP_FLAGS			(NQ_DB_KEY_CP    |	\
+					 NQ_DB_IDX_VALID |	\
+					 NQ_DB_IRQ_DIS)
+
+struct bnxt_qplib_nq_db {
+	struct bnxt_qplib_reg_desc	reg;
+	struct bnxt_qplib_db_info	dbinfo;
+};
+
+typedef int (*cqn_handler_t)(struct bnxt_qplib_nq *nq,
+		struct bnxt_qplib_cq *cq);
+typedef int (*srqn_handler_t)(struct bnxt_qplib_nq *nq,
+		struct bnxt_qplib_srq *srq, u8 event);
+
+struct bnxt_qplib_nq {
+	struct pci_dev			*pdev;
+	struct bnxt_qplib_res		*res;
+	char				*name;
+	struct bnxt_qplib_hwq		hwq;
+	struct bnxt_qplib_nq_db		nq_db;
+	u16				ring_id;
+	int				msix_vec;
+	cpumask_t			mask;
+	struct tasklet_struct		nq_tasklet;
+	bool				requested;
+	int				budget;
+
+	cqn_handler_t			cqn_handler;
+	srqn_handler_t			srqn_handler;
+	struct workqueue_struct		*cqn_wq;
+};
+
+struct bnxt_qplib_nq_work {
+	struct work_struct      work;
+	struct bnxt_qplib_nq    *nq;
+	struct bnxt_qplib_cq    *cq;
+};
+
+void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill);
+void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq);
+int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx,
+			    int msix_vector, bool need_init);
+int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
+			 int nq_idx, int msix_vector, int bar_reg_offset,
+			 cqn_handler_t cqn_handler,
+			 srqn_handler_t srq_handler);
+int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
+			  struct bnxt_qplib_srq *srq);
+int bnxt_qplib_modify_srq(struct bnxt_qplib_res *res,
+			  struct bnxt_qplib_srq *srq);
+int bnxt_qplib_query_srq(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_srq *srq);
+void bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res,
+			    struct bnxt_qplib_srq *srq);
+int bnxt_qplib_post_srq_recv(struct bnxt_qplib_srq *srq,
+			     struct bnxt_qplib_swqe *wqe);
+int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp);
+int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp);
+int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp);
+int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp);
+int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp);
+void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp);
+void bnxt_qplib_free_qp_res(struct bnxt_qplib_res *res,
+			    struct bnxt_qplib_qp *qp);
+void *bnxt_qplib_get_qp1_sq_buf(struct bnxt_qplib_qp *qp,
+				struct bnxt_qplib_sge *sge);
+void *bnxt_qplib_get_qp1_rq_buf(struct bnxt_qplib_qp *qp,
+				struct bnxt_qplib_sge *sge);
+u32 bnxt_qplib_get_rq_prod_index(struct bnxt_qplib_qp *qp);
+dma_addr_t bnxt_qplib_get_qp_buf_from_index(struct bnxt_qplib_qp *qp,
+					    u32 index);
+void bnxt_qplib_post_send_db(struct bnxt_qplib_qp *qp);
+int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
+			 struct bnxt_qplib_swqe *wqe);
+void bnxt_qplib_post_recv_db(struct bnxt_qplib_qp *qp);
+int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp,
+			 struct bnxt_qplib_swqe *wqe);
+int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq);
+int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq);
+int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe,
+		       int num, struct bnxt_qplib_qp **qp);
+bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq);
+void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type);
+void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq);
+int bnxt_qplib_alloc_nq(struct bnxt_qplib_res *res, struct bnxt_qplib_nq *nq);
+void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp);
+void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp,
+				 unsigned long *flags);
+void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp,
+				 unsigned long *flags);
+int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq,
+				  struct bnxt_qplib_cqe *cqe,
+				  int num_cqes);
+void bnxt_qplib_flush_cqn_wq(struct bnxt_qplib_qp *qp);
+void bnxt_re_synchronize_nq(struct bnxt_qplib_nq *nq);
+
+static inline void *bnxt_qplib_get_swqe(struct bnxt_qplib_q *que, u32 *swq_idx)
+{
+	u32 idx;
+
+	idx = que->swq_start;
+	if (swq_idx)
+		*swq_idx = idx;
+	return &que->swq[idx];
+}
+
+static inline void bnxt_qplib_swq_mod_start(struct bnxt_qplib_q *que, u32 idx)
+{
+	que->swq_start = que->swq[idx].next_idx;
+}
+
+static inline u32 bnxt_qplib_get_depth(struct bnxt_qplib_q *que)
+{
+	return (que->wqe_size * que->max_wqe) / sizeof(struct sq_sge);
+}
+
+static inline u32 bnxt_qplib_set_sq_size(struct bnxt_qplib_q *que, u8 wqe_mode)
+{
+	return (wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) ?
+		que->max_wqe : bnxt_qplib_get_depth(que);
+}
+
+static inline u32 bnxt_qplib_set_sq_max_slot(u8 wqe_mode)
+{
+	return (wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) ?
+		sizeof(struct sq_send) / sizeof(struct sq_sge) : 1;
+}
+
+static inline u32 bnxt_qplib_set_rq_max_slot(u32 wqe_size)
+{
+	return (wqe_size / sizeof(struct sq_sge));
+}
+
+static inline u16 __xlate_qfd(u16 delta, u16 wqe_bytes)
+{
+	/* For Cu/Wh delta = 128, stride = 16, wqe_bytes = 128
+	 * For Gen-p5 B/C mode delta = 0, stride = 16, wqe_bytes = 128.
+	 * For Gen-p5 delta = 0, stride = 16, 32 <= wqe_bytes <= 512.
+	 * when 8916 is disabled.
+	 */
+	return (delta * wqe_bytes) / sizeof(struct sq_sge);
+}
+
+static inline u16 bnxt_qplib_calc_ilsize(struct bnxt_qplib_swqe *wqe, u16 max)
+{
+	u16 size = 0;
+	int indx;
+
+	for (indx = 0; indx < wqe->num_sge; indx++)
+		size += wqe->sg_list[indx].size;
+	if (size > max)
+		size = max;
+
+	return size;
+}
+#endif /* __BNXT_QPLIB_FP_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
new file mode 100644
index 000000000..75e0c42f6
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -0,0 +1,892 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: RDMA Controller HW interface
+ */
+
+#define dev_fmt(fmt) "QPLIB: " fmt
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/prefetch.h>
+#include <linux/delay.h>
+
+#include "roce_hsi.h"
+#include "qplib_res.h"
+#include "qplib_rcfw.h"
+#include "qplib_sp.h"
+#include "qplib_fp.h"
+
+static void bnxt_qplib_service_creq(struct tasklet_struct *t);
+
+/* Hardware communication channel */
+static int __wait_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie)
+{
+	struct bnxt_qplib_cmdq_ctx *cmdq;
+	u16 cbit;
+	int rc;
+
+	cmdq = &rcfw->cmdq;
+	cbit = cookie % rcfw->cmdq_depth;
+	rc = wait_event_timeout(cmdq->waitq,
+				!test_bit(cbit, cmdq->cmdq_bitmap),
+				msecs_to_jiffies(RCFW_CMD_WAIT_TIME_MS));
+	return rc ? 0 : -ETIMEDOUT;
+};
+
+static int __block_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie)
+{
+	u32 count = RCFW_BLOCKED_CMD_WAIT_COUNT;
+	struct bnxt_qplib_cmdq_ctx *cmdq;
+	u16 cbit;
+
+	cmdq = &rcfw->cmdq;
+	cbit = cookie % rcfw->cmdq_depth;
+	if (!test_bit(cbit, cmdq->cmdq_bitmap))
+		goto done;
+	do {
+		udelay(1);
+		bnxt_qplib_service_creq(&rcfw->creq.creq_tasklet);
+	} while (test_bit(cbit, cmdq->cmdq_bitmap) && --count);
+done:
+	return count ? 0 : -ETIMEDOUT;
+};
+
+static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req,
+			  struct creq_base *resp, void *sb, u8 is_block)
+{
+	struct bnxt_qplib_cmdq_ctx *cmdq = &rcfw->cmdq;
+	struct bnxt_qplib_hwq *hwq = &cmdq->hwq;
+	struct bnxt_qplib_crsqe *crsqe;
+	struct bnxt_qplib_cmdqe *cmdqe;
+	u32 sw_prod, cmdq_prod;
+	struct pci_dev *pdev;
+	unsigned long flags;
+	u32 size, opcode;
+	u16 cookie, cbit;
+	u8 *preq;
+
+	pdev = rcfw->pdev;
+
+	opcode = req->opcode;
+	if (!test_bit(FIRMWARE_INITIALIZED_FLAG, &cmdq->flags) &&
+	    (opcode != CMDQ_BASE_OPCODE_QUERY_FUNC &&
+	     opcode != CMDQ_BASE_OPCODE_INITIALIZE_FW &&
+	     opcode != CMDQ_BASE_OPCODE_QUERY_VERSION)) {
+		dev_err(&pdev->dev,
+			"RCFW not initialized, reject opcode 0x%x\n", opcode);
+		return -EINVAL;
+	}
+
+	if (test_bit(FIRMWARE_INITIALIZED_FLAG, &cmdq->flags) &&
+	    opcode == CMDQ_BASE_OPCODE_INITIALIZE_FW) {
+		dev_err(&pdev->dev, "RCFW already initialized!\n");
+		return -EINVAL;
+	}
+
+	if (test_bit(FIRMWARE_TIMED_OUT, &cmdq->flags))
+		return -ETIMEDOUT;
+
+	/* Cmdq are in 16-byte units, each request can consume 1 or more
+	 * cmdqe
+	 */
+	spin_lock_irqsave(&hwq->lock, flags);
+	if (req->cmd_size >= HWQ_FREE_SLOTS(hwq)) {
+		dev_err(&pdev->dev, "RCFW: CMDQ is full!\n");
+		spin_unlock_irqrestore(&hwq->lock, flags);
+		return -EAGAIN;
+	}
+
+
+	cookie = cmdq->seq_num & RCFW_MAX_COOKIE_VALUE;
+	cbit = cookie % rcfw->cmdq_depth;
+	if (is_block)
+		cookie |= RCFW_CMD_IS_BLOCKING;
+
+	set_bit(cbit, cmdq->cmdq_bitmap);
+	req->cookie = cpu_to_le16(cookie);
+	crsqe = &rcfw->crsqe_tbl[cbit];
+	if (crsqe->resp) {
+		spin_unlock_irqrestore(&hwq->lock, flags);
+		return -EBUSY;
+	}
+
+	size = req->cmd_size;
+	/* change the cmd_size to the number of 16byte cmdq unit.
+	 * req->cmd_size is modified here
+	 */
+	bnxt_qplib_set_cmd_slots(req);
+
+	memset(resp, 0, sizeof(*resp));
+	crsqe->resp = (struct creq_qp_event *)resp;
+	crsqe->resp->cookie = req->cookie;
+	crsqe->req_size = req->cmd_size;
+	if (req->resp_size && sb) {
+		struct bnxt_qplib_rcfw_sbuf *sbuf = sb;
+
+		req->resp_addr = cpu_to_le64(sbuf->dma_addr);
+		req->resp_size = (sbuf->size + BNXT_QPLIB_CMDQE_UNITS - 1) /
+				  BNXT_QPLIB_CMDQE_UNITS;
+	}
+
+	preq = (u8 *)req;
+	do {
+		/* Locate the next cmdq slot */
+		sw_prod = HWQ_CMP(hwq->prod, hwq);
+		cmdqe = bnxt_qplib_get_qe(hwq, sw_prod, NULL);
+		if (!cmdqe) {
+			dev_err(&pdev->dev,
+				"RCFW request failed with no cmdqe!\n");
+			goto done;
+		}
+		/* Copy a segment of the req cmd to the cmdq */
+		memset(cmdqe, 0, sizeof(*cmdqe));
+		memcpy(cmdqe, preq, min_t(u32, size, sizeof(*cmdqe)));
+		preq += min_t(u32, size, sizeof(*cmdqe));
+		size -= min_t(u32, size, sizeof(*cmdqe));
+		hwq->prod++;
+	} while (size > 0);
+	cmdq->seq_num++;
+
+	cmdq_prod = hwq->prod & 0xFFFF;
+	if (test_bit(FIRMWARE_FIRST_FLAG, &cmdq->flags)) {
+		/* The very first doorbell write
+		 * is required to set this flag
+		 * which prompts the FW to reset
+		 * its internal pointers
+		 */
+		cmdq_prod |= BIT(FIRMWARE_FIRST_FLAG);
+		clear_bit(FIRMWARE_FIRST_FLAG, &cmdq->flags);
+	}
+
+	/* ring CMDQ DB */
+	wmb();
+	writel(cmdq_prod, cmdq->cmdq_mbox.prod);
+	writel(RCFW_CMDQ_TRIG_VAL, cmdq->cmdq_mbox.db);
+done:
+	spin_unlock_irqrestore(&hwq->lock, flags);
+	/* Return the CREQ response pointer */
+	return 0;
+}
+
+int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
+				 struct cmdq_base *req,
+				 struct creq_base *resp,
+				 void *sb, u8 is_block)
+{
+	struct creq_qp_event *evnt = (struct creq_qp_event *)resp;
+	u16 cookie;
+	u8 opcode, retry_cnt = 0xFF;
+	int rc = 0;
+
+	/* Prevent posting if f/w is not in a state to process */
+	if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags))
+		return 0;
+
+	do {
+		opcode = req->opcode;
+		rc = __send_message(rcfw, req, resp, sb, is_block);
+		cookie = le16_to_cpu(req->cookie) & RCFW_MAX_COOKIE_VALUE;
+		if (!rc)
+			break;
+
+		if (!retry_cnt || (rc != -EAGAIN && rc != -EBUSY)) {
+			/* send failed */
+			dev_err(&rcfw->pdev->dev, "cmdq[%#x]=%#x send failed\n",
+				cookie, opcode);
+			return rc;
+		}
+		is_block ? mdelay(1) : usleep_range(500, 1000);
+
+	} while (retry_cnt--);
+
+	if (is_block)
+		rc = __block_for_resp(rcfw, cookie);
+	else
+		rc = __wait_for_resp(rcfw, cookie);
+	if (rc) {
+		/* timed out */
+		dev_err(&rcfw->pdev->dev, "cmdq[%#x]=%#x timedout (%d)msec\n",
+			cookie, opcode, RCFW_CMD_WAIT_TIME_MS);
+		set_bit(FIRMWARE_TIMED_OUT, &rcfw->cmdq.flags);
+		return rc;
+	}
+
+	if (evnt->status) {
+		/* failed with status */
+		dev_err(&rcfw->pdev->dev, "cmdq[%#x]=%#x status %#x\n",
+			cookie, opcode, evnt->status);
+		rc = -EFAULT;
+	}
+
+	return rc;
+}
+/* Completions */
+static int bnxt_qplib_process_func_event(struct bnxt_qplib_rcfw *rcfw,
+					 struct creq_func_event *func_event)
+{
+	int rc;
+
+	switch (func_event->event) {
+	case CREQ_FUNC_EVENT_EVENT_TX_WQE_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_TX_DATA_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_RX_WQE_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_RX_DATA_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CQ_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_TQM_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCQ_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCS_ERROR:
+		/* SRQ ctx error, call srq_handler??
+		 * But there's no SRQ handle!
+		 */
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCC_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_CFCM_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_TIM_ERROR:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_VF_COMM_REQUEST:
+		break;
+	case CREQ_FUNC_EVENT_EVENT_RESOURCE_EXHAUSTED:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rc = rcfw->creq.aeq_handler(rcfw, (void *)func_event, NULL);
+	return rc;
+}
+
+static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
+				       struct creq_qp_event *qp_event,
+				       u32 *num_wait)
+{
+	struct creq_qp_error_notification *err_event;
+	struct bnxt_qplib_hwq *hwq = &rcfw->cmdq.hwq;
+	struct bnxt_qplib_crsqe *crsqe;
+	struct bnxt_qplib_qp *qp;
+	u16 cbit, blocked = 0;
+	struct pci_dev *pdev;
+	unsigned long flags;
+	u32 wait_cmds = 0;
+	__le16  mcookie;
+	u16 cookie;
+	int rc = 0;
+	u32 qp_id, tbl_indx;
+
+	pdev = rcfw->pdev;
+	switch (qp_event->event) {
+	case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION:
+		err_event = (struct creq_qp_error_notification *)qp_event;
+		qp_id = le32_to_cpu(err_event->xid);
+		tbl_indx = map_qp_id_to_tbl_indx(qp_id, rcfw);
+		qp = rcfw->qp_tbl[tbl_indx].qp_handle;
+		dev_dbg(&pdev->dev, "Received QP error notification\n");
+		dev_dbg(&pdev->dev,
+			"qpid 0x%x, req_err=0x%x, resp_err=0x%x\n",
+			qp_id, err_event->req_err_state_reason,
+			err_event->res_err_state_reason);
+		if (!qp)
+			break;
+		bnxt_qplib_mark_qp_error(qp);
+		rc = rcfw->creq.aeq_handler(rcfw, qp_event, qp);
+		break;
+	default:
+		/*
+		 * Command Response
+		 * cmdq->lock needs to be acquired to synchronie
+		 * the command send and completion reaping. This function
+		 * is always called with creq->lock held. Using
+		 * the nested variant of spin_lock.
+		 *
+		 */
+
+		spin_lock_irqsave_nested(&hwq->lock, flags,
+					 SINGLE_DEPTH_NESTING);
+		cookie = le16_to_cpu(qp_event->cookie);
+		mcookie = qp_event->cookie;
+		blocked = cookie & RCFW_CMD_IS_BLOCKING;
+		cookie &= RCFW_MAX_COOKIE_VALUE;
+		cbit = cookie % rcfw->cmdq_depth;
+		crsqe = &rcfw->crsqe_tbl[cbit];
+		if (crsqe->resp &&
+		    crsqe->resp->cookie  == mcookie) {
+			memcpy(crsqe->resp, qp_event, sizeof(*qp_event));
+			crsqe->resp = NULL;
+		} else {
+			if (crsqe->resp && crsqe->resp->cookie)
+				dev_err(&pdev->dev,
+					"CMD %s cookie sent=%#x, recd=%#x\n",
+					crsqe->resp ? "mismatch" : "collision",
+					crsqe->resp ? crsqe->resp->cookie : 0,
+					mcookie);
+		}
+		if (!test_and_clear_bit(cbit, rcfw->cmdq.cmdq_bitmap))
+			dev_warn(&pdev->dev,
+				 "CMD bit %d was not requested\n", cbit);
+		hwq->cons += crsqe->req_size;
+		crsqe->req_size = 0;
+
+		if (!blocked)
+			wait_cmds++;
+		spin_unlock_irqrestore(&hwq->lock, flags);
+	}
+	*num_wait += wait_cmds;
+	return rc;
+}
+
+/* SP - CREQ Completion handlers */
+static void bnxt_qplib_service_creq(struct tasklet_struct *t)
+{
+	struct bnxt_qplib_rcfw *rcfw = from_tasklet(rcfw, t, creq.creq_tasklet);
+	struct bnxt_qplib_creq_ctx *creq = &rcfw->creq;
+	u32 type, budget = CREQ_ENTRY_POLL_BUDGET;
+	struct bnxt_qplib_hwq *hwq = &creq->hwq;
+	struct creq_base *creqe;
+	u32 sw_cons, raw_cons;
+	unsigned long flags;
+	u32 num_wakeup = 0;
+
+	/* Service the CREQ until budget is over */
+	spin_lock_irqsave(&hwq->lock, flags);
+	raw_cons = hwq->cons;
+	while (budget > 0) {
+		sw_cons = HWQ_CMP(raw_cons, hwq);
+		creqe = bnxt_qplib_get_qe(hwq, sw_cons, NULL);
+		if (!CREQ_CMP_VALID(creqe, raw_cons, hwq->max_elements))
+			break;
+		/* The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
+
+		type = creqe->type & CREQ_BASE_TYPE_MASK;
+		switch (type) {
+		case CREQ_BASE_TYPE_QP_EVENT:
+			bnxt_qplib_process_qp_event
+				(rcfw, (struct creq_qp_event *)creqe,
+				 &num_wakeup);
+			creq->stats.creq_qp_event_processed++;
+			break;
+		case CREQ_BASE_TYPE_FUNC_EVENT:
+			if (!bnxt_qplib_process_func_event
+			    (rcfw, (struct creq_func_event *)creqe))
+				creq->stats.creq_func_event_processed++;
+			else
+				dev_warn(&rcfw->pdev->dev,
+					 "aeqe:%#x Not handled\n", type);
+			break;
+		default:
+			if (type != ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT)
+				dev_warn(&rcfw->pdev->dev,
+					 "creqe with event 0x%x not handled\n",
+					 type);
+			break;
+		}
+		raw_cons++;
+		budget--;
+	}
+
+	if (hwq->cons != raw_cons) {
+		hwq->cons = raw_cons;
+		bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo,
+				      rcfw->res->cctx, true);
+	}
+	spin_unlock_irqrestore(&hwq->lock, flags);
+	if (num_wakeup)
+		wake_up_nr(&rcfw->cmdq.waitq, num_wakeup);
+}
+
+static irqreturn_t bnxt_qplib_creq_irq(int irq, void *dev_instance)
+{
+	struct bnxt_qplib_rcfw *rcfw = dev_instance;
+	struct bnxt_qplib_creq_ctx *creq;
+	struct bnxt_qplib_hwq *hwq;
+	u32 sw_cons;
+
+	creq = &rcfw->creq;
+	hwq = &creq->hwq;
+	/* Prefetch the CREQ element */
+	sw_cons = HWQ_CMP(hwq->cons, hwq);
+	prefetch(bnxt_qplib_get_qe(hwq, sw_cons, NULL));
+
+	tasklet_schedule(&creq->creq_tasklet);
+
+	return IRQ_HANDLED;
+}
+
+/* RCFW */
+int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw)
+{
+	struct cmdq_deinitialize_fw req;
+	struct creq_deinitialize_fw_resp resp;
+	u16 cmd_flags = 0;
+	int rc;
+
+	RCFW_CMD_PREP(req, DEINITIALIZE_FW, cmd_flags);
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  NULL, 0);
+	if (rc)
+		return rc;
+
+	clear_bit(FIRMWARE_INITIALIZED_FLAG, &rcfw->cmdq.flags);
+	return 0;
+}
+
+int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
+			 struct bnxt_qplib_ctx *ctx, int is_virtfn)
+{
+	struct creq_initialize_fw_resp resp;
+	struct cmdq_initialize_fw req;
+	u16 cmd_flags = 0;
+	u8 pgsz, lvl;
+	int rc;
+
+	RCFW_CMD_PREP(req, INITIALIZE_FW, cmd_flags);
+	/* Supply (log-base-2-of-host-page-size - base-page-shift)
+	 * to bono to adjust the doorbell page sizes.
+	 */
+	req.log2_dbr_pg_size = cpu_to_le16(PAGE_SHIFT -
+					   RCFW_DBR_BASE_PAGE_SHIFT);
+	/*
+	 * Gen P5 devices doesn't require this allocation
+	 * as the L2 driver does the same for RoCE also.
+	 * Also, VFs need not setup the HW context area, PF
+	 * shall setup this area for VF. Skipping the
+	 * HW programming
+	 */
+	if (is_virtfn)
+		goto skip_ctx_setup;
+	if (bnxt_qplib_is_chip_gen_p5(rcfw->res->cctx))
+		goto config_vf_res;
+
+	lvl = ctx->qpc_tbl.level;
+	pgsz = bnxt_qplib_base_pg_size(&ctx->qpc_tbl);
+	req.qpc_pg_size_qpc_lvl = (pgsz << CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT) |
+				   lvl;
+	lvl = ctx->mrw_tbl.level;
+	pgsz = bnxt_qplib_base_pg_size(&ctx->mrw_tbl);
+	req.mrw_pg_size_mrw_lvl = (pgsz << CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT) |
+				   lvl;
+	lvl = ctx->srqc_tbl.level;
+	pgsz = bnxt_qplib_base_pg_size(&ctx->srqc_tbl);
+	req.srq_pg_size_srq_lvl = (pgsz << CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT) |
+				   lvl;
+	lvl = ctx->cq_tbl.level;
+	pgsz = bnxt_qplib_base_pg_size(&ctx->cq_tbl);
+	req.cq_pg_size_cq_lvl = (pgsz << CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT) |
+				 lvl;
+	lvl = ctx->tim_tbl.level;
+	pgsz = bnxt_qplib_base_pg_size(&ctx->tim_tbl);
+	req.tim_pg_size_tim_lvl = (pgsz << CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT) |
+				   lvl;
+	lvl = ctx->tqm_ctx.pde.level;
+	pgsz = bnxt_qplib_base_pg_size(&ctx->tqm_ctx.pde);
+	req.tqm_pg_size_tqm_lvl = (pgsz << CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT) |
+				   lvl;
+	req.qpc_page_dir =
+		cpu_to_le64(ctx->qpc_tbl.pbl[PBL_LVL_0].pg_map_arr[0]);
+	req.mrw_page_dir =
+		cpu_to_le64(ctx->mrw_tbl.pbl[PBL_LVL_0].pg_map_arr[0]);
+	req.srq_page_dir =
+		cpu_to_le64(ctx->srqc_tbl.pbl[PBL_LVL_0].pg_map_arr[0]);
+	req.cq_page_dir =
+		cpu_to_le64(ctx->cq_tbl.pbl[PBL_LVL_0].pg_map_arr[0]);
+	req.tim_page_dir =
+		cpu_to_le64(ctx->tim_tbl.pbl[PBL_LVL_0].pg_map_arr[0]);
+	req.tqm_page_dir =
+		cpu_to_le64(ctx->tqm_ctx.pde.pbl[PBL_LVL_0].pg_map_arr[0]);
+
+	req.number_of_qp = cpu_to_le32(ctx->qpc_tbl.max_elements);
+	req.number_of_mrw = cpu_to_le32(ctx->mrw_tbl.max_elements);
+	req.number_of_srq = cpu_to_le32(ctx->srqc_tbl.max_elements);
+	req.number_of_cq = cpu_to_le32(ctx->cq_tbl.max_elements);
+
+config_vf_res:
+	req.max_qp_per_vf = cpu_to_le32(ctx->vf_res.max_qp_per_vf);
+	req.max_mrw_per_vf = cpu_to_le32(ctx->vf_res.max_mrw_per_vf);
+	req.max_srq_per_vf = cpu_to_le32(ctx->vf_res.max_srq_per_vf);
+	req.max_cq_per_vf = cpu_to_le32(ctx->vf_res.max_cq_per_vf);
+	req.max_gid_per_vf = cpu_to_le32(ctx->vf_res.max_gid_per_vf);
+
+skip_ctx_setup:
+	req.stat_ctx_id = cpu_to_le32(ctx->stats.fw_id);
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  NULL, 0);
+	if (rc)
+		return rc;
+	set_bit(FIRMWARE_INITIALIZED_FLAG, &rcfw->cmdq.flags);
+	return 0;
+}
+
+void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+{
+	bitmap_free(rcfw->cmdq.cmdq_bitmap);
+	kfree(rcfw->qp_tbl);
+	kfree(rcfw->crsqe_tbl);
+	bnxt_qplib_free_hwq(rcfw->res, &rcfw->cmdq.hwq);
+	bnxt_qplib_free_hwq(rcfw->res, &rcfw->creq.hwq);
+	rcfw->pdev = NULL;
+}
+
+int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
+				  struct bnxt_qplib_rcfw *rcfw,
+				  struct bnxt_qplib_ctx *ctx,
+				  int qp_tbl_sz)
+{
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_sg_info sginfo = {};
+	struct bnxt_qplib_cmdq_ctx *cmdq;
+	struct bnxt_qplib_creq_ctx *creq;
+
+	rcfw->pdev = res->pdev;
+	cmdq = &rcfw->cmdq;
+	creq = &rcfw->creq;
+	rcfw->res = res;
+
+	sginfo.pgsize = PAGE_SIZE;
+	sginfo.pgshft = PAGE_SHIFT;
+
+	hwq_attr.sginfo = &sginfo;
+	hwq_attr.res = rcfw->res;
+	hwq_attr.depth = BNXT_QPLIB_CREQE_MAX_CNT;
+	hwq_attr.stride = BNXT_QPLIB_CREQE_UNITS;
+	hwq_attr.type = bnxt_qplib_get_hwq_type(res);
+
+	if (bnxt_qplib_alloc_init_hwq(&creq->hwq, &hwq_attr)) {
+		dev_err(&rcfw->pdev->dev,
+			"HW channel CREQ allocation failed\n");
+		goto fail;
+	}
+	if (ctx->hwrm_intf_ver < HWRM_VERSION_RCFW_CMDQ_DEPTH_CHECK)
+		rcfw->cmdq_depth = BNXT_QPLIB_CMDQE_MAX_CNT_256;
+	else
+		rcfw->cmdq_depth = BNXT_QPLIB_CMDQE_MAX_CNT_8192;
+
+	sginfo.pgsize = bnxt_qplib_cmdqe_page_size(rcfw->cmdq_depth);
+	hwq_attr.depth = rcfw->cmdq_depth & 0x7FFFFFFF;
+	hwq_attr.stride = BNXT_QPLIB_CMDQE_UNITS;
+	hwq_attr.type = HWQ_TYPE_CTX;
+	if (bnxt_qplib_alloc_init_hwq(&cmdq->hwq, &hwq_attr)) {
+		dev_err(&rcfw->pdev->dev,
+			"HW channel CMDQ allocation failed\n");
+		goto fail;
+	}
+
+	rcfw->crsqe_tbl = kcalloc(cmdq->hwq.max_elements,
+				  sizeof(*rcfw->crsqe_tbl), GFP_KERNEL);
+	if (!rcfw->crsqe_tbl)
+		goto fail;
+
+	cmdq->cmdq_bitmap = bitmap_zalloc(rcfw->cmdq_depth, GFP_KERNEL);
+	if (!cmdq->cmdq_bitmap)
+		goto fail;
+
+	/* Allocate one extra to hold the QP1 entries */
+	rcfw->qp_tbl_size = qp_tbl_sz + 1;
+	rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
+			       GFP_KERNEL);
+	if (!rcfw->qp_tbl)
+		goto fail;
+
+	return 0;
+
+fail:
+	bnxt_qplib_free_rcfw_channel(rcfw);
+	return -ENOMEM;
+}
+
+void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill)
+{
+	struct bnxt_qplib_creq_ctx *creq;
+
+	creq = &rcfw->creq;
+
+	if (!creq->requested)
+		return;
+
+	tasklet_disable(&creq->creq_tasklet);
+	/* Mask h/w interrupts */
+	bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, rcfw->res->cctx, false);
+	/* Sync with last running IRQ-handler */
+	synchronize_irq(creq->msix_vec);
+	if (kill)
+		tasklet_kill(&creq->creq_tasklet);
+
+	free_irq(creq->msix_vec, rcfw);
+	kfree(creq->irq_name);
+	creq->irq_name = NULL;
+	creq->requested = false;
+}
+
+void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+{
+	struct bnxt_qplib_creq_ctx *creq;
+	struct bnxt_qplib_cmdq_ctx *cmdq;
+	unsigned long indx;
+
+	creq = &rcfw->creq;
+	cmdq = &rcfw->cmdq;
+	/* Make sure the HW channel is stopped! */
+	bnxt_qplib_rcfw_stop_irq(rcfw, true);
+
+	iounmap(cmdq->cmdq_mbox.reg.bar_reg);
+	iounmap(creq->creq_db.reg.bar_reg);
+
+	indx = find_first_bit(cmdq->cmdq_bitmap, rcfw->cmdq_depth);
