Merge tag 'doc-4.11-images' of git://git.lwn.net/linux into drm-misc-next

Pointer for Markus's image conversion work.

We need this so we can merge all the pretty drm graphs for 4.12.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

182 files changed, 17805 insertions, 4588 deletions

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 670917387eda..66f86027ed47 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -92,4 +92,6 @@ source "drivers/infiniband/hw/hfi1/Kconfig"
 
 source "drivers/infiniband/hw/qedr/Kconfig"
 
+source "drivers/infiniband/hw/bnxt_re/Kconfig"
+
 endif # INFINIBAND
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index edaae9f9853c..e426ac877d19 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -13,6 +13,7 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
+ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
 
 ib_cm-y :=			cm.o
 
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index ae04826e82fc..b1371eb9f46c 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -314,14 +314,13 @@ static void make_default_gid(struct  net_device *dev, union ib_gid *gid)
 int ib_cache_gid_add(struct ib_device *ib_dev, u8 port,
 		     union ib_gid *gid, struct ib_gid_attr *attr)
 {
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	struct ib_gid_table *table;
 	int ix;
 	int ret = 0;
 	struct net_device *idev;
 	int empty;
 
-	table = ports_table[port - rdma_start_port(ib_dev)];
+	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
 	if (!memcmp(gid, &zgid, sizeof(*gid)))
 		return -EINVAL;
@@ -369,11 +368,10 @@ out_unlock:
 int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
 		     union ib_gid *gid, struct ib_gid_attr *attr)
 {
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	struct ib_gid_table *table;
 	int ix;
 
-	table = ports_table[port - rdma_start_port(ib_dev)];
+	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
 	mutex_lock(&table->lock);
 	write_lock_irq(&table->rwlock);
@@ -399,12 +397,11 @@ out_unlock:
 int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
 				     struct net_device *ndev)
 {
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	struct ib_gid_table *table;
 	int ix;
 	bool deleted = false;
 
-	table  = ports_table[port - rdma_start_port(ib_dev)];
+	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
 	mutex_lock(&table->lock);
 	write_lock_irq(&table->rwlock);
@@ -428,10 +425,9 @@ int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
 static int __ib_cache_gid_get(struct ib_device *ib_dev, u8 port, int index,
 			      union ib_gid *gid, struct ib_gid_attr *attr)
 {
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	struct ib_gid_table *table;
 
-	table = ports_table[port - rdma_start_port(ib_dev)];
+	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
 	if (index < 0 || index >= table->sz)
 		return -EINVAL;
@@ -455,14 +451,13 @@ static int _ib_cache_gid_table_find(struct ib_device *ib_dev,
 				    unsigned long mask,
 				    u8 *port, u16 *index)
 {
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	struct ib_gid_table *table;
 	u8 p;
 	int local_index;
 	unsigned long flags;
 
 	for (p = 0; p < ib_dev->phys_port_cnt; p++) {
-		table = ports_table[p];
+		table = ib_dev->cache.ports[p].gid;
 		read_lock_irqsave(&table->rwlock, flags);
 		local_index = find_gid(table, gid, val, false, mask, NULL);
 		if (local_index >= 0) {
@@ -503,18 +498,16 @@ int ib_find_cached_gid_by_port(struct ib_device *ib_dev,
 			       u16 *index)
 {
 	int local_index;
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	struct ib_gid_table *table;
 	unsigned long mask = GID_ATTR_FIND_MASK_GID |
 			     GID_ATTR_FIND_MASK_GID_TYPE;
 	struct ib_gid_attr val = {.ndev = ndev, .gid_type = gid_type};
 	unsigned long flags;
 
-	if (port < rdma_start_port(ib_dev) ||
-	    port > rdma_end_port(ib_dev))
+	if (!rdma_is_port_valid(ib_dev, port))
 		return -ENOENT;
 
-	table = ports_table[port - rdma_start_port(ib_dev)];
+	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
 	if (ndev)
 		mask |= GID_ATTR_FIND_MASK_NETDEV;
@@ -562,21 +555,17 @@ static int ib_cache_gid_find_by_filter(struct ib_device *ib_dev,
 				       void *context,
 				       u16 *index)
 {
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	struct ib_gid_table *table;
 	unsigned int i;
 	unsigned long flags;
 	bool found = false;
 
-	if (!ports_table)
-		return -EOPNOTSUPP;
 
-	if (port < rdma_start_port(ib_dev) ||
-	    port > rdma_end_port(ib_dev) ||
+	if (!rdma_is_port_valid(ib_dev, port) ||
 	    !rdma_protocol_roce(ib_dev, port))
 		return -EPROTONOSUPPORT;
 
-	table = ports_table[port - rdma_start_port(ib_dev)];
+	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
 	read_lock_irqsave(&table->rwlock, flags);
 	for (i = 0; i < table->sz; i++) {
@@ -668,14 +657,13 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port,
 				  unsigned long gid_type_mask,
 				  enum ib_cache_gid_default_mode mode)
 {
-	struct ib_gid_table **ports_table = ib_dev->cache.gid_cache;
 	union ib_gid gid;
 	struct ib_gid_attr gid_attr;
 	struct ib_gid_attr zattr_type = zattr;
 	struct ib_gid_table *table;
 	unsigned int gid_type;
 
-	table  = ports_table[port - rdma_start_port(ib_dev)];
+	table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
 
 	make_default_gid(ndev, &gid);
 	memset(&gid_attr, 0, sizeof(gid_attr));
@@ -766,71 +754,64 @@ static int gid_table_reserve_default(struct ib_device *ib_dev, u8 port,
 static int _gid_table_setup_one(struct ib_device *ib_dev)
 {
 	u8 port;
-	struct ib_gid_table **table;
+	struct ib_gid_table *table;
 	int err = 0;
 
-	table = kcalloc(ib_dev->phys_port_cnt, sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return -ENOMEM;
-
 	for (port = 0; port < ib_dev->phys_port_cnt; port++) {
 		u8 rdma_port = port + rdma_start_port(ib_dev);
 
-		table[port] =
+		table =
 			alloc_gid_table(
 				ib_dev->port_immutable[rdma_port].gid_tbl_len);
-		if (!table[port]) {
+		if (!table) {
 			err = -ENOMEM;
 			goto rollback_table_setup;
 		}
 
 		err = gid_table_reserve_default(ib_dev,
 						port + rdma_start_port(ib_dev),
-						table[port]);
+						table);
 		if (err)
 			goto rollback_table_setup;
+		ib_dev->cache.ports[port].gid = table;
 	}
 
-	ib_dev->cache.gid_cache = table;
 	return 0;
 
 rollback_table_setup:
 	for (port = 0; port < ib_dev->phys_port_cnt; port++) {
+		table = ib_dev->cache.ports[port].gid;
+
 		cleanup_gid_table_port(ib_dev, port + rdma_start_port(ib_dev),
-				       table[port]);
-		release_gid_table(table[port]);
+				       table);
+		release_gid_table(table);
 	}
 
-	kfree(table);
 	return err;
 }
 
 static void gid_table_release_one(struct ib_device *ib_dev)
 {
-	struct ib_gid_table **table = ib_dev->cache.gid_cache;
+	struct ib_gid_table *table;
 	u8 port;
 
-	if (!table)
-		return;
-
-	for (port = 0; port < ib_dev->phys_port_cnt; port++)
-		release_gid_table(table[port]);
-
-	kfree(table);
-	ib_dev->cache.gid_cache = NULL;
+	for (port = 0; port < ib_dev->phys_port_cnt; port++) {
+		table = ib_dev->cache.ports[port].gid;
+		release_gid_table(table);
+		ib_dev->cache.ports[port].gid = NULL;
+	}
 }
 
 static void gid_table_cleanup_one(struct ib_device *ib_dev)
 {
-	struct ib_gid_table **table = ib_dev->cache.gid_cache;
+	struct ib_gid_table *table;
 	u8 port;
 
-	if (!table)
-		return;
-
-	for (port = 0; port < ib_dev->phys_port_cnt; port++)
+	for (port = 0; port < ib_dev->phys_port_cnt; port++) {
+		table = ib_dev->cache.ports[port].gid;
 		cleanup_gid_table_port(ib_dev, port + rdma_start_port(ib_dev),
-				       table[port]);
+				       table);
+	}
 }
 
 static int gid_table_setup_one(struct ib_device *ib_dev)
@@ -860,12 +841,12 @@ int ib_get_cached_gid(struct ib_device *device,
 {
 	int res;
 	unsigned long flags;
-	struct ib_gid_table **ports_table = device->cache.gid_cache;
-	struct ib_gid_table *table = ports_table[port_num - rdma_start_port(device)];
+	struct ib_gid_table *table;
 
-	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
+	table = device->cache.ports[port_num - rdma_start_port(device)].gid;
 	read_lock_irqsave(&table->rwlock, flags);
 	res = __ib_cache_gid_get(device, port_num, index, gid, gid_attr);
 	read_unlock_irqrestore(&table->rwlock, flags);
@@ -912,12 +893,12 @@ int ib_get_cached_pkey(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
+	cache = device->cache.ports[port_num - rdma_start_port(device)].pkey;
 
 	if (index < 0 || index >= cache->table_len)
 		ret = -EINVAL;
@@ -941,12 +922,12 @@ int ib_find_cached_pkey(struct ib_device *device,
 	int ret = -ENOENT;
 	int partial_ix = -1;
 
-	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
+	cache = device->cache.ports[port_num - rdma_start_port(device)].pkey;
 
 	*index = -1;
 
@@ -981,12 +962,12 @@ int ib_find_exact_cached_pkey(struct ib_device *device,
 	int i;
 	int ret = -ENOENT;
 
-	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
+	cache = device->cache.ports[port_num - rdma_start_port(device)].pkey;
 
 	*index = -1;
 
@@ -1010,17 +991,36 @@ int ib_get_cached_lmc(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
-	*lmc = device->cache.lmc_cache[port_num - rdma_start_port(device)];
+	*lmc = device->cache.ports[port_num - rdma_start_port(device)].lmc;
 	read_unlock_irqrestore(&device->cache.lock, flags);
 
 	return ret;
 }
 EXPORT_SYMBOL(ib_get_cached_lmc);
 
+int ib_get_cached_port_state(struct ib_device   *device,
+			     u8                  port_num,
+			     enum ib_port_state *port_state)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+		return -EINVAL;
+
+	read_lock_irqsave(&device->cache.lock, flags);
+	*port_state = device->cache.ports[port_num
+		- rdma_start_port(device)].port_state;
+	read_unlock_irqrestore(&device->cache.lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(ib_get_cached_port_state);
+
 static void ib_cache_update(struct ib_device *device,
 			    u8                port)
 {
@@ -1033,14 +1033,13 @@ static void ib_cache_update(struct ib_device *device,
 	int                        i;
 	int                        ret;
 	struct ib_gid_table	  *table;
-	struct ib_gid_table	 **ports_table = device->cache.gid_cache;
 	bool			   use_roce_gid_table =
 					rdma_cap_roce_gid_table(device, port);
 