+	if (indx != rcfw->cmdq_depth)
+		dev_err(&rcfw->pdev->dev,
+			"disabling RCFW with pending cmd-bit %lx\n", indx);
+
+	cmdq->cmdq_mbox.reg.bar_reg = NULL;
+	creq->creq_db.reg.bar_reg = NULL;
+	creq->aeq_handler = NULL;
+	creq->msix_vec = 0;
+}
+
+int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
+			      bool need_init)
+{
+	struct bnxt_qplib_creq_ctx *creq;
+	struct bnxt_qplib_res *res;
+	int rc;
+
+	creq = &rcfw->creq;
+	res = rcfw->res;
+
+	if (creq->requested)
+		return -EFAULT;
+
+	creq->msix_vec = msix_vector;
+	if (need_init)
+		tasklet_setup(&creq->creq_tasklet, bnxt_qplib_service_creq);
+	else
+		tasklet_enable(&creq->creq_tasklet);
+
+	creq->irq_name = kasprintf(GFP_KERNEL, "bnxt_re-creq@pci:%s",
+				   pci_name(res->pdev));
+	if (!creq->irq_name)
+		return -ENOMEM;
+	rc = request_irq(creq->msix_vec, bnxt_qplib_creq_irq, 0,
+			 creq->irq_name, rcfw);
+	if (rc) {
+		kfree(creq->irq_name);
+		creq->irq_name = NULL;
+		tasklet_disable(&creq->creq_tasklet);
+		return rc;
+	}
+	creq->requested = true;
+
+	bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, res->cctx, true);
+
+	return 0;
+}
+
+static int bnxt_qplib_map_cmdq_mbox(struct bnxt_qplib_rcfw *rcfw, bool is_vf)
+{
+	struct bnxt_qplib_cmdq_mbox *mbox;
+	resource_size_t bar_reg;
+	struct pci_dev *pdev;
+	u16 prod_offt;
+	int rc = 0;
+
+	pdev = rcfw->pdev;
+	mbox = &rcfw->cmdq.cmdq_mbox;
+
+	mbox->reg.bar_id = RCFW_COMM_PCI_BAR_REGION;
+	mbox->reg.len = RCFW_COMM_SIZE;
+	mbox->reg.bar_base = pci_resource_start(pdev, mbox->reg.bar_id);
+	if (!mbox->reg.bar_base) {
+		dev_err(&pdev->dev,
+			"QPLIB: CMDQ BAR region %d resc start is 0!\n",
+			mbox->reg.bar_id);
+		return -ENOMEM;
+	}
+
+	bar_reg = mbox->reg.bar_base + RCFW_COMM_BASE_OFFSET;
+	mbox->reg.len = RCFW_COMM_SIZE;
+	mbox->reg.bar_reg = ioremap(bar_reg, mbox->reg.len);
+	if (!mbox->reg.bar_reg) {
+		dev_err(&pdev->dev,
+			"QPLIB: CMDQ BAR region %d mapping failed\n",
+			mbox->reg.bar_id);
+		return -ENOMEM;
+	}
+
+	prod_offt = is_vf ? RCFW_VF_COMM_PROD_OFFSET :
+			    RCFW_PF_COMM_PROD_OFFSET;
+	mbox->prod = (void  __iomem *)(mbox->reg.bar_reg + prod_offt);
+	mbox->db = (void __iomem *)(mbox->reg.bar_reg + RCFW_COMM_TRIG_OFFSET);
+	return rc;
+}
+
+static int bnxt_qplib_map_creq_db(struct bnxt_qplib_rcfw *rcfw, u32 reg_offt)
+{
+	struct bnxt_qplib_creq_db *creq_db;
+	resource_size_t bar_reg;
+	struct pci_dev *pdev;
+
+	pdev = rcfw->pdev;
+	creq_db = &rcfw->creq.creq_db;
+
+	creq_db->reg.bar_id = RCFW_COMM_CONS_PCI_BAR_REGION;
+	creq_db->reg.bar_base = pci_resource_start(pdev, creq_db->reg.bar_id);
+	if (!creq_db->reg.bar_id)
+		dev_err(&pdev->dev,
+			"QPLIB: CREQ BAR region %d resc start is 0!",
+			creq_db->reg.bar_id);
+
+	bar_reg = creq_db->reg.bar_base + reg_offt;
+	/* Unconditionally map 8 bytes to support 57500 series */
+	creq_db->reg.len = 8;
+	creq_db->reg.bar_reg = ioremap(bar_reg, creq_db->reg.len);
+	if (!creq_db->reg.bar_reg) {
+		dev_err(&pdev->dev,
+			"QPLIB: CREQ BAR region %d mapping failed",
+			creq_db->reg.bar_id);
+		return -ENOMEM;
+	}
+	creq_db->dbinfo.db = creq_db->reg.bar_reg;
+	creq_db->dbinfo.hwq = &rcfw->creq.hwq;
+	creq_db->dbinfo.xid = rcfw->creq.ring_id;
+	return 0;
+}
+
+static void bnxt_qplib_start_rcfw(struct bnxt_qplib_rcfw *rcfw)
+{
+	struct bnxt_qplib_cmdq_ctx *cmdq;
+	struct bnxt_qplib_creq_ctx *creq;
+	struct bnxt_qplib_cmdq_mbox *mbox;
+	struct cmdq_init init = {0};
+
+	cmdq = &rcfw->cmdq;
+	creq = &rcfw->creq;
+	mbox = &cmdq->cmdq_mbox;
+
+	init.cmdq_pbl = cpu_to_le64(cmdq->hwq.pbl[PBL_LVL_0].pg_map_arr[0]);
+	init.cmdq_size_cmdq_lvl =
+			cpu_to_le16(((rcfw->cmdq_depth <<
+				      CMDQ_INIT_CMDQ_SIZE_SFT) &
+				    CMDQ_INIT_CMDQ_SIZE_MASK) |
+				    ((cmdq->hwq.level <<
+				      CMDQ_INIT_CMDQ_LVL_SFT) &
+				    CMDQ_INIT_CMDQ_LVL_MASK));
+	init.creq_ring_id = cpu_to_le16(creq->ring_id);
+	/* Write to the Bono mailbox register */
+	__iowrite32_copy(mbox->reg.bar_reg, &init, sizeof(init) / 4);
+}
+
+int bnxt_qplib_enable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw,
+				   int msix_vector,
+				   int cp_bar_reg_off, int virt_fn,
+				   aeq_handler_t aeq_handler)
+{
+	struct bnxt_qplib_cmdq_ctx *cmdq;
+	struct bnxt_qplib_creq_ctx *creq;
+	int rc;
+
+	cmdq = &rcfw->cmdq;
+	creq = &rcfw->creq;
+
+	/* Clear to defaults */
+
+	cmdq->seq_num = 0;
+	set_bit(FIRMWARE_FIRST_FLAG, &cmdq->flags);
+	init_waitqueue_head(&cmdq->waitq);
+
+	creq->stats.creq_qp_event_processed = 0;
+	creq->stats.creq_func_event_processed = 0;
+	creq->aeq_handler = aeq_handler;
+
+	rc = bnxt_qplib_map_cmdq_mbox(rcfw, virt_fn);
+	if (rc)
+		return rc;
+
+	rc = bnxt_qplib_map_creq_db(rcfw, cp_bar_reg_off);
+	if (rc)
+		return rc;
+
+	rc = bnxt_qplib_rcfw_start_irq(rcfw, msix_vector, true);
+	if (rc) {
+		dev_err(&rcfw->pdev->dev,
+			"Failed to request IRQ for CREQ rc = 0x%x\n", rc);
+		bnxt_qplib_disable_rcfw_channel(rcfw);
+		return rc;
+	}
+
+	bnxt_qplib_start_rcfw(rcfw);
+
+	return 0;
+}
+
+struct bnxt_qplib_rcfw_sbuf *bnxt_qplib_rcfw_alloc_sbuf(
+		struct bnxt_qplib_rcfw *rcfw,
+		u32 size)
+{
+	struct bnxt_qplib_rcfw_sbuf *sbuf;
+
+	sbuf = kzalloc(sizeof(*sbuf), GFP_KERNEL);
+	if (!sbuf)
+		return NULL;
+
+	sbuf->size = size;
+	sbuf->sb = dma_alloc_coherent(&rcfw->pdev->dev, sbuf->size,
+				      &sbuf->dma_addr, GFP_KERNEL);
+	if (!sbuf->sb)
+		goto bail;
+
+	return sbuf;
+bail:
+	kfree(sbuf);
+	return NULL;
+}
+
+void bnxt_qplib_rcfw_free_sbuf(struct bnxt_qplib_rcfw *rcfw,
+			       struct bnxt_qplib_rcfw_sbuf *sbuf)
+{
+	if (sbuf->sb)
+		dma_free_coherent(&rcfw->pdev->dev, sbuf->size,
+				  sbuf->sb, sbuf->dma_addr);
+	kfree(sbuf);
+}
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
new file mode 100644
index 000000000..b887e7fba
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -0,0 +1,226 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: RDMA Controller HW interface (header)
+ */
+
+#ifndef __BNXT_QPLIB_RCFW_H__
+#define __BNXT_QPLIB_RCFW_H__
+
+#define RCFW_CMDQ_TRIG_VAL		1
+#define RCFW_COMM_PCI_BAR_REGION	0
+#define RCFW_COMM_CONS_PCI_BAR_REGION	2
+#define RCFW_COMM_BASE_OFFSET		0x600
+#define RCFW_PF_COMM_PROD_OFFSET	0xc
+#define RCFW_VF_COMM_PROD_OFFSET	0xc
+#define RCFW_COMM_TRIG_OFFSET		0x100
+#define RCFW_COMM_SIZE			0x104
+
+#define RCFW_DBR_PCI_BAR_REGION		2
+#define RCFW_DBR_BASE_PAGE_SHIFT	12
+
+#define RCFW_CMD_PREP(req, CMD, cmd_flags)				\
+	do {								\
+		memset(&(req), 0, sizeof((req)));			\
+		(req).opcode = CMDQ_BASE_OPCODE_##CMD;			\
+		(req).cmd_size = sizeof((req));				\
+		(req).flags = cpu_to_le16(cmd_flags);			\
+	} while (0)
+
+#define RCFW_CMD_WAIT_TIME_MS		20000 /* 20 Seconds timeout */
+
+/* Cmdq contains a fix number of a 16-Byte slots */
+struct bnxt_qplib_cmdqe {
+	u8		data[16];
+};
+
+/* CMDQ elements */
+#define BNXT_QPLIB_CMDQE_MAX_CNT_256	256
+#define BNXT_QPLIB_CMDQE_MAX_CNT_8192	8192
+#define BNXT_QPLIB_CMDQE_UNITS		sizeof(struct bnxt_qplib_cmdqe)
+#define BNXT_QPLIB_CMDQE_BYTES(depth)	((depth) * BNXT_QPLIB_CMDQE_UNITS)
+
+static inline u32 bnxt_qplib_cmdqe_npages(u32 depth)
+{
+	u32 npages;
+
+	npages = BNXT_QPLIB_CMDQE_BYTES(depth) / PAGE_SIZE;
+	if (BNXT_QPLIB_CMDQE_BYTES(depth) % PAGE_SIZE)
+		npages++;
+	return npages;
+}
+
+static inline u32 bnxt_qplib_cmdqe_page_size(u32 depth)
+{
+	return (bnxt_qplib_cmdqe_npages(depth) * PAGE_SIZE);
+}
+
+/* Set the cmd_size to a factor of CMDQE unit */
+static inline void bnxt_qplib_set_cmd_slots(struct cmdq_base *req)
+{
+	req->cmd_size = (req->cmd_size + BNXT_QPLIB_CMDQE_UNITS - 1) /
+			 BNXT_QPLIB_CMDQE_UNITS;
+}
+
+#define RCFW_MAX_COOKIE_VALUE		0x7FFF
+#define RCFW_CMD_IS_BLOCKING		0x8000
+#define RCFW_BLOCKED_CMD_WAIT_COUNT	20000000UL /* 20 sec */
+
+#define HWRM_VERSION_RCFW_CMDQ_DEPTH_CHECK 0x1000900020011ULL
+
+/* Crsq buf is 1024-Byte */
+struct bnxt_qplib_crsbe {
+	u8			data[1024];
+};
+
+/* CREQ */
+/* Allocate 1 per QP for async error notification for now */
+#define BNXT_QPLIB_CREQE_MAX_CNT	(64 * 1024)
+#define BNXT_QPLIB_CREQE_UNITS		16	/* 16-Bytes per prod unit */
+#define CREQ_CMP_VALID(hdr, raw_cons, cp_bit)			\
+	(!!((hdr)->v & CREQ_BASE_V) ==				\
+	   !((raw_cons) & (cp_bit)))
+#define CREQ_ENTRY_POLL_BUDGET		0x100
+
+/* HWQ */
+typedef int (*aeq_handler_t)(struct bnxt_qplib_rcfw *, void *, void *);
+
+struct bnxt_qplib_crsqe {
+	struct creq_qp_event	*resp;
+	u32			req_size;
+};
+
+struct bnxt_qplib_rcfw_sbuf {
+	void *sb;
+	dma_addr_t dma_addr;
+	u32 size;
+};
+
+struct bnxt_qplib_qp_node {
+	u32 qp_id;              /* QP id */
+	void *qp_handle;        /* ptr to qplib_qp */
+};
+
+#define BNXT_QPLIB_OOS_COUNT_MASK 0xFFFFFFFF
+
+#define FIRMWARE_INITIALIZED_FLAG	(0)
+#define FIRMWARE_FIRST_FLAG		(31)
+#define FIRMWARE_TIMED_OUT		(3)
+#define ERR_DEVICE_DETACHED             (4)
+
+struct bnxt_qplib_cmdq_mbox {
+	struct bnxt_qplib_reg_desc	reg;
+	void __iomem			*prod;
+	void __iomem			*db;
+};
+
+struct bnxt_qplib_cmdq_ctx {
+	struct bnxt_qplib_hwq		hwq;
+	struct bnxt_qplib_cmdq_mbox	cmdq_mbox;
+	wait_queue_head_t		waitq;
+	unsigned long			flags;
+	unsigned long			*cmdq_bitmap;
+	u32				seq_num;
+};
+
+struct bnxt_qplib_creq_db {
+	struct bnxt_qplib_reg_desc	reg;
+	struct bnxt_qplib_db_info	dbinfo;
+};
+
+struct bnxt_qplib_creq_stat {
+	u64	creq_qp_event_processed;
+	u64	creq_func_event_processed;
+};
+
+struct bnxt_qplib_creq_ctx {
+	struct bnxt_qplib_hwq		hwq;
+	struct bnxt_qplib_creq_db	creq_db;
+	struct bnxt_qplib_creq_stat	stats;
+	struct tasklet_struct		creq_tasklet;
+	aeq_handler_t			aeq_handler;
+	u16				ring_id;
+	int				msix_vec;
+	bool				requested; /*irq handler installed */
+	char				*irq_name;
+};
+
+/* RCFW Communication Channels */
+struct bnxt_qplib_rcfw {
+	struct pci_dev		*pdev;
+	struct bnxt_qplib_res	*res;
+	struct bnxt_qplib_cmdq_ctx	cmdq;
+	struct bnxt_qplib_creq_ctx	creq;
+	struct bnxt_qplib_crsqe		*crsqe_tbl;
+	int qp_tbl_size;
+	struct bnxt_qplib_qp_node *qp_tbl;
+	u64 oos_prev;
+	u32 init_oos_stats;
+	u32 cmdq_depth;
+};
+
+void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
+int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
+				  struct bnxt_qplib_rcfw *rcfw,
+				  struct bnxt_qplib_ctx *ctx,
+				  int qp_tbl_sz);
+void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill);
+void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
+int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
+			      bool need_init);
+int bnxt_qplib_enable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw,
+				   int msix_vector,
+				   int cp_bar_reg_off, int virt_fn,
+				   aeq_handler_t aeq_handler);
+
+struct bnxt_qplib_rcfw_sbuf *bnxt_qplib_rcfw_alloc_sbuf(
+				struct bnxt_qplib_rcfw *rcfw,
+				u32 size);
+void bnxt_qplib_rcfw_free_sbuf(struct bnxt_qplib_rcfw *rcfw,
+			       struct bnxt_qplib_rcfw_sbuf *sbuf);
+int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
+				 struct cmdq_base *req, struct creq_base *resp,
+				 void *sbuf, u8 is_block);
+
+int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
+int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
+			 struct bnxt_qplib_ctx *ctx, int is_virtfn);
+void bnxt_qplib_mark_qp_error(void *qp_handle);
+static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw)
+{
+	/* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/
+	return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2;
+}
+#endif /* __BNXT_QPLIB_RCFW_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
new file mode 100644
index 000000000..81b0c5e87
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -0,0 +1,902 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: QPLib resource manager
+ */
+
+#define dev_fmt(fmt) "QPLIB: " fmt
+
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/inetdevice.h>
+#include <linux/dma-mapping.h>
+#include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_umem.h>
+
+#include "roce_hsi.h"
+#include "qplib_res.h"
+#include "qplib_sp.h"
+#include "qplib_rcfw.h"
+
+static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev,
+				      struct bnxt_qplib_stats *stats);
+static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+				      struct bnxt_qplib_chip_ctx *cctx,
+				      struct bnxt_qplib_stats *stats);
+
+/* PBL */
+static void __free_pbl(struct bnxt_qplib_res *res, struct bnxt_qplib_pbl *pbl,
+		       bool is_umem)
+{
+	struct pci_dev *pdev = res->pdev;
+	int i;
+
+	if (!is_umem) {
+		for (i = 0; i < pbl->pg_count; i++) {
+			if (pbl->pg_arr[i])
+				dma_free_coherent(&pdev->dev, pbl->pg_size,
+						  (void *)((unsigned long)
+						   pbl->pg_arr[i] &
+						  PAGE_MASK),
+						  pbl->pg_map_arr[i]);
+			else
+				dev_warn(&pdev->dev,
+					 "PBL free pg_arr[%d] empty?!\n", i);
+			pbl->pg_arr[i] = NULL;
+		}
+	}
+	vfree(pbl->pg_arr);
+	pbl->pg_arr = NULL;
+	vfree(pbl->pg_map_arr);
+	pbl->pg_map_arr = NULL;
+	pbl->pg_count = 0;
+	pbl->pg_size = 0;
+}
+
+static void bnxt_qplib_fill_user_dma_pages(struct bnxt_qplib_pbl *pbl,
+					   struct bnxt_qplib_sg_info *sginfo)
+{
+	struct ib_block_iter biter;
+	int i = 0;
+
+	rdma_umem_for_each_dma_block(sginfo->umem, &biter, sginfo->pgsize) {
+		pbl->pg_map_arr[i] = rdma_block_iter_dma_address(&biter);
+		pbl->pg_arr[i] = NULL;
+		pbl->pg_count++;
+		i++;
+	}
+}
+
+static int __alloc_pbl(struct bnxt_qplib_res *res,
+		       struct bnxt_qplib_pbl *pbl,
+		       struct bnxt_qplib_sg_info *sginfo)
+{
+	struct pci_dev *pdev = res->pdev;
+	bool is_umem = false;
+	u32 pages;
+	int i;
+
+	if (sginfo->nopte)
+		return 0;
+	if (sginfo->umem)
+		pages = ib_umem_num_dma_blocks(sginfo->umem, sginfo->pgsize);
+	else
+		pages = sginfo->npages;
+	/* page ptr arrays */
+	pbl->pg_arr = vmalloc(pages * sizeof(void *));
+	if (!pbl->pg_arr)
+		return -ENOMEM;
+
+	pbl->pg_map_arr = vmalloc(pages * sizeof(dma_addr_t));
+	if (!pbl->pg_map_arr) {
+		vfree(pbl->pg_arr);
+		pbl->pg_arr = NULL;
+		return -ENOMEM;
+	}
+	pbl->pg_count = 0;
+	pbl->pg_size = sginfo->pgsize;
+
+	if (!sginfo->umem) {
+		for (i = 0; i < pages; i++) {
+			pbl->pg_arr[i] = dma_alloc_coherent(&pdev->dev,
+							    pbl->pg_size,
+							    &pbl->pg_map_arr[i],
+							    GFP_KERNEL);
+			if (!pbl->pg_arr[i])
+				goto fail;
+			pbl->pg_count++;
+		}
+	} else {
+		is_umem = true;
+		bnxt_qplib_fill_user_dma_pages(pbl, sginfo);
+	}
+
+	return 0;
+fail:
+	__free_pbl(res, pbl, is_umem);
+	return -ENOMEM;
+}
+
+/* HWQ */
+void bnxt_qplib_free_hwq(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_hwq *hwq)
+{
+	int i;
+
+	if (!hwq->max_elements)
+		return;
+	if (hwq->level >= PBL_LVL_MAX)
+		return;
+
+	for (i = 0; i < hwq->level + 1; i++) {
+		if (i == hwq->level)
+			__free_pbl(res, &hwq->pbl[i], hwq->is_user);
+		else
+			__free_pbl(res, &hwq->pbl[i], false);
+	}
+
+	hwq->level = PBL_LVL_MAX;
+	hwq->max_elements = 0;
+	hwq->element_size = 0;
+	hwq->prod = 0;
+	hwq->cons = 0;
+	hwq->cp_bit = 0;
+}
+
+/* All HWQs are power of 2 in size */
+
+int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq,
+			      struct bnxt_qplib_hwq_attr *hwq_attr)
+{
+	u32 npages, aux_slots, pg_size, aux_pages = 0, aux_size = 0;
+	struct bnxt_qplib_sg_info sginfo = {};
+	u32 depth, stride, npbl, npde;
+	dma_addr_t *src_phys_ptr, **dst_virt_ptr;
+	struct bnxt_qplib_res *res;
+	struct pci_dev *pdev;
+	int i, rc, lvl;
+
+	res = hwq_attr->res;
+	pdev = res->pdev;
+	pg_size = hwq_attr->sginfo->pgsize;
+	hwq->level = PBL_LVL_MAX;
+
+	depth = roundup_pow_of_two(hwq_attr->depth);
+	stride = roundup_pow_of_two(hwq_attr->stride);
+	if (hwq_attr->aux_depth) {
+		aux_slots = hwq_attr->aux_depth;
+		aux_size = roundup_pow_of_two(hwq_attr->aux_stride);
+		aux_pages = (aux_slots * aux_size) / pg_size;
+		if ((aux_slots * aux_size) % pg_size)
+			aux_pages++;
+	}
+
+	if (!hwq_attr->sginfo->umem) {
+		hwq->is_user = false;
+		npages = (depth * stride) / pg_size + aux_pages;
+		if ((depth * stride) % pg_size)
+			npages++;
+		if (!npages)
+			return -EINVAL;
+		hwq_attr->sginfo->npages = npages;
+	} else {
+		npages = ib_umem_num_dma_blocks(hwq_attr->sginfo->umem,
+						hwq_attr->sginfo->pgsize);
+		hwq->is_user = true;
+	}
+
+	if (npages == MAX_PBL_LVL_0_PGS && !hwq_attr->sginfo->nopte) {
+		/* This request is Level 0, map PTE */
+		rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_0], hwq_attr->sginfo);
+		if (rc)
+			goto fail;
+		hwq->level = PBL_LVL_0;
+		goto done;
+	}
+
+	if (npages >= MAX_PBL_LVL_0_PGS) {
+		if (npages > MAX_PBL_LVL_1_PGS) {
+			u32 flag = (hwq_attr->type == HWQ_TYPE_L2_CMPL) ?
+				    0 : PTU_PTE_VALID;
+			/* 2 levels of indirection */
+			npbl = npages >> MAX_PBL_LVL_1_PGS_SHIFT;
+			if (npages % BIT(MAX_PBL_LVL_1_PGS_SHIFT))
+				npbl++;
+			npde = npbl >> MAX_PDL_LVL_SHIFT;
+			if (npbl % BIT(MAX_PDL_LVL_SHIFT))
+				npde++;
+			/* Alloc PDE pages */
+			sginfo.pgsize = npde * pg_size;
+			sginfo.npages = 1;
+			rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_0], &sginfo);
+
+			/* Alloc PBL pages */
+			sginfo.npages = npbl;
+			sginfo.pgsize = PAGE_SIZE;
+			rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_1], &sginfo);
+			if (rc)
+				goto fail;
+			/* Fill PDL with PBL page pointers */
+			dst_virt_ptr =
+				(dma_addr_t **)hwq->pbl[PBL_LVL_0].pg_arr;
+			src_phys_ptr = hwq->pbl[PBL_LVL_1].pg_map_arr;
+			if (hwq_attr->type == HWQ_TYPE_MR) {
+			/* For MR it is expected that we supply only 1 contigous
+			 * page i.e only 1 entry in the PDL that will contain
+			 * all the PBLs for the user supplied memory region
+			 */
+				for (i = 0; i < hwq->pbl[PBL_LVL_1].pg_count;
+				     i++)
+					dst_virt_ptr[0][i] = src_phys_ptr[i] |
+						flag;
+			} else {
+				for (i = 0; i < hwq->pbl[PBL_LVL_1].pg_count;
+				     i++)
+					dst_virt_ptr[PTR_PG(i)][PTR_IDX(i)] =
+						src_phys_ptr[i] |
+						PTU_PDE_VALID;
+			}
+			/* Alloc or init PTEs */
+			rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_2],
+					 hwq_attr->sginfo);
+			if (rc)
+				goto fail;
+			hwq->level = PBL_LVL_2;
+			if (hwq_attr->sginfo->nopte)
+				goto done;
+			/* Fill PBLs with PTE pointers */
+			dst_virt_ptr =
+				(dma_addr_t **)hwq->pbl[PBL_LVL_1].pg_arr;
+			src_phys_ptr = hwq->pbl[PBL_LVL_2].pg_map_arr;
+			for (i = 0; i < hwq->pbl[PBL_LVL_2].pg_count; i++) {
+				dst_virt_ptr[PTR_PG(i)][PTR_IDX(i)] =
+					src_phys_ptr[i] | PTU_PTE_VALID;
+			}
+			if (hwq_attr->type == HWQ_TYPE_QUEUE) {
+				/* Find the last pg of the size */
+				i = hwq->pbl[PBL_LVL_2].pg_count;
+				dst_virt_ptr[PTR_PG(i - 1)][PTR_IDX(i - 1)] |=
+								  PTU_PTE_LAST;
+				if (i > 1)
+					dst_virt_ptr[PTR_PG(i - 2)]
+						    [PTR_IDX(i - 2)] |=
+						    PTU_PTE_NEXT_TO_LAST;
+			}
+		} else { /* pages < 512 npbl = 1, npde = 0 */
+			u32 flag = (hwq_attr->type == HWQ_TYPE_L2_CMPL) ?
+				    0 : PTU_PTE_VALID;
+
+			/* 1 level of indirection */
+			npbl = npages >> MAX_PBL_LVL_1_PGS_SHIFT;
+			if (npages % BIT(MAX_PBL_LVL_1_PGS_SHIFT))
+				npbl++;
+			sginfo.npages = npbl;
+			sginfo.pgsize = PAGE_SIZE;
+			/* Alloc PBL page */
+			rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_0], &sginfo);
+			if (rc)
+				goto fail;
+			/* Alloc or init  PTEs */
+			rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_1],
+					 hwq_attr->sginfo);
+			if (rc)
+				goto fail;
+			hwq->level = PBL_LVL_1;
+			if (hwq_attr->sginfo->nopte)
+				goto done;
+			/* Fill PBL with PTE pointers */
+			dst_virt_ptr =
+				(dma_addr_t **)hwq->pbl[PBL_LVL_0].pg_arr;
+			src_phys_ptr = hwq->pbl[PBL_LVL_1].pg_map_arr;
+			for (i = 0; i < hwq->pbl[PBL_LVL_1].pg_count; i++)
+				dst_virt_ptr[PTR_PG(i)][PTR_IDX(i)] =
+					src_phys_ptr[i] | flag;
+			if (hwq_attr->type == HWQ_TYPE_QUEUE) {
+				/* Find the last pg of the size */
+				i = hwq->pbl[PBL_LVL_1].pg_count;
+				dst_virt_ptr[PTR_PG(i - 1)][PTR_IDX(i - 1)] |=
+								  PTU_PTE_LAST;
+				if (i > 1)
+					dst_virt_ptr[PTR_PG(i - 2)]
+						    [PTR_IDX(i - 2)] |=
+						    PTU_PTE_NEXT_TO_LAST;
+			}
+		}
+	}
+done:
+	hwq->prod = 0;
+	hwq->cons = 0;
+	hwq->pdev = pdev;
+	hwq->depth = hwq_attr->depth;
+	hwq->max_elements = depth;
+	hwq->element_size = stride;
+	hwq->qe_ppg = pg_size / stride;
+	/* For direct access to the elements */
+	lvl = hwq->level;
+	if (hwq_attr->sginfo->nopte && hwq->level)
+		lvl = hwq->level - 1;
+	hwq->pbl_ptr = hwq->pbl[lvl].pg_arr;
+	hwq->pbl_dma_ptr = hwq->pbl[lvl].pg_map_arr;
+	spin_lock_init(&hwq->lock);
+
+	return 0;
+fail:
+	bnxt_qplib_free_hwq(res, hwq);
+	return -ENOMEM;
+}
+
+/* Context Tables */
+void bnxt_qplib_free_ctx(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_ctx *ctx)
+{
+	int i;
+
+	bnxt_qplib_free_hwq(res, &ctx->qpc_tbl);
+	bnxt_qplib_free_hwq(res, &ctx->mrw_tbl);
+	bnxt_qplib_free_hwq(res, &ctx->srqc_tbl);
+	bnxt_qplib_free_hwq(res, &ctx->cq_tbl);
+	bnxt_qplib_free_hwq(res, &ctx->tim_tbl);
+	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
+		bnxt_qplib_free_hwq(res, &ctx->tqm_ctx.qtbl[i]);
+	/* restore original pde level before destroy */
+	ctx->tqm_ctx.pde.level = ctx->tqm_ctx.pde_level;
+	bnxt_qplib_free_hwq(res, &ctx->tqm_ctx.pde);
+	bnxt_qplib_free_stats_ctx(res->pdev, &ctx->stats);
+}
+
+static int bnxt_qplib_alloc_tqm_rings(struct bnxt_qplib_res *res,
+				      struct bnxt_qplib_ctx *ctx)
+{
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_sg_info sginfo = {};
+	struct bnxt_qplib_tqm_ctx *tqmctx;
+	int rc = 0;
+	int i;
+
+	tqmctx = &ctx->tqm_ctx;
+
+	sginfo.pgsize = PAGE_SIZE;
+	sginfo.pgshft = PAGE_SHIFT;
+	hwq_attr.sginfo = &sginfo;
+	hwq_attr.res = res;
+	hwq_attr.type = HWQ_TYPE_CTX;
+	hwq_attr.depth = 512;
+	hwq_attr.stride = sizeof(u64);
+	/* Alloc pdl buffer */
+	rc = bnxt_qplib_alloc_init_hwq(&tqmctx->pde, &hwq_attr);
+	if (rc)
+		goto out;
+	/* Save original pdl level */
+	tqmctx->pde_level = tqmctx->pde.level;
+
+	hwq_attr.stride = 1;
+	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++) {
+		if (!tqmctx->qcount[i])
+			continue;
+		hwq_attr.depth = ctx->qpc_count * tqmctx->qcount[i];
+		rc = bnxt_qplib_alloc_init_hwq(&tqmctx->qtbl[i], &hwq_attr);
+		if (rc)
+			goto out;
+	}
+out:
+	return rc;
+}
+
+static void bnxt_qplib_map_tqm_pgtbl(struct bnxt_qplib_tqm_ctx *ctx)
+{
+	struct bnxt_qplib_hwq *tbl;
+	dma_addr_t *dma_ptr;
+	__le64 **pbl_ptr, *ptr;
+	int i, j, k;
+	int fnz_idx = -1;
+	int pg_count;
+
+	pbl_ptr = (__le64 **)ctx->pde.pbl_ptr;
+
+	for (i = 0, j = 0; i < MAX_TQM_ALLOC_REQ;
+	     i++, j += MAX_TQM_ALLOC_BLK_SIZE) {
+		tbl = &ctx->qtbl[i];
+		if (!tbl->max_elements)
+			continue;
+		if (fnz_idx == -1)
+			fnz_idx = i; /* first non-zero index */
+		switch (tbl->level) {
+		case PBL_LVL_2:
+			pg_count = tbl->pbl[PBL_LVL_1].pg_count;
+			for (k = 0; k < pg_count; k++) {
+				ptr = &pbl_ptr[PTR_PG(j + k)][PTR_IDX(j + k)];
+				dma_ptr = &tbl->pbl[PBL_LVL_1].pg_map_arr[k];
+				*ptr = cpu_to_le64(*dma_ptr | PTU_PTE_VALID);
+			}
+			break;
+		case PBL_LVL_1:
+		case PBL_LVL_0:
+		default:
+			ptr = &pbl_ptr[PTR_PG(j)][PTR_IDX(j)];
+			*ptr = cpu_to_le64(tbl->pbl[PBL_LVL_0].pg_map_arr[0] |
+					   PTU_PTE_VALID);
+			break;
+		}
+	}
+	if (fnz_idx == -1)
+		fnz_idx = 0;
+	/* update pde level as per page table programming */
+	ctx->pde.level = (ctx->qtbl[fnz_idx].level == PBL_LVL_2) ? PBL_LVL_2 :
+			  ctx->qtbl[fnz_idx].level + 1;
+}
+
+static int bnxt_qplib_setup_tqm_rings(struct bnxt_qplib_res *res,
+				      struct bnxt_qplib_ctx *ctx)
+{
+	int rc = 0;
+
+	rc = bnxt_qplib_alloc_tqm_rings(res, ctx);
+	if (rc)
+		goto fail;
+
+	bnxt_qplib_map_tqm_pgtbl(&ctx->tqm_ctx);
+fail:
+	return rc;
+}
+
+/*
+ * Routine: bnxt_qplib_alloc_ctx
+ * Description:
+ *     Context tables are memories which are used by the chip fw.
+ *     The 6 tables defined are:
+ *             QPC ctx - holds QP states
+ *             MRW ctx - holds memory region and window
+ *             SRQ ctx - holds shared RQ states
+ *             CQ ctx - holds completion queue states
+ *             TQM ctx - holds Tx Queue Manager context
+ *             TIM ctx - holds timer context
+ *     Depending on the size of the tbl requested, either a 1 Page Buffer List
+ *     or a 1-to-2-stage indirection Page Directory List + 1 PBL is used
+ *     instead.
+ *     Table might be employed as follows:
+ *             For 0      < ctx size <= 1 PAGE, 0 level of ind is used
+ *             For 1 PAGE < ctx size <= 512 entries size, 1 level of ind is used
+ *             For 512    < ctx size <= MAX, 2 levels of ind is used
+ * Returns:
+ *     0 if success, else -ERRORS
+ */
+int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_ctx *ctx,
+			 bool virt_fn, bool is_p5)
+{
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_sg_info sginfo = {};
+	int rc = 0;
+
+	if (virt_fn || is_p5)
+		goto stats_alloc;
+
+	/* QPC Tables */
+	sginfo.pgsize = PAGE_SIZE;
+	sginfo.pgshft = PAGE_SHIFT;
+	hwq_attr.sginfo = &sginfo;
+
+	hwq_attr.res = res;
+	hwq_attr.depth = ctx->qpc_count;
+	hwq_attr.stride = BNXT_QPLIB_MAX_QP_CTX_ENTRY_SIZE;
+	hwq_attr.type = HWQ_TYPE_CTX;
+	rc = bnxt_qplib_alloc_init_hwq(&ctx->qpc_tbl, &hwq_attr);
+	if (rc)
+		goto fail;
+
+	/* MRW Tables */
+	hwq_attr.depth = ctx->mrw_count;
+	hwq_attr.stride = BNXT_QPLIB_MAX_MRW_CTX_ENTRY_SIZE;
+	rc = bnxt_qplib_alloc_init_hwq(&ctx->mrw_tbl, &hwq_attr);
+	if (rc)
+		goto fail;
+
+	/* SRQ Tables */
+	hwq_attr.depth = ctx->srqc_count;
+	hwq_attr.stride = BNXT_QPLIB_MAX_SRQ_CTX_ENTRY_SIZE;
+	rc = bnxt_qplib_alloc_init_hwq(&ctx->srqc_tbl, &hwq_attr);
+	if (rc)
+		goto fail;
+
+	/* CQ Tables */
+	hwq_attr.depth = ctx->cq_count;
+	hwq_attr.stride = BNXT_QPLIB_MAX_CQ_CTX_ENTRY_SIZE;
+	rc = bnxt_qplib_alloc_init_hwq(&ctx->cq_tbl, &hwq_attr);
+	if (rc)
+		goto fail;
+
+	/* TQM Buffer */
+	rc = bnxt_qplib_setup_tqm_rings(res, ctx);
+	if (rc)
+		goto fail;
+	/* TIM Buffer */
+	ctx->tim_tbl.max_elements = ctx->qpc_count * 16;
+	hwq_attr.depth = ctx->qpc_count * 16;
+	hwq_attr.stride = 1;
+	rc = bnxt_qplib_alloc_init_hwq(&ctx->tim_tbl, &hwq_attr);
+	if (rc)
+		goto fail;
+stats_alloc:
+	/* Stats */
+	rc = bnxt_qplib_alloc_stats_ctx(res->pdev, res->cctx, &ctx->stats);
+	if (rc)
+		goto fail;
+
+	return 0;
+
+fail:
+	bnxt_qplib_free_ctx(res, ctx);
+	return rc;
+}
+
+static void bnxt_qplib_free_sgid_tbl(struct bnxt_qplib_res *res,
+				     struct bnxt_qplib_sgid_tbl *sgid_tbl)
+{
+	kfree(sgid_tbl->tbl);
+	kfree(sgid_tbl->hw_id);
+	kfree(sgid_tbl->ctx);
+	kfree(sgid_tbl->vlan);
+	sgid_tbl->tbl = NULL;
+	sgid_tbl->hw_id = NULL;
+	sgid_tbl->ctx = NULL;
+	sgid_tbl->vlan = NULL;
+	sgid_tbl->max = 0;
+	sgid_tbl->active = 0;
+}
+
+static int bnxt_qplib_alloc_sgid_tbl(struct bnxt_qplib_res *res,
+				     struct bnxt_qplib_sgid_tbl *sgid_tbl,
+				     u16 max)
+{
+	sgid_tbl->tbl = kcalloc(max, sizeof(*sgid_tbl->tbl), GFP_KERNEL);
+	if (!sgid_tbl->tbl)
+		return -ENOMEM;
+
+	sgid_tbl->hw_id = kcalloc(max, sizeof(u16), GFP_KERNEL);
+	if (!sgid_tbl->hw_id)
+		goto out_free1;
+
+	sgid_tbl->ctx = kcalloc(max, sizeof(void *), GFP_KERNEL);
+	if (!sgid_tbl->ctx)
+		goto out_free2;
+
+	sgid_tbl->vlan = kcalloc(max, sizeof(u8), GFP_KERNEL);
+	if (!sgid_tbl->vlan)
+		goto out_free3;
+
+	sgid_tbl->max = max;
+	return 0;
+out_free3:
+	kfree(sgid_tbl->ctx);
+	sgid_tbl->ctx = NULL;
+out_free2:
+	kfree(sgid_tbl->hw_id);
+	sgid_tbl->hw_id = NULL;
+out_free1:
+	kfree(sgid_tbl->tbl);
+	sgid_tbl->tbl = NULL;
+	return -ENOMEM;
+};
+
+static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res,
+					struct bnxt_qplib_sgid_tbl *sgid_tbl)
+{
+	int i;
+
+	for (i = 0; i < sgid_tbl->max; i++) {
+		if (memcmp(&sgid_tbl->tbl[i], &bnxt_qplib_gid_zero,
+			   sizeof(bnxt_qplib_gid_zero)))
+			bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i].gid,
+					    sgid_tbl->tbl[i].vlan_id, true);
+	}
+	memset(sgid_tbl->tbl, 0, sizeof(*sgid_tbl->tbl) * sgid_tbl->max);
+	memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
+	memset(sgid_tbl->vlan, 0, sizeof(u8) * sgid_tbl->max);
+	sgid_tbl->active = 0;
+}
+
+static void bnxt_qplib_init_sgid_tbl(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+				     struct net_device *netdev)
+{
+	u32 i;
+
+	for (i = 0; i < sgid_tbl->max; i++)
+		sgid_tbl->tbl[i].vlan_id = 0xffff;
+
+	memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
+}
+
+/* PDs */
+int bnxt_qplib_alloc_pd(struct bnxt_qplib_pd_tbl *pdt, struct bnxt_qplib_pd *pd)
+{
+	u32 bit_num;
+
+	bit_num = find_first_bit(pdt->tbl, pdt->max);
+	if (bit_num == pdt->max)
+		return -ENOMEM;
+
+	/* Found unused PD */
+	clear_bit(bit_num, pdt->tbl);
+	pd->id = bit_num;
+	return 0;
+}
+
+int bnxt_qplib_dealloc_pd(struct bnxt_qplib_res *res,
+			  struct bnxt_qplib_pd_tbl *pdt,
+			  struct bnxt_qplib_pd *pd)
+{
+	if (test_and_set_bit(pd->id, pdt->tbl)) {
+		dev_warn(&res->pdev->dev, "Freeing an unused PD? pdn = %d\n",
+			 pd->id);
+		return -EINVAL;
+	}
+	pd->id = 0;
+	return 0;
+}
+
+static void bnxt_qplib_free_pd_tbl(struct bnxt_qplib_pd_tbl *pdt)
+{
+	kfree(pdt->tbl);
+	pdt->tbl = NULL;
+	pdt->max = 0;
+}
+
+static int bnxt_qplib_alloc_pd_tbl(struct bnxt_qplib_res *res,
+				   struct bnxt_qplib_pd_tbl *pdt,
+				   u32 max)
+{
+	u32 bytes;
+
+	bytes = max >> 3;
+	if (!bytes)
+		bytes = 1;
+	pdt->tbl = kmalloc(bytes, GFP_KERNEL);
+	if (!pdt->tbl)
+		return -ENOMEM;
+
+	pdt->max = max;
+	memset((u8 *)pdt->tbl, 0xFF, bytes);
+
+	return 0;
+}
+
+/* DPIs */
+int bnxt_qplib_alloc_dpi(struct bnxt_qplib_dpi_tbl *dpit,
+			 struct bnxt_qplib_dpi     *dpi,
+			 void                      *app)
+{
+	u32 bit_num;
+
+	bit_num = find_first_bit(dpit->tbl, dpit->max);
+	if (bit_num == dpit->max)
+		return -ENOMEM;
+
+	/* Found unused DPI */
+	clear_bit(bit_num, dpit->tbl);
+	dpit->app_tbl[bit_num] = app;
+
+	dpi->dpi = bit_num;
+	dpi->dbr = dpit->dbr_bar_reg_iomem + (bit_num * PAGE_SIZE);
+	dpi->umdbr = dpit->unmapped_dbr + (bit_num * PAGE_SIZE);
+
+	return 0;
+}
+
+int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res,
+			   struct bnxt_qplib_dpi_tbl *dpit,
+			   struct bnxt_qplib_dpi     *dpi)
+{
+	if (dpi->dpi >= dpit->max) {
+		dev_warn(&res->pdev->dev, "Invalid DPI? dpi = %d\n", dpi->dpi);
+		return -EINVAL;
+	}
+	if (test_and_set_bit(dpi->dpi, dpit->tbl)) {
+		dev_warn(&res->pdev->dev, "Freeing an unused DPI? dpi = %d\n",
+			 dpi->dpi);
+		return -EINVAL;
+	}
+	if (dpit->app_tbl)
+		dpit->app_tbl[dpi->dpi] = NULL;
+	memset(dpi, 0, sizeof(*dpi));
+
+	return 0;
+}
+
+static void bnxt_qplib_free_dpi_tbl(struct bnxt_qplib_res     *res,
+				    struct bnxt_qplib_dpi_tbl *dpit)
+{
+	kfree(dpit->tbl);
+	kfree(dpit->app_tbl);
+	if (dpit->dbr_bar_reg_iomem)
+		pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
+	memset(dpit, 0, sizeof(*dpit));
+}
+
+static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res     *res,
+				    struct bnxt_qplib_dpi_tbl *dpit,
+				    u32                       dbr_offset)
+{
+	u32 dbr_bar_reg = RCFW_DBR_PCI_BAR_REGION;
+	resource_size_t bar_reg_base;
+	u32 dbr_len, bytes;
+
+	if (dpit->dbr_bar_reg_iomem) {
+		dev_err(&res->pdev->dev, "DBR BAR region %d already mapped\n",
+			dbr_bar_reg);
+		return -EALREADY;
+	}
+
+	bar_reg_base = pci_resource_start(res->pdev, dbr_bar_reg);
+	if (!bar_reg_base) {
+		dev_err(&res->pdev->dev, "BAR region %d resc start failed\n",
+			dbr_bar_reg);
+		return -ENOMEM;
+	}
+
+	dbr_len = pci_resource_len(res->pdev, dbr_bar_reg) - dbr_offset;
+	if (!dbr_len || ((dbr_len & (PAGE_SIZE - 1)) != 0)) {
+		dev_err(&res->pdev->dev, "Invalid DBR length %d\n", dbr_len);
+		return -ENOMEM;
+	}
+
+	dpit->dbr_bar_reg_iomem = ioremap(bar_reg_base + dbr_offset,
+						  dbr_len);
+	if (!dpit->dbr_bar_reg_iomem) {
+		dev_err(&res->pdev->dev,
+			"FP: DBR BAR region %d mapping failed\n", dbr_bar_reg);
+		return -ENOMEM;
+	}
+
+	dpit->unmapped_dbr = bar_reg_base + dbr_offset;
+	dpit->max = dbr_len / PAGE_SIZE;
+
+	dpit->app_tbl = kcalloc(dpit->max, sizeof(void *), GFP_KERNEL);
+	if (!dpit->app_tbl)
+		goto unmap_io;
+
+	bytes = dpit->max >> 3;
+	if (!bytes)
+		bytes = 1;
+
+	dpit->tbl = kmalloc(bytes, GFP_KERNEL);
+	if (!dpit->tbl) {
+		kfree(dpit->app_tbl);
+		dpit->app_tbl = NULL;
+		goto unmap_io;
+	}
+
+	memset((u8 *)dpit->tbl, 0xFF, bytes);
+
+	return 0;
+
+unmap_io:
+	pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
+	dpit->dbr_bar_reg_iomem = NULL;
+	return -ENOMEM;
+}
+
+/* Stats */
+static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev,
+				      struct bnxt_qplib_stats *stats)
+{
+	if (stats->dma) {
+		dma_free_coherent(&pdev->dev, stats->size,
+				  stats->dma, stats->dma_map);
+	}
+	memset(stats, 0, sizeof(*stats));
+	stats->fw_id = -1;
+}
+
+static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+				      struct bnxt_qplib_chip_ctx *cctx,
+				      struct bnxt_qplib_stats *stats)
+{
+	memset(stats, 0, sizeof(*stats));
+	stats->fw_id = -1;
+	stats->size = cctx->hw_stats_size;
+	stats->dma = dma_alloc_coherent(&pdev->dev, stats->size,
+					&stats->dma_map, GFP_KERNEL);
+	if (!stats->dma) {
+		dev_err(&pdev->dev, "Stats DMA allocation failed\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void bnxt_qplib_cleanup_res(struct bnxt_qplib_res *res)
+{
+	bnxt_qplib_cleanup_sgid_tbl(res, &res->sgid_tbl);
+}
+
+int bnxt_qplib_init_res(struct bnxt_qplib_res *res)
+{
+	bnxt_qplib_init_sgid_tbl(&res->sgid_tbl, res->netdev);
+
+	return 0;
+}
+
+void bnxt_qplib_free_res(struct bnxt_qplib_res *res)
+{
+	bnxt_qplib_free_sgid_tbl(res, &res->sgid_tbl);
+	bnxt_qplib_free_pd_tbl(&res->pd_tbl);
+	bnxt_qplib_free_dpi_tbl(res, &res->dpi_tbl);
+}
+
+int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
+			 struct net_device *netdev,
+			 struct bnxt_qplib_dev_attr *dev_attr)
+{
+	int rc = 0;
+
+	res->pdev = pdev;
+	res->netdev = netdev;
+
+	rc = bnxt_qplib_alloc_sgid_tbl(res, &res->sgid_tbl, dev_attr->max_sgid);
+	if (rc)
+		goto fail;
+
+	rc = bnxt_qplib_alloc_pd_tbl(res, &res->pd_tbl, dev_attr->max_pd);
+	if (rc)
+		goto fail;
+
+	rc = bnxt_qplib_alloc_dpi_tbl(res, &res->dpi_tbl, dev_attr->l2_db_size);
+	if (rc)
+		goto fail;
+
+	return 0;
+fail:
+	bnxt_qplib_free_res(res);
+	return rc;
+}
+
+int bnxt_qplib_determine_atomics(struct pci_dev *dev)
+{
+	int comp;
+	u16 ctl2;
+
+	comp = pci_enable_atomic_ops_to_root(dev,
+					     PCI_EXP_DEVCAP2_ATOMIC_COMP32);
+	if (comp)
+		return -EOPNOTSUPP;
+	comp = pci_enable_atomic_ops_to_root(dev,
+					     PCI_EXP_DEVCAP2_ATOMIC_COMP64);
+	if (comp)
+		return -EOPNOTSUPP;
+	pcie_capability_read_word(dev, PCI_EXP_DEVCTL2, &ctl2);
+	return !(ctl2 & PCI_EXP_DEVCTL2_ATOMIC_REQ);
+}
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
new file mode 100644
index 000000000..982e2c96d
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -0,0 +1,452 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: QPLib resource manager (header)
+ */
+
+#ifndef __BNXT_QPLIB_RES_H__
+#define __BNXT_QPLIB_RES_H__
+
+extern const struct bnxt_qplib_gid bnxt_qplib_gid_zero;
+
+#define CHIP_NUM_57508		0x1750
+#define CHIP_NUM_57504		0x1751
+#define CHIP_NUM_57502		0x1752
+
+struct bnxt_qplib_drv_modes {
+	u8	wqe_mode;
+	/* Other modes to follow here */
+};
+
+struct bnxt_qplib_chip_ctx {
+	u16	chip_num;
+	u8	chip_rev;
+	u8	chip_metal;
+	u16	hw_stats_size;
+	struct bnxt_qplib_drv_modes modes;
+};
+
+#define PTR_CNT_PER_PG		(PAGE_SIZE / sizeof(void *))
+#define PTR_MAX_IDX_PER_PG	(PTR_CNT_PER_PG - 1)
+#define PTR_PG(x)		(((x) & ~PTR_MAX_IDX_PER_PG) / PTR_CNT_PER_PG)
+#define PTR_IDX(x)		((x) & PTR_MAX_IDX_PER_PG)
+
+#define HWQ_CMP(idx, hwq)	((idx) & ((hwq)->max_elements - 1))
+
+#define HWQ_FREE_SLOTS(hwq)	(hwq->max_elements - \
+				((HWQ_CMP(hwq->prod, hwq)\
+				- HWQ_CMP(hwq->cons, hwq))\
+				& (hwq->max_elements - 1)))
+enum bnxt_qplib_hwq_type {
+	HWQ_TYPE_CTX,
+	HWQ_TYPE_QUEUE,
+	HWQ_TYPE_L2_CMPL,
+	HWQ_TYPE_MR
+};
+
+#define MAX_PBL_LVL_0_PGS		1
+#define MAX_PBL_LVL_1_PGS		512
+#define MAX_PBL_LVL_1_PGS_SHIFT		9
+#define MAX_PBL_LVL_1_PGS_FOR_LVL_2	256
+#define MAX_PBL_LVL_2_PGS		(256 * 512)
+#define MAX_PDL_LVL_SHIFT               9
+
+enum bnxt_qplib_pbl_lvl {
+	PBL_LVL_0,
+	PBL_LVL_1,
+	PBL_LVL_2,
+	PBL_LVL_MAX
+};
+
+#define ROCE_PG_SIZE_4K		(4 * 1024)
+#define ROCE_PG_SIZE_8K		(8 * 1024)
+#define ROCE_PG_SIZE_64K	(64 * 1024)
+#define ROCE_PG_SIZE_2M		(2 * 1024 * 1024)
+#define ROCE_PG_SIZE_8M		(8 * 1024 * 1024)
+#define ROCE_PG_SIZE_1G		(1024 * 1024 * 1024)
+
+enum bnxt_qplib_hwrm_pg_size {
+	BNXT_QPLIB_HWRM_PG_SIZE_4K	= 0,
+	BNXT_QPLIB_HWRM_PG_SIZE_8K	= 1,
+	BNXT_QPLIB_HWRM_PG_SIZE_64K	= 2,
+	BNXT_QPLIB_HWRM_PG_SIZE_2M	= 3,
+	BNXT_QPLIB_HWRM_PG_SIZE_8M	= 4,
+	BNXT_QPLIB_HWRM_PG_SIZE_1G	= 5,
+};
+
+struct bnxt_qplib_reg_desc {
+	u8		bar_id;
+	resource_size_t	bar_base;
+	void __iomem	*bar_reg;
+	size_t		len;
+};
+
+struct bnxt_qplib_pbl {
+	u32				pg_count;
+	u32				pg_size;
+	void				**pg_arr;
+	dma_addr_t			*pg_map_arr;
+};
+
+struct bnxt_qplib_sg_info {
+	struct ib_umem			*umem;
+	u32				npages;
+	u32				pgshft;
+	u32				pgsize;
+	bool				nopte;
+};
+
+struct bnxt_qplib_hwq_attr {
+	struct bnxt_qplib_res		*res;
+	struct bnxt_qplib_sg_info	*sginfo;
+	enum bnxt_qplib_hwq_type	type;
+	u32				depth;
+	u32				stride;
+	u32				aux_stride;
+	u32				aux_depth;
+};
+
+struct bnxt_qplib_hwq {
+	struct pci_dev			*pdev;
+	/* lock to protect qplib_hwq */
+	spinlock_t			lock;
+	struct bnxt_qplib_pbl		pbl[PBL_LVL_MAX + 1];
+	enum bnxt_qplib_pbl_lvl		level;		/* 0, 1, or 2 */
+	/* ptr for easy access to the PBL entries */
+	void				**pbl_ptr;
+	/* ptr for easy access to the dma_addr */
+	dma_addr_t			*pbl_dma_ptr;
+	u32				max_elements;
+	u32				depth;
+	u16				element_size;	/* Size of each entry */
+	u16				qe_ppg;	/* queue entry per page */
+
+	u32				prod;		/* raw */
+	u32				cons;		/* raw */
+	u8				cp_bit;
+	u8				is_user;
+	u64				*pad_pg;
+	u32				pad_stride;
+	u32				pad_pgofft;
+};
+
+struct bnxt_qplib_db_info {
+	void __iomem		*db;
+	void __iomem		*priv_db;
+	struct bnxt_qplib_hwq	*hwq;
+	u32			xid;
+	u32			max_slot;
+};
+
+/* Tables */
+struct bnxt_qplib_pd_tbl {
+	unsigned long			*tbl;
+	u32				max;
+};
+
+struct bnxt_qplib_sgid_tbl {
+	struct bnxt_qplib_gid_info	*tbl;
+	u16				*hw_id;
+	u16				max;
+	u16				active;
+	void				*ctx;
+	u8				*vlan;
+};
+
+struct bnxt_qplib_dpi {
+	u32				dpi;
+	void __iomem			*dbr;
+	u64				umdbr;
+};
+
+struct bnxt_qplib_dpi_tbl {
+	void				**app_tbl;
+	unsigned long			*tbl;
+	u16				max;
+	void __iomem			*dbr_bar_reg_iomem;
+	u64				unmapped_dbr;
+};
+
+struct bnxt_qplib_stats {
+	dma_addr_t			dma_map;
+	void				*dma;
+	u32				size;
+	u32				fw_id;
+};
+
+struct bnxt_qplib_vf_res {
+	u32 max_qp_per_vf;
+	u32 max_mrw_per_vf;
+	u32 max_srq_per_vf;
+	u32 max_cq_per_vf;
+	u32 max_gid_per_vf;
+};
+
+#define BNXT_QPLIB_MAX_QP_CTX_ENTRY_SIZE	448
+#define BNXT_QPLIB_MAX_SRQ_CTX_ENTRY_SIZE	64
+#define BNXT_QPLIB_MAX_CQ_CTX_ENTRY_SIZE	64
+#define BNXT_QPLIB_MAX_MRW_CTX_ENTRY_SIZE	128
+
+#define MAX_TQM_ALLOC_REQ               48
+#define MAX_TQM_ALLOC_BLK_SIZE          8
+struct bnxt_qplib_tqm_ctx {
+	struct bnxt_qplib_hwq           pde;
+	u8                              pde_level; /* Original level */
+	struct bnxt_qplib_hwq           qtbl[MAX_TQM_ALLOC_REQ];
+	u8                              qcount[MAX_TQM_ALLOC_REQ];
+};
+
+struct bnxt_qplib_ctx {
+	u32				qpc_count;
+	struct bnxt_qplib_hwq		qpc_tbl;
+	u32				mrw_count;
+	struct bnxt_qplib_hwq		mrw_tbl;
+	u32				srqc_count;
+	struct bnxt_qplib_hwq		srqc_tbl;
+	u32				cq_count;
+	struct bnxt_qplib_hwq		cq_tbl;
+	struct bnxt_qplib_hwq		tim_tbl;
+	struct bnxt_qplib_tqm_ctx	tqm_ctx;
+	struct bnxt_qplib_stats		stats;
+	struct bnxt_qplib_vf_res	vf_res;
+	u64				hwrm_intf_ver;
+};
+
+struct bnxt_qplib_res {
+	struct pci_dev			*pdev;
+	struct bnxt_qplib_chip_ctx	*cctx;
+	struct bnxt_qplib_dev_attr      *dattr;
+	struct net_device		*netdev;
+	struct bnxt_qplib_rcfw		*rcfw;
+	struct bnxt_qplib_pd_tbl	pd_tbl;
+	struct bnxt_qplib_sgid_tbl	sgid_tbl;
+	struct bnxt_qplib_dpi_tbl	dpi_tbl;
+	bool				prio;
+	bool                            is_vf;
+};
+
+static inline bool bnxt_qplib_is_chip_gen_p5(struct bnxt_qplib_chip_ctx *cctx)
+{
+	return (cctx->chip_num == CHIP_NUM_57508 ||
+		cctx->chip_num == CHIP_NUM_57504 ||
+		cctx->chip_num == CHIP_NUM_57502);
+}
+
+static inline u8 bnxt_qplib_get_hwq_type(struct bnxt_qplib_res *res)
+{
+	return bnxt_qplib_is_chip_gen_p5(res->cctx) ?
+					HWQ_TYPE_QUEUE : HWQ_TYPE_L2_CMPL;
+}
+
+static inline u8 bnxt_qplib_get_ring_type(struct bnxt_qplib_chip_ctx *cctx)
+{
+	return bnxt_qplib_is_chip_gen_p5(cctx) ?
+	       RING_ALLOC_REQ_RING_TYPE_NQ :
+	       RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL;
+}
+
+static inline u8 bnxt_qplib_base_pg_size(struct bnxt_qplib_hwq *hwq)
+{
+	u8 pg_size = BNXT_QPLIB_HWRM_PG_SIZE_4K;
+	struct bnxt_qplib_pbl *pbl;
+
+	pbl = &hwq->pbl[PBL_LVL_0];
+	switch (pbl->pg_size) {
+	case ROCE_PG_SIZE_4K:
+		pg_size = BNXT_QPLIB_HWRM_PG_SIZE_4K;
+		break;
+	case ROCE_PG_SIZE_8K:
+		pg_size = BNXT_QPLIB_HWRM_PG_SIZE_8K;
+		break;
+	case ROCE_PG_SIZE_64K:
+		pg_size = BNXT_QPLIB_HWRM_PG_SIZE_64K;
+		break;
+	case ROCE_PG_SIZE_2M:
+		pg_size = BNXT_QPLIB_HWRM_PG_SIZE_2M;
+		break;
+	case ROCE_PG_SIZE_8M:
+		pg_size = BNXT_QPLIB_HWRM_PG_SIZE_8M;
+		break;
+	case ROCE_PG_SIZE_1G:
+		pg_size = BNXT_QPLIB_HWRM_PG_SIZE_1G;
+		break;
+	default:
+		break;
+	}
+
+	return pg_size;
+}
+
+static inline void *bnxt_qplib_get_qe(struct bnxt_qplib_hwq *hwq,
+				      u32 indx, u64 *pg)
+{
+	u32 pg_num, pg_idx;
+
+	pg_num = (indx / hwq->qe_ppg);
+	pg_idx = (indx % hwq->qe_ppg);
+	if (pg)
+		*pg = (u64)&hwq->pbl_ptr[pg_num];
+	return (void *)(hwq->pbl_ptr[pg_num] + hwq->element_size * pg_idx);
+}
+
+static inline void *bnxt_qplib_get_prod_qe(struct bnxt_qplib_hwq *hwq, u32 idx)
+{
+	idx += hwq->prod;
+	if (idx >= hwq->depth)
+		idx -= hwq->depth;
+	return bnxt_qplib_get_qe(hwq, idx, NULL);
+}
+
+#define to_bnxt_qplib(ptr, type, member)	\
+	container_of(ptr, type, member)
+
+struct bnxt_qplib_pd;
+struct bnxt_qplib_dev_attr;
+
+void bnxt_qplib_free_hwq(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_hwq *hwq);
+int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq,
+			      struct bnxt_qplib_hwq_attr *hwq_attr);
+int bnxt_qplib_alloc_pd(struct bnxt_qplib_pd_tbl *pd_tbl,
+			struct bnxt_qplib_pd *pd);
+int bnxt_qplib_dealloc_pd(struct bnxt_qplib_res *res,
+			  struct bnxt_qplib_pd_tbl *pd_tbl,
+			  struct bnxt_qplib_pd *pd);
+int bnxt_qplib_alloc_dpi(struct bnxt_qplib_dpi_tbl *dpit,
+			 struct bnxt_qplib_dpi     *dpi,
+			 void                      *app);
+int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res,
+			   struct bnxt_qplib_dpi_tbl *dpi_tbl,
+			   struct bnxt_qplib_dpi *dpi);
+void bnxt_qplib_cleanup_res(struct bnxt_qplib_res *res);
+int bnxt_qplib_init_res(struct bnxt_qplib_res *res);
+void bnxt_qplib_free_res(struct bnxt_qplib_res *res);
+int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
+			 struct net_device *netdev,
+			 struct bnxt_qplib_dev_attr *dev_attr);
+void bnxt_qplib_free_ctx(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_ctx *ctx);
+int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_ctx *ctx,
+			 bool virt_fn, bool is_p5);
+int bnxt_qplib_determine_atomics(struct pci_dev *dev);
+
+static inline void bnxt_qplib_hwq_incr_prod(struct bnxt_qplib_hwq *hwq, u32 cnt)
+{
+	hwq->prod = (hwq->prod + cnt) % hwq->depth;
+}
+
+static inline void bnxt_qplib_hwq_incr_cons(struct bnxt_qplib_hwq *hwq,
+					    u32 cnt)
+{
+	hwq->cons = (hwq->cons + cnt) % hwq->depth;
+}
+
+static inline void bnxt_qplib_ring_db32(struct bnxt_qplib_db_info *info,
+					bool arm)
+{
+	u32 key;
+
+	key = info->hwq->cons & (info->hwq->max_elements - 1);
+	key |= (CMPL_DOORBELL_IDX_VALID |
+		(CMPL_DOORBELL_KEY_CMPL & CMPL_DOORBELL_KEY_MASK));
+	if (!arm)
+		key |= CMPL_DOORBELL_MASK;
+	writel(key, info->db);
+}
+
+static inline void bnxt_qplib_ring_db(struct bnxt_qplib_db_info *info,
+				      u32 type)
+{
+	u64 key = 0;
+
+	key = (info->xid & DBC_DBC_XID_MASK) | DBC_DBC_PATH_ROCE | type;
+	key <<= 32;
+	key |= (info->hwq->cons & (info->hwq->max_elements - 1)) &
+		DBC_DBC_INDEX_MASK;
+	writeq(key, info->db);
+}
+
+static inline void bnxt_qplib_ring_prod_db(struct bnxt_qplib_db_info *info,
+					   u32 type)
+{
+	u64 key = 0;
+
+	key = (info->xid & DBC_DBC_XID_MASK) | DBC_DBC_PATH_ROCE | type;
+	key <<= 32;
+	key |= ((info->hwq->prod / info->max_slot)) & DBC_DBC_INDEX_MASK;
+	writeq(key, info->db);
+}
+
+static inline void bnxt_qplib_armen_db(struct bnxt_qplib_db_info *info,
+				       u32 type)
+{
+	u64 key = 0;
+
+	key = (info->xid & DBC_DBC_XID_MASK) | DBC_DBC_PATH_ROCE | type;
+	key <<= 32;
+	writeq(key, info->priv_db);
+}
+
+static inline void bnxt_qplib_srq_arm_db(struct bnxt_qplib_db_info *info,
+					 u32 th)
+{
+	u64 key = 0;
+
+	key = (info->xid & DBC_DBC_XID_MASK) | DBC_DBC_PATH_ROCE | th;
+	key <<= 32;
+	key |=  th & DBC_DBC_INDEX_MASK;
+	writeq(key, info->priv_db);
+}
+
+static inline void bnxt_qplib_ring_nq_db(struct bnxt_qplib_db_info *info,
+					 struct bnxt_qplib_chip_ctx *cctx,
+					 bool arm)
+{
+	u32 type;
+
+	type = arm ? DBC_DBC_TYPE_NQ_ARM : DBC_DBC_TYPE_NQ;
+	if (bnxt_qplib_is_chip_gen_p5(cctx))
+		bnxt_qplib_ring_db(info, type);
+	else
+		bnxt_qplib_ring_db32(info, arm);
+}
+
+static inline bool _is_ext_stats_supported(u16 dev_cap_flags)
+{
+	return dev_cap_flags &
+		CREQ_QUERY_FUNC_RESP_SB_EXT_STATS;
+}
+#endif /* __BNXT_QPLIB_RES_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
new file mode 100644
index 000000000..bae7d8926
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -0,0 +1,824 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Slow Path Operators
+ */
+
+#define dev_fmt(fmt) "QPLIB: " fmt
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/pci.h>
+
+#include "roce_hsi.h"
+
+#include "qplib_res.h"
+#include "qplib_rcfw.h"
+#include "qplib_sp.h"
+
+const struct bnxt_qplib_gid bnxt_qplib_gid_zero = {{ 0, 0, 0, 0, 0, 0, 0, 0,
+						     0, 0, 0, 0, 0, 0, 0, 0 } };
+
+/* Device */
+
+static bool bnxt_qplib_is_atomic_cap(struct bnxt_qplib_rcfw *rcfw)
+{
+	u16 pcie_ctl2 = 0;
+
+	if (!bnxt_qplib_is_chip_gen_p5(rcfw->res->cctx))
+		return false;
+
+	pcie_capability_read_word(rcfw->pdev, PCI_EXP_DEVCTL2, &pcie_ctl2);
+	return (pcie_ctl2 & PCI_EXP_DEVCTL2_ATOMIC_REQ);
+}
+
+static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw,
+				     char *fw_ver)
+{
+	struct cmdq_query_version req;
+	struct creq_query_version_resp resp;
+	u16 cmd_flags = 0;
+	int rc = 0;
+
+	RCFW_CMD_PREP(req, QUERY_VERSION, cmd_flags);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		return;
+	fw_ver[0] = resp.fw_maj;
+	fw_ver[1] = resp.fw_minor;
+	fw_ver[2] = resp.fw_bld;
+	fw_ver[3] = resp.fw_rsvd;
+}
+
+int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
+			    struct bnxt_qplib_dev_attr *attr, bool vf)
+{
+	struct cmdq_query_func req;
+	struct creq_query_func_resp resp;
+	struct bnxt_qplib_rcfw_sbuf *sbuf;
+	struct creq_query_func_resp_sb *sb;
+	u16 cmd_flags = 0;
+	u32 temp;
+	u8 *tqm_alloc;
+	int i, rc = 0;
+
+	RCFW_CMD_PREP(req, QUERY_FUNC, cmd_flags);
+
+	sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb));
+	if (!sbuf) {
+		dev_err(&rcfw->pdev->dev,
+			"SP: QUERY_FUNC alloc side buffer failed\n");
+		return -ENOMEM;
+	}
+
+	sb = sbuf->sb;
+	req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS;
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  (void *)sbuf, 0);
+	if (rc)
+		goto bail;
+
+	/* Extract the context from the side buffer */
+	attr->max_qp = le32_to_cpu(sb->max_qp);
+	/* max_qp value reported by FW for PF doesn't include the QP1 for PF */
+	if (!vf)
+		attr->max_qp += 1;
+	attr->max_qp_rd_atom =
+		sb->max_qp_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ?
+		BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_rd_atom;
+	attr->max_qp_init_rd_atom =
+		sb->max_qp_init_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ?
+		BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_init_rd_atom;
+	attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr);
+	/*
+	 * 128 WQEs needs to be reserved for the HW (8916). Prevent
+	 * reporting the max number
+	 */
+	attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1;
+	attr->max_qp_sges = bnxt_qplib_is_chip_gen_p5(rcfw->res->cctx) ?