-	if (port < rdma_start_port(device) || port > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port))
 		return;
 
-	table = ports_table[port - rdma_start_port(device)];
+	table = device->cache.ports[port - rdma_start_port(device)].gid;
 
 	tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
 	if (!tprops)
@@ -1092,9 +1091,10 @@ static void ib_cache_update(struct ib_device *device,
 
 	write_lock_irq(&device->cache.lock);
 
-	old_pkey_cache = device->cache.pkey_cache[port - rdma_start_port(device)];
+	old_pkey_cache = device->cache.ports[port -
+		rdma_start_port(device)].pkey;
 
-	device->cache.pkey_cache[port - rdma_start_port(device)] = pkey_cache;
+	device->cache.ports[port - rdma_start_port(device)].pkey = pkey_cache;
 	if (!use_roce_gid_table) {
 		write_lock(&table->rwlock);
 		for (i = 0; i < gid_cache->table_len; i++) {
@@ -1104,7 +1104,9 @@ static void ib_cache_update(struct ib_device *device,
 		write_unlock(&table->rwlock);
 	}
 
-	device->cache.lmc_cache[port - rdma_start_port(device)] = tprops->lmc;
+	device->cache.ports[port - rdma_start_port(device)].lmc = tprops->lmc;
+	device->cache.ports[port - rdma_start_port(device)].port_state =
+		tprops->state;
 
 	write_unlock_irq(&device->cache.lock);
 
@@ -1157,22 +1159,17 @@ int ib_cache_setup_one(struct ib_device *device)
 
 	rwlock_init(&device->cache.lock);
 
-	device->cache.pkey_cache =
-		kzalloc(sizeof *device->cache.pkey_cache *
+	device->cache.ports =
+		kzalloc(sizeof(*device->cache.ports) *
 			(rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL);
-	device->cache.lmc_cache = kmalloc(sizeof *device->cache.lmc_cache *
-					  (rdma_end_port(device) -
-					   rdma_start_port(device) + 1),
-					  GFP_KERNEL);
-	if (!device->cache.pkey_cache ||
-	    !device->cache.lmc_cache) {
+	if (!device->cache.ports) {
 		err = -ENOMEM;
-		goto free;
+		goto out;
 	}
 
 	err = gid_table_setup_one(device);
 	if (err)
-		goto free;
+		goto out;
 
 	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p)
 		ib_cache_update(device, p + rdma_start_port(device));
@@ -1187,9 +1184,7 @@ int ib_cache_setup_one(struct ib_device *device)
 
 err:
 	gid_table_cleanup_one(device);
-free:
-	kfree(device->cache.pkey_cache);
-	kfree(device->cache.lmc_cache);
+out:
 	return err;
 }
 
@@ -1203,14 +1198,11 @@ void ib_cache_release_one(struct ib_device *device)
 	 * all the device's resources when the cache could no
 	 * longer be accessed.
 	 */
-	if (device->cache.pkey_cache)
-		for (p = 0;
-		     p <= rdma_end_port(device) - rdma_start_port(device); ++p)
-			kfree(device->cache.pkey_cache[p]);
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p)
+		kfree(device->cache.ports[p].pkey);
 
 	gid_table_release_one(device);
-	kfree(device->cache.pkey_cache);
-	kfree(device->cache.lmc_cache);
+	kfree(device->cache.ports);
 }
 
 void ib_cache_cleanup_one(struct ib_device *device)
diff --git a/drivers/infiniband/core/cgroup.c b/drivers/infiniband/core/cgroup.c
new file mode 100644
index 000000000000..126ac5f99db7
--- /dev/null
+++ b/drivers/infiniband/core/cgroup.c
@@ -0,0 +1,62 @@
+/*
+ * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include "core_priv.h"
+
+/**
+ * ib_device_register_rdmacg - register with rdma cgroup.
+ * @device: device to register to participate in resource
+ *          accounting by rdma cgroup.
+ *
+ * Register with the rdma cgroup. Should be called before
+ * exposing rdma device to user space applications to avoid
+ * resource accounting leak.
+ * Returns 0 on success or otherwise failure code.
+ */
+int ib_device_register_rdmacg(struct ib_device *device)
+{
+	device->cg_device.name = device->name;
+	return rdmacg_register_device(&device->cg_device);
+}
+
+/**
+ * ib_device_unregister_rdmacg - unregister with rdma cgroup.
+ * @device: device to unregister.
+ *
+ * Unregister with the rdma cgroup. Should be called after
+ * all the resources are deallocated, and after a stage when any
+ * other resource allocation by user application cannot be done
+ * for this device to avoid any leak in accounting.
+ */
+void ib_device_unregister_rdmacg(struct ib_device *device)
+{
+	rdmacg_unregister_device(&device->cg_device);
+}
+
+int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj,
+			 struct ib_device *device,
+			 enum rdmacg_resource_type resource_index)
+{
+	return rdmacg_try_charge(&cg_obj->cg, &device->cg_device,
+				 resource_index);
+}
+EXPORT_SYMBOL(ib_rdmacg_try_charge);
+
+void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj,
+			struct ib_device *device,
+			enum rdmacg_resource_type resource_index)
+{
+	rdmacg_uncharge(cg_obj->cg, &device->cg_device,
+			resource_index);
+}
+EXPORT_SYMBOL(ib_rdmacg_uncharge);
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index cf1edfa1cbac..6535f09dc575 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -3409,6 +3409,8 @@ static void cm_process_send_error(struct ib_mad_send_buf *msg,
 	if (msg != cm_id_priv->msg || state != cm_id_priv->id.state)
 		goto discard;
 
+	pr_debug_ratelimited("CM: failed sending MAD in state %d. (%s)\n",
+			     state, ib_wc_status_msg(wc_status));
 	switch (state) {
 	case IB_CM_REQ_SENT:
 	case IB_CM_MRA_REQ_RCVD:
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 3e70a9c5d79d..acd10d666f1c 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -198,6 +198,7 @@ struct cma_device {
 	atomic_t		refcount;
 	struct list_head	id_list;
 	enum ib_gid_type	*default_gid_type;
+	u8			*default_roce_tos;
 };
 
 struct rdma_bind_list {
@@ -269,8 +270,7 @@ struct cma_device *cma_enum_devices_by_ibdev(cma_device_filter	filter,
 int cma_get_default_gid_type(struct cma_device *cma_dev,
 			     unsigned int port)
 {
-	if (port < rdma_start_port(cma_dev->device) ||
-	    port > rdma_end_port(cma_dev->device))
+	if (!rdma_is_port_valid(cma_dev->device, port))
 		return -EINVAL;
 
 	return cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)];
@@ -282,8 +282,7 @@ int cma_set_default_gid_type(struct cma_device *cma_dev,
 {
 	unsigned long supported_gids;
 
-	if (port < rdma_start_port(cma_dev->device) ||
-	    port > rdma_end_port(cma_dev->device))
+	if (!rdma_is_port_valid(cma_dev->device, port))
 		return -EINVAL;
 
 	supported_gids = roce_gid_type_mask_support(cma_dev->device, port);
@@ -297,6 +296,25 @@ int cma_set_default_gid_type(struct cma_device *cma_dev,
 	return 0;
 }
 
+int cma_get_default_roce_tos(struct cma_device *cma_dev, unsigned int port)
+{
+	if (!rdma_is_port_valid(cma_dev->device, port))
+		return -EINVAL;
+
+	return cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)];
+}
+
+int cma_set_default_roce_tos(struct cma_device *cma_dev, unsigned int port,
+			     u8 default_roce_tos)
+{
+	if (!rdma_is_port_valid(cma_dev->device, port))
+		return -EINVAL;
+
+	cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)] =
+		 default_roce_tos;
+
+	return 0;
+}
 struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev)
 {
 	return cma_dev->device;
@@ -343,6 +361,7 @@ struct rdma_id_private {
 	u32			options;
 	u8			srq;
 	u8			tos;
+	bool			tos_set;
 	u8			reuseaddr;
 	u8			afonly;
 	enum ib_gid_type	gid_type;
@@ -709,6 +728,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 	union ib_gid gid, sgid, *dgid;
 	u16 pkey, index;
 	u8 p;
+	enum ib_port_state port_state;
 	int i;
 
 	cma_dev = NULL;
@@ -724,6 +744,8 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 			if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index))
 				continue;
 
+			if (ib_get_cached_port_state(cur_dev->device, p, &port_state))
+				continue;
 			for (i = 0; !ib_get_cached_gid(cur_dev->device, p, i,
 						       &gid, NULL);
 			     i++) {
@@ -735,7 +757,8 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 				}
 
 				if (!cma_dev && (gid.global.subnet_prefix ==
-						 dgid->global.subnet_prefix)) {
+				    dgid->global.subnet_prefix) &&
+				    port_state == IB_PORT_ACTIVE) {
 					cma_dev = cur_dev;
 					sgid = gid;
 					id_priv->id.port_num = p;
@@ -778,6 +801,7 @@ struct rdma_cm_id *rdma_create_id(struct net *net,
 	id_priv->id.event_handler = event_handler;
 	id_priv->id.ps = ps;
 	id_priv->id.qp_type = qp_type;
+	id_priv->tos_set = false;
 	spin_lock_init(&id_priv->lock);
 	mutex_init(&id_priv->qp_mutex);
 	init_completion(&id_priv->comp);
@@ -1689,6 +1713,7 @@ static int cma_rep_recv(struct rdma_id_private *id_priv)
 
 	return 0;
 reject:
+	pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret);
 	cma_modify_qp_err(id_priv);
 	ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED,
 		       NULL, 0, NULL, 0);
@@ -1760,6 +1785,8 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 		/* ignore event */
 		goto out;
 	case IB_CM_REJ_RECEIVED:
+		pr_debug_ratelimited("RDMA CM: REJECTED: %s\n", rdma_reject_msg(&id_priv->id,
+										ib_event->param.rej_rcvd.reason));
 		cma_modify_qp_err(id_priv);
 		event.status = ib_event->param.rej_rcvd.reason;
 		event.event = RDMA_CM_EVENT_REJECTED;
@@ -2266,6 +2293,7 @@ void rdma_set_service_type(struct rdma_cm_id *id, int tos)
 
 	id_priv = container_of(id, struct rdma_id_private, id);
 	id_priv->tos = (u8) tos;
+	id_priv->tos_set = true;
 }
 EXPORT_SYMBOL(rdma_set_service_type);
 