+			    6 : sb->max_sge;
+	attr->max_cq = le32_to_cpu(sb->max_cq);
+	attr->max_cq_wqes = le32_to_cpu(sb->max_cqe);
+	attr->max_cq_sges = attr->max_qp_sges;
+	attr->max_mr = le32_to_cpu(sb->max_mr);
+	attr->max_mw = le32_to_cpu(sb->max_mw);
+
+	attr->max_mr_size = le64_to_cpu(sb->max_mr_size);
+	attr->max_pd = 64 * 1024;
+	attr->max_raw_ethy_qp = le32_to_cpu(sb->max_raw_eth_qp);
+	attr->max_ah = le32_to_cpu(sb->max_ah);
+
+	attr->max_srq = le16_to_cpu(sb->max_srq);
+	attr->max_srq_wqes = le32_to_cpu(sb->max_srq_wr) - 1;
+	attr->max_srq_sges = sb->max_srq_sge;
+	attr->max_pkey = 1;
+	attr->max_inline_data = le32_to_cpu(sb->max_inline_data);
+	attr->l2_db_size = (sb->l2_db_space_size + 1) *
+			    (0x01 << RCFW_DBR_BASE_PAGE_SHIFT);
+	attr->max_sgid = BNXT_QPLIB_NUM_GIDS_SUPPORTED;
+	attr->dev_cap_flags = le16_to_cpu(sb->dev_cap_flags);
+
+	bnxt_qplib_query_version(rcfw, attr->fw_ver);
+
+	for (i = 0; i < MAX_TQM_ALLOC_REQ / 4; i++) {
+		temp = le32_to_cpu(sb->tqm_alloc_reqs[i]);
+		tqm_alloc = (u8 *)&temp;
+		attr->tqm_alloc_reqs[i * 4] = *tqm_alloc;
+		attr->tqm_alloc_reqs[i * 4 + 1] = *(++tqm_alloc);
+		attr->tqm_alloc_reqs[i * 4 + 2] = *(++tqm_alloc);
+		attr->tqm_alloc_reqs[i * 4 + 3] = *(++tqm_alloc);
+	}
+
+	attr->is_atomic = bnxt_qplib_is_atomic_cap(rcfw);
+bail:
+	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
+	return rc;
+}
+
+int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res,
+				  struct bnxt_qplib_rcfw *rcfw,
+				  struct bnxt_qplib_ctx *ctx)
+{
+	struct cmdq_set_func_resources req;
+	struct creq_set_func_resources_resp resp;
+	u16 cmd_flags = 0;
+	int rc = 0;
+
+	RCFW_CMD_PREP(req, SET_FUNC_RESOURCES, cmd_flags);
+
+	req.number_of_qp = cpu_to_le32(ctx->qpc_count);
+	req.number_of_mrw = cpu_to_le32(ctx->mrw_count);
+	req.number_of_srq =  cpu_to_le32(ctx->srqc_count);
+	req.number_of_cq = cpu_to_le32(ctx->cq_count);
+
+	req.max_qp_per_vf = cpu_to_le32(ctx->vf_res.max_qp_per_vf);
+	req.max_mrw_per_vf = cpu_to_le32(ctx->vf_res.max_mrw_per_vf);
+	req.max_srq_per_vf = cpu_to_le32(ctx->vf_res.max_srq_per_vf);
+	req.max_cq_per_vf = cpu_to_le32(ctx->vf_res.max_cq_per_vf);
+	req.max_gid_per_vf = cpu_to_le32(ctx->vf_res.max_gid_per_vf);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp,
+					  NULL, 0);
+	if (rc) {
+		dev_err(&res->pdev->dev, "Failed to set function resources\n");
+	}
+	return rc;
+}
+
+/* SGID */
+int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_sgid_tbl *sgid_tbl, int index,
+			struct bnxt_qplib_gid *gid)
+{
+	if (index >= sgid_tbl->max) {
+		dev_err(&res->pdev->dev,
+			"Index %d exceeded SGID table max (%d)\n",
+			index, sgid_tbl->max);
+		return -EINVAL;
+	}
+	memcpy(gid, &sgid_tbl->tbl[index].gid, sizeof(*gid));
+	return 0;
+}
+
+int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			struct bnxt_qplib_gid *gid, u16 vlan_id, bool update)
+{
+	struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl,
+						   struct bnxt_qplib_res,
+						   sgid_tbl);
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	int index;
+
+	if (!sgid_tbl) {
+		dev_err(&res->pdev->dev, "SGID table not allocated\n");
+		return -EINVAL;
+	}
+	/* Do we need a sgid_lock here? */
+	if (!sgid_tbl->active) {
+		dev_err(&res->pdev->dev, "SGID table has no active entries\n");
+		return -ENOMEM;
+	}
+	for (index = 0; index < sgid_tbl->max; index++) {
+		if (!memcmp(&sgid_tbl->tbl[index].gid, gid, sizeof(*gid)) &&
+		    vlan_id == sgid_tbl->tbl[index].vlan_id)
+			break;
+	}
+	if (index == sgid_tbl->max) {
+		dev_warn(&res->pdev->dev, "GID not found in the SGID table\n");
+		return 0;
+	}
+	/* Remove GID from the SGID table */
+	if (update) {
+		struct cmdq_delete_gid req;
+		struct creq_delete_gid_resp resp;
+		u16 cmd_flags = 0;
+		int rc;
+
+		RCFW_CMD_PREP(req, DELETE_GID, cmd_flags);
+		if (sgid_tbl->hw_id[index] == 0xFFFF) {
+			dev_err(&res->pdev->dev,
+				"GID entry contains an invalid HW id\n");
+			return -EINVAL;
+		}
+		req.gid_index = cpu_to_le16(sgid_tbl->hw_id[index]);
+		rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						  (void *)&resp, NULL, 0);
+		if (rc)
+			return rc;
+	}
+	memcpy(&sgid_tbl->tbl[index].gid, &bnxt_qplib_gid_zero,
+	       sizeof(bnxt_qplib_gid_zero));
+	sgid_tbl->tbl[index].vlan_id = 0xFFFF;
+	sgid_tbl->vlan[index] = 0;
+	sgid_tbl->active--;
+	dev_dbg(&res->pdev->dev,
+		"SGID deleted hw_id[0x%x] = 0x%x active = 0x%x\n",
+		 index, sgid_tbl->hw_id[index], sgid_tbl->active);
+	sgid_tbl->hw_id[index] = (u16)-1;
+
+	/* unlock */
+	return 0;
+}
+
+int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			struct bnxt_qplib_gid *gid, const u8 *smac,
+			u16 vlan_id, bool update, u32 *index)
+{
+	struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl,
+						   struct bnxt_qplib_res,
+						   sgid_tbl);
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	int i, free_idx;
+
+	if (!sgid_tbl) {
+		dev_err(&res->pdev->dev, "SGID table not allocated\n");
+		return -EINVAL;
+	}
+	/* Do we need a sgid_lock here? */
+	if (sgid_tbl->active == sgid_tbl->max) {
+		dev_err(&res->pdev->dev, "SGID table is full\n");
+		return -ENOMEM;
+	}
+	free_idx = sgid_tbl->max;
+	for (i = 0; i < sgid_tbl->max; i++) {
+		if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid)) &&
+		    sgid_tbl->tbl[i].vlan_id == vlan_id) {
+			dev_dbg(&res->pdev->dev,
+				"SGID entry already exist in entry %d!\n", i);
+			*index = i;
+			return -EALREADY;
+		} else if (!memcmp(&sgid_tbl->tbl[i], &bnxt_qplib_gid_zero,
+				   sizeof(bnxt_qplib_gid_zero)) &&
+			   free_idx == sgid_tbl->max) {
+			free_idx = i;
+		}
+	}
+	if (free_idx == sgid_tbl->max) {
+		dev_err(&res->pdev->dev,
+			"SGID table is FULL but count is not MAX??\n");
+		return -ENOMEM;
+	}
+	if (update) {
+		struct cmdq_add_gid req;
+		struct creq_add_gid_resp resp;
+		u16 cmd_flags = 0;
+		int rc;
+
+		RCFW_CMD_PREP(req, ADD_GID, cmd_flags);
+
+		req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]);
+		req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]);
+		req.gid[2] = cpu_to_be32(((u32 *)gid->data)[1]);
+		req.gid[3] = cpu_to_be32(((u32 *)gid->data)[0]);
+		/*
+		 * driver should ensure that all RoCE traffic is always VLAN
+		 * tagged if RoCE traffic is running on non-zero VLAN ID or
+		 * RoCE traffic is running on non-zero Priority.
+		 */
+		if ((vlan_id != 0xFFFF) || res->prio) {
+			if (vlan_id != 0xFFFF)
+				req.vlan = cpu_to_le16
+				(vlan_id & CMDQ_ADD_GID_VLAN_VLAN_ID_MASK);
+			req.vlan |= cpu_to_le16
+					(CMDQ_ADD_GID_VLAN_TPID_TPID_8100 |
+					 CMDQ_ADD_GID_VLAN_VLAN_EN);
+		}
+
+		/* MAC in network format */
+		req.src_mac[0] = cpu_to_be16(((u16 *)smac)[0]);
+		req.src_mac[1] = cpu_to_be16(((u16 *)smac)[1]);
+		req.src_mac[2] = cpu_to_be16(((u16 *)smac)[2]);
+
+		rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						  (void *)&resp, NULL, 0);
+		if (rc)
+			return rc;
+		sgid_tbl->hw_id[free_idx] = le32_to_cpu(resp.xid);
+	}
+	/* Add GID to the sgid_tbl */
+	memcpy(&sgid_tbl->tbl[free_idx], gid, sizeof(*gid));
+	sgid_tbl->tbl[free_idx].vlan_id = vlan_id;
+	sgid_tbl->active++;
+	if (vlan_id != 0xFFFF)
+		sgid_tbl->vlan[free_idx] = 1;
+
+	dev_dbg(&res->pdev->dev,
+		"SGID added hw_id[0x%x] = 0x%x active = 0x%x\n",
+		 free_idx, sgid_tbl->hw_id[free_idx], sgid_tbl->active);
+
+	*index = free_idx;
+	/* unlock */
+	return 0;
+}
+
+int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			   struct bnxt_qplib_gid *gid, u16 gid_idx,
+			   const u8 *smac)
+{
+	struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl,
+						   struct bnxt_qplib_res,
+						   sgid_tbl);
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct creq_modify_gid_resp resp;
+	struct cmdq_modify_gid req;
+	int rc;
+	u16 cmd_flags = 0;
+
+	RCFW_CMD_PREP(req, MODIFY_GID, cmd_flags);
+
+	req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]);
+	req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]);
+	req.gid[2] = cpu_to_be32(((u32 *)gid->data)[1]);
+	req.gid[3] = cpu_to_be32(((u32 *)gid->data)[0]);
+	if (res->prio) {
+		req.vlan |= cpu_to_le16
+			(CMDQ_ADD_GID_VLAN_TPID_TPID_8100 |
+			 CMDQ_ADD_GID_VLAN_VLAN_EN);
+	}
+
+	/* MAC in network format */
+	req.src_mac[0] = cpu_to_be16(((u16 *)smac)[0]);
+	req.src_mac[1] = cpu_to_be16(((u16 *)smac)[1]);
+	req.src_mac[2] = cpu_to_be16(((u16 *)smac)[2]);
+
+	req.gid_index = cpu_to_le16(gid_idx);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	return rc;
+}
+
+/* AH */
+int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah,
+			 bool block)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_create_ah req;
+	struct creq_create_ah_resp resp;
+	u16 cmd_flags = 0;
+	u32 temp32[4];
+	u16 temp16[3];
+	int rc;
+
+	RCFW_CMD_PREP(req, CREATE_AH, cmd_flags);
+
+	memcpy(temp32, ah->dgid.data, sizeof(struct bnxt_qplib_gid));
+	req.dgid[0] = cpu_to_le32(temp32[0]);
+	req.dgid[1] = cpu_to_le32(temp32[1]);
+	req.dgid[2] = cpu_to_le32(temp32[2]);
+	req.dgid[3] = cpu_to_le32(temp32[3]);
+
+	req.type = ah->nw_type;
+	req.hop_limit = ah->hop_limit;
+	req.sgid_index = cpu_to_le16(res->sgid_tbl.hw_id[ah->sgid_index]);
+	req.dest_vlan_id_flow_label = cpu_to_le32((ah->flow_label &
+					CMDQ_CREATE_AH_FLOW_LABEL_MASK) |
+					CMDQ_CREATE_AH_DEST_VLAN_ID_MASK);
+	req.pd_id = cpu_to_le32(ah->pd->id);
+	req.traffic_class = ah->traffic_class;
+
+	/* MAC in network format */
+	memcpy(temp16, ah->dmac, 6);
+	req.dest_mac[0] = cpu_to_le16(temp16[0]);
+	req.dest_mac[1] = cpu_to_le16(temp16[1]);
+	req.dest_mac[2] = cpu_to_le16(temp16[2]);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  NULL, block);
+	if (rc)
+		return rc;
+
+	ah->id = le32_to_cpu(resp.xid);
+	return 0;
+}
+
+void bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah,
+			   bool block)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_destroy_ah req;
+	struct creq_destroy_ah_resp resp;
+	u16 cmd_flags = 0;
+
+	/* Clean up the AH table in the device */
+	RCFW_CMD_PREP(req, DESTROY_AH, cmd_flags);
+
+	req.ah_cid = cpu_to_le32(ah->id);
+
+	bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL,
+				     block);
+}
+
+/* MRW */
+int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_deallocate_key req;
+	struct creq_deallocate_key_resp resp;
+	u16 cmd_flags = 0;
+	int rc;
+
+	if (mrw->lkey == 0xFFFFFFFF) {
+		dev_info(&res->pdev->dev, "SP: Free a reserved lkey MRW\n");
+		return 0;
+	}
+
+	RCFW_CMD_PREP(req, DEALLOCATE_KEY, cmd_flags);
+
+	req.mrw_flags = mrw->type;
+
+	if ((mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE1)  ||
+	    (mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2A) ||
+	    (mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B))
+		req.key = cpu_to_le32(mrw->rkey);
+	else
+		req.key = cpu_to_le32(mrw->lkey);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  NULL, 0);
+	if (rc)
+		return rc;
+
+	/* Free the qplib's MRW memory */
+	if (mrw->hwq.max_elements)
+		bnxt_qplib_free_hwq(res, &mrw->hwq);
+
+	return 0;
+}
+
+int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_allocate_mrw req;
+	struct creq_allocate_mrw_resp resp;
+	u16 cmd_flags = 0;
+	unsigned long tmp;
+	int rc;
+
+	RCFW_CMD_PREP(req, ALLOCATE_MRW, cmd_flags);
+
+	req.pd_id = cpu_to_le32(mrw->pd->id);
+	req.mrw_flags = mrw->type;
+	if ((mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR &&
+	     mrw->flags & BNXT_QPLIB_FR_PMR) ||
+	    mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2A ||
+	    mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B)
+		req.access = CMDQ_ALLOCATE_MRW_ACCESS_CONSUMER_OWNED_KEY;
+	tmp = (unsigned long)mrw;
+	req.mrw_handle = cpu_to_le64(tmp);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	if (rc)
+		return rc;
+
+	if ((mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE1)  ||
+	    (mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2A) ||
+	    (mrw->type == CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B))
+		mrw->rkey = le32_to_cpu(resp.xid);
+	else
+		mrw->lkey = le32_to_cpu(resp.xid);
+	return 0;
+}
+
+int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw,
+			 bool block)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_deregister_mr req;
+	struct creq_deregister_mr_resp resp;
+	u16 cmd_flags = 0;
+	int rc;
+
+	RCFW_CMD_PREP(req, DEREGISTER_MR, cmd_flags);
+
+	req.lkey = cpu_to_le32(mrw->lkey);
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, block);
+	if (rc)
+		return rc;
+
+	/* Free the qplib's MR memory */
+	if (mrw->hwq.max_elements) {
+		mrw->va = 0;
+		mrw->total_size = 0;
+		bnxt_qplib_free_hwq(res, &mrw->hwq);
+	}
+
+	return 0;
+}
+
+int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr,
+		      struct ib_umem *umem, int num_pbls, u32 buf_pg_size)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_sg_info sginfo = {};
+	struct creq_register_mr_resp resp;
+	struct cmdq_register_mr req;
+	u16 cmd_flags = 0, level;
+	int pages, rc;
+	u32 pg_size;
+
+	if (num_pbls) {
+		pages = roundup_pow_of_two(num_pbls);
+		/* Allocate memory for the non-leaf pages to store buf ptrs.
+		 * Non-leaf pages always uses system PAGE_SIZE
+		 */
+		/* Free the hwq if it already exist, must be a rereg */
+		if (mr->hwq.max_elements)
+			bnxt_qplib_free_hwq(res, &mr->hwq);
+		hwq_attr.res = res;
+		hwq_attr.depth = pages;
+		hwq_attr.stride = sizeof(dma_addr_t);
+		hwq_attr.type = HWQ_TYPE_MR;
+		hwq_attr.sginfo = &sginfo;
+		hwq_attr.sginfo->umem = umem;
+		hwq_attr.sginfo->npages = pages;
+		hwq_attr.sginfo->pgsize = buf_pg_size;
+		hwq_attr.sginfo->pgshft = ilog2(buf_pg_size);
+		rc = bnxt_qplib_alloc_init_hwq(&mr->hwq, &hwq_attr);
+		if (rc) {
+			dev_err(&res->pdev->dev,
+				"SP: Reg MR memory allocation failed\n");
+			return -ENOMEM;
+		}
+	}
+
+	RCFW_CMD_PREP(req, REGISTER_MR, cmd_flags);
+
+	/* Configure the request */
+	if (mr->hwq.level == PBL_LVL_MAX) {
+		/* No PBL provided, just use system PAGE_SIZE */
+		level = 0;
+		req.pbl = 0;
+		pg_size = PAGE_SIZE;
+	} else {
+		level = mr->hwq.level;
+		req.pbl = cpu_to_le64(mr->hwq.pbl[PBL_LVL_0].pg_map_arr[0]);
+	}
+	pg_size = buf_pg_size ? buf_pg_size : PAGE_SIZE;
+	req.log2_pg_size_lvl = (level << CMDQ_REGISTER_MR_LVL_SFT) |
+			       ((ilog2(pg_size) <<
+				 CMDQ_REGISTER_MR_LOG2_PG_SIZE_SFT) &
+				CMDQ_REGISTER_MR_LOG2_PG_SIZE_MASK);
+	req.log2_pbl_pg_size = cpu_to_le16(((ilog2(PAGE_SIZE) <<
+				 CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_SFT) &
+				CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_MASK));
+	req.access = (mr->flags & 0xFFFF);
+	req.va = cpu_to_le64(mr->va);
+	req.key = cpu_to_le32(mr->lkey);
+	req.mr_size = cpu_to_le64(mr->total_size);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, false);
+	if (rc)
+		goto fail;
+
+	return 0;
+
+fail:
+	if (mr->hwq.max_elements)
+		bnxt_qplib_free_hwq(res, &mr->hwq);
+	return rc;
+}
+
+int bnxt_qplib_alloc_fast_reg_page_list(struct bnxt_qplib_res *res,
+					struct bnxt_qplib_frpl *frpl,
+					int max_pg_ptrs)
+{
+	struct bnxt_qplib_hwq_attr hwq_attr = {};
+	struct bnxt_qplib_sg_info sginfo = {};
+	int pg_ptrs, pages, rc;
+
+	/* Re-calculate the max to fit the HWQ allocation model */
+	pg_ptrs = roundup_pow_of_two(max_pg_ptrs);
+	pages = pg_ptrs >> MAX_PBL_LVL_1_PGS_SHIFT;
+	if (!pages)
+		pages++;
+
+	if (pages > MAX_PBL_LVL_1_PGS)
+		return -ENOMEM;
+
+	sginfo.pgsize = PAGE_SIZE;
+	sginfo.nopte = true;
+
+	hwq_attr.res = res;
+	hwq_attr.depth = pg_ptrs;
+	hwq_attr.stride = PAGE_SIZE;
+	hwq_attr.sginfo = &sginfo;
+	hwq_attr.type = HWQ_TYPE_CTX;
+	rc = bnxt_qplib_alloc_init_hwq(&frpl->hwq, &hwq_attr);
+	if (!rc)
+		frpl->max_pg_ptrs = pg_ptrs;
+
+	return rc;
+}
+
+int bnxt_qplib_free_fast_reg_page_list(struct bnxt_qplib_res *res,
+				       struct bnxt_qplib_frpl *frpl)
+{
+	bnxt_qplib_free_hwq(res, &frpl->hwq);
+	return 0;
+}
+
+int bnxt_qplib_map_tc2cos(struct bnxt_qplib_res *res, u16 *cids)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_map_tc_to_cos req;
+	struct creq_map_tc_to_cos_resp resp;
+	u16 cmd_flags = 0;
+
+	RCFW_CMD_PREP(req, MAP_TC_TO_COS, cmd_flags);
+	req.cos0 = cpu_to_le16(cids[0]);
+	req.cos1 = cpu_to_le16(cids[1]);
+
+	return bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+						NULL, 0);
+}
+
+int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw,
+			      struct bnxt_qplib_roce_stats *stats)
+{
+	struct cmdq_query_roce_stats req;
+	struct creq_query_roce_stats_resp resp;
+	struct bnxt_qplib_rcfw_sbuf *sbuf;
+	struct creq_query_roce_stats_resp_sb *sb;
+	u16 cmd_flags = 0;
+	int rc = 0;
+
+	RCFW_CMD_PREP(req, QUERY_ROCE_STATS, cmd_flags);
+
+	sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb));
+	if (!sbuf) {
+		dev_err(&rcfw->pdev->dev,
+			"SP: QUERY_ROCE_STATS alloc side buffer failed\n");
+		return -ENOMEM;
+	}
+
+	sb = sbuf->sb;
+	req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS;
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp,
+					  (void *)sbuf, 0);
+	if (rc)
+		goto bail;
+	/* Extract the context from the side buffer */
+	stats->to_retransmits = le64_to_cpu(sb->to_retransmits);
+	stats->seq_err_naks_rcvd = le64_to_cpu(sb->seq_err_naks_rcvd);
+	stats->max_retry_exceeded = le64_to_cpu(sb->max_retry_exceeded);
+	stats->rnr_naks_rcvd = le64_to_cpu(sb->rnr_naks_rcvd);
+	stats->missing_resp = le64_to_cpu(sb->missing_resp);
+	stats->unrecoverable_err = le64_to_cpu(sb->unrecoverable_err);
+	stats->bad_resp_err = le64_to_cpu(sb->bad_resp_err);
+	stats->local_qp_op_err = le64_to_cpu(sb->local_qp_op_err);
+	stats->local_protection_err = le64_to_cpu(sb->local_protection_err);
+	stats->mem_mgmt_op_err = le64_to_cpu(sb->mem_mgmt_op_err);
+	stats->remote_invalid_req_err = le64_to_cpu(sb->remote_invalid_req_err);
+	stats->remote_access_err = le64_to_cpu(sb->remote_access_err);
+	stats->remote_op_err = le64_to_cpu(sb->remote_op_err);
+	stats->dup_req = le64_to_cpu(sb->dup_req);
+	stats->res_exceed_max = le64_to_cpu(sb->res_exceed_max);
+	stats->res_length_mismatch = le64_to_cpu(sb->res_length_mismatch);
+	stats->res_exceeds_wqe = le64_to_cpu(sb->res_exceeds_wqe);
+	stats->res_opcode_err = le64_to_cpu(sb->res_opcode_err);
+	stats->res_rx_invalid_rkey = le64_to_cpu(sb->res_rx_invalid_rkey);
+	stats->res_rx_domain_err = le64_to_cpu(sb->res_rx_domain_err);
+	stats->res_rx_no_perm = le64_to_cpu(sb->res_rx_no_perm);
+	stats->res_rx_range_err = le64_to_cpu(sb->res_rx_range_err);
+	stats->res_tx_invalid_rkey = le64_to_cpu(sb->res_tx_invalid_rkey);
+	stats->res_tx_domain_err = le64_to_cpu(sb->res_tx_domain_err);
+	stats->res_tx_no_perm = le64_to_cpu(sb->res_tx_no_perm);
+	stats->res_tx_range_err = le64_to_cpu(sb->res_tx_range_err);
+	stats->res_irrq_oflow = le64_to_cpu(sb->res_irrq_oflow);
+	stats->res_unsup_opcode = le64_to_cpu(sb->res_unsup_opcode);
+	stats->res_unaligned_atomic = le64_to_cpu(sb->res_unaligned_atomic);
+	stats->res_rem_inv_err = le64_to_cpu(sb->res_rem_inv_err);
+	stats->res_mem_error = le64_to_cpu(sb->res_mem_error);
+	stats->res_srq_err = le64_to_cpu(sb->res_srq_err);
+	stats->res_cmp_err = le64_to_cpu(sb->res_cmp_err);
+	stats->res_invalid_dup_rkey = le64_to_cpu(sb->res_invalid_dup_rkey);
+	stats->res_wqe_format_err = le64_to_cpu(sb->res_wqe_format_err);
+	stats->res_cq_load_err = le64_to_cpu(sb->res_cq_load_err);
+	stats->res_srq_load_err = le64_to_cpu(sb->res_srq_load_err);
+	stats->res_tx_pci_err = le64_to_cpu(sb->res_tx_pci_err);
+	stats->res_rx_pci_err = le64_to_cpu(sb->res_rx_pci_err);
+	if (!rcfw->init_oos_stats) {
+		rcfw->oos_prev = le64_to_cpu(sb->res_oos_drop_count);
+		rcfw->init_oos_stats = 1;
+	} else {
+		stats->res_oos_drop_count +=
+				(le64_to_cpu(sb->res_oos_drop_count) -
+				 rcfw->oos_prev) & BNXT_QPLIB_OOS_COUNT_MASK;
+		rcfw->oos_prev = le64_to_cpu(sb->res_oos_drop_count);
+	}
+
+bail:
+	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
+	return rc;
+}
+
+int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid,
+			 struct bnxt_qplib_ext_stat *estat)
+{
+	struct creq_query_roce_stats_ext_resp resp = {};
+	struct creq_query_roce_stats_ext_resp_sb *sb;
+	struct cmdq_query_roce_stats_ext req = {};
+	struct bnxt_qplib_rcfw_sbuf *sbuf;
+	u16 cmd_flags = 0;
+	int rc;
+
+	sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb));
+	if (!sbuf) {
+		dev_err(&rcfw->pdev->dev,
+			"SP: QUERY_ROCE_STATS_EXT alloc sb failed");
+		return -ENOMEM;
+	}
+
+	RCFW_CMD_PREP(req, QUERY_ROCE_STATS_EXT, cmd_flags);
+
+	req.resp_size = ALIGN(sizeof(*sb), BNXT_QPLIB_CMDQE_UNITS);
+	req.resp_addr = cpu_to_le64(sbuf->dma_addr);
+	req.function_id = cpu_to_le32(fid);
+	req.flags = cpu_to_le16(CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_FUNCTION_ID);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, (void *)sbuf, 0);
+	if (rc)
+		goto bail;
+
+	sb = sbuf->sb;
+	estat->tx_atomic_req = le64_to_cpu(sb->tx_atomic_req_pkts);
+	estat->tx_read_req = le64_to_cpu(sb->tx_read_req_pkts);
+	estat->tx_read_res = le64_to_cpu(sb->tx_read_res_pkts);
+	estat->tx_write_req = le64_to_cpu(sb->tx_write_req_pkts);
+	estat->tx_send_req = le64_to_cpu(sb->tx_send_req_pkts);
+	estat->rx_atomic_req = le64_to_cpu(sb->rx_atomic_req_pkts);
+	estat->rx_read_req = le64_to_cpu(sb->rx_read_req_pkts);
+	estat->rx_read_res = le64_to_cpu(sb->rx_read_res_pkts);
+	estat->rx_write_req = le64_to_cpu(sb->rx_write_req_pkts);
+	estat->rx_send_req = le64_to_cpu(sb->rx_send_req_pkts);
+	estat->rx_roce_good_pkts = le64_to_cpu(sb->rx_roce_good_pkts);
+	estat->rx_roce_good_bytes = le64_to_cpu(sb->rx_roce_good_bytes);
+	estat->rx_out_of_buffer = le64_to_cpu(sb->rx_out_of_buffer_pkts);
+	estat->rx_out_of_sequence = le64_to_cpu(sb->rx_out_of_sequence_pkts);
+
+bail:
+	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
+	return rc;
+}
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
new file mode 100644
index 000000000..5939e8fc8
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -0,0 +1,286 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: Slow Path Operators (header)
+ *
+ */
+
+#ifndef __BNXT_QPLIB_SP_H__
+#define __BNXT_QPLIB_SP_H__
+
+#define BNXT_QPLIB_RESERVED_QP_WRS	128
+
+struct bnxt_qplib_dev_attr {
+#define FW_VER_ARR_LEN			4
+	u8				fw_ver[FW_VER_ARR_LEN];
+#define BNXT_QPLIB_NUM_GIDS_SUPPORTED	256
+	u16				max_sgid;
+	u16				max_mrw;
+	u32				max_qp;
+#define BNXT_QPLIB_MAX_OUT_RD_ATOM	126
+	u32				max_qp_rd_atom;
+	u32				max_qp_init_rd_atom;
+	u32				max_qp_wqes;
+	u32				max_qp_sges;
+	u32				max_cq;
+	u32				max_cq_wqes;
+	u32				max_cq_sges;
+	u32				max_mr;
+	u64				max_mr_size;
+	u32				max_pd;
+	u32				max_mw;
+	u32				max_raw_ethy_qp;
+	u32				max_ah;
+	u32				max_srq;
+	u32				max_srq_wqes;
+	u32				max_srq_sges;
+	u32				max_pkey;
+	u32				max_inline_data;
+	u32				l2_db_size;
+	u8				tqm_alloc_reqs[MAX_TQM_ALLOC_REQ];
+	bool				is_atomic;
+	u16                             dev_cap_flags;
+};
+
+struct bnxt_qplib_pd {
+	u32				id;
+};
+
+struct bnxt_qplib_gid {
+	u8				data[16];
+};
+
+struct bnxt_qplib_gid_info {
+	struct bnxt_qplib_gid gid;
+	u16 vlan_id;
+};
+
+struct bnxt_qplib_ah {
+	struct bnxt_qplib_gid		dgid;
+	struct bnxt_qplib_pd		*pd;
+	u32				id;
+	u8				sgid_index;
+	/* For Query AH if the hw table and SW table are differnt */
+	u8				host_sgid_index;
+	u8				traffic_class;
+	u32				flow_label;
+	u8				hop_limit;
+	u8				sl;
+	u8				dmac[6];
+	u16				vlan_id;
+	u8				nw_type;
+};
+
+struct bnxt_qplib_mrw {
+	struct bnxt_qplib_pd		*pd;
+	int				type;
+	u32				flags;
+#define BNXT_QPLIB_FR_PMR		0x80000000
+	u32				lkey;
+	u32				rkey;
+#define BNXT_QPLIB_RSVD_LKEY		0xFFFFFFFF
+	u64				va;
+	u64				total_size;
+	u32				npages;
+	u64				mr_handle;
+	struct bnxt_qplib_hwq		hwq;
+};
+
+struct bnxt_qplib_frpl {
+	int				max_pg_ptrs;
+	struct bnxt_qplib_hwq		hwq;
+};
+
+#define BNXT_QPLIB_ACCESS_LOCAL_WRITE	BIT(0)
+#define BNXT_QPLIB_ACCESS_REMOTE_READ	BIT(1)
+#define BNXT_QPLIB_ACCESS_REMOTE_WRITE	BIT(2)
+#define BNXT_QPLIB_ACCESS_REMOTE_ATOMIC	BIT(3)
+#define BNXT_QPLIB_ACCESS_MW_BIND	BIT(4)
+#define BNXT_QPLIB_ACCESS_ZERO_BASED	BIT(5)
+#define BNXT_QPLIB_ACCESS_ON_DEMAND	BIT(6)
+
+struct bnxt_qplib_roce_stats {
+	u64 to_retransmits;
+	u64 seq_err_naks_rcvd;
+	/* seq_err_naks_rcvd is 64 b */
+	u64 max_retry_exceeded;
+	/* max_retry_exceeded is 64 b */
+	u64 rnr_naks_rcvd;
+	/* rnr_naks_rcvd is 64 b */
+	u64 missing_resp;
+	u64 unrecoverable_err;
+	/* unrecoverable_err is 64 b */
+	u64 bad_resp_err;
+	/* bad_resp_err is 64 b */
+	u64 local_qp_op_err;
+	/* local_qp_op_err is 64 b */
+	u64 local_protection_err;
+	/* local_protection_err is 64 b */
+	u64 mem_mgmt_op_err;
+	/* mem_mgmt_op_err is 64 b */
+	u64 remote_invalid_req_err;
+	/* remote_invalid_req_err is 64 b */
+	u64 remote_access_err;
+	/* remote_access_err is 64 b */
+	u64 remote_op_err;
+	/* remote_op_err is 64 b */
+	u64 dup_req;
+	/* dup_req is 64 b */
+	u64 res_exceed_max;
+	/* res_exceed_max is 64 b */
+	u64 res_length_mismatch;
+	/* res_length_mismatch is 64 b */
+	u64 res_exceeds_wqe;
+	/* res_exceeds_wqe is 64 b */
+	u64 res_opcode_err;
+	/* res_opcode_err is 64 b */
+	u64 res_rx_invalid_rkey;
+	/* res_rx_invalid_rkey is 64 b */
+	u64 res_rx_domain_err;
+	/* res_rx_domain_err is 64 b */
+	u64 res_rx_no_perm;
+	/* res_rx_no_perm is 64 b */
+	u64 res_rx_range_err;
+	/* res_rx_range_err is 64 b */
+	u64 res_tx_invalid_rkey;
+	/* res_tx_invalid_rkey is 64 b */
+	u64 res_tx_domain_err;
+	/* res_tx_domain_err is 64 b */
+	u64 res_tx_no_perm;
+	/* res_tx_no_perm is 64 b */
+	u64 res_tx_range_err;
+	/* res_tx_range_err is 64 b */
+	u64 res_irrq_oflow;
+	/* res_irrq_oflow is 64 b */
+	u64 res_unsup_opcode;
+	/* res_unsup_opcode is 64 b */
+	u64 res_unaligned_atomic;
+	/* res_unaligned_atomic is 64 b */
+	u64 res_rem_inv_err;
+	/* res_rem_inv_err is 64 b */
+	u64 res_mem_error;
+	/* res_mem_error is 64 b */
+	u64 res_srq_err;
+	/* res_srq_err is 64 b */
+	u64 res_cmp_err;
+	/* res_cmp_err is 64 b */
+	u64 res_invalid_dup_rkey;
+	/* res_invalid_dup_rkey is 64 b */
+	u64 res_wqe_format_err;
+	/* res_wqe_format_err is 64 b */
+	u64 res_cq_load_err;
+	/* res_cq_load_err is 64 b */
+	u64 res_srq_load_err;
+	/* res_srq_load_err is 64 b */
+	u64 res_tx_pci_err;
+	/* res_tx_pci_err is 64 b */
+	u64 res_rx_pci_err;
+	/* res_rx_pci_err is 64 b */
+	u64 res_oos_drop_count;
+	/* res_oos_drop_count */
+	u64     active_qp_count_p0;
+	/* port 0 active qps */
+	u64     active_qp_count_p1;
+	/* port 1 active qps */
+	u64     active_qp_count_p2;
+	/* port 2 active qps */
+	u64     active_qp_count_p3;
+	/* port 3 active qps */
+};
+
+struct bnxt_qplib_ext_stat {
+	u64  tx_atomic_req;
+	u64  tx_read_req;
+	u64  tx_read_res;
+	u64  tx_write_req;
+	u64  tx_send_req;
+	u64  tx_roce_pkts;
+	u64  tx_roce_bytes;
+	u64  rx_atomic_req;
+	u64  rx_read_req;
+	u64  rx_read_res;
+	u64  rx_write_req;
+	u64  rx_send_req;
+	u64  rx_roce_pkts;
+	u64  rx_roce_bytes;
+	u64  rx_roce_good_pkts;
+	u64  rx_roce_good_bytes;
+	u64  rx_out_of_buffer;
+	u64  rx_out_of_sequence;
+	u64  tx_cnp;
+	u64  rx_cnp;
+	u64  rx_ecn_marked;
+};
+
+int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_sgid_tbl *sgid_tbl, int index,
+			struct bnxt_qplib_gid *gid);
+int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			struct bnxt_qplib_gid *gid, u16 vlan_id, bool update);
+int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			struct bnxt_qplib_gid *gid, const u8 *mac, u16 vlan_id,
+			bool update, u32 *index);
+int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			   struct bnxt_qplib_gid *gid, u16 gid_idx,
+			   const u8 *smac);
+int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
+			    struct bnxt_qplib_dev_attr *attr, bool vf);
+int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res,
+				  struct bnxt_qplib_rcfw *rcfw,
+				  struct bnxt_qplib_ctx *ctx);
+int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah,
+			 bool block);
+void bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah,
+			   bool block);
+int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_mrw *mrw);
+int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw,
+			 bool block);
+int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr,
+		      struct ib_umem *umem, int num_pbls, u32 buf_pg_size);
+int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr);
+int bnxt_qplib_alloc_fast_reg_mr(struct bnxt_qplib_res *res,
+				 struct bnxt_qplib_mrw *mr, int max);
+int bnxt_qplib_alloc_fast_reg_page_list(struct bnxt_qplib_res *res,
+					struct bnxt_qplib_frpl *frpl, int max);
+int bnxt_qplib_free_fast_reg_page_list(struct bnxt_qplib_res *res,
+				       struct bnxt_qplib_frpl *frpl);
+int bnxt_qplib_map_tc2cos(struct bnxt_qplib_res *res, u16 *cids);
+int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw,
+			      struct bnxt_qplib_roce_stats *stats);
+int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid,
+			 struct bnxt_qplib_ext_stat *estat);
+
+#endif /* __BNXT_QPLIB_SP_H__*/
diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
new file mode 100644
index 000000000..ecb719098
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -0,0 +1,3210 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * 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:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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 AUTHOR 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 AUTHOR 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.