@@ -2285,6 +2313,8 @@ static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
 		work->new_state = RDMA_CM_ADDR_RESOLVED;
 		work->event.event = RDMA_CM_EVENT_ROUTE_ERROR;
 		work->event.status = status;
+		pr_debug_ratelimited("RDMA CM: ROUTE_ERROR: failed to query path. status %d\n",
+				     status);
 	}
 
 	queue_work(cma_wq, &work->work);
@@ -2467,14 +2497,12 @@ static int iboe_tos_to_sl(struct net_device *ndev, int tos)
 	struct net_device *dev;
 
 	prio = rt_tos2priority(tos);
-	dev = ndev->priv_flags & IFF_802_1Q_VLAN ?
-		vlan_dev_real_dev(ndev) : ndev;
-
+	dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev;
 	if (dev->num_tc)
 		return netdev_get_prio_tc_map(dev, prio);
 
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
-	if (ndev->priv_flags & IFF_802_1Q_VLAN)
+	if (is_vlan_dev(ndev))
 		return (vlan_dev_get_egress_qos_mask(ndev, prio) &
 			VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 #endif
@@ -2500,6 +2528,9 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	struct cma_work *work;
 	int ret;
 	struct net_device *ndev = NULL;
+	u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num -
+					rdma_start_port(id_priv->cma_dev->device)];
+	u8 tos = id_priv->tos_set ? id_priv->tos : default_roce_tos;
 
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
@@ -2573,7 +2604,8 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	route->path_rec->reversible = 1;
 	route->path_rec->pkey = cpu_to_be16(0xffff);
 	route->path_rec->mtu_selector = IB_SA_EQ;
-	route->path_rec->sl = iboe_tos_to_sl(ndev, id_priv->tos);
+	route->path_rec->sl = iboe_tos_to_sl(ndev, tos);
+	route->path_rec->traffic_class = tos;
 	route->path_rec->mtu = iboe_get_mtu(ndev->mtu);
 	route->path_rec->rate_selector = IB_SA_EQ;
 	route->path_rec->rate = iboe_get_rate(ndev);
@@ -2652,8 +2684,8 @@ static void cma_set_loopback(struct sockaddr *addr)
 static int cma_bind_loopback(struct rdma_id_private *id_priv)
 {
 	struct cma_device *cma_dev, *cur_dev;
-	struct ib_port_attr port_attr;
 	union ib_gid gid;
+	enum ib_port_state port_state;
 	u16 pkey;
 	int ret;
 	u8 p;
@@ -2669,8 +2701,8 @@ static int cma_bind_loopback(struct rdma_id_private *id_priv)
 			cma_dev = cur_dev;
 
 		for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) {
-			if (!ib_query_port(cur_dev->device, p, &port_attr) &&
-			    port_attr.state == IB_PORT_ACTIVE) {
+			if (!ib_get_cached_port_state(cur_dev->device, p, &port_state) &&
+			    port_state == IB_PORT_ACTIVE) {
 				cma_dev = cur_dev;
 				goto port_found;
 			}
@@ -2720,8 +2752,14 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 		goto out;
 
 	memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
-	if (!status && !id_priv->cma_dev)
+	if (!status && !id_priv->cma_dev) {
 		status = cma_acquire_dev(id_priv, NULL);
+		if (status)
+			pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n",
+					     status);
+	} else {
+		pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status);
+	}
 
 	if (status) {
 		if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED,
@@ -2833,20 +2871,26 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
 	int ret;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
+	memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
 	if (id_priv->state == RDMA_CM_IDLE) {
 		ret = cma_bind_addr(id, src_addr, dst_addr);
-		if (ret)
+		if (ret) {
+			memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
 			return ret;
+		}
 	}
 
-	if (cma_family(id_priv) != dst_addr->sa_family)
+	if (cma_family(id_priv) != dst_addr->sa_family) {
+		memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
 		return -EINVAL;
+	}
 
-	if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))
+	if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) {
+		memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
 		return -EINVAL;
+	}
 
 	atomic_inc(&id_priv->refcount);
-	memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
 	if (cma_any_addr(dst_addr)) {
 		ret = cma_resolve_loopback(id_priv);
 	} else {
@@ -2962,6 +3006,43 @@ err:
 	return ret == -ENOSPC ? -EADDRNOTAVAIL : ret;
 }
 
+static int cma_port_is_unique(struct rdma_bind_list *bind_list,
+			      struct rdma_id_private *id_priv)
+{
+	struct rdma_id_private *cur_id;
+	struct sockaddr  *daddr = cma_dst_addr(id_priv);
+	struct sockaddr  *saddr = cma_src_addr(id_priv);
+	__be16 dport = cma_port(daddr);
+
+	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
+		struct sockaddr  *cur_daddr = cma_dst_addr(cur_id);
+		struct sockaddr  *cur_saddr = cma_src_addr(cur_id);
+		__be16 cur_dport = cma_port(cur_daddr);
+
+		if (id_priv == cur_id)
+			continue;
+
+		/* different dest port -> unique */
+		if (!cma_any_port(cur_daddr) &&
+		    (dport != cur_dport))
+			continue;
+
+		/* different src address -> unique */
+		if (!cma_any_addr(saddr) &&
+		    !cma_any_addr(cur_saddr) &&
+		    cma_addr_cmp(saddr, cur_saddr))
+			continue;
+
+		/* different dst address -> unique */
+		if (!cma_any_addr(cur_daddr) &&
+		    cma_addr_cmp(daddr, cur_daddr))
+			continue;
+
+		return -EADDRNOTAVAIL;
+	}
+	return 0;
+}
+
 static int cma_alloc_any_port(enum rdma_port_space ps,
 			      struct rdma_id_private *id_priv)
 {
@@ -2974,9 +3055,19 @@ static int cma_alloc_any_port(enum rdma_port_space ps,
 	remaining = (high - low) + 1;
 	rover = prandom_u32() % remaining + low;
 retry:
-	if (last_used_port != rover &&
-	    !cma_ps_find(net, ps, (unsigned short)rover)) {
-		int ret = cma_alloc_port(ps, id_priv, rover);
+	if (last_used_port != rover) {
+		struct rdma_bind_list *bind_list;
+		int ret;
+
+		bind_list = cma_ps_find(net, ps, (unsigned short)rover);
+
+		if (!bind_list) {
+			ret = cma_alloc_port(ps, id_priv, rover);
+		} else {
+			ret = cma_port_is_unique(bind_list, id_priv);
+			if (!ret)
+				cma_bind_port(bind_list, id_priv);
+		}
 		/*
 		 * Remember previously used port number in order to avoid
 		 * re-using same port immediately after it is closed.
@@ -3205,6 +3296,7 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 {
 	struct rdma_id_private *id_priv;
 	int ret;
+	struct sockaddr  *daddr;
 
 	if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 &&
 	    addr->sa_family != AF_IB)
@@ -3244,6 +3336,9 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 	if (ret)
 		goto err2;
 
+	daddr = cma_dst_addr(id_priv);
+	daddr->sa_family = addr->sa_family;
+
 	return 0;
 err2:
 	if (id_priv->cma_dev)
@@ -3308,10 +3403,13 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
 		if (rep->status != IB_SIDR_SUCCESS) {
 			event.event = RDMA_CM_EVENT_UNREACHABLE;
 			event.status = ib_event->param.sidr_rep_rcvd.status;
+			pr_debug_ratelimited("RDMA CM: UNREACHABLE: bad SIDR reply. status %d\n",
+					     event.status);
 			break;
 		}
 		ret = cma_set_qkey(id_priv, rep->qkey);
 		if (ret) {
+			pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to set qkey. status %d\n", ret);
 			event.event = RDMA_CM_EVENT_ADDR_ERROR;
 			event.status = ret;
 			break;
@@ -3583,6 +3681,9 @@ static int cma_accept_iw(struct rdma_id_private *id_priv,
 	struct iw_cm_conn_param iw_param;
 	int ret;
 
+	if (!conn_param)
+		return -EINVAL;
+
 	ret = cma_modify_qp_rtr(id_priv, conn_param);
 	if (ret)
 		return ret;
@@ -3760,10 +3861,17 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
 
 	if (!status)
 		status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey));
+	else
+		pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n",
+				     status);
 	mutex_lock(&id_priv->qp_mutex);
-	if (!status && id_priv->id.qp)
+	if (!status && id_priv->id.qp) {
 		status = ib_attach_mcast(id_priv->id.qp, &multicast->rec.mgid,
 					 be16_to_cpu(multicast->rec.mlid));
+		if (status)
+			pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to attach QP. status %d\n",
+					     status);
+	}
 	mutex_unlock(&id_priv->qp_mutex);
 
 	memset(&event, 0, sizeof event);
@@ -4229,15 +4337,21 @@ static void cma_add_one(struct ib_device *device)
 	cma_dev->default_gid_type = kcalloc(device->phys_port_cnt,
 					    sizeof(*cma_dev->default_gid_type),
 					    GFP_KERNEL);
-	if (!cma_dev->default_gid_type) {
-		kfree(cma_dev);
-		return;
-	}
+	if (!cma_dev->default_gid_type)
+		goto free_cma_dev;
+
+	cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt,
+					    sizeof(*cma_dev->default_roce_tos),
+					    GFP_KERNEL);
+	if (!cma_dev->default_roce_tos)
+		goto free_gid_type;
+
 	for (i = rdma_start_port(device); i <= rdma_end_port(device); i++) {
 		supported_gids = roce_gid_type_mask_support(device, i);
 		WARN_ON(!supported_gids);
 		cma_dev->default_gid_type[i - rdma_start_port(device)] =
 			find_first_bit(&supported_gids, BITS_PER_LONG);
+		cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0;
 	}
 
 	init_completion(&cma_dev->comp);
@@ -4250,6 +4364,16 @@ static void cma_add_one(struct ib_device *device)
 	list_for_each_entry(id_priv, &listen_any_list, list)
 		cma_listen_on_dev(id_priv, cma_dev);
 	mutex_unlock(&lock);
+
+	return;
+
+free_gid_type:
+	kfree(cma_dev->default_gid_type);
+
+free_cma_dev:
+	kfree(cma_dev);
+
+	return;
 }
 
 static int cma_remove_id_dev(struct rdma_id_private *id_priv)
@@ -4318,6 +4442,7 @@ static void cma_remove_one(struct ib_device *device, void *client_data)
 	mutex_unlock(&lock);
 
 	cma_process_remove(cma_dev);
+	kfree(cma_dev->default_roce_tos);
 	kfree(cma_dev->default_gid_type);
 	kfree(cma_dev);
 }
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 41573df1d9fc..54076a3e8007 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -139,8 +139,50 @@ static ssize_t default_roce_mode_store(struct config_item *item,
 
 CONFIGFS_ATTR(, default_roce_mode);
 
+static ssize_t default_roce_tos_show(struct config_item *item, char *buf)
+{
+	struct cma_device *cma_dev;
+	struct cma_dev_port_group *group;
+	ssize_t ret;
+	u8 tos;
+
+	ret = cma_configfs_params_get(item, &cma_dev, &group);
+	if (ret)
+		return ret;
+
+	tos = cma_get_default_roce_tos(cma_dev, group->port_num);
+	cma_configfs_params_put(cma_dev);
+
+	return sprintf(buf, "%u\n", tos);
+}
+
+static ssize_t default_roce_tos_store(struct config_item *item,
+				      const char *buf, size_t count)
+{
+	struct cma_device *cma_dev;
+	struct cma_dev_port_group *group;
+	ssize_t ret;
+	u8 tos;
+
+	ret = kstrtou8(buf, 0, &tos);
+	if (ret)
+		return ret;
+
+	ret = cma_configfs_params_get(item, &cma_dev, &group);
+	if (ret)
+		return ret;
+
+	ret = cma_set_default_roce_tos(cma_dev, group->port_num, tos);
+	cma_configfs_params_put(cma_dev);
+
+	return ret ? ret : strnlen(buf, count);
+}
+
+CONFIGFS_ATTR(, default_roce_tos);
+
 static struct configfs_attribute *cma_configfs_attributes[] = {
 	&attr_default_roce_mode,
+	&attr_default_roce_tos,
 	NULL,
 };
 
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index d29372624f3a..cb7d372e4bdf 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -35,6 +35,7 @@
 
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <linux/cgroup_rdma.h>
 
 #include <rdma/ib_verbs.h>
 
@@ -62,6 +63,9 @@ int cma_get_default_gid_type(struct cma_device *cma_dev,
 int cma_set_default_gid_type(struct cma_device *cma_dev,
 			     unsigned int port,
 			     enum ib_gid_type default_gid_type);
+int cma_get_default_roce_tos(struct cma_device *cma_dev, unsigned int port);
+int cma_set_default_roce_tos(struct cma_device *a_dev, unsigned int port,
+			     u8 default_roce_tos);
 struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev);
 
 int  ib_device_register_sysfs(struct ib_device *device,
@@ -121,6 +125,35 @@ int ib_cache_setup_one(struct ib_device *device);
 void ib_cache_cleanup_one(struct ib_device *device);
 void ib_cache_release_one(struct ib_device *device);
 
+#ifdef CONFIG_CGROUP_RDMA
+int ib_device_register_rdmacg(struct ib_device *device);
+void ib_device_unregister_rdmacg(struct ib_device *device);
+
+int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj,
+			 struct ib_device *device,
+			 enum rdmacg_resource_type resource_index);
+
+void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj,
+			struct ib_device *device,
+			enum rdmacg_resource_type resource_index);
+#else
+static inline int ib_device_register_rdmacg(struct ib_device *device)
+{ return 0; }
+
+static inline void ib_device_unregister_rdmacg(struct ib_device *device)
+{ }
+
+static inline int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj,
+				       struct ib_device *device,
+				       enum rdmacg_resource_type resource_index)
+{ return 0; }
+
+static inline void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj,
+				      struct ib_device *device,
+				      enum rdmacg_resource_type resource_index)
+{ }
+#endif
+
 static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
 					 struct net_device *upper)
 {
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index a754fc727de5..e95510117a6d 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -58,8 +58,8 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
  * %IB_POLL_DIRECT CQ.  It does not offload CQ processing to a different
  * context and does not ask for completion interrupts from the HCA.
  *
- * Note: for compatibility reasons -1 can be passed in %budget for unlimited
- * polling.  Do not use this feature in new code, it will be removed soon.
+ * Note: do not pass -1 as %budget unless it is guaranteed that the number
+ * of completions that will be processed is small.
  */
 int ib_process_cq_direct(struct ib_cq *cq, int budget)
 {
@@ -120,7 +120,7 @@ static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
  *
  * This is the proper interface to allocate a CQ for in-kernel users. A
  * CQ allocated with this interface will automatically be polled from the
- * specified context.  The ULP needs must use wr->wr_cqe instead of wr->wr_id
+ * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id
  * to use this CQ abstraction.
  */
 struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 571974cd3919..593d2ce6ec7c 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -333,6 +333,15 @@ int ib_register_device(struct ib_device *device,
 	int ret;
 	struct ib_client *client;
 	struct ib_udata uhw = {.outlen = 0, .inlen = 0};
+	struct device *parent = device->dev.parent;
+
+	WARN_ON_ONCE(!parent);
+	if (!device->dev.dma_ops)
+		device->dev.dma_ops = parent->dma_ops;
+	if (!device->dev.dma_mask)
+		device->dev.dma_mask = parent->dma_mask;
+	if (!device->dev.coherent_dma_mask)
+		device->dev.coherent_dma_mask = parent->coherent_dma_mask;
 
 	mutex_lock(&device_mutex);
 
@@ -360,10 +369,18 @@ int ib_register_device(struct ib_device *device,
 		goto out;
 	}
 
+	ret = ib_device_register_rdmacg(device);
+	if (ret) {
+		pr_warn("Couldn't register device with rdma cgroup\n");
+		ib_cache_cleanup_one(device);
+		goto out;
+	}
+
 	memset(&device->attrs, 0, sizeof(device->attrs));
 	ret = device->query_device(device, &device->attrs, &uhw);
 	if (ret) {
 		pr_warn("Couldn't query the device attributes\n");
+		ib_device_unregister_rdmacg(device);
 		ib_cache_cleanup_one(device);
 		goto out;
 	}
@@ -372,6 +389,7 @@ int ib_register_device(struct ib_device *device,
 	if (ret) {
 		pr_warn("Couldn't register device %s with driver model\n",
 			device->name);
+		ib_device_unregister_rdmacg(device);
 		ib_cache_cleanup_one(device);
 		goto out;
 	}
@@ -421,6 +439,7 @@ void ib_unregister_device(struct ib_device *device)
 
 	mutex_unlock(&device_mutex);
 
+	ib_device_unregister_rdmacg(device);
 	ib_device_unregister_sysfs(device);
 	ib_cache_cleanup_one(device);
 
@@ -659,7 +678,7 @@ int ib_query_port(struct ib_device *device,
 	union ib_gid gid;
 	int err;
 
-	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
 	memset(port_attr, 0, sizeof(*port_attr));
@@ -825,7 +844,7 @@ int ib_modify_port(struct ib_device *device,
 	if (!device->modify_port)
 		return -ENOSYS;
 
-	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
 	return device->modify_port(device, port_num, port_modify_mask,
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index a009f7132c73..57f231f1c721 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -316,7 +316,9 @@ struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
 	/* Validate device and port */
 	port_priv = ib_get_mad_port(device, port_num);
 	if (!port_priv) {
-		dev_notice(&device->dev, "ib_register_mad_agent: Invalid port\n");
+		dev_notice(&device->dev,
+			   "ib_register_mad_agent: Invalid port %d\n",
+			   port_num);
 		ret = ERR_PTR(-ENODEV);
 		goto error1;
 	}
diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index 0621f4455732..db958d3207ef 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -144,7 +144,6 @@ static enum bonding_slave_state is_eth_active_slave_of_bonding_rcu(struct net_de
 static int is_eth_port_of_netdev(struct ib_device *ib_dev, u8 port,
 				 struct net_device *rdma_ndev, void *cookie)
 {
-	struct net_device *event_ndev = (struct net_device *)cookie;
 	struct net_device *real_dev;
 	int res;
 
@@ -152,11 +151,11 @@ static int is_eth_port_of_netdev(struct ib_device *ib_dev, u8 port,
 		return 0;
 
 	rcu_read_lock();
-	real_dev = rdma_vlan_dev_real_dev(event_ndev);
+	real_dev = rdma_vlan_dev_real_dev(cookie);
 	if (!real_dev)
-		real_dev = event_ndev;
+		real_dev = cookie;
 
-	res = ((rdma_is_upper_dev_rcu(rdma_ndev, event_ndev) &&
+	res = ((rdma_is_upper_dev_rcu(rdma_ndev, cookie) &&
 	       (is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) &
 		REQUIRED_BOND_STATES)) ||
 	       real_dev == rdma_ndev);
@@ -192,17 +191,16 @@ static int pass_all_filter(struct ib_device *ib_dev, u8 port,
 static int upper_device_filter(struct ib_device *ib_dev, u8 port,
 			       struct net_device *rdma_ndev, void *cookie)
 {
-	struct net_device *event_ndev = (struct net_device *)cookie;
 	int res;
 
 	if (!rdma_ndev)
 		return 0;
 
-	if (rdma_ndev == event_ndev)
+	if (rdma_ndev == cookie)
 		return 1;
 
 	rcu_read_lock();
-	res = rdma_is_upper_dev_rcu(rdma_ndev, event_ndev);
+	res = rdma_is_upper_dev_rcu(rdma_ndev, cookie);
 	rcu_read_unlock();
 
 	return res;
@@ -379,18 +377,14 @@ static void _add_netdev_ips(struct ib_device *ib_dev, u8 port,
 static void add_netdev_ips(struct ib_device *ib_dev, u8 port,
 			   struct net_device *rdma_ndev, void *cookie)
 {
-	struct net_device *event_ndev = (struct net_device *)cookie;
-
-	enum_netdev_default_gids(ib_dev, port, event_ndev, rdma_ndev);
-	_add_netdev_ips(ib_dev, port, event_ndev);
+	enum_netdev_default_gids(ib_dev, port, cookie, rdma_ndev);
+	_add_netdev_ips(ib_dev, port, cookie);
 }
 
 static void del_netdev_ips(struct ib_device *ib_dev, u8 port,
 			   struct net_device *rdma_ndev, void *cookie)
 {
-	struct net_device *event_ndev = (struct net_device *)cookie;
-
-	ib_cache_gid_del_all_netdev_gids(ib_dev, port, event_ndev);
+	ib_cache_gid_del_all_netdev_gids(ib_dev, port, cookie);
 }
 
 static void enum_all_gids_of_dev_cb(struct ib_device *ib_dev,
@@ -460,7 +454,7 @@ static void handle_netdev_upper(struct ib_device *ib_dev, u8 port,
 						      u8 port,
 						      struct net_device *ndev))
 {
-	struct net_device *ndev = (struct net_device *)cookie;
+	struct net_device *ndev = cookie;
 	struct upper_list *upper_iter;
 	struct upper_list *upper_temp;
 	LIST_HEAD(upper_list);
@@ -519,9 +513,7 @@ static void del_netdev_default_ips_join(struct ib_device *ib_dev, u8 port,
 static void del_netdev_default_ips(struct ib_device *ib_dev, u8 port,
 				   struct net_device *rdma_ndev, void *cookie)
 {
-	struct net_device *event_ndev = (struct net_device *)cookie;
-
-	bond_delete_netdev_default_gids(ib_dev, port, event_ndev, rdma_ndev);
+	bond_delete_netdev_default_gids(ib_dev, port, cookie, rdma_ndev);
 }
 