+ *
+ * Description: RoCE HSI File - Autogenerated
+ */
+
+#ifndef __BNXT_RE_HSI_H__
+#define __BNXT_RE_HSI_H__
+
+/* include bnxt_hsi.h from bnxt_en driver */
+#include "bnxt_hsi.h"
+
+/* CMP Door Bell Format (4 bytes) */
+struct cmpl_doorbell {
+	__le32 key_mask_valid_idx;
+	#define CMPL_DOORBELL_IDX_MASK				    0xffffffUL
+	#define CMPL_DOORBELL_IDX_SFT				    0
+	#define CMPL_DOORBELL_RESERVED_MASK			    0x3000000UL
+	#define CMPL_DOORBELL_RESERVED_SFT			    24
+	#define CMPL_DOORBELL_IDX_VALID				    0x4000000UL
+	#define CMPL_DOORBELL_MASK				    0x8000000UL
+	#define CMPL_DOORBELL_KEY_MASK				    0xf0000000UL
+	#define CMPL_DOORBELL_KEY_SFT				    28
+	#define CMPL_DOORBELL_KEY_CMPL				(0x2UL << 28)
+};
+
+/* Status Door Bell Format (4 bytes) */
+struct status_doorbell {
+	__le32 key_idx;
+	#define STATUS_DOORBELL_IDX_MASK			    0xffffffUL
+	#define STATUS_DOORBELL_IDX_SFT			    0
+	#define STATUS_DOORBELL_RESERVED_MASK			    0xf000000UL
+	#define STATUS_DOORBELL_RESERVED_SFT			    24
+	#define STATUS_DOORBELL_KEY_MASK			    0xf0000000UL
+	#define STATUS_DOORBELL_KEY_SFT			    28
+	#define STATUS_DOORBELL_KEY_STAT			   (0x3UL << 28)
+};
+
+/* RoCE Host Structures */
+
+/* Doorbell Structures */
+/* dbc_dbc (size:64b/8B) */
+struct dbc_dbc {
+	__le32  index;
+	#define DBC_DBC_INDEX_MASK		0xffffffUL
+	#define DBC_DBC_INDEX_SFT		0
+	__le32  type_path_xid;
+	#define DBC_DBC_XID_MASK		0xfffffUL
+	#define DBC_DBC_XID_SFT			0
+	#define DBC_DBC_PATH_MASK		0x3000000UL
+	#define DBC_DBC_PATH_SFT		24
+	#define DBC_DBC_PATH_ROCE		(0x0UL << 24)
+	#define DBC_DBC_PATH_L2			(0x1UL << 24)
+	#define DBC_DBC_PATH_ENGINE		(0x2UL << 24)
+	#define DBC_DBC_PATH_LAST		DBC_DBC_PATH_ENGINE
+	#define DBC_DBC_DEBUG_TRACE		0x8000000UL
+	#define DBC_DBC_TYPE_MASK		0xf0000000UL
+	#define DBC_DBC_TYPE_SFT		28
+	#define DBC_DBC_TYPE_SQ			(0x0UL << 28)
+	#define DBC_DBC_TYPE_RQ			(0x1UL << 28)
+	#define DBC_DBC_TYPE_SRQ		(0x2UL << 28)
+	#define DBC_DBC_TYPE_SRQ_ARM		(0x3UL << 28)
+	#define DBC_DBC_TYPE_CQ			(0x4UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMSE		(0x5UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMALL		(0x6UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMENA		(0x7UL << 28)
+	#define DBC_DBC_TYPE_SRQ_ARMENA		(0x8UL << 28)
+	#define DBC_DBC_TYPE_CQ_CUTOFF_ACK	(0x9UL << 28)
+	#define DBC_DBC_TYPE_NQ			(0xaUL << 28)
+	#define DBC_DBC_TYPE_NQ_ARM		(0xbUL << 28)
+	#define DBC_DBC_TYPE_NULL		(0xfUL << 28)
+	#define DBC_DBC_TYPE_LAST		DBC_DBC_TYPE_NULL
+};
+
+/* dbc_dbc32 (size:32b/4B) */
+struct dbc_dbc32 {
+	__le32  type_abs_incr_xid;
+	#define DBC_DBC32_XID_MASK		0xfffffUL
+	#define DBC_DBC32_XID_SFT		0
+	#define DBC_DBC32_PATH_MASK		0xc00000UL
+	#define DBC_DBC32_PATH_SFT		22
+	#define DBC_DBC32_PATH_ROCE		(0x0UL << 22)
+	#define DBC_DBC32_PATH_L2		(0x1UL << 22)
+	#define DBC_DBC32_PATH_LAST		DBC_DBC32_PATH_L2
+	#define DBC_DBC32_INCR_MASK		0xf000000UL
+	#define DBC_DBC32_INCR_SFT		24
+	#define DBC_DBC32_ABS			0x10000000UL
+	#define DBC_DBC32_TYPE_MASK		0xe0000000UL
+	#define DBC_DBC32_TYPE_SFT		29
+	#define DBC_DBC32_TYPE_SQ		(0x0UL << 29)
+	#define DBC_DBC32_TYPE_LAST		DBC_DBC32_TYPE_SQ
+};
+
+/* SQ WQE Structures */
+/* Base SQ WQE (8 bytes) */
+struct sq_base {
+	u8 wqe_type;
+	#define SQ_BASE_WQE_TYPE_SEND				   0x0UL
+	#define SQ_BASE_WQE_TYPE_SEND_W_IMMEAD			   0x1UL
+	#define SQ_BASE_WQE_TYPE_SEND_W_INVALID		   0x2UL
+	#define SQ_BASE_WQE_TYPE_WRITE_WQE			   0x4UL
+	#define SQ_BASE_WQE_TYPE_WRITE_W_IMMEAD		   0x5UL
+	#define SQ_BASE_WQE_TYPE_READ_WQE			   0x6UL
+	#define SQ_BASE_WQE_TYPE_ATOMIC_CS			   0x8UL
+	#define SQ_BASE_WQE_TYPE_ATOMIC_FA			   0xbUL
+	#define SQ_BASE_WQE_TYPE_LOCAL_INVALID			   0xcUL
+	#define SQ_BASE_WQE_TYPE_FR_PMR			   0xdUL
+	#define SQ_BASE_WQE_TYPE_BIND				   0xeUL
+	u8 unused_0[7];
+};
+
+/* WQE SGE (16 bytes) */
+struct sq_sge {
+	__le64 va_or_pa;
+	__le32 l_key;
+	__le32 size;
+};
+
+/* PSN Search Structure (8 bytes) */
+struct sq_psn_search {
+	__le32 opcode_start_psn;
+	#define SQ_PSN_SEARCH_START_PSN_MASK			    0xffffffUL
+	#define SQ_PSN_SEARCH_START_PSN_SFT			    0
+	#define SQ_PSN_SEARCH_OPCODE_MASK			    0xff000000UL
+	#define SQ_PSN_SEARCH_OPCODE_SFT			    24
+	__le32 flags_next_psn;
+	#define SQ_PSN_SEARCH_NEXT_PSN_MASK			    0xffffffUL
+	#define SQ_PSN_SEARCH_NEXT_PSN_SFT			    0
+	#define SQ_PSN_SEARCH_FLAGS_MASK			    0xff000000UL
+	#define SQ_PSN_SEARCH_FLAGS_SFT				    24
+};
+
+/* sq_psn_search_ext (size:128b/16B) */
+struct sq_psn_search_ext {
+	__le32  opcode_start_psn;
+	#define SQ_PSN_SEARCH_EXT_START_PSN_MASK		    0xffffffUL
+	#define SQ_PSN_SEARCH_EXT_START_PSN_SFT			    0
+	#define SQ_PSN_SEARCH_EXT_OPCODE_MASK			    0xff000000UL
+	#define SQ_PSN_SEARCH_EXT_OPCODE_SFT			    24
+	__le32  flags_next_psn;
+	#define SQ_PSN_SEARCH_EXT_NEXT_PSN_MASK			    0xffffffUL
+	#define SQ_PSN_SEARCH_EXT_NEXT_PSN_SFT			    0
+	#define SQ_PSN_SEARCH_EXT_FLAGS_MASK			    0xff000000UL
+	#define SQ_PSN_SEARCH_EXT_FLAGS_SFT			    24
+	__le16  start_slot_idx;
+	__le16  reserved16;
+	__le32  reserved32;
+};
+
+/* Send SQ WQE (40 bytes) */
+struct sq_send {
+	u8 wqe_type;
+	#define SQ_SEND_WQE_TYPE_SEND				   0x0UL
+	#define SQ_SEND_WQE_TYPE_SEND_W_IMMEAD			   0x1UL
+	#define SQ_SEND_WQE_TYPE_SEND_W_INVALID		   0x2UL
+	u8 flags;
+	#define SQ_SEND_FLAGS_SIGNAL_COMP			    0x1UL
+	#define SQ_SEND_FLAGS_RD_OR_ATOMIC_FENCE		    0x2UL
+	#define SQ_SEND_FLAGS_UC_FENCE				    0x4UL
+	#define SQ_SEND_FLAGS_SE				    0x8UL
+	#define SQ_SEND_FLAGS_INLINE				    0x10UL
+	u8 wqe_size;
+	u8 reserved8_1;
+	__le32 inv_key_or_imm_data;
+	__le32 length;
+	__le32 q_key;
+	__le32 dst_qp;
+	#define SQ_SEND_DST_QP_MASK				    0xffffffUL
+	#define SQ_SEND_DST_QP_SFT				    0
+	#define SQ_SEND_RESERVED8_2_MASK			    0xff000000UL
+	#define SQ_SEND_RESERVED8_2_SFT			    24
+	__le32 avid;
+	#define SQ_SEND_AVID_MASK				    0xfffffUL
+	#define SQ_SEND_AVID_SFT				    0
+	#define SQ_SEND_RESERVED_AVID_MASK			    0xfff00000UL
+	#define SQ_SEND_RESERVED_AVID_SFT			    20
+	__le64 reserved64;
+	__le32 data[24];
+};
+
+/* sq_send_hdr (size:256b/32B) */
+struct sq_send_hdr {
+	u8	wqe_type;
+	u8	flags;
+	u8	wqe_size;
+	u8	reserved8_1;
+	__le32	inv_key_or_imm_data;
+	__le32	length;
+	__le32	q_key;
+	__le32	dst_qp;
+	__le32	avid;
+	__le64	reserved64;
+};
+
+/* Send Raw Ethernet and QP1 SQ WQE (40 bytes) */
+struct sq_send_raweth_qp1 {
+	u8 wqe_type;
+	#define SQ_SEND_RAWETH_QP1_WQE_TYPE_SEND		   0x0UL
+	u8 flags;
+	#define SQ_SEND_RAWETH_QP1_FLAGS_SIGNAL_COMP		    0x1UL
+	#define SQ_SEND_RAWETH_QP1_FLAGS_RD_OR_ATOMIC_FENCE	    0x2UL
+	#define SQ_SEND_RAWETH_QP1_FLAGS_UC_FENCE		    0x4UL
+	#define SQ_SEND_RAWETH_QP1_FLAGS_SE			    0x8UL
+	#define SQ_SEND_RAWETH_QP1_FLAGS_INLINE		    0x10UL
+	u8 wqe_size;
+	u8 reserved8;
+	__le16 lflags;
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_TCP_UDP_CHKSUM	    0x1UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_IP_CHKSUM		    0x2UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_NOCRC		    0x4UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_STAMP		    0x8UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_T_IP_CHKSUM		    0x10UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_RESERVED1_1		    0x20UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_RESERVED1_2		    0x40UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_RESERVED1_3		    0x80UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_ROCE_CRC		    0x100UL
+	#define SQ_SEND_RAWETH_QP1_LFLAGS_FCOE_CRC		    0x200UL
+	__le16 cfa_action;
+	__le32 length;
+	__le32 reserved32_1;
+	__le32 cfa_meta;
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_MASK	    0xfffUL
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_SFT	    0
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_DE		    0x1000UL
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_PRI_MASK	    0xe000UL
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_PRI_SFT	    13
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_MASK	    0x70000UL
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_SFT	    16
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID88A8    (0x0UL << 16)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID8100    (0x1UL << 16)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9100    (0x2UL << 16)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9200    (0x3UL << 16)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9300    (0x4UL << 16)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPIDCFG     (0x5UL << 16)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_LAST	\
+				SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPIDCFG
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_RESERVED_MASK     0xff80000UL
+	#define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_RESERVED_SFT      19
+	#define SQ_SEND_RAWETH_QP1_CFA_META_KEY_MASK		    0xf0000000UL
+	#define SQ_SEND_RAWETH_QP1_CFA_META_KEY_SFT		    28
+	#define SQ_SEND_RAWETH_QP1_CFA_META_KEY_NONE		   (0x0UL << 28)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_KEY_VLAN_TAG	   (0x1UL << 28)
+	#define SQ_SEND_RAWETH_QP1_CFA_META_KEY_LAST		\
+				SQ_SEND_RAWETH_QP1_CFA_META_KEY_VLAN_TAG
+	__le32 reserved32_2;
+	__le64 reserved64;
+	__le32 data[24];
+};
+
+/* sq_send_raweth_qp1_hdr (size:256b/32B) */
+struct sq_send_raweth_qp1_hdr {
+	u8	wqe_type;
+	u8	flags;
+	u8	wqe_size;
+	u8	reserved8;
+	__le16	lflags;
+	__le16	cfa_action;
+	__le32	length;
+	__le32	reserved32_1;
+	__le32	cfa_meta;
+	__le32	reserved32_2;
+	__le64	reserved64;
+};
+
+/* RDMA SQ WQE (40 bytes) */
+struct sq_rdma {
+	u8 wqe_type;
+	#define SQ_RDMA_WQE_TYPE_WRITE_WQE			   0x4UL
+	#define SQ_RDMA_WQE_TYPE_WRITE_W_IMMEAD		   0x5UL
+	#define SQ_RDMA_WQE_TYPE_READ_WQE			   0x6UL
+	u8 flags;
+	#define SQ_RDMA_FLAGS_SIGNAL_COMP			    0x1UL
+	#define SQ_RDMA_FLAGS_RD_OR_ATOMIC_FENCE		    0x2UL
+	#define SQ_RDMA_FLAGS_UC_FENCE				    0x4UL
+	#define SQ_RDMA_FLAGS_SE				    0x8UL
+	#define SQ_RDMA_FLAGS_INLINE				    0x10UL
+	u8 wqe_size;
+	u8 reserved8;
+	__le32 imm_data;
+	__le32 length;
+	__le32 reserved32_1;
+	__le64 remote_va;
+	__le32 remote_key;
+	__le32 reserved32_2;
+	__le32 data[24];
+};
+
+/* sq_rdma_hdr (size:256b/32B) */
+struct sq_rdma_hdr {
+	u8	wqe_type;
+	u8	flags;
+	u8	wqe_size;
+	u8	reserved8;
+	__le32	imm_data;
+	__le32	length;
+	__le32	reserved32_1;
+	__le64	remote_va;
+	__le32	remote_key;
+	__le32	reserved32_2;
+};
+
+/* Atomic SQ WQE (40 bytes) */
+struct sq_atomic {
+	u8 wqe_type;
+	#define SQ_ATOMIC_WQE_TYPE_ATOMIC_CS			   0x8UL
+	#define SQ_ATOMIC_WQE_TYPE_ATOMIC_FA			   0xbUL
+	u8 flags;
+	#define SQ_ATOMIC_FLAGS_SIGNAL_COMP			    0x1UL
+	#define SQ_ATOMIC_FLAGS_RD_OR_ATOMIC_FENCE		    0x2UL
+	#define SQ_ATOMIC_FLAGS_UC_FENCE			    0x4UL
+	#define SQ_ATOMIC_FLAGS_SE				    0x8UL
+	#define SQ_ATOMIC_FLAGS_INLINE				    0x10UL
+	__le16 reserved16;
+	__le32 remote_key;
+	__le64 remote_va;
+	__le64 swap_data;
+	__le64 cmp_data;
+	__le32 data[24];
+};
+
+/* sq_atomic_hdr (size:256b/32B) */
+struct sq_atomic_hdr {
+	u8	wqe_type;
+	u8	flags;
+	__le16	reserved16;
+	__le32	remote_key;
+	__le64	remote_va;
+	__le64	swap_data;
+	__le64	cmp_data;
+};
+
+/* Local Invalidate SQ WQE (40 bytes) */
+struct sq_localinvalidate {
+	u8 wqe_type;
+	#define SQ_LOCALINVALIDATE_WQE_TYPE_LOCAL_INVALID	   0xcUL
+	u8 flags;
+	#define SQ_LOCALINVALIDATE_FLAGS_SIGNAL_COMP		    0x1UL
+	#define SQ_LOCALINVALIDATE_FLAGS_RD_OR_ATOMIC_FENCE	    0x2UL
+	#define SQ_LOCALINVALIDATE_FLAGS_UC_FENCE		    0x4UL
+	#define SQ_LOCALINVALIDATE_FLAGS_SE			    0x8UL
+	#define SQ_LOCALINVALIDATE_FLAGS_INLINE		    0x10UL
+	__le16 reserved16;
+	__le32 inv_l_key;
+	__le64 reserved64;
+	__le32 reserved128[4];
+	__le32 data[24];
+};
+
+/* sq_localinvalidate_hdr (size:256b/32B) */
+struct sq_localinvalidate_hdr {
+	u8	wqe_type;
+	u8	flags;
+	__le16	reserved16;
+	__le32	inv_l_key;
+	__le64	reserved64;
+	u8	reserved128[16];
+};
+
+/* FR-PMR SQ WQE (40 bytes) */
+struct sq_fr_pmr {
+	u8 wqe_type;
+	#define SQ_FR_PMR_WQE_TYPE_FR_PMR			   0xdUL
+	u8 flags;
+	#define SQ_FR_PMR_FLAGS_SIGNAL_COMP			    0x1UL
+	#define SQ_FR_PMR_FLAGS_RD_OR_ATOMIC_FENCE		    0x2UL
+	#define SQ_FR_PMR_FLAGS_UC_FENCE			    0x4UL
+	#define SQ_FR_PMR_FLAGS_SE				    0x8UL
+	#define SQ_FR_PMR_FLAGS_INLINE				    0x10UL
+	u8 access_cntl;
+	#define SQ_FR_PMR_ACCESS_CNTL_LOCAL_WRITE		    0x1UL
+	#define SQ_FR_PMR_ACCESS_CNTL_REMOTE_READ		    0x2UL
+	#define SQ_FR_PMR_ACCESS_CNTL_REMOTE_WRITE		    0x4UL
+	#define SQ_FR_PMR_ACCESS_CNTL_REMOTE_ATOMIC		    0x8UL
+	#define SQ_FR_PMR_ACCESS_CNTL_WINDOW_BIND		    0x10UL
+	u8 zero_based_page_size_log;
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_MASK			    0x1fUL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_SFT			    0
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4K		   0x0UL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_8K		   0x1UL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_64K		   0x4UL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_256K		   0x6UL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_1M		   0x8UL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_2M		   0x9UL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4M		   0xaUL
+	#define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_1G		   0x12UL
+	#define SQ_FR_PMR_ZERO_BASED				    0x20UL
+	#define SQ_FR_PMR_RESERVED2_MASK			    0xc0UL
+	#define SQ_FR_PMR_RESERVED2_SFT			    6
+	__le32 l_key;
+	u8 length[5];
+	u8 reserved8_1;
+	u8 reserved8_2;
+	u8 numlevels_pbl_page_size_log;
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_MASK		    0x1fUL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_SFT		    0
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4K		   0x0UL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_8K		   0x1UL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_64K		   0x4UL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_256K		   0x6UL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_1M		   0x8UL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_2M		   0x9UL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4M		   0xaUL
+	#define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_1G		   0x12UL
+	#define SQ_FR_PMR_RESERVED1				    0x20UL
+	#define SQ_FR_PMR_NUMLEVELS_MASK			    0xc0UL
+	#define SQ_FR_PMR_NUMLEVELS_SFT			    6
+	#define SQ_FR_PMR_NUMLEVELS_PHYSICAL			   (0x0UL << 6)
+	#define SQ_FR_PMR_NUMLEVELS_LAYER1			   (0x1UL << 6)
+	#define SQ_FR_PMR_NUMLEVELS_LAYER2			   (0x2UL << 6)
+	__le64 pblptr;
+	__le64 va;
+	__le32 data[24];
+};
+
+/* sq_fr_pmr_hdr (size:256b/32B) */
+struct sq_fr_pmr_hdr {
+	u8	wqe_type;
+	u8	flags;
+	u8	access_cntl;
+	u8	zero_based_page_size_log;
+	__le32	l_key;
+	u8	length[5];
+	u8	reserved8_1;
+	u8	reserved8_2;
+	u8	numlevels_pbl_page_size_log;
+	__le64	pblptr;
+	__le64	va;
+};
+
+/* Bind SQ WQE (40 bytes) */
+struct sq_bind {
+	u8 wqe_type;
+	#define SQ_BIND_WQE_TYPE_BIND				   0xeUL
+	u8 flags;
+	#define SQ_BIND_FLAGS_SIGNAL_COMP			    0x1UL
+	#define SQ_BIND_FLAGS_RD_OR_ATOMIC_FENCE		    0x2UL
+	#define SQ_BIND_FLAGS_UC_FENCE				    0x4UL
+	#define SQ_BIND_FLAGS_SE				    0x8UL
+	#define SQ_BIND_FLAGS_INLINE				    0x10UL
+	u8 access_cntl;
+	#define SQ_BIND_ACCESS_CNTL_LOCAL_WRITE		    0x1UL
+	#define SQ_BIND_ACCESS_CNTL_REMOTE_READ		    0x2UL
+	#define SQ_BIND_ACCESS_CNTL_REMOTE_WRITE		    0x4UL
+	#define SQ_BIND_ACCESS_CNTL_REMOTE_ATOMIC		    0x8UL
+	#define SQ_BIND_ACCESS_CNTL_WINDOW_BIND		    0x10UL
+	u8 reserved8_1;
+	u8 mw_type_zero_based;
+	#define SQ_BIND_ZERO_BASED				    0x1UL
+	#define SQ_BIND_MW_TYPE				    0x2UL
+	#define SQ_BIND_MW_TYPE_TYPE1				   (0x0UL << 1)
+	#define SQ_BIND_MW_TYPE_TYPE2				   (0x1UL << 1)
+	#define SQ_BIND_RESERVED6_MASK				    0xfcUL
+	#define SQ_BIND_RESERVED6_SFT				    2
+	u8 reserved8_2;
+	__le16 reserved16;
+	__le32 parent_l_key;
+	__le32 l_key;
+	__le64 va;
+	u8 length[5];
+	u8 data_reserved24[99];
+	#define SQ_BIND_RESERVED24_MASK			    0xffffff00UL
+	#define SQ_BIND_RESERVED24_SFT				    8
+	#define SQ_BIND_DATA_MASK				    0xffffffffUL
+	#define SQ_BIND_DATA_SFT				    0
+};
+
+/* sq_bind_hdr (size:256b/32B) */
+struct sq_bind_hdr {
+	u8	wqe_type;
+	u8	flags;
+	u8	access_cntl;
+	u8	reserved8_1;
+	u8	mw_type_zero_based;
+	u8	reserved8_2;
+	__le16	reserved16;
+	__le32	parent_l_key;
+	__le32	l_key;
+	__le64	va;
+	u8	length[5];
+	u8	reserved24[3];
+};
+
+/* RQ/SRQ WQE Structures */
+/* RQ/SRQ WQE (40 bytes) */
+struct rq_wqe {
+	u8 wqe_type;
+	#define RQ_WQE_WQE_TYPE_RCV				   0x80UL
+	u8 flags;
+	u8 wqe_size;
+	u8 reserved8;
+	__le32 reserved32;
+	__le32 wr_id[2];
+	#define RQ_WQE_WR_ID_MASK				    0xfffffUL
+	#define RQ_WQE_WR_ID_SFT				    0
+	#define RQ_WQE_RESERVED44_MASK				    0xfff00000UL
+	#define RQ_WQE_RESERVED44_SFT				    20
+	__le32 reserved128[4];
+	__le32 data[24];
+};
+
+/* rq_wqe_hdr (size:256b/32B) */
+struct rq_wqe_hdr {
+	u8	wqe_type;
+	u8	flags;
+	u8	wqe_size;
+	u8	reserved8;
+	__le32	reserved32;
+	__le32	wr_id[2];
+	u8	reserved128[16];
+};
+
+/* CQ CQE Structures */
+/* Base CQE (32 bytes) */
+struct cq_base {
+	__le64 reserved64_1;
+	__le64 reserved64_2;
+	__le64 reserved64_3;
+	u8 cqe_type_toggle;
+	#define CQ_BASE_TOGGLE					    0x1UL
+	#define CQ_BASE_CQE_TYPE_MASK				    0x1eUL
+	#define CQ_BASE_CQE_TYPE_SFT				    1
+	#define CQ_BASE_CQE_TYPE_REQ				   (0x0UL << 1)
+	#define CQ_BASE_CQE_TYPE_RES_RC			   (0x1UL << 1)
+	#define CQ_BASE_CQE_TYPE_RES_UD			   (0x2UL << 1)
+	#define CQ_BASE_CQE_TYPE_RES_RAWETH_QP1		   (0x3UL << 1)
+	#define CQ_BASE_CQE_TYPE_TERMINAL			   (0xeUL << 1)
+	#define CQ_BASE_CQE_TYPE_CUT_OFF			   (0xfUL << 1)
+	#define CQ_BASE_RESERVED3_MASK				    0xe0UL
+	#define CQ_BASE_RESERVED3_SFT				    5
+	u8 status;
+	__le16 reserved16;
+	__le32 reserved32;
+};
+
+/* Requester CQ CQE (32 bytes) */
+struct cq_req {
+	__le64 qp_handle;
+	__le16 sq_cons_idx;
+	__le16 reserved16_1;
+	__le32 reserved32_2;
+	__le64 reserved64;
+	u8 cqe_type_toggle;
+	#define CQ_REQ_TOGGLE					    0x1UL
+	#define CQ_REQ_CQE_TYPE_MASK				    0x1eUL
+	#define CQ_REQ_CQE_TYPE_SFT				    1
+	#define CQ_REQ_CQE_TYPE_REQ				   (0x0UL << 1)
+	#define CQ_REQ_RESERVED3_MASK				    0xe0UL
+	#define CQ_REQ_RESERVED3_SFT				    5
+	u8 status;
+	#define CQ_REQ_STATUS_OK				   0x0UL
+	#define CQ_REQ_STATUS_BAD_RESPONSE_ERR			   0x1UL
+	#define CQ_REQ_STATUS_LOCAL_LENGTH_ERR			   0x2UL
+	#define CQ_REQ_STATUS_LOCAL_QP_OPERATION_ERR		   0x3UL
+	#define CQ_REQ_STATUS_LOCAL_PROTECTION_ERR		   0x4UL
+	#define CQ_REQ_STATUS_MEMORY_MGT_OPERATION_ERR		   0x5UL
+	#define CQ_REQ_STATUS_REMOTE_INVALID_REQUEST_ERR	   0x6UL
+	#define CQ_REQ_STATUS_REMOTE_ACCESS_ERR		   0x7UL
+	#define CQ_REQ_STATUS_REMOTE_OPERATION_ERR		   0x8UL
+	#define CQ_REQ_STATUS_RNR_NAK_RETRY_CNT_ERR		   0x9UL
+	#define CQ_REQ_STATUS_TRANSPORT_RETRY_CNT_ERR		   0xaUL
+	#define CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR		   0xbUL
+	__le16 reserved16_2;
+	__le32 reserved32_1;
+};
+
+/* Responder RC CQE (32 bytes) */
+struct cq_res_rc {
+	__le32 length;
+	__le32 imm_data_or_inv_r_key;
+	__le64 qp_handle;
+	__le64 mr_handle;
+	u8 cqe_type_toggle;
+	#define CQ_RES_RC_TOGGLE				    0x1UL
+	#define CQ_RES_RC_CQE_TYPE_MASK			    0x1eUL
+	#define CQ_RES_RC_CQE_TYPE_SFT				    1
+	#define CQ_RES_RC_CQE_TYPE_RES_RC			   (0x1UL << 1)
+	#define CQ_RES_RC_RESERVED3_MASK			    0xe0UL
+	#define CQ_RES_RC_RESERVED3_SFT			    5
+	u8 status;
+	#define CQ_RES_RC_STATUS_OK				   0x0UL
+	#define CQ_RES_RC_STATUS_LOCAL_ACCESS_ERROR		   0x1UL
+	#define CQ_RES_RC_STATUS_LOCAL_LENGTH_ERR		   0x2UL
+	#define CQ_RES_RC_STATUS_LOCAL_PROTECTION_ERR		   0x3UL
+	#define CQ_RES_RC_STATUS_LOCAL_QP_OPERATION_ERR	   0x4UL
+	#define CQ_RES_RC_STATUS_MEMORY_MGT_OPERATION_ERR	   0x5UL
+	#define CQ_RES_RC_STATUS_REMOTE_INVALID_REQUEST_ERR       0x6UL
+	#define CQ_RES_RC_STATUS_WORK_REQUEST_FLUSHED_ERR	   0x7UL
+	#define CQ_RES_RC_STATUS_HW_FLUSH_ERR			   0x8UL
+	__le16 flags;
+	#define CQ_RES_RC_FLAGS_SRQ				    0x1UL
+	#define CQ_RES_RC_FLAGS_SRQ_RQ				   (0x0UL << 0)
+	#define CQ_RES_RC_FLAGS_SRQ_SRQ			   (0x1UL << 0)
+	#define CQ_RES_RC_FLAGS_SRQ_LAST    CQ_RES_RC_FLAGS_SRQ_SRQ
+	#define CQ_RES_RC_FLAGS_IMM				    0x2UL
+	#define CQ_RES_RC_FLAGS_INV				    0x4UL
+	#define CQ_RES_RC_FLAGS_RDMA				    0x8UL
+	#define CQ_RES_RC_FLAGS_RDMA_SEND			   (0x0UL << 3)
+	#define CQ_RES_RC_FLAGS_RDMA_RDMA_WRITE		   (0x1UL << 3)
+	#define CQ_RES_RC_FLAGS_RDMA_LAST    CQ_RES_RC_FLAGS_RDMA_RDMA_WRITE
+	__le32 srq_or_rq_wr_id;
+	#define CQ_RES_RC_SRQ_OR_RQ_WR_ID_MASK			    0xfffffUL
+	#define CQ_RES_RC_SRQ_OR_RQ_WR_ID_SFT			    0
+	#define CQ_RES_RC_RESERVED12_MASK			    0xfff00000UL
+	#define CQ_RES_RC_RESERVED12_SFT			    20
+};
+
+/* Responder UD CQE (32 bytes) */
+struct cq_res_ud {
+	__le16 length;
+	#define CQ_RES_UD_LENGTH_MASK				    0x3fffUL
+	#define CQ_RES_UD_LENGTH_SFT				    0
+	__le16 cfa_metadata;
+	#define CQ_RES_UD_CFA_METADATA_VID_MASK			0xfffUL
+	#define CQ_RES_UD_CFA_METADATA_VID_SFT			0
+	#define CQ_RES_UD_CFA_METADATA_DE			0x1000UL
+	#define CQ_RES_UD_CFA_METADATA_PRI_MASK			0xe000UL
+	#define CQ_RES_UD_CFA_METADATA_PRI_SFT			13
+	__le32 imm_data;
+	__le64 qp_handle;
+	__le16 src_mac[3];
+	__le16 src_qp_low;
+	u8 cqe_type_toggle;
+	#define CQ_RES_UD_TOGGLE				   0x1UL
+	#define CQ_RES_UD_CQE_TYPE_MASK				   0x1eUL
+	#define CQ_RES_UD_CQE_TYPE_SFT				   1
+	#define CQ_RES_UD_CQE_TYPE_RES_UD			   (0x2UL << 1)
+	u8 status;
+	#define CQ_RES_UD_STATUS_OK				   0x0UL
+	#define CQ_RES_UD_STATUS_LOCAL_ACCESS_ERROR		   0x1UL
+	#define CQ_RES_UD_STATUS_HW_LOCAL_LENGTH_ERR		   0x2UL
+	#define CQ_RES_UD_STATUS_LOCAL_PROTECTION_ERR		   0x3UL
+	#define CQ_RES_UD_STATUS_LOCAL_QP_OPERATION_ERR	   0x4UL
+	#define CQ_RES_UD_STATUS_MEMORY_MGT_OPERATION_ERR	   0x5UL
+	#define CQ_RES_UD_STATUS_WORK_REQUEST_FLUSHED_ERR	   0x7UL
+	#define CQ_RES_UD_STATUS_HW_FLUSH_ERR			   0x8UL
+	__le16 flags;
+	#define CQ_RES_UD_FLAGS_SRQ				    0x1UL
+	#define CQ_RES_UD_FLAGS_SRQ_RQ				   (0x0UL << 0)
+	#define CQ_RES_UD_FLAGS_SRQ_SRQ			   (0x1UL << 0)
+	#define CQ_RES_UD_FLAGS_SRQ_LAST    CQ_RES_UD_FLAGS_SRQ_SRQ
+	#define CQ_RES_UD_FLAGS_IMM				    0x2UL
+	#define CQ_RES_UD_FLAGS_UNUSED_MASK			0xcUL
+	#define CQ_RES_UD_FLAGS_UNUSED_SFT			2
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_MASK		0x30UL
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_SFT			4
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_V1			(0x0UL << 4)
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV4		(0x2UL << 4)
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6		(0x3UL << 4)
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_LAST		\
+					CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6
+	#define CQ_RES_UD_FLAGS_META_FORMAT_MASK		0x3c0UL
+	#define CQ_RES_UD_FLAGS_META_FORMAT_SFT			6
+	#define CQ_RES_UD_FLAGS_META_FORMAT_NONE		(0x0UL << 6)
+	#define CQ_RES_UD_FLAGS_META_FORMAT_VLAN		(0x1UL << 6)
+	#define CQ_RES_UD_FLAGS_META_FORMAT_TUNNEL_ID		(0x2UL << 6)
+	#define CQ_RES_UD_FLAGS_META_FORMAT_CHDR_DATA		(0x3UL << 6)
+	#define CQ_RES_UD_FLAGS_META_FORMAT_HDR_OFFSET		(0x4UL << 6)
+	#define CQ_RES_UD_FLAGS_META_FORMAT_LAST		\
+					CQ_RES_UD_FLAGS_META_FORMAT_HDR_OFFSET
+	#define CQ_RES_UD_FLAGS_EXT_META_FORMAT_MASK		0xc00UL
+	#define CQ_RES_UD_FLAGS_EXT_META_FORMAT_SFT		10
+
+	__le32 src_qp_high_srq_or_rq_wr_id;
+	#define CQ_RES_UD_SRQ_OR_RQ_WR_ID_MASK			    0xfffffUL
+	#define CQ_RES_UD_SRQ_OR_RQ_WR_ID_SFT			    0
+	#define CQ_RES_UD_SRC_QP_HIGH_MASK			    0xff000000UL
+	#define CQ_RES_UD_SRC_QP_HIGH_SFT			    24
+};
+
+/* Responder RawEth and QP1 CQE (32 bytes) */
+struct cq_res_raweth_qp1 {
+	__le16 length;
+	#define CQ_RES_RAWETH_QP1_LENGTH_MASK			    0x3fffUL
+	#define CQ_RES_RAWETH_QP1_LENGTH_SFT			    0
+	#define CQ_RES_RAWETH_QP1_RESERVED2_MASK		    0xc000UL
+	#define CQ_RES_RAWETH_QP1_RESERVED2_SFT		    14
+	__le16 raweth_qp1_flags;
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ERROR	    0x1UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_RESERVED5_1_MASK 0x3eUL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_RESERVED5_1_SFT 1
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_MASK      0x3c0UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_SFT       6
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_NOT_KNOWN (0x0UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_IP       (0x1UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_TCP      (0x2UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_UDP      (0x3UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_FCOE     (0x4UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ROCE     (0x5UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ICMP     (0x7UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_WO_TIMESTAMP \
+								 (0x8UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP \
+								 (0x9UL << 6)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_LAST	\
+		CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_MASK	    0x3ffUL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_SFT		    0
+	#define CQ_RES_RAWETH_QP1_RESERVED6_MASK		    0xfc00UL
+	#define CQ_RES_RAWETH_QP1_RESERVED6_SFT		    10
+	__le16 raweth_qp1_errors;
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_RESERVED4_MASK 0xfUL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_RESERVED4_SFT  0
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_IP_CS_ERROR    0x10UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_L4_CS_ERROR    0x20UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_IP_CS_ERROR  0x40UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_L4_CS_ERROR  0x80UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_CRC_ERROR      0x100UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_MASK 0xe00UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_SFT 9
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_NO_ERROR \
+								(0x0UL << 9)
+	#define \
+	   CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_VERSION \
+								(0x1UL << 9)
+	#define \
+	   CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_HDR_LEN \
+								(0x2UL << 9)
+	#define \
+	   CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_TUNNEL_TOTAL_ERROR \
+								(0x3UL << 9)
+	#define \
+	   CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_IP_TOTAL_ERROR \
+								(0x4UL << 9)
+	#define \
+	   CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_UDP_TOTAL_ERROR \
+								(0x5UL << 9)
+	#define \
+	   CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL \
+								(0x6UL << 9)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_LAST \
+		CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_MASK 0xf000UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_SFT  12
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_NO_ERROR \
+								(0x0UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_VERSION \
+								(0x1UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_HDR_LEN \
+								 (0x2UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_TTL \
+								 (0x3UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_IP_TOTAL_ERROR \
+								 (0x4UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_UDP_TOTAL_ERROR \
+								 (0x5UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN \
+								 (0x6UL << 12)
+	#define \
+	 CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN_TOO_SMALL\
+								 (0x7UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN \
+								 (0x8UL << 12)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_LAST \
+		CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN
+	__le16 raweth_qp1_cfa_code;
+	__le64 qp_handle;
+	__le32 raweth_qp1_flags2;
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_CS_CALC     0x1UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_L4_CS_CALC     0x2UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_T_IP_CS_CALC   0x4UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_T_L4_CS_CALC   0x8UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_MASK 0xf0UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_SFT 4
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_NONE \
+								(0x0UL << 4)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_VLAN \
+								(0x1UL << 4)
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_LAST\
+			CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_VLAN
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_TYPE	    0x100UL
+	__le32 raweth_qp1_metadata;
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_VID_MASK     0xfffUL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_VID_SFT      0
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_DE	    0x1000UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_MASK     0xe000UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_SFT      13
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_MASK    0xffff0000UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_SFT     16
+	u8 cqe_type_toggle;
+	#define CQ_RES_RAWETH_QP1_TOGGLE			    0x1UL
+	#define CQ_RES_RAWETH_QP1_CQE_TYPE_MASK		    0x1eUL
+	#define CQ_RES_RAWETH_QP1_CQE_TYPE_SFT			    1
+	#define CQ_RES_RAWETH_QP1_CQE_TYPE_RES_RAWETH_QP1	   (0x3UL << 1)
+	#define CQ_RES_RAWETH_QP1_RESERVED3_MASK		    0xe0UL
+	#define CQ_RES_RAWETH_QP1_RESERVED3_SFT		    5
+	u8 status;
+	#define CQ_RES_RAWETH_QP1_STATUS_OK			   0x0UL
+	#define CQ_RES_RAWETH_QP1_STATUS_LOCAL_ACCESS_ERROR       0x1UL
+	#define CQ_RES_RAWETH_QP1_STATUS_HW_LOCAL_LENGTH_ERR      0x2UL
+	#define CQ_RES_RAWETH_QP1_STATUS_LOCAL_PROTECTION_ERR     0x3UL
+	#define CQ_RES_RAWETH_QP1_STATUS_LOCAL_QP_OPERATION_ERR   0x4UL
+	#define CQ_RES_RAWETH_QP1_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL
+	#define CQ_RES_RAWETH_QP1_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL
+	#define CQ_RES_RAWETH_QP1_STATUS_HW_FLUSH_ERR		   0x8UL
+	__le16 flags;
+	#define CQ_RES_RAWETH_QP1_FLAGS_SRQ			    0x1UL
+	#define CQ_RES_RAWETH_QP1_FLAGS_SRQ_RQ			   0x0UL
+	#define CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ		   0x1UL
+	#define CQ_RES_RAWETH_QP1_FLAGS_SRQ_LAST \
+					CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ
+	__le32 raweth_qp1_payload_offset_srq_or_rq_wr_id;
+	#define CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_MASK		    0xfffffUL
+	#define CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_SFT		    0
+	#define CQ_RES_RAWETH_QP1_RESERVED4_MASK		    0xf00000UL
+	#define CQ_RES_RAWETH_QP1_RESERVED4_SFT		    20
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_PAYLOAD_OFFSET_MASK   0xff000000UL
+	#define CQ_RES_RAWETH_QP1_RAWETH_QP1_PAYLOAD_OFFSET_SFT    24
+};
+
+/* Terminal CQE (32 bytes) */
+struct cq_terminal {
+	__le64 qp_handle;
+	__le16 sq_cons_idx;
+	__le16 rq_cons_idx;
+	__le32 reserved32_1;
+	__le64 reserved64_3;
+	u8 cqe_type_toggle;
+	#define CQ_TERMINAL_TOGGLE				    0x1UL
+	#define CQ_TERMINAL_CQE_TYPE_MASK			    0x1eUL
+	#define CQ_TERMINAL_CQE_TYPE_SFT			    1
+	#define CQ_TERMINAL_CQE_TYPE_TERMINAL			   (0xeUL << 1)
+	#define CQ_TERMINAL_RESERVED3_MASK			    0xe0UL
+	#define CQ_TERMINAL_RESERVED3_SFT			    5
+	u8 status;
+	#define CQ_TERMINAL_STATUS_OK				   0x0UL
+	__le16 reserved16;
+	__le32 reserved32_2;
+};
+
+/* Cutoff CQE (32 bytes) */
+struct cq_cutoff {
+	__le64 reserved64_1;
+	__le64 reserved64_2;
+	__le64 reserved64_3;
+	u8 cqe_type_toggle;
+	#define CQ_CUTOFF_TOGGLE				    0x1UL
+	#define CQ_CUTOFF_CQE_TYPE_MASK			    0x1eUL
+	#define CQ_CUTOFF_CQE_TYPE_SFT				    1
+	#define CQ_CUTOFF_CQE_TYPE_CUT_OFF			   (0xfUL << 1)
+	#define CQ_CUTOFF_RESERVED3_MASK			    0xe0UL
+	#define CQ_CUTOFF_RESERVED3_SFT			    5
+	u8 status;
+	#define CQ_CUTOFF_STATUS_OK				   0x0UL
+	__le16 reserved16;
+	__le32 reserved32;
+};
+
+/* Notification Queue (NQ) Structures */
+/* Base NQ Record (16 bytes) */
+struct nq_base {
+	__le16 info10_type;
+	#define NQ_BASE_TYPE_MASK				    0x3fUL
+	#define NQ_BASE_TYPE_SFT				    0
+	#define NQ_BASE_TYPE_CQ_NOTIFICATION			   0x30UL
+	#define NQ_BASE_TYPE_SRQ_EVENT				   0x32UL
+	#define NQ_BASE_TYPE_DBQ_EVENT				   0x34UL
+	#define NQ_BASE_TYPE_QP_EVENT				   0x38UL
+	#define NQ_BASE_TYPE_FUNC_EVENT			   0x3aUL
+	#define NQ_BASE_INFO10_MASK				    0xffc0UL
+	#define NQ_BASE_INFO10_SFT				    6
+	__le16 info16;
+	__le32 info32;
+	__le32 info63_v[2];
+	#define NQ_BASE_V					    0x1UL
+	#define NQ_BASE_INFO63_MASK				    0xfffffffeUL
+	#define NQ_BASE_INFO63_SFT				    1
+};
+
+/* Completion Queue Notification (16 bytes) */
+struct nq_cn {
+	__le16 type;
+	#define NQ_CN_TYPE_MASK				    0x3fUL
+	#define NQ_CN_TYPE_SFT					    0
+	#define NQ_CN_TYPE_CQ_NOTIFICATION			   0x30UL
+	#define NQ_CN_RESERVED9_MASK				    0xffc0UL
+	#define NQ_CN_RESERVED9_SFT				    6
+	__le16 reserved16;
+	__le32 cq_handle_low;
+	__le32 v;
+	#define NQ_CN_V					    0x1UL
+	#define NQ_CN_RESERVED31_MASK				    0xfffffffeUL
+	#define NQ_CN_RESERVED31_SFT				    1
+	__le32 cq_handle_high;
+};
+
+/* SRQ Event Notification (16 bytes) */
+struct nq_srq_event {
+	u8 type;
+	#define NQ_SRQ_EVENT_TYPE_MASK				    0x3fUL
+	#define NQ_SRQ_EVENT_TYPE_SFT				    0
+	#define NQ_SRQ_EVENT_TYPE_SRQ_EVENT			   0x32UL
+	#define NQ_SRQ_EVENT_RESERVED1_MASK			    0xc0UL
+	#define NQ_SRQ_EVENT_RESERVED1_SFT			    6
+	u8 event;
+	#define NQ_SRQ_EVENT_EVENT_SRQ_THRESHOLD_EVENT		   0x1UL
+	__le16 reserved16;
+	__le32 srq_handle_low;
+	__le32 v;
+	#define NQ_SRQ_EVENT_V					    0x1UL
+	#define NQ_SRQ_EVENT_RESERVED31_MASK			    0xfffffffeUL
+	#define NQ_SRQ_EVENT_RESERVED31_SFT			    1
+	__le32 srq_handle_high;
+};
+
+/* DBQ Async Event Notification (16 bytes) */
+struct nq_dbq_event {
+	u8 type;
+	#define NQ_DBQ_EVENT_TYPE_MASK				    0x3fUL
+	#define NQ_DBQ_EVENT_TYPE_SFT				    0
+	#define NQ_DBQ_EVENT_TYPE_DBQ_EVENT			   0x34UL
+	#define NQ_DBQ_EVENT_RESERVED1_MASK			    0xc0UL
+	#define NQ_DBQ_EVENT_RESERVED1_SFT			    6
+	u8 event;
+	#define NQ_DBQ_EVENT_EVENT_DBQ_THRESHOLD_EVENT		   0x1UL
+	__le16 db_pfid;
+	#define NQ_DBQ_EVENT_DB_PFID_MASK			    0xfUL
+	#define NQ_DBQ_EVENT_DB_PFID_SFT			    0
+	#define NQ_DBQ_EVENT_RESERVED12_MASK			    0xfff0UL
+	#define NQ_DBQ_EVENT_RESERVED12_SFT			    4
+	__le32 db_dpi;
+	#define NQ_DBQ_EVENT_DB_DPI_MASK			    0xfffffUL
+	#define NQ_DBQ_EVENT_DB_DPI_SFT			    0
+	#define NQ_DBQ_EVENT_RESERVED12_2_MASK			    0xfff00000UL
+	#define NQ_DBQ_EVENT_RESERVED12_2_SFT			    20
+	__le32 v;
+	#define NQ_DBQ_EVENT_V					    0x1UL
+	#define NQ_DBQ_EVENT_RESERVED32_MASK			    0xfffffffeUL
+	#define NQ_DBQ_EVENT_RESERVED32_SFT			    1
+	__le32 db_type_db_xid;
+	#define NQ_DBQ_EVENT_DB_XID_MASK			    0xfffffUL
+	#define NQ_DBQ_EVENT_DB_XID_SFT			    0
+	#define NQ_DBQ_EVENT_RESERVED8_MASK			    0xff00000UL
+	#define NQ_DBQ_EVENT_RESERVED8_SFT			    20
+	#define NQ_DBQ_EVENT_DB_TYPE_MASK			    0xf0000000UL
+	#define NQ_DBQ_EVENT_DB_TYPE_SFT			    28
+};
+
+/* Read Request/Response Queue Structures */
+/* Input Read Request Queue (IRRQ) Message (32 bytes) */
+struct xrrq_irrq {
+	__le16 credits_type;
+	#define XRRQ_IRRQ_TYPE					    0x1UL
+	#define XRRQ_IRRQ_TYPE_READ_REQ			   0x0UL
+	#define XRRQ_IRRQ_TYPE_ATOMIC_REQ			   0x1UL
+	#define XRRQ_IRRQ_RESERVED10_MASK			    0x7feUL
+	#define XRRQ_IRRQ_RESERVED10_SFT			    1
+	#define XRRQ_IRRQ_CREDITS_MASK				    0xf800UL
+	#define XRRQ_IRRQ_CREDITS_SFT				    11
+	__le16 reserved16;
+	__le32 reserved32;
+	__le32 psn;
+	#define XRRQ_IRRQ_PSN_MASK				    0xffffffUL
+	#define XRRQ_IRRQ_PSN_SFT				    0
+	#define XRRQ_IRRQ_RESERVED8_1_MASK			    0xff000000UL
+	#define XRRQ_IRRQ_RESERVED8_1_SFT			    24
+	__le32 msn;
+	#define XRRQ_IRRQ_MSN_MASK				    0xffffffUL
+	#define XRRQ_IRRQ_MSN_SFT				    0
+	#define XRRQ_IRRQ_RESERVED8_2_MASK			    0xff000000UL
+	#define XRRQ_IRRQ_RESERVED8_2_SFT			    24
+	__le64 va_or_atomic_result;
+	__le32 rdma_r_key;
+	__le32 length;
+};
+
+/* Output Read Request Queue (ORRQ) Message (32 bytes) */
+struct xrrq_orrq {
+	__le16 num_sges_type;
+	#define XRRQ_ORRQ_TYPE					    0x1UL
+	#define XRRQ_ORRQ_TYPE_READ_REQ			   0x0UL
+	#define XRRQ_ORRQ_TYPE_ATOMIC_REQ			   0x1UL
+	#define XRRQ_ORRQ_RESERVED10_MASK			    0x7feUL
+	#define XRRQ_ORRQ_RESERVED10_SFT			    1
+	#define XRRQ_ORRQ_NUM_SGES_MASK			    0xf800UL
+	#define XRRQ_ORRQ_NUM_SGES_SFT				    11
+	__le16 reserved16;
+	__le32 length;
+	__le32 psn;
+	#define XRRQ_ORRQ_PSN_MASK				    0xffffffUL
+	#define XRRQ_ORRQ_PSN_SFT				    0
+	#define XRRQ_ORRQ_RESERVED8_1_MASK			    0xff000000UL
+	#define XRRQ_ORRQ_RESERVED8_1_SFT			    24
+	__le32 end_psn;
+	#define XRRQ_ORRQ_END_PSN_MASK				    0xffffffUL
+	#define XRRQ_ORRQ_END_PSN_SFT				    0
+	#define XRRQ_ORRQ_RESERVED8_2_MASK			    0xff000000UL
+	#define XRRQ_ORRQ_RESERVED8_2_SFT			    24
+	__le64 first_sge_phy_or_sing_sge_va;
+	__le32 single_sge_l_key;
+	__le32 single_sge_size;
+};
+
+/* Page Buffer List Memory Structures (PBL) */
+/* Page Table Entry (PTE) (8 bytes) */
+struct ptu_pte {
+	__le32 page_next_to_last_last_valid[2];
+	#define PTU_PTE_VALID					    0x1UL
+	#define PTU_PTE_LAST					    0x2UL
+	#define PTU_PTE_NEXT_TO_LAST				    0x4UL
+	#define PTU_PTE_PAGE_MASK				    0xfffff000UL
+	#define PTU_PTE_PAGE_SFT				    12
+};
+
+/* Page Directory Entry (PDE) (8 bytes) */
+struct ptu_pde {
+	__le32 page_valid[2];
+	#define PTU_PDE_VALID					    0x1UL
+	#define PTU_PDE_PAGE_MASK				    0xfffff000UL
+	#define PTU_PDE_PAGE_SFT				    12
+};
+
+/* RoCE Fastpath Host Structures */
+/* Command Queue (CMDQ) Interface */
+/* Init CMDQ (16 bytes) */
+struct cmdq_init {
+	__le64 cmdq_pbl;
+	__le16 cmdq_size_cmdq_lvl;
+	#define CMDQ_INIT_CMDQ_LVL_MASK			    0x3UL
+	#define CMDQ_INIT_CMDQ_LVL_SFT				    0
+	#define CMDQ_INIT_CMDQ_SIZE_MASK			    0xfffcUL
+	#define CMDQ_INIT_CMDQ_SIZE_SFT			    2
+	__le16 creq_ring_id;
+	__le32 prod_idx;
+};
+
+/* Update CMDQ producer index (16 bytes) */
+struct cmdq_update {
+	__le64 reserved64;
+	__le32 reserved32;
+	__le32 prod_idx;
+};
+
+/* CMDQ common header structure (16 bytes) */
+struct cmdq_base {
+	u8 opcode;
+	#define CMDQ_BASE_OPCODE_CREATE_QP			   0x1UL
+	#define CMDQ_BASE_OPCODE_DESTROY_QP			   0x2UL
+	#define CMDQ_BASE_OPCODE_MODIFY_QP			   0x3UL
+	#define CMDQ_BASE_OPCODE_QUERY_QP			   0x4UL
+	#define CMDQ_BASE_OPCODE_CREATE_SRQ			   0x5UL
+	#define CMDQ_BASE_OPCODE_DESTROY_SRQ			   0x6UL
+	#define CMDQ_BASE_OPCODE_QUERY_SRQ			   0x8UL
+	#define CMDQ_BASE_OPCODE_CREATE_CQ			   0x9UL
+	#define CMDQ_BASE_OPCODE_DESTROY_CQ			   0xaUL
+	#define CMDQ_BASE_OPCODE_RESIZE_CQ			   0xcUL
+	#define CMDQ_BASE_OPCODE_ALLOCATE_MRW			   0xdUL
+	#define CMDQ_BASE_OPCODE_DEALLOCATE_KEY		   0xeUL
+	#define CMDQ_BASE_OPCODE_REGISTER_MR			   0xfUL
+	#define CMDQ_BASE_OPCODE_DEREGISTER_MR			   0x10UL
+	#define CMDQ_BASE_OPCODE_ADD_GID			   0x11UL
+	#define CMDQ_BASE_OPCODE_DELETE_GID			   0x12UL
+	#define CMDQ_BASE_OPCODE_MODIFY_GID			   0x17UL
+	#define CMDQ_BASE_OPCODE_QUERY_GID			   0x18UL
+	#define CMDQ_BASE_OPCODE_CREATE_QP1			   0x13UL
+	#define CMDQ_BASE_OPCODE_DESTROY_QP1			   0x14UL
+	#define CMDQ_BASE_OPCODE_CREATE_AH			   0x15UL
+	#define CMDQ_BASE_OPCODE_DESTROY_AH			   0x16UL
+	#define CMDQ_BASE_OPCODE_INITIALIZE_FW			   0x80UL
+	#define CMDQ_BASE_OPCODE_DEINITIALIZE_FW		   0x81UL
+	#define CMDQ_BASE_OPCODE_STOP_FUNC			   0x82UL
+	#define CMDQ_BASE_OPCODE_QUERY_FUNC			   0x83UL
+	#define CMDQ_BASE_OPCODE_SET_FUNC_RESOURCES		   0x84UL
+	#define CMDQ_BASE_OPCODE_READ_CONTEXT			   0x85UL
+	#define CMDQ_BASE_OPCODE_VF_BACKCHANNEL_REQUEST	   0x86UL
+	#define CMDQ_BASE_OPCODE_READ_VF_MEMORY		   0x87UL
+	#define CMDQ_BASE_OPCODE_COMPLETE_VF_REQUEST		   0x88UL
+	#define CMDQ_BASE_OPCODE_EXTEND_CONTEXT_ARRRAY		   0x89UL
+	#define CMDQ_BASE_OPCODE_MAP_TC_TO_COS			   0x8aUL
+	#define CMDQ_BASE_OPCODE_QUERY_VERSION			   0x8bUL
+	#define CMDQ_BASE_OPCODE_MODIFY_CC			   0x8cUL
+	#define CMDQ_BASE_OPCODE_QUERY_CC			   0x8dUL
+	#define CMDQ_BASE_OPCODE_QUERY_ROCE_STATS	   0x8eUL
+	#define CMDQ_BASE_OPCODE_QUERY_ROCE_STATS_EXT      0x92UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+};
+
+/* Create QP command (96 bytes) */
+struct cmdq_create_qp {
+	u8 opcode;
+	#define CMDQ_CREATE_QP_OPCODE_CREATE_QP		   0x1UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le64 qp_handle;
+	__le32 qp_flags;
+	#define CMDQ_CREATE_QP_QP_FLAGS_SRQ_USED		   0x1UL
+	#define CMDQ_CREATE_QP_QP_FLAGS_FORCE_COMPLETION	   0x2UL
+	#define CMDQ_CREATE_QP_QP_FLAGS_RESERVED_LKEY_ENABLE      0x4UL
+	#define CMDQ_CREATE_QP_QP_FLAGS_FR_PMR_ENABLED		   0x8UL
+	#define CMDQ_CREATE_QP_QP_FLAGS_VARIABLE_SIZED_WQE_ENABLED 0x10UL
+	#define CMDQ_CREATE_QP_QP_FLAGS_EXT_STATS_ENABLED          0x80UL
+	#define CMDQ_CREATE_QP_QP_FLAGS_LAST	\
+		CMDQ_CREATE_QP_QP_FLAGS_EXT_STATS_ENABLED
+
+	u8 type;
+	#define CMDQ_CREATE_QP_TYPE_RC				   0x2UL
+	#define CMDQ_CREATE_QP_TYPE_UD				   0x4UL
+	#define CMDQ_CREATE_QP_TYPE_RAW_ETHERTYPE		   0x6UL
+	#define CMDQ_CREATE_QP_TYPE_GSI				   0x7UL
+	u8 sq_pg_size_sq_lvl;
+	#define CMDQ_CREATE_QP_SQ_LVL_MASK			    0xfUL
+	#define CMDQ_CREATE_QP_SQ_LVL_SFT			    0
+	#define CMDQ_CREATE_QP_SQ_LVL_LVL_0			   0x0UL
+	#define CMDQ_CREATE_QP_SQ_LVL_LVL_1			   0x1UL
+	#define CMDQ_CREATE_QP_SQ_LVL_LVL_2			   0x2UL
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_MASK			    0xf0UL
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_SFT			    4
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 rq_pg_size_rq_lvl;
+	#define CMDQ_CREATE_QP_RQ_LVL_MASK			    0xfUL
+	#define CMDQ_CREATE_QP_RQ_LVL_SFT			    0
+	#define CMDQ_CREATE_QP_RQ_LVL_LVL_0			   0x0UL
+	#define CMDQ_CREATE_QP_RQ_LVL_LVL_1			   0x1UL
+	#define CMDQ_CREATE_QP_RQ_LVL_LVL_2			   0x2UL
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_MASK			    0xf0UL
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_SFT			    4
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 unused_0;
+	__le32 dpi;
+	__le32 sq_size;
+	__le32 rq_size;
+	__le16 sq_fwo_sq_sge;
+	#define CMDQ_CREATE_QP_SQ_SGE_MASK			    0xfUL
+	#define CMDQ_CREATE_QP_SQ_SGE_SFT			    0
+	#define CMDQ_CREATE_QP_SQ_FWO_MASK			    0xfff0UL
+	#define CMDQ_CREATE_QP_SQ_FWO_SFT			    4
+	__le16 rq_fwo_rq_sge;
+	#define CMDQ_CREATE_QP_RQ_SGE_MASK			    0xfUL
+	#define CMDQ_CREATE_QP_RQ_SGE_SFT			    0
+	#define CMDQ_CREATE_QP_RQ_FWO_MASK			    0xfff0UL
+	#define CMDQ_CREATE_QP_RQ_FWO_SFT			    4
+	__le32 scq_cid;
+	__le32 rcq_cid;
+	__le32 srq_cid;
+	__le32 pd_id;
+	__le64 sq_pbl;
+	__le64 rq_pbl;
+	__le64 irrq_addr;
+	__le64 orrq_addr;
+};
+
+/* Destroy QP command (24 bytes) */
+struct cmdq_destroy_qp {
+	u8 opcode;
+	#define CMDQ_DESTROY_QP_OPCODE_DESTROY_QP		   0x2UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 qp_cid;
+	__le32 unused_0;
+};
+
+/* Modify QP command (112 bytes) */
+struct cmdq_modify_qp {
+	u8 opcode;
+	#define CMDQ_MODIFY_QP_OPCODE_MODIFY_QP		   0x3UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 modify_mask;
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_STATE		    0x1UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_EN_SQD_ASYNC_NOTIFY     0x2UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS		    0x4UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_PKEY		    0x8UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_QKEY		    0x10UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_DGID		    0x20UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL		    0x40UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX		    0x80UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT		    0x100UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS	    0x200UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC		    0x400UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU		    0x1000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_TIMEOUT		    0x2000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_RETRY_CNT		    0x4000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_RNR_RETRY		    0x8000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN		    0x10000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_RD_ATOMIC	    0x20000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER	    0x40000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_PSN		    0x80000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC      0x100000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SIZE		    0x200000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SIZE		    0x400000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SGE		    0x800000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SGE		    0x1000000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_INLINE_DATA	    0x2000000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID		    0x4000000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_SRC_MAC		    0x8000000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID		    0x10000000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_ENABLE_CC		    0x20000000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_TOS_ECN		    0x40000000UL
+	#define CMDQ_MODIFY_QP_MODIFY_MASK_TOS_DSCP		    0x80000000UL
+	__le32 qp_cid;
+	u8 network_type_en_sqd_async_notify_new_state;
+	#define CMDQ_MODIFY_QP_NEW_STATE_MASK			    0xfUL
+	#define CMDQ_MODIFY_QP_NEW_STATE_SFT			    0
+	#define CMDQ_MODIFY_QP_NEW_STATE_RESET			   0x0UL
+	#define CMDQ_MODIFY_QP_NEW_STATE_INIT			   0x1UL
+	#define CMDQ_MODIFY_QP_NEW_STATE_RTR			   0x2UL
+	#define CMDQ_MODIFY_QP_NEW_STATE_RTS			   0x3UL
+	#define CMDQ_MODIFY_QP_NEW_STATE_SQD			   0x4UL
+	#define CMDQ_MODIFY_QP_NEW_STATE_SQE			   0x5UL
+	#define CMDQ_MODIFY_QP_NEW_STATE_ERR			   0x6UL
+	#define CMDQ_MODIFY_QP_EN_SQD_ASYNC_NOTIFY		    0x10UL
+	#define CMDQ_MODIFY_QP_NETWORK_TYPE_MASK		    0xc0UL
+	#define CMDQ_MODIFY_QP_NETWORK_TYPE_SFT		    6
+	#define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV1		   (0x0UL << 6)
+	#define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV4	   (0x2UL << 6)
+	#define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV6	   (0x3UL << 6)
+	u8 access;
+	#define CMDQ_MODIFY_QP_ACCESS_LOCAL_WRITE		    0x1UL
+	#define CMDQ_MODIFY_QP_ACCESS_REMOTE_WRITE		    0x2UL
+	#define CMDQ_MODIFY_QP_ACCESS_REMOTE_READ		    0x4UL
+	#define CMDQ_MODIFY_QP_ACCESS_REMOTE_ATOMIC		    0x8UL
+	__le16 pkey;
+	__le32 qkey;
+	__le32 dgid[4];
+	__le32 flow_label;
+	__le16 sgid_index;
+	u8 hop_limit;
+	u8 traffic_class;
+	__le16 dest_mac[3];
+	u8 tos_dscp_tos_ecn;
+	#define CMDQ_MODIFY_QP_TOS_ECN_MASK			    0x3UL
+	#define CMDQ_MODIFY_QP_TOS_ECN_SFT			    0
+	#define CMDQ_MODIFY_QP_TOS_DSCP_MASK			    0xfcUL
+	#define CMDQ_MODIFY_QP_TOS_DSCP_SFT			    2
+	u8 path_mtu;
+	#define CMDQ_MODIFY_QP_PATH_MTU_MASK			    0xf0UL
+	#define CMDQ_MODIFY_QP_PATH_MTU_SFT			    4
+	#define CMDQ_MODIFY_QP_PATH_MTU_MTU_256		   (0x0UL << 4)
+	#define CMDQ_MODIFY_QP_PATH_MTU_MTU_512		   (0x1UL << 4)
+	#define CMDQ_MODIFY_QP_PATH_MTU_MTU_1024		   (0x2UL << 4)
+	#define CMDQ_MODIFY_QP_PATH_MTU_MTU_2048		   (0x3UL << 4)
+	#define CMDQ_MODIFY_QP_PATH_MTU_MTU_4096		   (0x4UL << 4)
+	#define CMDQ_MODIFY_QP_PATH_MTU_MTU_8192		   (0x5UL << 4)
+	u8 timeout;
+	u8 retry_cnt;
+	u8 rnr_retry;
+	u8 min_rnr_timer;
+	__le32 rq_psn;
+	__le32 sq_psn;
+	u8 max_rd_atomic;
+	u8 max_dest_rd_atomic;
+	__le16 enable_cc;
+	#define CMDQ_MODIFY_QP_ENABLE_CC			    0x1UL
+	__le32 sq_size;
+	__le32 rq_size;
+	__le16 sq_sge;
+	__le16 rq_sge;
+	__le32 max_inline_data;
+	__le32 dest_qp_id;
+	__le32 unused_3;
+	__le16 src_mac[3];
+	__le16 vlan_pcp_vlan_dei_vlan_id;
+	#define CMDQ_MODIFY_QP_VLAN_ID_MASK			    0xfffUL
+	#define CMDQ_MODIFY_QP_VLAN_ID_SFT			    0
+	#define CMDQ_MODIFY_QP_VLAN_DEI			    0x1000UL
+	#define CMDQ_MODIFY_QP_VLAN_PCP_MASK			    0xe000UL
+	#define CMDQ_MODIFY_QP_VLAN_PCP_SFT			    13
+};
+
+/* Query QP command (24 bytes) */
+struct cmdq_query_qp {
+	u8 opcode;
+	#define CMDQ_QUERY_QP_OPCODE_QUERY_QP			   0x4UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 qp_cid;
+	__le32 unused_0;
+};
+
+/* Create SRQ command (48 bytes) */
+struct cmdq_create_srq {
+	u8 opcode;
+	#define CMDQ_CREATE_SRQ_OPCODE_CREATE_SRQ		   0x5UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le64 srq_handle;
+	__le16 pg_size_lvl;
+	#define CMDQ_CREATE_SRQ_LVL_MASK			    0x3UL
+	#define CMDQ_CREATE_SRQ_LVL_SFT			    0
+	#define CMDQ_CREATE_SRQ_LVL_LVL_0			   0x0UL
+	#define CMDQ_CREATE_SRQ_LVL_LVL_1			   0x1UL
+	#define CMDQ_CREATE_SRQ_LVL_LVL_2			   0x2UL
+	#define CMDQ_CREATE_SRQ_PG_SIZE_MASK			    0x1cUL
+	#define CMDQ_CREATE_SRQ_PG_SIZE_SFT			    2
+	#define CMDQ_CREATE_SRQ_PG_SIZE_PG_4K			   (0x0UL << 2)
+	#define CMDQ_CREATE_SRQ_PG_SIZE_PG_8K			   (0x1UL << 2)
+	#define CMDQ_CREATE_SRQ_PG_SIZE_PG_64K			   (0x2UL << 2)
+	#define CMDQ_CREATE_SRQ_PG_SIZE_PG_2M			   (0x3UL << 2)
+	#define CMDQ_CREATE_SRQ_PG_SIZE_PG_8M			   (0x4UL << 2)
+	#define CMDQ_CREATE_SRQ_PG_SIZE_PG_1G			   (0x5UL << 2)
+	__le16 eventq_id;
+	#define CMDQ_CREATE_SRQ_EVENTQ_ID_MASK			    0xfffUL
+	#define CMDQ_CREATE_SRQ_EVENTQ_ID_SFT			    0
+	__le16 srq_size;
+	__le16 srq_fwo;
+	__le32 dpi;
+	__le32 pd_id;
+	__le64 pbl;
+};
+
+/* Destroy SRQ command (24 bytes) */
+struct cmdq_destroy_srq {
+	u8 opcode;
+	#define CMDQ_DESTROY_SRQ_OPCODE_DESTROY_SRQ		   0x6UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 srq_cid;
+	__le32 unused_0;
+};
+
+/* Query SRQ command (24 bytes) */
+struct cmdq_query_srq {
+	u8 opcode;
+	#define CMDQ_QUERY_SRQ_OPCODE_QUERY_SRQ		   0x8UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 srq_cid;
+	__le32 unused_0;
+};
+
+/* Create CQ command (48 bytes) */
+struct cmdq_create_cq {
+	u8 opcode;
+	#define CMDQ_CREATE_CQ_OPCODE_CREATE_CQ		   0x9UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le64 cq_handle;
+	__le32 pg_size_lvl;
+	#define CMDQ_CREATE_CQ_LVL_MASK			    0x3UL
+	#define CMDQ_CREATE_CQ_LVL_SFT				    0
+	#define CMDQ_CREATE_CQ_LVL_LVL_0			   0x0UL
+	#define CMDQ_CREATE_CQ_LVL_LVL_1			   0x1UL
+	#define CMDQ_CREATE_CQ_LVL_LVL_2			   0x2UL
+	#define CMDQ_CREATE_CQ_PG_SIZE_MASK			    0x1cUL
+	#define CMDQ_CREATE_CQ_PG_SIZE_SFT			    2
+	#define CMDQ_CREATE_CQ_PG_SIZE_PG_4K			   (0x0UL << 2)
+	#define CMDQ_CREATE_CQ_PG_SIZE_PG_8K			   (0x1UL << 2)
+	#define CMDQ_CREATE_CQ_PG_SIZE_PG_64K			   (0x2UL << 2)
+	#define CMDQ_CREATE_CQ_PG_SIZE_PG_2M			   (0x3UL << 2)
+	#define CMDQ_CREATE_CQ_PG_SIZE_PG_8M			   (0x4UL << 2)
+	#define CMDQ_CREATE_CQ_PG_SIZE_PG_1G			   (0x5UL << 2)
+	__le32 cq_fco_cnq_id;
+	#define CMDQ_CREATE_CQ_CNQ_ID_MASK			    0xfffUL
+	#define CMDQ_CREATE_CQ_CNQ_ID_SFT			    0
+	#define CMDQ_CREATE_CQ_CQ_FCO_MASK			    0xfffff000UL
+	#define CMDQ_CREATE_CQ_CQ_FCO_SFT			    12
+	__le32 dpi;
+	__le32 cq_size;
+	__le64 pbl;
+};
+
+/* Destroy CQ command (24 bytes) */
+struct cmdq_destroy_cq {
+	u8 opcode;
+	#define CMDQ_DESTROY_CQ_OPCODE_DESTROY_CQ		   0xaUL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 cq_cid;
+	__le32 unused_0;
+};
+
+/* Resize CQ command (40 bytes) */
+struct cmdq_resize_cq {
+	u8 opcode;
+	#define CMDQ_RESIZE_CQ_OPCODE_RESIZE_CQ		   0xcUL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 cq_cid;
+	__le32 new_cq_size_pg_size_lvl;
+	#define CMDQ_RESIZE_CQ_LVL_MASK			    0x3UL
+	#define CMDQ_RESIZE_CQ_LVL_SFT				    0
+	#define CMDQ_RESIZE_CQ_LVL_LVL_0			   0x0UL
+	#define CMDQ_RESIZE_CQ_LVL_LVL_1			   0x1UL
+	#define CMDQ_RESIZE_CQ_LVL_LVL_2			   0x2UL
+	#define CMDQ_RESIZE_CQ_PG_SIZE_MASK			    0x1cUL
+	#define CMDQ_RESIZE_CQ_PG_SIZE_SFT			    2
+	#define CMDQ_RESIZE_CQ_PG_SIZE_PG_4K			   (0x0UL << 2)
+	#define CMDQ_RESIZE_CQ_PG_SIZE_PG_8K			   (0x1UL << 2)
+	#define CMDQ_RESIZE_CQ_PG_SIZE_PG_64K			   (0x2UL << 2)
+	#define CMDQ_RESIZE_CQ_PG_SIZE_PG_2M			   (0x3UL << 2)
+	#define CMDQ_RESIZE_CQ_PG_SIZE_PG_8M			   (0x4UL << 2)
+	#define CMDQ_RESIZE_CQ_PG_SIZE_PG_1G			   (0x5UL << 2)
+	#define CMDQ_RESIZE_CQ_NEW_CQ_SIZE_MASK		    0x1fffe0UL
+	#define CMDQ_RESIZE_CQ_NEW_CQ_SIZE_SFT			    5
+	__le64 new_pbl;
+	__le32 new_cq_fco;
+	__le32 unused_2;
+};
+
+/* Allocate MRW command (32 bytes) */
+struct cmdq_allocate_mrw {
+	u8 opcode;
+	#define CMDQ_ALLOCATE_MRW_OPCODE_ALLOCATE_MRW		   0xdUL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le64 mrw_handle;
+	u8 mrw_flags;
+	#define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MASK		    0xfUL
+	#define CMDQ_ALLOCATE_MRW_MRW_FLAGS_SFT		    0
+	#define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MR			   0x0UL
+	#define CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR		   0x1UL
+	#define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE1		   0x2UL
+	#define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2A		   0x3UL
+	#define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B		   0x4UL
+	u8 access;
+	#define CMDQ_ALLOCATE_MRW_ACCESS_RESERVED_MASK		    0x1fUL
+	#define CMDQ_ALLOCATE_MRW_ACCESS_RESERVED_SFT		    0
+	#define CMDQ_ALLOCATE_MRW_ACCESS_CONSUMER_OWNED_KEY	    0x20UL
+	__le16 unused_1;
+	__le32 pd_id;
+};
+
+/* De-allocate key command (24 bytes) */
+struct cmdq_deallocate_key {
+	u8 opcode;
+	#define CMDQ_DEALLOCATE_KEY_OPCODE_DEALLOCATE_KEY	   0xeUL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	u8 mrw_flags;
+	#define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MASK		    0xfUL
+	#define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_SFT		    0
+	#define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MR		   0x0UL
+	#define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_PMR		   0x1UL
+	#define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE1		   0x2UL
+	#define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE2A	   0x3UL
+	#define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE2B	   0x4UL
+	u8 unused_1[3];
+	__le32 key;
+};
+
+/* Register MR command (48 bytes) */
+struct cmdq_register_mr {
+	u8 opcode;
+	#define CMDQ_REGISTER_MR_OPCODE_REGISTER_MR		   0xfUL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	u8 log2_pg_size_lvl;
+	#define CMDQ_REGISTER_MR_LVL_MASK			    0x3UL
+	#define CMDQ_REGISTER_MR_LVL_SFT			    0
+	#define CMDQ_REGISTER_MR_LVL_LVL_0			   0x0UL
+	#define CMDQ_REGISTER_MR_LVL_LVL_1			   0x1UL
+	#define CMDQ_REGISTER_MR_LVL_LVL_2			   0x2UL
+	#define CMDQ_REGISTER_MR_LVL_LAST             CMDQ_REGISTER_MR_LVL_LVL_2
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_MASK		    0x7cUL
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_SFT		    2
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_4K    (0xcUL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_8K    (0xdUL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_64K   (0x10UL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_256K  (0x12UL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1M    (0x14UL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_2M    (0x15UL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_4M    (0x16UL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1G    (0x1eUL << 2)
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_LAST	\
+					CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1G
+	#define CMDQ_REGISTER_MR_UNUSED1             0x80UL