 /* The following functions operate on all IB devices. netdevice_event and
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index c1fb545e8d78..daadf3130c9f 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -1258,7 +1258,7 @@ int ib_device_register_sysfs(struct ib_device *device,
 	int ret;
 	int i;
 
-	device->dev.parent = device->dma_device;
+	WARN_ON_ONCE(!device->dev.parent);
 	ret = dev_set_name(class_dev, "%s", device->name);
 	if (ret)
 		return ret;
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index e0a995b85a2d..cc0d51fb06e3 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -1290,7 +1290,7 @@ static void ib_ucm_add_one(struct ib_device *device)
 		goto err;
 
 	ucm_dev->dev.class = &cm_class;
-	ucm_dev->dev.parent = device->dma_device;
+	ucm_dev->dev.parent = device->dev.parent;
 	ucm_dev->dev.devt = ucm_dev->cdev.dev;
 	ucm_dev->dev.release = ib_ucm_release_dev;
 	dev_set_name(&ucm_dev->dev, "ucm%d", ucm_dev->devnum);
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 4609b921f899..27f155d2df8d 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -34,7 +34,8 @@
 
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/export.h>
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
@@ -99,9 +100,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (dmasync)
 		dma_attrs |= DMA_ATTR_WRITE_BARRIER;
 
-	if (!size)
-		return ERR_PTR(-EINVAL);
-
 	/*
 	 * If the combination of the addr and size requested for this memory
 	 * region causes an integer overflow, return error.
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 6b079a31dced..cb2742b548bb 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -32,6 +32,8 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/pid.h>
 #include <linux/slab.h>
 #include <linux/export.h>
@@ -239,6 +241,71 @@ static const struct mmu_notifier_ops ib_umem_notifiers = {
 	.invalidate_range_end       = ib_umem_notifier_invalidate_range_end,
 };
 
+struct ib_umem *ib_alloc_odp_umem(struct ib_ucontext *context,
+				  unsigned long addr,
+				  size_t size)
+{
+	struct ib_umem *umem;
+	struct ib_umem_odp *odp_data;
+	int pages = size >> PAGE_SHIFT;
+	int ret;
+
+	umem = kzalloc(sizeof(*umem), GFP_KERNEL);
+	if (!umem)
+		return ERR_PTR(-ENOMEM);
+
+	umem->context   = context;
+	umem->length    = size;
+	umem->address   = addr;
+	umem->page_size = PAGE_SIZE;
+	umem->writable  = 1;
+
+	odp_data = kzalloc(sizeof(*odp_data), GFP_KERNEL);
+	if (!odp_data) {
+		ret = -ENOMEM;
+		goto out_umem;
+	}
+	odp_data->umem = umem;
+
+	mutex_init(&odp_data->umem_mutex);
+	init_completion(&odp_data->notifier_completion);
+
+	odp_data->page_list = vzalloc(pages * sizeof(*odp_data->page_list));
+	if (!odp_data->page_list) {
+		ret = -ENOMEM;
+		goto out_odp_data;
+	}
+
+	odp_data->dma_list = vzalloc(pages * sizeof(*odp_data->dma_list));
+	if (!odp_data->dma_list) {
+		ret = -ENOMEM;
+		goto out_page_list;
+	}
+
+	down_write(&context->umem_rwsem);
+	context->odp_mrs_count++;
+	rbt_ib_umem_insert(&odp_data->interval_tree, &context->umem_tree);
+	if (likely(!atomic_read(&context->notifier_count)))
+		odp_data->mn_counters_active = true;
+	else
+		list_add(&odp_data->no_private_counters,
+			 &context->no_private_counters);
+	up_write(&context->umem_rwsem);
+
+	umem->odp_data = odp_data;
+
+	return umem;
+
+out_page_list:
+	vfree(odp_data->page_list);
+out_odp_data:
+	kfree(odp_data);
+out_umem:
+	kfree(umem);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(ib_alloc_odp_umem);
+
 int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
 {
 	int ret_val;
@@ -270,18 +337,20 @@ int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
 
 	init_completion(&umem->odp_data->notifier_completion);
 
-	umem->odp_data->page_list = vzalloc(ib_umem_num_pages(umem) *
+	if (ib_umem_num_pages(umem)) {
+		umem->odp_data->page_list = vzalloc(ib_umem_num_pages(umem) *
 					    sizeof(*umem->odp_data->page_list));
-	if (!umem->odp_data->page_list) {
-		ret_val = -ENOMEM;
-		goto out_odp_data;
-	}
+		if (!umem->odp_data->page_list) {
+			ret_val = -ENOMEM;
+			goto out_odp_data;
+		}
 
-	umem->odp_data->dma_list = vzalloc(ib_umem_num_pages(umem) *
+		umem->odp_data->dma_list = vzalloc(ib_umem_num_pages(umem) *
 					  sizeof(*umem->odp_data->dma_list));
-	if (!umem->odp_data->dma_list) {
-		ret_val = -ENOMEM;
-		goto out_page_list;
+		if (!umem->odp_data->dma_list) {
+			ret_val = -ENOMEM;
+			goto out_page_list;
+		}
 	}
 
 	/*
@@ -466,6 +535,7 @@ static int ib_umem_odp_map_dma_single_page(
 		}
 		umem->odp_data->dma_list[page_index] = dma_addr | access_mask;
 		umem->odp_data->page_list[page_index] = page;
+		umem->npages++;
 		stored_page = 1;
 	} else if (umem->odp_data->page_list[page_index] == page) {
 		umem->odp_data->dma_list[page_index] |= access_mask;
@@ -505,7 +575,8 @@ out:
  * for failure.
  * An -EAGAIN error code is returned when a concurrent mmu notifier prevents
  * the function from completing its task.
- *
+ * An -ENOENT error code indicates that userspace process is being terminated
+ * and mm was already destroyed.
  * @umem: the umem to map and pin
  * @user_virt: the address from which we need to map.
  * @bcnt: the minimal number of bytes to pin and map. The mapping might be
@@ -553,7 +624,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 
 	owning_mm = get_task_mm(owning_process);
 	if (owning_mm == NULL) {
-		ret = -EINVAL;
+		ret = -ENOENT;
 		goto out_put_task;
 	}
 
@@ -665,6 +736,7 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 				put_page(page);
 			umem->odp_data->page_list[idx] = NULL;
 			umem->odp_data->dma_list[idx] = 0;
+			umem->npages--;
 		}
 	}
 	mutex_unlock(&umem->odp_data->umem_mutex);
diff --git a/drivers/infiniband/core/umem_rbtree.c b/drivers/infiniband/core/umem_rbtree.c
index 727d788448f5..d176597b4d78 100644
--- a/drivers/infiniband/core/umem_rbtree.c
+++ b/drivers/infiniband/core/umem_rbtree.c
@@ -78,17 +78,32 @@ int rbt_ib_umem_for_each_in_range(struct rb_root *root,
 				  void *cookie)
 {
 	int ret_val = 0;
-	struct umem_odp_node *node;
+	struct umem_odp_node *node, *next;
 	struct ib_umem_odp *umem;
 
 	if (unlikely(start == last))
 		return ret_val;
 
-	for (node = rbt_ib_umem_iter_first(root, start, last - 1); node;
-			node = rbt_ib_umem_iter_next(node, start, last - 1)) {
+	for (node = rbt_ib_umem_iter_first(root, start, last - 1);
+			node; node = next) {
+		next = rbt_ib_umem_iter_next(node, start, last - 1);
 		umem = container_of(node, struct ib_umem_odp, interval_tree);
 		ret_val = cb(umem->umem, start, last, cookie) || ret_val;
 	}
 
 	return ret_val;
 }
+EXPORT_SYMBOL(rbt_ib_umem_for_each_in_range);
+
+struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root *root,
+				       u64 addr, u64 length)
+{
+	struct umem_odp_node *node;
+
+	node = rbt_ib_umem_iter_first(root, addr, addr + length - 1);
+	if (node)
+		return container_of(node, struct ib_umem_odp, interval_tree);
+	return NULL;
+
+}
+EXPORT_SYMBOL(rbt_ib_umem_lookup);
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 249b403b43a4..aca7ff7abedc 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -1188,7 +1188,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 	if (cdev_add(&port->cdev, base, 1))
 		goto err_cdev;
 
-	port->dev = device_create(umad_class, device->dma_device,
+	port->dev = device_create(umad_class, device->dev.parent,
 				  port->cdev.dev, port,
 				  "umad%d", port->dev_num);
 	if (IS_ERR(port->dev))
@@ -1207,7 +1207,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 	if (cdev_add(&port->sm_cdev, base, 1))
 		goto err_sm_cdev;
 
-	port->sm_dev = device_create(umad_class, device->dma_device,
+	port->sm_dev = device_create(umad_class, device->dev.parent,
 				     port->sm_cdev.dev, port,
 				     "issm%d", port->dev_num);
 	if (IS_ERR(port->sm_dev))
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 455034ac994e..e1bedf0bac04 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -228,6 +228,7 @@ struct ib_uverbs_flow_spec {
 		struct ib_uverbs_flow_spec_ipv4    ipv4;
 		struct ib_uverbs_flow_spec_tcp_udp tcp_udp;
 		struct ib_uverbs_flow_spec_ipv6    ipv6;
+		struct ib_uverbs_flow_spec_action_tag	flow_tag;
 	};
 };
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 700782203483..7b7a76e1279a 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -316,6 +316,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	struct ib_udata                   udata;
 	struct ib_ucontext		 *ucontext;
 	struct file			 *filp;
+	struct ib_rdmacg_object		 cg_obj;
 	int ret;
 
 	if (out_len < sizeof resp)
@@ -335,13 +336,18 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 		   (unsigned long) cmd.response + sizeof resp,
 		   in_len - sizeof cmd, out_len - sizeof resp);
 
+	ret = ib_rdmacg_try_charge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
+	if (ret)
+		goto err;
+
 	ucontext = ib_dev->alloc_ucontext(ib_dev, &udata);
 	if (IS_ERR(ucontext)) {
 		ret = PTR_ERR(ucontext);
-		goto err;
+		goto err_alloc;
 	}
 
 	ucontext->device = ib_dev;
+	ucontext->cg_obj = cg_obj;
 	INIT_LIST_HEAD(&ucontext->pd_list);
 	INIT_LIST_HEAD(&ucontext->mr_list);
 	INIT_LIST_HEAD(&ucontext->mw_list);
@@ -407,6 +413,9 @@ err_free:
 	put_pid(ucontext->tgid);
 	ib_dev->dealloc_ucontext(ucontext);
 
+err_alloc:
+	ib_rdmacg_uncharge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
+
 err:
 	mutex_unlock(&file->mutex);
 	return ret;
@@ -561,6 +570,13 @@ ssize_t ib_uverbs_alloc_pd(struct ib_uverbs_file *file,
 		return -ENOMEM;
 
 	init_uobj(uobj, 0, file->ucontext, &pd_lock_class);
+	ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (ret) {
+		kfree(uobj);
+		return ret;
+	}
+
 	down_write(&uobj->mutex);
 
 	pd = ib_dev->alloc_pd(ib_dev, file->ucontext, &udata);
@@ -605,6 +621,7 @@ err_idr:
 	ib_dealloc_pd(pd);
 
 err:
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
 	put_uobj_write(uobj);
 	return ret;
 }
@@ -637,6 +654,8 @@ ssize_t ib_uverbs_dealloc_pd(struct ib_uverbs_file *file,
 	if (ret)
 		goto err_put;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	uobj->live = 0;
 	put_uobj_write(uobj);
 
@@ -1006,6 +1025,10 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 			goto err_put;
 		}
 	}
+	ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (ret)
+		goto err_charge;
 
 	mr = pd->device->reg_user_mr(pd, cmd.start, cmd.length, cmd.hca_va,
 				     cmd.access_flags, &udata);
@@ -1054,6 +1077,9 @@ err_unreg:
 	ib_dereg_mr(mr);
 
 err_put:
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
 	put_pd_read(pd);
 
 err_free:
@@ -1178,6 +1204,8 @@ ssize_t ib_uverbs_dereg_mr(struct ib_uverbs_file *file,
 	if (ret)
 		return ret;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	idr_remove_uobj(&ib_uverbs_mr_idr, uobj);
 
 	mutex_lock(&file->mutex);
@@ -1226,6 +1254,11 @@ ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file,
 		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
 		   out_len - sizeof(resp));
 
+	ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (ret)
+		goto err_charge;
+
 	mw = pd->device->alloc_mw(pd, cmd.mw_type, &udata);
 	if (IS_ERR(mw)) {
 		ret = PTR_ERR(mw);
@@ -1271,6 +1304,9 @@ err_unalloc:
 	uverbs_dealloc_mw(mw);
 
 err_put:
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
 	put_pd_read(pd);
 
 err_free:
@@ -1306,6 +1342,8 @@ ssize_t ib_uverbs_dealloc_mw(struct ib_uverbs_file *file,
 	if (ret)
 		return ret;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
 
 	mutex_lock(&file->mutex);
@@ -1405,6 +1443,11 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file,
 	if (cmd_sz > offsetof(typeof(*cmd), flags) + sizeof(cmd->flags))
 		attr.flags = cmd->flags;
 
+	ret = ib_rdmacg_try_charge(&obj->uobject.cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (ret)
+		goto err_charge;
+
 	cq = ib_dev->create_cq(ib_dev, &attr,
 					     file->ucontext, uhw);
 	if (IS_ERR(cq)) {
@@ -1452,6 +1495,10 @@ err_free:
 	ib_destroy_cq(cq);
 
 err_file:
+	ib_rdmacg_uncharge(&obj->uobject.cg_obj, ib_dev,
+			   RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
 	if (ev_file)
 		ib_uverbs_release_ucq(file, ev_file, obj);
 
@@ -1732,6 +1779,8 @@ ssize_t ib_uverbs_destroy_cq(struct ib_uverbs_file *file,
 	if (ret)
 		return ret;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	idr_remove_uobj(&ib_uverbs_cq_idr, uobj);
 
 	mutex_lock(&file->mutex);
@@ -1891,7 +1940,8 @@ static int create_qp(struct ib_uverbs_file *file,
 				IB_QP_CREATE_CROSS_CHANNEL |
 				IB_QP_CREATE_MANAGED_SEND |
 				IB_QP_CREATE_MANAGED_RECV |
-				IB_QP_CREATE_SCATTER_FCS)) {
+				IB_QP_CREATE_SCATTER_FCS |
+				IB_QP_CREATE_CVLAN_STRIPPING)) {
 		ret = -EINVAL;
 		goto err_put;
 	}
@@ -1904,6 +1954,11 @@ static int create_qp(struct ib_uverbs_file *file,
 			goto err_put;
 		}
 
+	ret = ib_rdmacg_try_charge(&obj->uevent.uobject.cg_obj, device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (ret)
+		goto err_put;
+
 	if (cmd->qp_type == IB_QPT_XRC_TGT)
 		qp = ib_create_qp(pd, &attr);
 	else
@@ -1911,7 +1966,7 @@ static int create_qp(struct ib_uverbs_file *file,
 
 	if (IS_ERR(qp)) {
 		ret = PTR_ERR(qp);
-		goto err_put;
+		goto err_create;
 	}
 
 	if (cmd->qp_type != IB_QPT_XRC_TGT) {
@@ -1992,6 +2047,10 @@ err_cb:
 err_destroy:
 	ib_destroy_qp(qp);
 
+err_create:
+	ib_rdmacg_uncharge(&obj->uevent.uobject.cg_obj, device,
+			   RDMACG_RESOURCE_HCA_OBJECT);
+
 err_put:
 	if (xrcd)
 		put_xrcd_read(xrcd_uobj);
@@ -2518,6 +2577,8 @@ ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file,
 	if (ret)
 		return ret;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	if (obj->uxrcd)
 		atomic_dec(&obj->uxrcd->refcnt);
 
@@ -2969,11 +3030,16 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	memset(&attr.dmac, 0, sizeof(attr.dmac));
 	memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16);
 
+	ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (ret)
+		goto err_charge;
+
 	ah = pd->device->create_ah(pd, &attr, &udata);
 
 	if (IS_ERR(ah)) {
 		ret = PTR_ERR(ah);
-		goto err_put;
+		goto err_create;
 	}
 
 	ah->device  = pd->device;
@@ -3012,7 +3078,10 @@ err_copy:
 err_destroy:
 	ib_destroy_ah(ah);
 
-err_put:
+err_create:
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
 	put_pd_read(pd);
 
 err:
@@ -3046,6 +3115,8 @@ ssize_t ib_uverbs_destroy_ah(struct ib_uverbs_file *file,
 	if (ret)
 		return ret;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	idr_remove_uobj(&ib_uverbs_ah_idr, uobj);
 
 	mutex_lock(&file->mutex);
@@ -3143,6 +3214,25 @@ out_put:
 	return ret ? ret : in_len;
 }
 
+static int kern_spec_to_ib_spec_action(struct ib_uverbs_flow_spec *kern_spec,
+				       union ib_flow_spec *ib_spec)
+{
+	ib_spec->type = kern_spec->type;
+	switch (ib_spec->type) {
+	case IB_FLOW_SPEC_ACTION_TAG:
+		if (kern_spec->flow_tag.size !=
+		    sizeof(struct ib_uverbs_flow_spec_action_tag))
+			return -EINVAL;
+
+		ib_spec->flow_tag.size = sizeof(struct ib_flow_spec_action_tag);
+		ib_spec->flow_tag.tag_id = kern_spec->flow_tag.tag_id;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static size_t kern_spec_filter_sz(struct ib_uverbs_flow_spec_hdr *spec)
 {
 	/* Returns user space filter size, includes padding */
@@ -3167,8 +3257,8 @@ static ssize_t spec_filter_size(void *kern_spec_filter, u16 kern_filter_size,
 	return kern_filter_size;
 }
 
-static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
-				union ib_flow_spec *ib_spec)
+static int kern_spec_to_ib_spec_filter(struct ib_uverbs_flow_spec *kern_spec,
+				       union ib_flow_spec *ib_spec)
 {
 	ssize_t actual_filter_sz;
 	ssize_t kern_filter_sz;
@@ -3263,6 +3353,18 @@ static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 	return 0;
 }
 
+static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
+				union ib_flow_spec *ib_spec)
+{
+	if (kern_spec->reserved)
+		return -EINVAL;
+
+	if (kern_spec->type >= IB_FLOW_SPEC_ACTION_TAG)
+		return kern_spec_to_ib_spec_action(kern_spec, ib_spec);
+	else
+		return kern_spec_to_ib_spec_filter(kern_spec, ib_spec);
+}
+
 int ib_uverbs_ex_create_wq(struct ib_uverbs_file *file,
 			   struct ib_device *ib_dev,
 			   struct ib_udata *ucore,
@@ -3325,6 +3427,9 @@ int ib_uverbs_ex_create_wq(struct ib_uverbs_file *file,
 	wq_init_attr.wq_context = file;
 	wq_init_attr.wq_type = cmd.wq_type;
 	wq_init_attr.event_handler = ib_uverbs_wq_event_handler;
+	if (ucore->inlen >= (offsetof(typeof(cmd), create_flags) +
+			     sizeof(cmd.create_flags)))
+		wq_init_attr.create_flags = cmd.create_flags;
 	obj->uevent.events_reported = 0;
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 	wq = pd->device->create_wq(pd, &wq_init_attr, uhw);
@@ -3480,7 +3585,7 @@ int ib_uverbs_ex_modify_wq(struct ib_uverbs_file *file,
 	if (!cmd.attr_mask)
 		return -EINVAL;
 
-	if (cmd.attr_mask > (IB_WQ_STATE | IB_WQ_CUR_STATE))
+	if (cmd.attr_mask > (IB_WQ_STATE | IB_WQ_CUR_STATE | IB_WQ_FLAGS))
 		return -EINVAL;
 
 	wq = idr_read_wq(cmd.wq_handle, file->ucontext);
@@ -3489,6 +3594,10 @@ int ib_uverbs_ex_modify_wq(struct ib_uverbs_file *file,
 
 	wq_attr.curr_wq_state = cmd.curr_wq_state;
 	wq_attr.wq_state = cmd.wq_state;
+	if (cmd.attr_mask & IB_WQ_FLAGS) {
+		wq_attr.flags = cmd.flags;
+		wq_attr.flags_mask = cmd.flags_mask;
+	}
 	ret = wq->device->modify_wq(wq, &wq_attr, cmd.attr_mask, uhw);
 	put_wq_read(wq);
 	return ret;
@@ -3822,10 +3931,16 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		err = -EINVAL;
 		goto err_free;
 	}
+
+	err = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (err)
+		goto err_free;
+
 	flow_id = ib_create_flow(qp, flow_attr, IB_FLOW_DOMAIN_USER);
 	if (IS_ERR(flow_id)) {
 		err = PTR_ERR(flow_id);
-		goto err_free;
+		goto err_create;
 	}
 	flow_id->uobject = uobj;
 	uobj->object = flow_id;
@@ -3858,6 +3973,8 @@ err_copy:
 	idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
 destroy_flow:
 	ib_destroy_flow(flow_id);
+err_create:
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
 err_free:
 	kfree(flow_attr);
 err_put:
@@ -3897,8 +4014,11 @@ int ib_uverbs_ex_destroy_flow(struct ib_uverbs_file *file,
 	flow_id = uobj->object;
 
 	ret = ib_destroy_flow(flow_id);
-	if (!ret)
+	if (!ret) {
+		ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		uobj->live = 0;
+	}
 
 	put_uobj_write(uobj);
 