+	u8 access;
+	#define CMDQ_REGISTER_MR_ACCESS_LOCAL_WRITE		    0x1UL
+	#define CMDQ_REGISTER_MR_ACCESS_REMOTE_READ		    0x2UL
+	#define CMDQ_REGISTER_MR_ACCESS_REMOTE_WRITE		    0x4UL
+	#define CMDQ_REGISTER_MR_ACCESS_REMOTE_ATOMIC		    0x8UL
+	#define CMDQ_REGISTER_MR_ACCESS_MW_BIND		    0x10UL
+	#define CMDQ_REGISTER_MR_ACCESS_ZERO_BASED		    0x20UL
+	__le16	log2_pbl_pg_size;
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_MASK   0x1fUL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_SFT    0
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_4K    0xcUL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_8K    0xdUL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_64K   0x10UL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_256K  0x12UL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1M    0x14UL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_2M    0x15UL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_4M    0x16UL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1G    0x1eUL
+	#define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_LAST    \
+				CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1G
+	#define CMDQ_REGISTER_MR_UNUSED11_MASK           0xffe0UL
+	#define CMDQ_REGISTER_MR_UNUSED11_SFT            5
+	__le32 key;
+	__le64 pbl;
+	__le64 va;
+	__le64 mr_size;
+};
+
+/* Deregister MR command (24 bytes) */
+struct cmdq_deregister_mr {
+	u8 opcode;
+	#define CMDQ_DEREGISTER_MR_OPCODE_DEREGISTER_MR	   0x10UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 lkey;
+	__le32 unused_0;
+};
+
+/* Add GID command (48 bytes) */
+struct cmdq_add_gid {
+	u8 opcode;
+	#define CMDQ_ADD_GID_OPCODE_ADD_GID			   0x11UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__be32 gid[4];
+	__be16 src_mac[3];
+	__le16 vlan;
+	#define CMDQ_ADD_GID_VLAN_VLAN_ID_MASK			    0xfffUL
+	#define CMDQ_ADD_GID_VLAN_VLAN_ID_SFT			    0
+	#define CMDQ_ADD_GID_VLAN_TPID_MASK			    0x7000UL
+	#define CMDQ_ADD_GID_VLAN_TPID_SFT			    12
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_88A8		   (0x0UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_8100		   (0x1UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_9100		   (0x2UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_9200		   (0x3UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_9300		   (0x4UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG1		   (0x5UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG2		   (0x6UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG3		   (0x7UL << 12)
+	#define CMDQ_ADD_GID_VLAN_TPID_LAST    CMDQ_ADD_GID_VLAN_TPID_TPID_CFG3
+	#define CMDQ_ADD_GID_VLAN_VLAN_EN			    0x8000UL
+	__le16 ipid;
+	__le16 stats_ctx;
+	#define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_ID_MASK	    0x7fffUL
+	#define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_ID_SFT	    0
+	#define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_VALID		    0x8000UL
+	__le32 unused_0;
+};
+
+/* Delete GID command (24 bytes) */
+struct cmdq_delete_gid {
+	u8 opcode;
+	#define CMDQ_DELETE_GID_OPCODE_DELETE_GID		   0x12UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le16 gid_index;
+	__le16 unused_0;
+	__le32 unused_1;
+};
+
+/* Modify GID command (48 bytes) */
+struct cmdq_modify_gid {
+	u8 opcode;
+	#define CMDQ_MODIFY_GID_OPCODE_MODIFY_GID		   0x17UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__be32 gid[4];
+	__be16 src_mac[3];
+	__le16 vlan;
+	#define CMDQ_MODIFY_GID_VLAN_VLAN_ID_MASK		    0xfffUL
+	#define CMDQ_MODIFY_GID_VLAN_VLAN_ID_SFT		    0
+	#define CMDQ_MODIFY_GID_VLAN_TPID_MASK			    0x7000UL
+	#define CMDQ_MODIFY_GID_VLAN_TPID_SFT			    12
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_88A8		   (0x0UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_8100		   (0x1UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9100		   (0x2UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9200		   (0x3UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9300		   (0x4UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG1		   (0x5UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG2		   (0x6UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG3		   (0x7UL << 12)
+	#define CMDQ_MODIFY_GID_VLAN_TPID_LAST		\
+					CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG3
+	#define CMDQ_MODIFY_GID_VLAN_VLAN_EN			    0x8000UL
+	__le16 ipid;
+	__le16 gid_index;
+	__le16 stats_ctx;
+	#define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_ID_MASK	    0x7fffUL
+	#define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_ID_SFT	    0
+	#define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_VALID	    0x8000UL
+	__le16 unused_0;
+};
+
+/* Query GID command (24 bytes) */
+struct cmdq_query_gid {
+	u8 opcode;
+	#define CMDQ_QUERY_GID_OPCODE_QUERY_GID		   0x18UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le16 gid_index;
+	__le16 unused_0;
+	__le32 unused_1;
+};
+
+/* Create QP1 command (80 bytes) */
+struct cmdq_create_qp1 {
+	u8 opcode;
+	#define CMDQ_CREATE_QP1_OPCODE_CREATE_QP1		   0x13UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le64 qp_handle;
+	__le32 qp_flags;
+	#define CMDQ_CREATE_QP1_QP_FLAGS_SRQ_USED		   0x1UL
+	#define CMDQ_CREATE_QP1_QP_FLAGS_FORCE_COMPLETION	   0x2UL
+	#define CMDQ_CREATE_QP1_QP_FLAGS_RESERVED_LKEY_ENABLE     0x4UL
+	u8 type;
+	#define CMDQ_CREATE_QP1_TYPE_GSI			   0x1UL
+	u8 sq_pg_size_sq_lvl;
+	#define CMDQ_CREATE_QP1_SQ_LVL_MASK			    0xfUL
+	#define CMDQ_CREATE_QP1_SQ_LVL_SFT			    0
+	#define CMDQ_CREATE_QP1_SQ_LVL_LVL_0			   0x0UL
+	#define CMDQ_CREATE_QP1_SQ_LVL_LVL_1			   0x1UL
+	#define CMDQ_CREATE_QP1_SQ_LVL_LVL_2			   0x2UL
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_SFT			    4
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 rq_pg_size_rq_lvl;
+	#define CMDQ_CREATE_QP1_RQ_LVL_MASK			    0xfUL
+	#define CMDQ_CREATE_QP1_RQ_LVL_SFT			    0
+	#define CMDQ_CREATE_QP1_RQ_LVL_LVL_0			   0x0UL
+	#define CMDQ_CREATE_QP1_RQ_LVL_LVL_1			   0x1UL
+	#define CMDQ_CREATE_QP1_RQ_LVL_LVL_2			   0x2UL
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_SFT			    4
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 unused_0;
+	__le32 dpi;
+	__le32 sq_size;
+	__le32 rq_size;
+	__le16 sq_fwo_sq_sge;
+	#define CMDQ_CREATE_QP1_SQ_SGE_MASK			    0xfUL
+	#define CMDQ_CREATE_QP1_SQ_SGE_SFT			    0
+	#define CMDQ_CREATE_QP1_SQ_FWO_MASK			    0xfff0UL
+	#define CMDQ_CREATE_QP1_SQ_FWO_SFT			    4
+	__le16 rq_fwo_rq_sge;
+	#define CMDQ_CREATE_QP1_RQ_SGE_MASK			    0xfUL
+	#define CMDQ_CREATE_QP1_RQ_SGE_SFT			    0
+	#define CMDQ_CREATE_QP1_RQ_FWO_MASK			    0xfff0UL
+	#define CMDQ_CREATE_QP1_RQ_FWO_SFT			    4
+	__le32 scq_cid;
+	__le32 rcq_cid;
+	__le32 srq_cid;
+	__le32 pd_id;
+	__le64 sq_pbl;
+	__le64 rq_pbl;
+};
+
+/* Destroy QP1 command (24 bytes) */
+struct cmdq_destroy_qp1 {
+	u8 opcode;
+	#define CMDQ_DESTROY_QP1_OPCODE_DESTROY_QP1		   0x14UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 qp1_cid;
+	__le32 unused_0;
+};
+
+/* Create AH command (64 bytes) */
+struct cmdq_create_ah {
+	u8 opcode;
+	#define CMDQ_CREATE_AH_OPCODE_CREATE_AH		   0x15UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le64 ah_handle;
+	__le32 dgid[4];
+	u8 type;
+	#define CMDQ_CREATE_AH_TYPE_V1				   0x0UL
+	#define CMDQ_CREATE_AH_TYPE_V2IPV4			   0x2UL
+	#define CMDQ_CREATE_AH_TYPE_V2IPV6			   0x3UL
+	u8 hop_limit;
+	__le16 sgid_index;
+	__le32 dest_vlan_id_flow_label;
+	#define CMDQ_CREATE_AH_FLOW_LABEL_MASK			    0xfffffUL
+	#define CMDQ_CREATE_AH_FLOW_LABEL_SFT			    0
+	#define CMDQ_CREATE_AH_DEST_VLAN_ID_MASK		    0xfff00000UL
+	#define CMDQ_CREATE_AH_DEST_VLAN_ID_SFT		    20
+	__le32 pd_id;
+	__le32 unused_0;
+	__le16 dest_mac[3];
+	u8 traffic_class;
+	u8 unused_1;
+};
+
+/* Destroy AH command (24 bytes) */
+struct cmdq_destroy_ah {
+	u8 opcode;
+	#define CMDQ_DESTROY_AH_OPCODE_DESTROY_AH		   0x16UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 ah_cid;
+	__le32 unused_0;
+};
+
+/* Initialize Firmware command (112 bytes) */
+struct cmdq_initialize_fw {
+	u8 opcode;
+	#define CMDQ_INITIALIZE_FW_OPCODE_INITIALIZE_FW	   0x80UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	u8 qpc_pg_size_qpc_lvl;
+	#define CMDQ_INITIALIZE_FW_QPC_LVL_MASK		    0xfUL
+	#define CMDQ_INITIALIZE_FW_QPC_LVL_SFT			    0
+	#define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_0		   0x0UL
+	#define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_1		   0x1UL
+	#define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_2		   0x2UL
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT		    4
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 mrw_pg_size_mrw_lvl;
+	#define CMDQ_INITIALIZE_FW_MRW_LVL_MASK		    0xfUL
+	#define CMDQ_INITIALIZE_FW_MRW_LVL_SFT			    0
+	#define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_0		   0x0UL
+	#define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_1		   0x1UL
+	#define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_2		   0x2UL
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_SFT		    4
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 srq_pg_size_srq_lvl;
+	#define CMDQ_INITIALIZE_FW_SRQ_LVL_MASK		    0xfUL
+	#define CMDQ_INITIALIZE_FW_SRQ_LVL_SFT			    0
+	#define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_0		   0x0UL
+	#define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_1		   0x1UL
+	#define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_2		   0x2UL
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_SFT		    4
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 cq_pg_size_cq_lvl;
+	#define CMDQ_INITIALIZE_FW_CQ_LVL_MASK			    0xfUL
+	#define CMDQ_INITIALIZE_FW_CQ_LVL_SFT			    0
+	#define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_0		   0x0UL
+	#define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_1		   0x1UL
+	#define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_2		   0x2UL
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_SFT		    4
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 tqm_pg_size_tqm_lvl;
+	#define CMDQ_INITIALIZE_FW_TQM_LVL_MASK		    0xfUL
+	#define CMDQ_INITIALIZE_FW_TQM_LVL_SFT			    0
+	#define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_0		   0x0UL
+	#define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_1		   0x1UL
+	#define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_2		   0x2UL
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_SFT		    4
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_1G		   (0x5UL << 4)
+	u8 tim_pg_size_tim_lvl;
+	#define CMDQ_INITIALIZE_FW_TIM_LVL_MASK		    0xfUL
+	#define CMDQ_INITIALIZE_FW_TIM_LVL_SFT			    0
+	#define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_0		   0x0UL
+	#define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_1		   0x1UL
+	#define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_2		   0x2UL
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_MASK		    0xf0UL
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_SFT		    4
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_4K		   (0x0UL << 4)
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8K		   (0x1UL << 4)
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_64K		   (0x2UL << 4)
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_2M		   (0x3UL << 4)
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8M		   (0x4UL << 4)
+	#define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_1G		   (0x5UL << 4)
+	/* This value is (log-base-2-of-DBR-page-size - 12).
+	 * 0 for 4KB. HW supported values are enumerated below.
+	 */
+	__le16  log2_dbr_pg_size;
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_MASK	0xfUL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_SFT		0
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4K	0x0UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8K	0x1UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16K	0x2UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32K	0x3UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64K	0x4UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128K	0x5UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_256K	0x6UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_512K	0x7UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_1M	0x8UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_2M	0x9UL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4M	0xaUL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8M	0xbUL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16M	0xcUL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32M	0xdUL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64M	0xeUL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M	0xfUL
+	#define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_LAST		\
+			CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M
+	__le64 qpc_page_dir;
+	__le64 mrw_page_dir;
+	__le64 srq_page_dir;
+	__le64 cq_page_dir;
+	__le64 tqm_page_dir;
+	__le64 tim_page_dir;
+	__le32 number_of_qp;
+	__le32 number_of_mrw;
+	__le32 number_of_srq;
+	__le32 number_of_cq;
+	__le32 max_qp_per_vf;
+	__le32 max_mrw_per_vf;
+	__le32 max_srq_per_vf;
+	__le32 max_cq_per_vf;
+	__le32 max_gid_per_vf;
+	__le32 stat_ctx_id;
+};
+
+/* De-initialize Firmware command (16 bytes) */
+struct cmdq_deinitialize_fw {
+	u8 opcode;
+	#define CMDQ_DEINITIALIZE_FW_OPCODE_DEINITIALIZE_FW       0x81UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+};
+
+/* Stop function command (16 bytes) */
+struct cmdq_stop_func {
+	u8 opcode;
+	#define CMDQ_STOP_FUNC_OPCODE_STOP_FUNC		   0x82UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+};
+
+/* Query function command (16 bytes) */
+struct cmdq_query_func {
+	u8 opcode;
+	#define CMDQ_QUERY_FUNC_OPCODE_QUERY_FUNC		   0x83UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+};
+
+/* Set function resources command (16 bytes) */
+struct cmdq_set_func_resources {
+	u8 opcode;
+	#define CMDQ_SET_FUNC_RESOURCES_OPCODE_SET_FUNC_RESOURCES 0x84UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 number_of_qp;
+	__le32 number_of_mrw;
+	__le32 number_of_srq;
+	__le32 number_of_cq;
+	__le32 max_qp_per_vf;
+	__le32 max_mrw_per_vf;
+	__le32 max_srq_per_vf;
+	__le32 max_cq_per_vf;
+	__le32 max_gid_per_vf;
+	__le32 stat_ctx_id;
+};
+
+/* Read hardware resource context command (24 bytes) */
+struct cmdq_read_context {
+	u8 opcode;
+	#define CMDQ_READ_CONTEXT_OPCODE_READ_CONTEXT		   0x85UL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le32 type_xid;
+	#define CMDQ_READ_CONTEXT_XID_MASK			    0xffffffUL
+	#define CMDQ_READ_CONTEXT_XID_SFT			    0
+	#define CMDQ_READ_CONTEXT_TYPE_MASK			    0xff000000UL
+	#define CMDQ_READ_CONTEXT_TYPE_SFT			    24
+	#define CMDQ_READ_CONTEXT_TYPE_QPC			   (0x0UL << 24)
+	#define CMDQ_READ_CONTEXT_TYPE_CQ			   (0x1UL << 24)
+	#define CMDQ_READ_CONTEXT_TYPE_MRW			   (0x2UL << 24)
+	#define CMDQ_READ_CONTEXT_TYPE_SRQ			   (0x3UL << 24)
+	__le32 unused_0;
+};
+
+/* Map TC to COS. Can only be issued from a PF (24 bytes) */
+struct cmdq_map_tc_to_cos {
+	u8 opcode;
+	#define CMDQ_MAP_TC_TO_COS_OPCODE_MAP_TC_TO_COS	   0x8aUL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+	__le16 cos0;
+	#define CMDQ_MAP_TC_TO_COS_COS0_NO_CHANGE		   0xffffUL
+	__le16 cos1;
+	#define CMDQ_MAP_TC_TO_COS_COS1_DISABLE		   0x8000UL
+	#define CMDQ_MAP_TC_TO_COS_COS1_NO_CHANGE		   0xffffUL
+	__le32 unused_0;
+};
+
+/* Query version command (16 bytes) */
+struct cmdq_query_version {
+	u8 opcode;
+	#define CMDQ_QUERY_VERSION_OPCODE_QUERY_VERSION	   0x8bUL
+	u8 cmd_size;
+	__le16 flags;
+	__le16 cookie;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 resp_addr;
+};
+
+/* Command-Response Event Queue (CREQ) Structures */
+/* Base CREQ Record (16 bytes) */
+struct creq_base {
+	u8 type;
+	#define CREQ_BASE_TYPE_MASK				    0x3fUL
+	#define CREQ_BASE_TYPE_SFT				    0
+	#define CREQ_BASE_TYPE_QP_EVENT			   0x38UL
+	#define CREQ_BASE_TYPE_FUNC_EVENT			   0x3aUL
+	#define CREQ_BASE_RESERVED2_MASK			    0xc0UL
+	#define CREQ_BASE_RESERVED2_SFT			    6
+	u8 reserved56[7];
+	u8 v;
+	#define CREQ_BASE_V					    0x1UL
+	#define CREQ_BASE_RESERVED7_MASK			    0xfeUL
+	#define CREQ_BASE_RESERVED7_SFT			    1
+	u8 event;
+	__le16 reserved48[3];
+};
+
+/* RoCE Function Async Event Notification (16 bytes) */
+struct creq_func_event {
+	u8 type;
+	#define CREQ_FUNC_EVENT_TYPE_MASK			    0x3fUL
+	#define CREQ_FUNC_EVENT_TYPE_SFT			    0
+	#define CREQ_FUNC_EVENT_TYPE_FUNC_EVENT		   0x3aUL
+	#define CREQ_FUNC_EVENT_RESERVED2_MASK			    0xc0UL
+	#define CREQ_FUNC_EVENT_RESERVED2_SFT			    6
+	u8 reserved56[7];
+	u8 v;
+	#define CREQ_FUNC_EVENT_V				    0x1UL
+	#define CREQ_FUNC_EVENT_RESERVED7_MASK			    0xfeUL
+	#define CREQ_FUNC_EVENT_RESERVED7_SFT			    1
+	u8 event;
+	#define CREQ_FUNC_EVENT_EVENT_TX_WQE_ERROR		   0x1UL
+	#define CREQ_FUNC_EVENT_EVENT_TX_DATA_ERROR		   0x2UL
+	#define CREQ_FUNC_EVENT_EVENT_RX_WQE_ERROR		   0x3UL
+	#define CREQ_FUNC_EVENT_EVENT_RX_DATA_ERROR		   0x4UL
+	#define CREQ_FUNC_EVENT_EVENT_CQ_ERROR			   0x5UL
+	#define CREQ_FUNC_EVENT_EVENT_TQM_ERROR		   0x6UL
+	#define CREQ_FUNC_EVENT_EVENT_CFCQ_ERROR		   0x7UL
+	#define CREQ_FUNC_EVENT_EVENT_CFCS_ERROR		   0x8UL
+	#define CREQ_FUNC_EVENT_EVENT_CFCC_ERROR		   0x9UL
+	#define CREQ_FUNC_EVENT_EVENT_CFCM_ERROR		   0xaUL
+	#define CREQ_FUNC_EVENT_EVENT_TIM_ERROR		   0xbUL
+	#define CREQ_FUNC_EVENT_EVENT_VF_COMM_REQUEST		   0x80UL
+	#define CREQ_FUNC_EVENT_EVENT_RESOURCE_EXHAUSTED	   0x81UL
+	__le16 reserved48[3];
+};
+
+/* RoCE Slowpath Command Completion (16 bytes) */
+struct creq_qp_event {
+	u8 type;
+	#define CREQ_QP_EVENT_TYPE_MASK			    0x3fUL
+	#define CREQ_QP_EVENT_TYPE_SFT				    0
+	#define CREQ_QP_EVENT_TYPE_QP_EVENT			   0x38UL
+	#define CREQ_QP_EVENT_RESERVED2_MASK			    0xc0UL
+	#define CREQ_QP_EVENT_RESERVED2_SFT			    6
+	u8 status;
+	__le16 cookie;
+	__le32 reserved32;
+	u8 v;
+	#define CREQ_QP_EVENT_V				    0x1UL
+	#define CREQ_QP_EVENT_RESERVED7_MASK			    0xfeUL
+	#define CREQ_QP_EVENT_RESERVED7_SFT			    1
+	u8 event;
+	#define CREQ_QP_EVENT_EVENT_CREATE_QP			   0x1UL
+	#define CREQ_QP_EVENT_EVENT_DESTROY_QP			   0x2UL
+	#define CREQ_QP_EVENT_EVENT_MODIFY_QP			   0x3UL
+	#define CREQ_QP_EVENT_EVENT_QUERY_QP			   0x4UL
+	#define CREQ_QP_EVENT_EVENT_CREATE_SRQ			   0x5UL
+	#define CREQ_QP_EVENT_EVENT_DESTROY_SRQ		   0x6UL
+	#define CREQ_QP_EVENT_EVENT_QUERY_SRQ			   0x8UL
+	#define CREQ_QP_EVENT_EVENT_CREATE_CQ			   0x9UL
+	#define CREQ_QP_EVENT_EVENT_DESTROY_CQ			   0xaUL
+	#define CREQ_QP_EVENT_EVENT_RESIZE_CQ			   0xcUL
+	#define CREQ_QP_EVENT_EVENT_ALLOCATE_MRW		   0xdUL
+	#define CREQ_QP_EVENT_EVENT_DEALLOCATE_KEY		   0xeUL
+	#define CREQ_QP_EVENT_EVENT_REGISTER_MR		   0xfUL
+	#define CREQ_QP_EVENT_EVENT_DEREGISTER_MR		   0x10UL
+	#define CREQ_QP_EVENT_EVENT_ADD_GID			   0x11UL
+	#define CREQ_QP_EVENT_EVENT_DELETE_GID			   0x12UL
+	#define CREQ_QP_EVENT_EVENT_MODIFY_GID			   0x17UL
+	#define CREQ_QP_EVENT_EVENT_QUERY_GID			   0x18UL
+	#define CREQ_QP_EVENT_EVENT_CREATE_QP1			   0x13UL
+	#define CREQ_QP_EVENT_EVENT_DESTROY_QP1		   0x14UL
+	#define CREQ_QP_EVENT_EVENT_CREATE_AH			   0x15UL
+	#define CREQ_QP_EVENT_EVENT_DESTROY_AH			   0x16UL
+	#define CREQ_QP_EVENT_EVENT_INITIALIZE_FW		   0x80UL
+	#define CREQ_QP_EVENT_EVENT_DEINITIALIZE_FW		   0x81UL
+	#define CREQ_QP_EVENT_EVENT_STOP_FUNC			   0x82UL
+	#define CREQ_QP_EVENT_EVENT_QUERY_FUNC			   0x83UL
+	#define CREQ_QP_EVENT_EVENT_SET_FUNC_RESOURCES		   0x84UL
+	#define CREQ_QP_EVENT_EVENT_MAP_TC_TO_COS		   0x8aUL
+	#define CREQ_QP_EVENT_EVENT_QUERY_VERSION		   0x8bUL
+	#define CREQ_QP_EVENT_EVENT_MODIFY_CC			   0x8cUL
+	#define CREQ_QP_EVENT_EVENT_QUERY_CC			   0x8dUL
+	#define CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION	   0xc0UL
+	__le16 reserved48[3];
+};
+
+/* Create QP command response (16 bytes) */
+struct creq_create_qp_resp {
+	u8 type;
+	#define CREQ_CREATE_QP_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_CREATE_QP_RESP_TYPE_SFT			    0
+	#define CREQ_CREATE_QP_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_CREATE_QP_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_CREATE_QP_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_CREATE_QP_RESP_V				    0x1UL
+	#define CREQ_CREATE_QP_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_CREATE_QP_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_CREATE_QP_RESP_EVENT_CREATE_QP		   0x1UL
+	__le16 reserved48[3];
+};
+
+/* Destroy QP command response (16 bytes) */
+struct creq_destroy_qp_resp {
+	u8 type;
+	#define CREQ_DESTROY_QP_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_DESTROY_QP_RESP_TYPE_SFT			    0
+	#define CREQ_DESTROY_QP_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DESTROY_QP_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_DESTROY_QP_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DESTROY_QP_RESP_V				    0x1UL
+	#define CREQ_DESTROY_QP_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_DESTROY_QP_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DESTROY_QP_RESP_EVENT_DESTROY_QP		   0x2UL
+	__le16 reserved48[3];
+};
+
+/* Modify QP command response (16 bytes) */
+struct creq_modify_qp_resp {
+	u8 type;
+	#define CREQ_MODIFY_QP_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_MODIFY_QP_RESP_TYPE_SFT			    0
+	#define CREQ_MODIFY_QP_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_MODIFY_QP_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_MODIFY_QP_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_MODIFY_QP_RESP_V				    0x1UL
+	#define CREQ_MODIFY_QP_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_MODIFY_QP_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_MODIFY_QP_RESP_EVENT_MODIFY_QP		   0x3UL
+	__le16 reserved48[3];
+};
+
+/* cmdq_query_roce_stats (size:128b/16B) */
+struct cmdq_query_roce_stats {
+	u8	opcode;
+	#define CMDQ_QUERY_ROCE_STATS_OPCODE_QUERY_ROCE_STATS 0x8eUL
+	#define CMDQ_QUERY_ROCE_STATS_OPCODE_LAST	\
+				CMDQ_QUERY_ROCE_STATS_OPCODE_QUERY_ROCE_STATS
+	u8	cmd_size;
+	__le16	flags;
+	__le16	cookie;
+	u8	resp_size;
+	u8	reserved8;
+	__le64	resp_addr;
+};
+
+/* Query QP command response (16 bytes) */
+struct creq_query_qp_resp {
+	u8 type;
+	#define CREQ_QUERY_QP_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_QUERY_QP_RESP_TYPE_SFT			    0
+	#define CREQ_QUERY_QP_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_QUERY_QP_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_QUERY_QP_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 size;
+	u8 v;
+	#define CREQ_QUERY_QP_RESP_V				    0x1UL
+	#define CREQ_QUERY_QP_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_QUERY_QP_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_QUERY_QP_RESP_EVENT_QUERY_QP		   0x4UL
+	__le16 reserved48[3];
+};
+
+/* Query QP command response side buffer structure (104 bytes) */
+struct creq_query_qp_resp_sb {
+	u8 opcode;
+	#define CREQ_QUERY_QP_RESP_SB_OPCODE_QUERY_QP		   0x4UL
+	u8 status;
+	__le16 cookie;
+	__le16 flags;
+	u8 resp_size;
+	u8 reserved8;
+	__le32 xid;
+	u8 en_sqd_async_notify_state;
+	#define CREQ_QUERY_QP_RESP_SB_STATE_MASK		    0xfUL
+	#define CREQ_QUERY_QP_RESP_SB_STATE_SFT		    0
+	#define CREQ_QUERY_QP_RESP_SB_STATE_RESET		   0x0UL
+	#define CREQ_QUERY_QP_RESP_SB_STATE_INIT		   0x1UL
+	#define CREQ_QUERY_QP_RESP_SB_STATE_RTR		   0x2UL
+	#define CREQ_QUERY_QP_RESP_SB_STATE_RTS		   0x3UL
+	#define CREQ_QUERY_QP_RESP_SB_STATE_SQD		   0x4UL
+	#define CREQ_QUERY_QP_RESP_SB_STATE_SQE		   0x5UL
+	#define CREQ_QUERY_QP_RESP_SB_STATE_ERR		   0x6UL
+	#define CREQ_QUERY_QP_RESP_SB_EN_SQD_ASYNC_NOTIFY	    0x10UL
+	u8 access;
+	#define CREQ_QUERY_QP_RESP_SB_ACCESS_LOCAL_WRITE	    0x1UL
+	#define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_WRITE	    0x2UL
+	#define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_READ	    0x4UL
+	#define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_ATOMIC	    0x8UL
+	__le16 pkey;
+	__le32 qkey;
+	__le32 reserved32;
+	__le32 dgid[4];
+	__le32 flow_label;
+	__le16 sgid_index;
+	u8 hop_limit;
+	u8 traffic_class;
+	__le16 dest_mac[3];
+	__le16 path_mtu_dest_vlan_id;
+	#define CREQ_QUERY_QP_RESP_SB_DEST_VLAN_ID_MASK	    0xfffUL
+	#define CREQ_QUERY_QP_RESP_SB_DEST_VLAN_ID_SFT		    0
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MASK		    0xf000UL
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_SFT		    12
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_256		   (0x0UL << 12)
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_512		   (0x1UL << 12)
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_1024	   (0x2UL << 12)
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_2048	   (0x3UL << 12)
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_4096	   (0x4UL << 12)
+	#define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_8192	   (0x5UL << 12)
+	u8 timeout;
+	u8 retry_cnt;
+	u8 rnr_retry;
+	u8 min_rnr_timer;
+	__le32 rq_psn;
+	__le32 sq_psn;
+	u8 max_rd_atomic;
+	u8 max_dest_rd_atomic;
+	u8 tos_dscp_tos_ecn;
+	#define CREQ_QUERY_QP_RESP_SB_TOS_ECN_MASK		    0x3UL
+	#define CREQ_QUERY_QP_RESP_SB_TOS_ECN_SFT		    0
+	#define CREQ_QUERY_QP_RESP_SB_TOS_DSCP_MASK		    0xfcUL
+	#define CREQ_QUERY_QP_RESP_SB_TOS_DSCP_SFT		    2
+	u8 enable_cc;
+	#define CREQ_QUERY_QP_RESP_SB_ENABLE_CC		    0x1UL
+	#define CREQ_QUERY_QP_RESP_SB_RESERVED7_MASK		    0xfeUL
+	#define CREQ_QUERY_QP_RESP_SB_RESERVED7_SFT		    1
+	__le32 sq_size;
+	__le32 rq_size;
+	__le16 sq_sge;
+	__le16 rq_sge;
+	__le32 max_inline_data;
+	__le32 dest_qp_id;
+	__le32 unused_1;
+	__le16 src_mac[3];
+	__le16 vlan_pcp_vlan_dei_vlan_id;
+	#define CREQ_QUERY_QP_RESP_SB_VLAN_ID_MASK		    0xfffUL
+	#define CREQ_QUERY_QP_RESP_SB_VLAN_ID_SFT		    0
+	#define CREQ_QUERY_QP_RESP_SB_VLAN_DEI			    0x1000UL
+	#define CREQ_QUERY_QP_RESP_SB_VLAN_PCP_MASK		    0xe000UL
+	#define CREQ_QUERY_QP_RESP_SB_VLAN_PCP_SFT		    13
+};
+
+/* Create SRQ command response (16 bytes) */
+struct creq_create_srq_resp {
+	u8 type;
+	#define CREQ_CREATE_SRQ_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_CREATE_SRQ_RESP_TYPE_SFT			    0
+	#define CREQ_CREATE_SRQ_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_CREATE_SRQ_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_CREATE_SRQ_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_CREATE_SRQ_RESP_V				    0x1UL
+	#define CREQ_CREATE_SRQ_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_CREATE_SRQ_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_CREATE_SRQ_RESP_EVENT_CREATE_SRQ		   0x5UL
+	__le16 reserved48[3];
+};
+
+/* Destroy SRQ command response (16 bytes) */
+struct creq_destroy_srq_resp {
+	u8 type;
+	#define CREQ_DESTROY_SRQ_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_DESTROY_SRQ_RESP_TYPE_SFT			    0
+	#define CREQ_DESTROY_SRQ_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DESTROY_SRQ_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_DESTROY_SRQ_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DESTROY_SRQ_RESP_V			    0x1UL
+	#define CREQ_DESTROY_SRQ_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_DESTROY_SRQ_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DESTROY_SRQ_RESP_EVENT_DESTROY_SRQ	   0x6UL
+	__le16 enable_for_arm[3];
+	#define CREQ_DESTROY_SRQ_RESP_ENABLE_FOR_ARM_MASK	    0x30000UL
+	#define CREQ_DESTROY_SRQ_RESP_ENABLE_FOR_ARM_SFT	    16
+	#define CREQ_DESTROY_SRQ_RESP_RESERVED46_MASK		    0xfffc0000UL
+	#define CREQ_DESTROY_SRQ_RESP_RESERVED46_SFT		    18
+};
+
+/* Query SRQ command response (16 bytes) */