@@ -3966,6 +4086,11 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 	obj->uevent.events_reported = 0;
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 
+	ret = ib_rdmacg_try_charge(&obj->uevent.uobject.cg_obj, ib_dev,
+				   RDMACG_RESOURCE_HCA_OBJECT);
+	if (ret)
+		goto err_put_cq;
+
 	srq = pd->device->create_srq(pd, &attr, udata);
 	if (IS_ERR(srq)) {
 		ret = PTR_ERR(srq);
@@ -4030,6 +4155,8 @@ err_destroy:
 	ib_destroy_srq(srq);
 
 err_put:
+	ib_rdmacg_uncharge(&obj->uevent.uobject.cg_obj, ib_dev,
+			   RDMACG_RESOURCE_HCA_OBJECT);
 	put_pd_read(pd);
 
 err_put_cq:
@@ -4216,6 +4343,8 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file,
 	if (ret)
 		return ret;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	if (srq_type == IB_SRQT_XRC) {
 		us = container_of(obj, struct ib_usrq_object, uevent);
 		atomic_dec(&us->uxrcd->refcnt);
@@ -4323,6 +4452,12 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 
 	resp.max_wq_type_rq = attr.max_wq_type_rq;
 	resp.response_length += sizeof(resp.max_wq_type_rq);
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.raw_packet_caps))
+		goto end;
+
+	resp.raw_packet_caps = attr.raw_packet_caps;
+	resp.response_length += sizeof(resp.raw_packet_caps);
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index b3f95d453fba..35c788a32e26 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -51,6 +51,7 @@
 #include <rdma/ib.h>
 
 #include "uverbs.h"
+#include "core_priv.h"
 
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("InfiniBand userspace verbs access");
@@ -237,6 +238,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 
 		idr_remove_uobj(&ib_uverbs_ah_idr, uobj);
 		ib_destroy_ah(ah);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		kfree(uobj);
 	}
 
@@ -246,6 +249,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 
 		idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
 		uverbs_dealloc_mw(mw);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		kfree(uobj);
 	}
 
@@ -254,6 +259,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 
 		idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
 		ib_destroy_flow(flow_id);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		kfree(uobj);
 	}
 
@@ -266,6 +273,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 		if (qp == qp->real_qp)
 			ib_uverbs_detach_umcast(qp, uqp);
 		ib_destroy_qp(qp);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		ib_uverbs_release_uevent(file, &uqp->uevent);
 		kfree(uqp);
 	}
@@ -298,6 +307,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 
 		idr_remove_uobj(&ib_uverbs_srq_idr, uobj);
 		ib_destroy_srq(srq);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		ib_uverbs_release_uevent(file, uevent);
 		kfree(uevent);
 	}
@@ -310,6 +321,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 
 		idr_remove_uobj(&ib_uverbs_cq_idr, uobj);
 		ib_destroy_cq(cq);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		ib_uverbs_release_ucq(file, ev_file, ucq);
 		kfree(ucq);
 	}
@@ -319,6 +332,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 
 		idr_remove_uobj(&ib_uverbs_mr_idr, uobj);
 		ib_dereg_mr(mr);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		kfree(uobj);
 	}
 
@@ -339,11 +354,16 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 
 		idr_remove_uobj(&ib_uverbs_pd_idr, uobj);
 		ib_dealloc_pd(pd);
+		ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+				   RDMACG_RESOURCE_HCA_OBJECT);
 		kfree(uobj);
 	}
 
 	put_pid(context->tgid);
 
+	ib_rdmacg_uncharge(&context->cg_obj, context->device,
+			   RDMACG_RESOURCE_HCA_HANDLE);
+
 	return context->device->dealloc_ucontext(context);
 }
 
@@ -1174,7 +1194,7 @@ static void ib_uverbs_add_one(struct ib_device *device)
 	if (cdev_add(&uverbs_dev->cdev, base, 1))
 		goto err_cdev;
 
-	uverbs_dev->dev = device_create(uverbs_class, device->dma_device,
+	uverbs_dev->dev = device_create(uverbs_class, device->dev.parent,
 					uverbs_dev->cdev.dev, uverbs_dev,
 					"uverbs%d", uverbs_dev->devnum);
 	if (IS_ERR(uverbs_dev->dev))
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 71580cc28c9e..85ed5051fdfd 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1205,8 +1205,7 @@ int ib_resolve_eth_dmac(struct ib_device *device,
 {
 	int           ret = 0;
 
-	if (ah_attr->port_num < rdma_start_port(device) ||
-	    ah_attr->port_num > rdma_end_port(device))
+	if (!rdma_is_port_valid(device, ah_attr->port_num))
 		return -EINVAL;
 
 	if (!rdma_cap_eth_ah(device, ah_attr->port_num))
@@ -1949,17 +1948,12 @@ static void ib_drain_qp_done(struct ib_cq *cq, struct ib_wc *wc)
  */
 static void __ib_drain_sq(struct ib_qp *qp)
 {
+	struct ib_cq *cq = qp->send_cq;
 	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
 	struct ib_drain_cqe sdrain;
 	struct ib_send_wr swr = {}, *bad_swr;
 	int ret;
 
-	if (qp->send_cq->poll_ctx == IB_POLL_DIRECT) {
-		WARN_ONCE(qp->send_cq->poll_ctx == IB_POLL_DIRECT,
-			  "IB_POLL_DIRECT poll_ctx not supported for drain\n");
-		return;
-	}
-
 	swr.wr_cqe = &sdrain.cqe;
 	sdrain.cqe.done = ib_drain_qp_done;
 	init_completion(&sdrain.done);
@@ -1976,7 +1970,11 @@ static void __ib_drain_sq(struct ib_qp *qp)
 		return;
 	}
 
-	wait_for_completion(&sdrain.done);
+	if (cq->poll_ctx == IB_POLL_DIRECT)
+		while (wait_for_completion_timeout(&sdrain.done, HZ / 10) <= 0)
+			ib_process_cq_direct(cq, -1);
+	else
+		wait_for_completion(&sdrain.done);
 }
 
 /*
@@ -1984,17 +1982,12 @@ static void __ib_drain_sq(struct ib_qp *qp)
  */
 static void __ib_drain_rq(struct ib_qp *qp)
 {
+	struct ib_cq *cq = qp->recv_cq;
 	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
 	struct ib_drain_cqe rdrain;
 	struct ib_recv_wr rwr = {}, *bad_rwr;
 	int ret;
 
-	if (qp->recv_cq->poll_ctx == IB_POLL_DIRECT) {
-		WARN_ONCE(qp->recv_cq->poll_ctx == IB_POLL_DIRECT,
-			  "IB_POLL_DIRECT poll_ctx not supported for drain\n");
-		return;
-	}
-
 	rwr.wr_cqe = &rdrain.cqe;
 	rdrain.cqe.done = ib_drain_qp_done;
 	init_completion(&rdrain.done);
@@ -2011,7 +2004,11 @@ static void __ib_drain_rq(struct ib_qp *qp)
 		return;
 	}
 
-	wait_for_completion(&rdrain.done);
+	if (cq->poll_ctx == IB_POLL_DIRECT)
+		while (wait_for_completion_timeout(&rdrain.done, HZ / 10) <= 0)
+			ib_process_cq_direct(cq, -1);
+	else
+		wait_for_completion(&rdrain.done);
 }
 