+struct creq_query_srq_resp {
+	u8 type;
+	#define CREQ_QUERY_SRQ_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_QUERY_SRQ_RESP_TYPE_SFT			    0
+	#define CREQ_QUERY_SRQ_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_QUERY_SRQ_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_QUERY_SRQ_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 size;
+	u8 v;
+	#define CREQ_QUERY_SRQ_RESP_V				    0x1UL
+	#define CREQ_QUERY_SRQ_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_QUERY_SRQ_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_QUERY_SRQ_RESP_EVENT_QUERY_SRQ		   0x8UL
+	__le16 reserved48[3];
+};
+
+/* Query SRQ command response side buffer structure (24 bytes) */
+struct creq_query_srq_resp_sb {
+	u8 opcode;
+	#define CREQ_QUERY_SRQ_RESP_SB_OPCODE_QUERY_SRQ	   0x8UL
+	u8 status;
+	__le16 cookie;
+	__le16 flags;
+	u8 resp_size;
+	u8 reserved8;
+	__le32 xid;
+	__le16 srq_limit;
+	__le16 reserved16;
+	__le32 data[4];
+};
+
+/* Create CQ command Response (16 bytes) */
+struct creq_create_cq_resp {
+	u8 type;
+	#define CREQ_CREATE_CQ_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_CREATE_CQ_RESP_TYPE_SFT			    0
+	#define CREQ_CREATE_CQ_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_CREATE_CQ_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_CREATE_CQ_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_CREATE_CQ_RESP_V				    0x1UL
+	#define CREQ_CREATE_CQ_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_CREATE_CQ_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_CREATE_CQ_RESP_EVENT_CREATE_CQ		   0x9UL
+	__le16 reserved48[3];
+};
+
+/* Destroy CQ command response (16 bytes) */
+struct creq_destroy_cq_resp {
+	u8 type;
+	#define CREQ_DESTROY_CQ_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_DESTROY_CQ_RESP_TYPE_SFT			    0
+	#define CREQ_DESTROY_CQ_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DESTROY_CQ_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_DESTROY_CQ_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DESTROY_CQ_RESP_V				    0x1UL
+	#define CREQ_DESTROY_CQ_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_DESTROY_CQ_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DESTROY_CQ_RESP_EVENT_DESTROY_CQ		   0xaUL
+	__le16 cq_arm_lvl;
+	#define CREQ_DESTROY_CQ_RESP_CQ_ARM_LVL_MASK		    0x3UL
+	#define CREQ_DESTROY_CQ_RESP_CQ_ARM_LVL_SFT		    0
+	#define CREQ_DESTROY_CQ_RESP_RESERVED14_MASK		    0xfffcUL
+	#define CREQ_DESTROY_CQ_RESP_RESERVED14_SFT		    2
+	__le16 total_cnq_events;
+	__le16 reserved16;
+};
+
+/* Resize CQ command response (16 bytes) */
+struct creq_resize_cq_resp {
+	u8 type;
+	#define CREQ_RESIZE_CQ_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_RESIZE_CQ_RESP_TYPE_SFT			    0
+	#define CREQ_RESIZE_CQ_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_RESIZE_CQ_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_RESIZE_CQ_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_RESIZE_CQ_RESP_V				    0x1UL
+	#define CREQ_RESIZE_CQ_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_RESIZE_CQ_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_RESIZE_CQ_RESP_EVENT_RESIZE_CQ		   0xcUL
+	__le16 reserved48[3];
+};
+
+/* Allocate MRW command response (16 bytes) */
+struct creq_allocate_mrw_resp {
+	u8 type;
+	#define CREQ_ALLOCATE_MRW_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_ALLOCATE_MRW_RESP_TYPE_SFT		    0
+	#define CREQ_ALLOCATE_MRW_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_ALLOCATE_MRW_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_ALLOCATE_MRW_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_ALLOCATE_MRW_RESP_V			    0x1UL
+	#define CREQ_ALLOCATE_MRW_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_ALLOCATE_MRW_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_ALLOCATE_MRW_RESP_EVENT_ALLOCATE_MRW	   0xdUL
+	__le16 reserved48[3];
+};
+
+/* De-allocate key command response (16 bytes) */
+struct creq_deallocate_key_resp {
+	u8 type;
+	#define CREQ_DEALLOCATE_KEY_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_DEALLOCATE_KEY_RESP_TYPE_SFT		    0
+	#define CREQ_DEALLOCATE_KEY_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DEALLOCATE_KEY_RESP_RESERVED2_MASK	    0xc0UL
+	#define CREQ_DEALLOCATE_KEY_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DEALLOCATE_KEY_RESP_V			    0x1UL
+	#define CREQ_DEALLOCATE_KEY_RESP_RESERVED7_MASK	    0xfeUL
+	#define CREQ_DEALLOCATE_KEY_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DEALLOCATE_KEY_RESP_EVENT_DEALLOCATE_KEY     0xeUL
+	__le16 reserved16;
+	__le32 bound_window_info;
+};
+
+/* Register MR command response (16 bytes) */
+struct creq_register_mr_resp {
+	u8 type;
+	#define CREQ_REGISTER_MR_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_REGISTER_MR_RESP_TYPE_SFT			    0
+	#define CREQ_REGISTER_MR_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_REGISTER_MR_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_REGISTER_MR_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_REGISTER_MR_RESP_V			    0x1UL
+	#define CREQ_REGISTER_MR_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_REGISTER_MR_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_REGISTER_MR_RESP_EVENT_REGISTER_MR	   0xfUL
+	__le16 reserved48[3];
+};
+
+/* Deregister MR command response (16 bytes) */
+struct creq_deregister_mr_resp {
+	u8 type;
+	#define CREQ_DEREGISTER_MR_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_DEREGISTER_MR_RESP_TYPE_SFT		    0
+	#define CREQ_DEREGISTER_MR_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DEREGISTER_MR_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_DEREGISTER_MR_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DEREGISTER_MR_RESP_V			    0x1UL
+	#define CREQ_DEREGISTER_MR_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_DEREGISTER_MR_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DEREGISTER_MR_RESP_EVENT_DEREGISTER_MR       0x10UL
+	__le16 reserved16;
+	__le32 bound_windows;
+};
+
+/* Add GID command response (16 bytes) */
+struct creq_add_gid_resp {
+	u8 type;
+	#define CREQ_ADD_GID_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_ADD_GID_RESP_TYPE_SFT			    0
+	#define CREQ_ADD_GID_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_ADD_GID_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_ADD_GID_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_ADD_GID_RESP_V				    0x1UL
+	#define CREQ_ADD_GID_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_ADD_GID_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_ADD_GID_RESP_EVENT_ADD_GID		   0x11UL
+	__le16 reserved48[3];
+};
+
+/* Delete GID command response (16 bytes) */
+struct creq_delete_gid_resp {
+	u8 type;
+	#define CREQ_DELETE_GID_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_DELETE_GID_RESP_TYPE_SFT			    0
+	#define CREQ_DELETE_GID_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DELETE_GID_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_DELETE_GID_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DELETE_GID_RESP_V				    0x1UL
+	#define CREQ_DELETE_GID_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_DELETE_GID_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DELETE_GID_RESP_EVENT_DELETE_GID		   0x12UL
+	__le16 reserved48[3];
+};
+
+/* Modify GID command response (16 bytes) */
+struct creq_modify_gid_resp {
+	u8 type;
+	#define CREQ_MODIFY_GID_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_MODIFY_GID_RESP_TYPE_SFT			    0
+	#define CREQ_MODIFY_GID_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_MODIFY_GID_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_MODIFY_GID_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_MODIFY_GID_RESP_V				    0x1UL
+	#define CREQ_MODIFY_GID_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_MODIFY_GID_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_MODIFY_GID_RESP_EVENT_ADD_GID		   0x11UL
+	__le16 reserved48[3];
+};
+
+/* Query GID command response (16 bytes) */
+struct creq_query_gid_resp {
+	u8 type;
+	#define CREQ_QUERY_GID_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_QUERY_GID_RESP_TYPE_SFT			    0
+	#define CREQ_QUERY_GID_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_QUERY_GID_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_QUERY_GID_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 size;
+	u8 v;
+	#define CREQ_QUERY_GID_RESP_V				    0x1UL
+	#define CREQ_QUERY_GID_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_QUERY_GID_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_QUERY_GID_RESP_EVENT_QUERY_GID		   0x18UL
+	__le16 reserved48[3];
+};
+
+/* Query GID command response side buffer structure (40 bytes) */
+struct creq_query_gid_resp_sb {
+	u8 opcode;
+	#define CREQ_QUERY_GID_RESP_SB_OPCODE_QUERY_GID	   0x18UL
+	u8 status;
+	__le16 cookie;
+	__le16 flags;
+	u8 resp_size;
+	u8 reserved8;
+	__le32 gid[4];
+	__le16 src_mac[3];
+	__le16 vlan;
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_ID_MASK	    0xfffUL
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_ID_SFT	    0
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_MASK		    0x7000UL
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_SFT		    12
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_88A8	   (0x0UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_8100	   (0x1UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9100	   (0x2UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9200	   (0x3UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9300	   (0x4UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG1	   (0x5UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG2	   (0x6UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG3	   (0x7UL << 12)
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_LAST	\
+				CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG3
+	#define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_EN		    0x8000UL
+	__le16 ipid;
+	__le16 gid_index;
+	__le32 unused_0;
+};
+
+/* Create QP1 command response (16 bytes) */
+struct creq_create_qp1_resp {
+	u8 type;
+	#define CREQ_CREATE_QP1_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_CREATE_QP1_RESP_TYPE_SFT			    0
+	#define CREQ_CREATE_QP1_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_CREATE_QP1_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_CREATE_QP1_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_CREATE_QP1_RESP_V				    0x1UL
+	#define CREQ_CREATE_QP1_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_CREATE_QP1_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_CREATE_QP1_RESP_EVENT_CREATE_QP1		   0x13UL
+	__le16 reserved48[3];
+};
+
+/* Destroy QP1 command response (16 bytes) */
+struct creq_destroy_qp1_resp {
+	u8 type;
+	#define CREQ_DESTROY_QP1_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_DESTROY_QP1_RESP_TYPE_SFT			    0
+	#define CREQ_DESTROY_QP1_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DESTROY_QP1_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_DESTROY_QP1_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DESTROY_QP1_RESP_V			    0x1UL
+	#define CREQ_DESTROY_QP1_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_DESTROY_QP1_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DESTROY_QP1_RESP_EVENT_DESTROY_QP1	   0x14UL
+	__le16 reserved48[3];
+};
+
+/* Create AH command response (16 bytes) */
+struct creq_create_ah_resp {
+	u8 type;
+	#define CREQ_CREATE_AH_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_CREATE_AH_RESP_TYPE_SFT			    0
+	#define CREQ_CREATE_AH_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_CREATE_AH_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_CREATE_AH_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_CREATE_AH_RESP_V				    0x1UL
+	#define CREQ_CREATE_AH_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_CREATE_AH_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_CREATE_AH_RESP_EVENT_CREATE_AH		   0x15UL
+	__le16 reserved48[3];
+};
+
+/* Destroy AH command response (16 bytes) */
+struct creq_destroy_ah_resp {
+	u8 type;
+	#define CREQ_DESTROY_AH_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_DESTROY_AH_RESP_TYPE_SFT			    0
+	#define CREQ_DESTROY_AH_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_DESTROY_AH_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_DESTROY_AH_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 xid;
+	u8 v;
+	#define CREQ_DESTROY_AH_RESP_V				    0x1UL
+	#define CREQ_DESTROY_AH_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_DESTROY_AH_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_DESTROY_AH_RESP_EVENT_DESTROY_AH		   0x16UL
+	__le16 reserved48[3];
+};
+
+/* Initialize Firmware command response (16 bytes) */
+struct creq_initialize_fw_resp {
+	u8 type;
+	#define CREQ_INITIALIZE_FW_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_INITIALIZE_FW_RESP_TYPE_SFT		    0
+	#define CREQ_INITIALIZE_FW_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_INITIALIZE_FW_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_INITIALIZE_FW_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 reserved32;
+	u8 v;
+	#define CREQ_INITIALIZE_FW_RESP_V			    0x1UL
+	#define CREQ_INITIALIZE_FW_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_INITIALIZE_FW_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_INITIALIZE_FW_RESP_EVENT_INITIALIZE_FW       0x80UL
+	__le16 reserved48[3];
+};
+
+/* De-initialize Firmware command response (16 bytes) */
+struct creq_deinitialize_fw_resp {
+	u8 type;
+	#define CREQ_DEINITIALIZE_FW_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_DEINITIALIZE_FW_RESP_TYPE_SFT		    0
+	#define CREQ_DEINITIALIZE_FW_RESP_TYPE_QP_EVENT	   0x38UL
+	#define CREQ_DEINITIALIZE_FW_RESP_RESERVED2_MASK	    0xc0UL
+	#define CREQ_DEINITIALIZE_FW_RESP_RESERVED2_SFT	    6
+	u8 status;
+	__le16 cookie;
+	__le32 reserved32;
+	u8 v;
+	#define CREQ_DEINITIALIZE_FW_RESP_V			    0x1UL
+	#define CREQ_DEINITIALIZE_FW_RESP_RESERVED7_MASK	    0xfeUL
+	#define CREQ_DEINITIALIZE_FW_RESP_RESERVED7_SFT	    1
+	u8 event;
+	#define CREQ_DEINITIALIZE_FW_RESP_EVENT_DEINITIALIZE_FW   0x81UL
+	__le16 reserved48[3];
+};
+
+/* Stop function command response (16 bytes) */
+struct creq_stop_func_resp {
+	u8 type;
+	#define CREQ_STOP_FUNC_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_STOP_FUNC_RESP_TYPE_SFT			    0
+	#define CREQ_STOP_FUNC_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_STOP_FUNC_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_STOP_FUNC_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 reserved32;
+	u8 v;
+	#define CREQ_STOP_FUNC_RESP_V				    0x1UL
+	#define CREQ_STOP_FUNC_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_STOP_FUNC_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_STOP_FUNC_RESP_EVENT_STOP_FUNC		   0x82UL
+	__le16 reserved48[3];
+};
+
+/* Query function command response (16 bytes) */
+struct creq_query_func_resp {
+	u8 type;
+	#define CREQ_QUERY_FUNC_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_QUERY_FUNC_RESP_TYPE_SFT			    0
+	#define CREQ_QUERY_FUNC_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_QUERY_FUNC_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_QUERY_FUNC_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 size;
+	u8 v;
+	#define CREQ_QUERY_FUNC_RESP_V				    0x1UL
+	#define CREQ_QUERY_FUNC_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_QUERY_FUNC_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_QUERY_FUNC_RESP_EVENT_QUERY_FUNC		   0x83UL
+	__le16 reserved48[3];
+};
+
+/* Query function command response side buffer structure (88 bytes) */
+struct creq_query_func_resp_sb {
+	u8 opcode;
+	#define CREQ_QUERY_FUNC_RESP_SB_OPCODE_QUERY_FUNC	   0x83UL
+	u8 status;
+	__le16 cookie;
+	__le16 flags;
+	u8 resp_size;
+	u8 reserved8;
+	__le64 max_mr_size;
+	__le32 max_qp;
+	__le16 max_qp_wr;
+	__le16 dev_cap_flags;
+	#define CREQ_QUERY_FUNC_RESP_SB_DEV_CAP_FLAGS_RESIZE_QP   0x1UL
+	#define CREQ_QUERY_FUNC_RESP_SB_EXT_STATS                 0x10UL
+	__le32 max_cq;
+	__le32 max_cqe;
+	__le32 max_pd;
+	u8 max_sge;
+	u8 max_srq_sge;
+	u8 max_qp_rd_atom;
+	u8 max_qp_init_rd_atom;
+	__le32 max_mr;
+	__le32 max_mw;
+	__le32 max_raw_eth_qp;
+	__le32 max_ah;
+	__le32 max_fmr;
+	__le32 max_srq_wr;
+	__le32 max_pkeys;
+	__le32 max_inline_data;
+	u8 max_map_per_fmr;
+	u8 l2_db_space_size;
+	__le16 max_srq;
+	__le32 max_gid;
+	__le32 tqm_alloc_reqs[12];
+	__le32 max_dpi;
+	__le32 reserved_32;
+};
+
+/* Set resources command response (16 bytes) */
+struct creq_set_func_resources_resp {
+	u8 type;
+	#define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_SFT		    0
+	#define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_QP_EVENT	   0x38UL
+	#define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED2_MASK	    0xc0UL
+	#define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED2_SFT	    6
+	u8 status;
+	__le16 cookie;
+	__le32 reserved32;
+	u8 v;
+	#define CREQ_SET_FUNC_RESOURCES_RESP_V			    0x1UL
+	#define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED7_MASK	    0xfeUL
+	#define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED7_SFT	    1
+	u8 event;
+	#define CREQ_SET_FUNC_RESOURCES_RESP_EVENT_SET_FUNC_RESOURCES 0x84UL
+	__le16 reserved48[3];
+};
+
+/* Map TC to COS response (16 bytes) */
+struct creq_map_tc_to_cos_resp {
+	u8 type;
+	#define CREQ_MAP_TC_TO_COS_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_MAP_TC_TO_COS_RESP_TYPE_SFT		    0
+	#define CREQ_MAP_TC_TO_COS_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_MAP_TC_TO_COS_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_MAP_TC_TO_COS_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 reserved32;
+	u8 v;
+	#define CREQ_MAP_TC_TO_COS_RESP_V			    0x1UL
+	#define CREQ_MAP_TC_TO_COS_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_MAP_TC_TO_COS_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_MAP_TC_TO_COS_RESP_EVENT_MAP_TC_TO_COS       0x8aUL
+	__le16 reserved48[3];
+};
+
+/* Query version response (16 bytes) */
+struct creq_query_version_resp {
+	u8 type;
+	#define CREQ_QUERY_VERSION_RESP_TYPE_MASK		    0x3fUL
+	#define CREQ_QUERY_VERSION_RESP_TYPE_SFT		    0
+	#define CREQ_QUERY_VERSION_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_QUERY_VERSION_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_QUERY_VERSION_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	u8 fw_maj;
+	u8 fw_minor;
+	u8 fw_bld;
+	u8 fw_rsvd;
+	u8 v;
+	#define CREQ_QUERY_VERSION_RESP_V			    0x1UL
+	#define CREQ_QUERY_VERSION_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_QUERY_VERSION_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_QUERY_VERSION_RESP_EVENT_QUERY_VERSION       0x8bUL
+	__le16 reserved16;
+	u8 intf_maj;
+	u8 intf_minor;
+	u8 intf_bld;
+	u8 intf_rsvd;
+};
+
+/* Modify congestion control command response (16 bytes) */
+struct creq_modify_cc_resp {
+	u8 type;
+	#define CREQ_MODIFY_CC_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_MODIFY_CC_RESP_TYPE_SFT			    0
+	#define CREQ_MODIFY_CC_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_MODIFY_CC_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_MODIFY_CC_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 reserved32;
+	u8 v;
+	#define CREQ_MODIFY_CC_RESP_V				    0x1UL
+	#define CREQ_MODIFY_CC_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_MODIFY_CC_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_MODIFY_CC_RESP_EVENT_MODIFY_CC		   0x8cUL
+	__le16 reserved48[3];
+};
+
+/* Query congestion control command response (16 bytes) */
+struct creq_query_cc_resp {
+	u8 type;
+	#define CREQ_QUERY_CC_RESP_TYPE_MASK			    0x3fUL
+	#define CREQ_QUERY_CC_RESP_TYPE_SFT			    0
+	#define CREQ_QUERY_CC_RESP_TYPE_QP_EVENT		   0x38UL
+	#define CREQ_QUERY_CC_RESP_RESERVED2_MASK		    0xc0UL
+	#define CREQ_QUERY_CC_RESP_RESERVED2_SFT		    6
+	u8 status;
+	__le16 cookie;
+	__le32 size;
+	u8 v;
+	#define CREQ_QUERY_CC_RESP_V				    0x1UL
+	#define CREQ_QUERY_CC_RESP_RESERVED7_MASK		    0xfeUL
+	#define CREQ_QUERY_CC_RESP_RESERVED7_SFT		    1
+	u8 event;
+	#define CREQ_QUERY_CC_RESP_EVENT_QUERY_CC		   0x8dUL
+	__le16 reserved48[3];
+};
+
+/* Query congestion control command response side buffer structure (32 bytes) */
+struct creq_query_cc_resp_sb {
+	u8 opcode;
+	#define CREQ_QUERY_CC_RESP_SB_OPCODE_QUERY_CC		   0x8dUL
+	u8 status;
+	__le16 cookie;
+	__le16 flags;
+	u8 resp_size;
+	u8 reserved8;
+	u8 enable_cc;
+	#define CREQ_QUERY_CC_RESP_SB_ENABLE_CC		    0x1UL
+	u8 g;
+	#define CREQ_QUERY_CC_RESP_SB_G_MASK			    0x7UL
+	#define CREQ_QUERY_CC_RESP_SB_G_SFT			    0
+	u8 num_phases_per_state;
+	__le16 init_cr;
+	u8 unused_2;
+	__le16 unused_3;
+	u8 unused_4;
+	__le16 init_tr;
+	u8 tos_dscp_tos_ecn;
+	#define CREQ_QUERY_CC_RESP_SB_TOS_ECN_MASK		    0x3UL
+	#define CREQ_QUERY_CC_RESP_SB_TOS_ECN_SFT		    0
+	#define CREQ_QUERY_CC_RESP_SB_TOS_DSCP_MASK		    0xfcUL
+	#define CREQ_QUERY_CC_RESP_SB_TOS_DSCP_SFT		    2
+	__le64 reserved64;
+	__le64 reserved64_1;
+};
+
+/* creq_query_roce_stats_resp (size:128b/16B) */
+struct creq_query_roce_stats_resp {
+	u8	type;
+	#define CREQ_QUERY_ROCE_STATS_RESP_TYPE_MASK    0x3fUL
+	#define CREQ_QUERY_ROCE_STATS_RESP_TYPE_SFT     0
+	#define CREQ_QUERY_ROCE_STATS_RESP_TYPE_QP_EVENT  0x38UL
+	#define CREQ_QUERY_ROCE_STATS_RESP_TYPE_LAST	\
+				CREQ_QUERY_ROCE_STATS_RESP_TYPE_QP_EVENT
+	u8	status;
+	__le16	cookie;
+	__le32	size;
+	u8	v;
+	#define CREQ_QUERY_ROCE_STATS_RESP_V     0x1UL
+	u8	event;
+	#define CREQ_QUERY_ROCE_STATS_RESP_EVENT_QUERY_ROCE_STATS 0x8eUL
+	#define CREQ_QUERY_ROCE_STATS_RESP_EVENT_LAST	\
+			CREQ_QUERY_ROCE_STATS_RESP_EVENT_QUERY_ROCE_STATS
+	u8	reserved48[6];
+};
+
+/* creq_query_roce_stats_resp_sb (size:2624b/328B) */
+struct creq_query_roce_stats_resp_sb {
+	u8	opcode;
+	#define CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_QUERY_ROCE_STATS 0x8eUL
+	#define CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_LAST \
+			CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_QUERY_ROCE_STATS
+	u8	status;
+	__le16	cookie;
+	__le16	flags;
+	u8	resp_size;
+	u8	rsvd;
+	__le32	num_counters;
+	__le32	rsvd1;
+	__le64	to_retransmits;
+	__le64	seq_err_naks_rcvd;
+	__le64	max_retry_exceeded;
+	__le64	rnr_naks_rcvd;
+	__le64	missing_resp;
+	__le64	unrecoverable_err;
+	__le64	bad_resp_err;
+	__le64	local_qp_op_err;
+	__le64	local_protection_err;
+	__le64	mem_mgmt_op_err;
+	__le64	remote_invalid_req_err;
+	__le64	remote_access_err;
+	__le64	remote_op_err;
+	__le64	dup_req;
+	__le64	res_exceed_max;
+	__le64	res_length_mismatch;
+	__le64	res_exceeds_wqe;
+	__le64	res_opcode_err;
+	__le64	res_rx_invalid_rkey;
+	__le64	res_rx_domain_err;
+	__le64	res_rx_no_perm;
+	__le64	res_rx_range_err;
+	__le64	res_tx_invalid_rkey;
+	__le64	res_tx_domain_err;
+	__le64	res_tx_no_perm;
+	__le64	res_tx_range_err;
+	__le64	res_irrq_oflow;
+	__le64	res_unsup_opcode;
+	__le64	res_unaligned_atomic;
+	__le64	res_rem_inv_err;
+	__le64	res_mem_error;
+	__le64	res_srq_err;
+	__le64	res_cmp_err;
+	__le64	res_invalid_dup_rkey;
+	__le64	res_wqe_format_err;
+	__le64	res_cq_load_err;
+	__le64	res_srq_load_err;
+	__le64	res_tx_pci_err;
+	__le64	res_rx_pci_err;
+	__le64  res_oos_drop_count;
+	__le64  active_qp_count_p0;
+	__le64  active_qp_count_p1;
+	__le64  active_qp_count_p2;
+	__le64  active_qp_count_p3;
+};
+
+/* cmdq_query_roce_stats_ext (size:192b/24B) */
+struct cmdq_query_roce_stats_ext {
+	u8      opcode;
+	#define CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_QUERY_ROCE_STATS 0x92UL
+	#define CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_LAST            \
+		CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_QUERY_ROCE_STATS
+	u8      cmd_size;
+	__le16  flags;
+	#define CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_COLLECTION_ID     0x1UL
+	#define CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_FUNCTION_ID       0x2UL
+	__le16  cookie;
+	u8      resp_size;
+	u8      collection_id;
+	__le64  resp_addr;
+	__le32  function_id;
+	#define CMDQ_QUERY_ROCE_STATS_EXT_PF_NUM_MASK  0xffUL
+	#define CMDQ_QUERY_ROCE_STATS_EXT_PF_NUM_SFT   0
+	#define CMDQ_QUERY_ROCE_STATS_EXT_VF_NUM_MASK  0xffff00UL
+	#define CMDQ_QUERY_ROCE_STATS_EXT_VF_NUM_SFT   8
+	#define CMDQ_QUERY_ROCE_STATS_EXT_VF_VALID     0x1000000UL
+	__le32  reserved32;
+};
+
+/* creq_query_roce_stats_ext_resp (size:128b/16B) */
+struct creq_query_roce_stats_ext_resp {
+	u8      type;
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_MASK    0x3fUL
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_SFT     0
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_QP_EVENT  0x38UL
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_LAST     \
+		CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_QP_EVENT
+	u8      status;
+	__le16  cookie;
+	__le32  size;
+	u8      v;
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_V     0x1UL
+	u8      event;
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_EVENT_QUERY_ROCE_STATS_EXT 0x92UL
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_EVENT_LAST \
+		CREQ_QUERY_ROCE_STATS_EXT_RESP_EVENT_QUERY_ROCE_STATS_EXT
+	u8      reserved48[6];
+};
+
+/* creq_query_roce_stats_ext_resp_sb (size:1536b/192B) */
+struct creq_query_roce_stats_ext_resp_sb {
+	u8      opcode;
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_QUERY_ROCE_STATS_EXT 0x92UL
+	#define CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_LAST \
+		CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_QUERY_ROCE_STATS_EXT
+	u8      status;
+	__le16  cookie;
+	__le16  flags;
+	u8      resp_size;
+	u8      rsvd;
+	__le64  tx_atomic_req_pkts;
+	__le64  tx_read_req_pkts;
+	__le64  tx_read_res_pkts;
+	__le64  tx_write_req_pkts;
+	__le64  tx_send_req_pkts;
+	__le64  tx_roce_pkts;
+	__le64  tx_roce_bytes;
+	__le64  rx_atomic_req_pkts;
+	__le64  rx_read_req_pkts;
+	__le64  rx_read_res_pkts;
+	__le64  rx_write_req_pkts;
+	__le64  rx_send_req_pkts;
+	__le64  rx_roce_pkts;
+	__le64  rx_roce_bytes;
+	__le64  rx_roce_good_pkts;
+	__le64  rx_roce_good_bytes;
+	__le64  rx_out_of_buffer_pkts;
+	__le64  rx_out_of_sequence_pkts;
+	__le64  tx_cnp_pkts;
+	__le64  rx_cnp_pkts;
+	__le64  rx_ecn_marked_pkts;
+	__le64  tx_cnp_bytes;
+	__le64  rx_cnp_bytes;
+};
+
+/* QP error notification event (16 bytes) */
+struct creq_qp_error_notification {
+	u8 type;
+	#define CREQ_QP_ERROR_NOTIFICATION_TYPE_MASK		    0x3fUL
+	#define CREQ_QP_ERROR_NOTIFICATION_TYPE_SFT		    0
+	#define CREQ_QP_ERROR_NOTIFICATION_TYPE_QP_EVENT	   0x38UL
+	#define CREQ_QP_ERROR_NOTIFICATION_RESERVED2_MASK	    0xc0UL
+	#define CREQ_QP_ERROR_NOTIFICATION_RESERVED2_SFT	    6
+	u8 status;
+	u8 req_slow_path_state;
+	u8 req_err_state_reason;
+	__le32 xid;
+	u8 v;
+	#define CREQ_QP_ERROR_NOTIFICATION_V			    0x1UL
+	#define CREQ_QP_ERROR_NOTIFICATION_RESERVED7_MASK	    0xfeUL
+	#define CREQ_QP_ERROR_NOTIFICATION_RESERVED7_SFT	    1
+	u8 event;
+	#define CREQ_QP_ERROR_NOTIFICATION_EVENT_QP_ERROR_NOTIFICATION 0xc0UL
+	u8 res_slow_path_state;
+	u8 res_err_state_reason;
+	__le16 sq_cons_idx;
+	__le16 rq_cons_idx;
+};
+
+/* RoCE Slowpath HSI Specification 1.6.0 */
+#define ROCE_SP_HSI_VERSION_MAJOR	1
+#define ROCE_SP_HSI_VERSION_MINOR	6
+#define ROCE_SP_HSI_VERSION_UPDATE	0
+
+#define ROCE_SP_HSI_VERSION_STR	"1.6.0"
+/*
+ * Following is the signature for ROCE_SP_HSI message field that indicates not
+ * applicable (All F's). Need to cast it the size of the field if needed.
+ */
+#define ROCE_SP_HSI_NA_SIGNATURE	((__le32)(-1))
+#endif /* __BNXT_RE_HSI_H__ */