 /**
@@ -2028,8 +2025,7 @@ static void __ib_drain_rq(struct ib_qp *qp)
  * ensure there is room in the CQ and SQ for the drain work request and
  * completion.
  *
- * allocate the CQ using ib_alloc_cq() and the CQ poll context cannot be
- * IB_POLL_DIRECT.
+ * allocate the CQ using ib_alloc_cq().
  *
  * ensure that there are no other contexts that are posting WRs concurrently.
  * Otherwise the drain is not guaranteed.
@@ -2057,8 +2053,7 @@ EXPORT_SYMBOL(ib_drain_sq);
  * ensure there is room in the CQ and RQ for the drain work request and
  * completion.
  *
- * allocate the CQ using ib_alloc_cq() and the CQ poll context cannot be
- * IB_POLL_DIRECT.
+ * allocate the CQ using ib_alloc_cq().
  *
  * ensure that there are no other contexts that are posting WRs concurrently.
  * Otherwise the drain is not guaranteed.
@@ -2082,8 +2077,7 @@ EXPORT_SYMBOL(ib_drain_rq);
  * ensure there is room in the CQ(s), SQ, and RQ for drain work requests
  * and completions.
  *
- * allocate the CQs using ib_alloc_cq() and the CQ poll context cannot be
- * IB_POLL_DIRECT.
+ * allocate the CQs using ib_alloc_cq().
  *
  * ensure that there are no other contexts that are posting WRs concurrently.
  * Otherwise the drain is not guaranteed.
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
index ed553de2ca12..34c93abf0fe0 100644
--- a/drivers/infiniband/hw/Makefile
+++ b/drivers/infiniband/hw/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_INFINIBAND_USNIC)		+= usnic/
 obj-$(CONFIG_INFINIBAND_HFI1)		+= hfi1/
 obj-$(CONFIG_INFINIBAND_HNS)		+= hns/
 obj-$(CONFIG_INFINIBAND_QEDR)		+= qedr/
+obj-$(CONFIG_INFINIBAND_BNXT_RE)	+= bnxt_re/
diff --git a/drivers/infiniband/hw/bnxt_re/Kconfig b/drivers/infiniband/hw/bnxt_re/Kconfig
new file mode 100644
index 000000000000..19982a4a9bba
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/Kconfig
@@ -0,0 +1,9 @@
+config INFINIBAND_BNXT_RE
+    tristate "Broadcom Netxtreme HCA support"
+    depends on ETHERNET && NETDEVICES && PCI && INET && DCB
+    select NET_VENDOR_BROADCOM
+    select BNXT
+    ---help---
+	  This driver supports Broadcom NetXtreme-E 10/25/40/50 gigabit
+	  RoCE HCAs.  To compile this driver as a module, choose M here:
+	  the module will be called bnxt_re.
diff --git a/drivers/infiniband/hw/bnxt_re/Makefile b/drivers/infiniband/hw/bnxt_re/Makefile
new file mode 100644
index 000000000000..036f84efbc73
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/Makefile
@@ -0,0 +1,6 @@
+
+ccflags-y := -Idrivers/net/ethernet/broadcom/bnxt
+obj-$(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
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 000000000000..ebf7be8d4139
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -0,0 +1,146 @@
+/*
+ * 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__
+#define ROCE_DRV_MODULE_NAME		"bnxt_re"
+#define ROCE_DRV_MODULE_VERSION		"1.0.0"
+
+#define BNXT_RE_DESC	"Broadcom NetXtreme-C/E RoCE Driver"
+
+#define BNXT_RE_PAGE_SIZE_4K		BIT(12)
+#define BNXT_RE_PAGE_SIZE_8K		BIT(13)
+#define BNXT_RE_PAGE_SIZE_64K		BIT(16)
+#define BNXT_RE_PAGE_SIZE_2M		BIT(21)
+#define BNXT_RE_PAGE_SIZE_8M		BIT(23)
+#define BNXT_RE_PAGE_SIZE_1G		BIT(30)
+
+#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)
+
+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_MIN_MSIX		2
+#define BNXT_RE_MAX_MSIX		16
+#define BNXT_RE_AEQ_IDX			0
+#define BNXT_RE_NQ_IDX			1
+
+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_IBDEV_REGISTERED	1
+#define BNXT_RE_FLAG_GOT_MSIX		2
+#define BNXT_RE_FLAG_RCFW_CHANNEL_EN	8
+#define BNXT_RE_FLAG_QOS_WORK_REG	16
+	struct net_device		*netdev;
+	unsigned int			version, major, minor;
+	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;
+
+	/* FP Notification Queue (CQ & SRQ) */
+	struct tasklet_struct		nq_task;
+
+	/* RCFW Channel */
+	struct bnxt_qplib_rcfw		rcfw;
+
+	/* NQ */
+	struct bnxt_qplib_nq		nq;
+
+	/* 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;
+	/* Max of 2 lossless traffic class supported per port */
+	u16				cosq[2];
+
+	/* QP for for handling QP1 packets */
+	u32				sqp_id;
+	struct bnxt_re_qp		*qp1_sqp;
+	struct bnxt_re_ah		*sqp_ah;
+	struct bnxt_re_sqp_entries sqp_tbl[1024];
+};
+
+#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/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
new file mode 100644
index 000000000000..33af2e3de399
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -0,0 +1,3202 @@
+/*
+ * 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 <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 "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 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 */
+struct net_device *bnxt_re_get_netdev(struct ib_device *ibdev, u8 port_num)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct net_device *netdev = NULL;
+
+	rcu_read_lock();
+	if (rdev)
+		netdev = rdev->netdev;
+	if (netdev)
+		dev_hold(netdev);
+
+	rcu_read_unlock();
+	return netdev;
+}
+
+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));
+
+	ib_attr->fw_ver = (u64)(unsigned long)(dev_attr->fw_ver);
+	bnxt_qplib_get_guid(rdev->netdev->dev_addr,
+			    (u8 *)&ib_attr->sys_image_guid);
+	ib_attr->max_mr_size = ~0ull;
+	ib_attr->page_size_cap = BNXT_RE_PAGE_SIZE_4K | BNXT_RE_PAGE_SIZE_8K |
+				 BNXT_RE_PAGE_SIZE_64K | BNXT_RE_PAGE_SIZE_2M |
+				 BNXT_RE_PAGE_SIZE_8M | BNXT_RE_PAGE_SIZE_1G;
+
+	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_LOCAL_DMA_LKEY
+				    | 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->max_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_rd_atom;
+	ib_attr->atomic_cap = IB_ATOMIC_HCA;
+	ib_attr->masked_atomic_cap = IB_ATOMIC_HCA;
+
+	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_fmr = dev_attr->max_fmr;
+	ib_attr->max_map_per_fmr = 1;	/* ? */
+
+	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 = 0;
+	return 0;
+}
+
+int bnxt_re_modify_device(struct ib_device *ibdev,
+			  int device_modify_mask,
+			  struct ib_device_modify *device_modify)
+{
+	switch (device_modify_mask) {
+	case IB_DEVICE_MODIFY_SYS_IMAGE_GUID:
+		/* Modify the GUID requires the modification of the GID table */
+		/* GUID should be made as READ-ONLY */
+		break;
+	case IB_DEVICE_MODIFY_NODE_DESC:
+		/* Node Desc should be made as READ-ONLY */
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static void __to_ib_speed_width(struct net_device *netdev, u8 *speed, u8 *width)
+{
+	struct ethtool_link_ksettings lksettings;
+	u32 espeed;
+
+	if (netdev->ethtool_ops && netdev->ethtool_ops->get_link_ksettings) {
+		memset(&lksettings, 0, sizeof(lksettings));
+		rtnl_lock();
+		netdev->ethtool_ops->get_link_ksettings(netdev, &lksettings);
+		rtnl_unlock();
+		espeed = lksettings.base.speed;
+	} else {
+		espeed = SPEED_UNKNOWN;
+	}
+	switch (espeed) {
+	case SPEED_1000:
+		*speed = IB_SPEED_SDR;
+		*width = IB_WIDTH_1X;
+		break;
+	case SPEED_10000:
+		*speed = IB_SPEED_QDR;
+		*width = IB_WIDTH_1X;
+		break;
+	case SPEED_20000:
+		*speed = IB_SPEED_DDR;
+		*width = IB_WIDTH_4X;
+		break;
+	case SPEED_25000:
+		*speed = IB_SPEED_EDR;
+		*width = IB_WIDTH_1X;
+		break;
+	case SPEED_40000:
+		*speed = IB_SPEED_QDR;
+		*width = IB_WIDTH_4X;
+		break;
+	case SPEED_50000:
+		break;
+	default:
+		*speed = IB_SPEED_SDR;
+		*width = IB_WIDTH_1X;
+		break;
+	}
+}
+
+/* Port */
+int bnxt_re_query_port(struct ib_device *ibdev, u8 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 = 5;
+	} else {
+		port_attr->state = IB_PORT_DOWN;
+		port_attr->phys_state = 3;
+	}
+	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 |
+				    IB_PORT_IP_BASED_GIDS;
+
+	/* Max MSG size set to 2G for now */
+	port_attr->max_msg_sz = 0x80000000;
+	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;
+	/* call the underlying netdev's ethtool hooks to query speed settings
+	 * for which we acquire rtnl_lock _only_ if it's registered with
+	 * IB stack to avoid race in the NETDEV_UNREG path
+	 */
+	if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
+		__to_ib_speed_width(rdev->netdev, &port_attr->active_speed,
+				    &port_attr->active_width);
+	return 0;
+}
+
+int bnxt_re_modify_port(struct ib_device *ibdev, u8 port_num,
+			int port_modify_mask,
+			struct ib_port_modify *port_modify)
+{
+	switch (port_modify_mask) {
+	case IB_PORT_SHUTDOWN:
+		break;
+	case IB_PORT_INIT_TYPE:
+		break;
+	case IB_PORT_RESET_QKEY_CNTR:
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+int bnxt_re_get_port_immutable(struct ib_device *ibdev, u8 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;
+}
+
+int bnxt_re_query_pkey(struct ib_device *ibdev, u8 port_num,
+		       u16 index, u16 *pkey)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+
+	/* Ignore port_num */
+
+	memset(pkey, 0, sizeof(*pkey));
+	return bnxt_qplib_get_pkey(&rdev->qplib_res,
+				   &rdev->qplib_res.pkey_tbl, index, pkey);
+}
+
+int bnxt_re_query_gid(struct ib_device *ibdev, u8 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(struct ib_device *ibdev, u8 port_num,
+		    unsigned int index, void **context)
+{
+	int rc = 0;
+	struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+
+	/* 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;
+		ctx->refcnt--;
+		if (!ctx->refcnt) {
+			rc = bnxt_qplib_del_sgid
+					(sgid_tbl,
+					 &sgid_tbl->tbl[ctx->idx], true);
+			if (rc)
+				dev_err(rdev_to_dev(rdev),
+					"Failed to remove GID: %#x", rc);
+			ctx_tbl = sgid_tbl->ctx;
+			ctx_tbl[ctx->idx] = NULL;
+			kfree(ctx);
+		}
+	} else {
+		return -EINVAL;
+	}
+	return rc;
+}
+
+int bnxt_re_add_gid(struct ib_device *ibdev, u8 port_num,
+		    unsigned int index, const union ib_gid *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(ibdev, ibdev);
+	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+
+	if ((attr->ndev) && is_vlan_dev(attr->ndev))
+		vlan_id = vlan_dev_vlan_id(attr->ndev);
+
+	rc = bnxt_qplib_add_sgid(sgid_tbl, (struct bnxt_qplib_gid *)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) {
+		dev_err(rdev_to_dev(rdev), "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;
+
+	return rc;
+}
+
+enum rdma_link_layer bnxt_re_get_link_layer(struct ib_device *ibdev,
+					    u8 port_num)
+{
+	return IB_LINK_LAYER_ETHERNET;
+}
+
+/* Protection Domains */
+int bnxt_re_dealloc_pd(struct ib_pd *ib_pd)
+{
+	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
+	struct bnxt_re_dev *rdev = pd->rdev;
+	int rc;
+
+	if (ib_pd->uobject && pd->dpi.dbr) {
+		struct ib_ucontext *ib_uctx = ib_pd->uobject->context;
+		struct bnxt_re_ucontext *ucntx;
+
+		/* Free DPI only if this is the first PD allocated by the
+		 * application and mark the context dpi as NULL
+		 */
+		ucntx = container_of(ib_uctx, struct bnxt_re_ucontext, ib_uctx);
+
+		rc = bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
+					    &rdev->qplib_res.dpi_tbl,
+					    &pd->dpi);
+		if (rc)
+			dev_err(rdev_to_dev(rdev), "Failed to deallocate HW DPI");
+			/* Don't fail, continue*/
+		ucntx->dpi = NULL;
+	}
+
+	rc = bnxt_qplib_dealloc_pd(&rdev->qplib_res,
+				   &rdev->qplib_res.pd_tbl,
+				   &pd->qplib_pd);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to deallocate HW PD");
+		return rc;
+	}
+
+	kfree(pd);
+	return 0;
+}
+
+struct ib_pd *bnxt_re_alloc_pd(struct ib_device *ibdev,
+			       struct ib_ucontext *ucontext,
+			       struct ib_udata *udata)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct bnxt_re_ucontext *ucntx = container_of(ucontext,
+						      struct bnxt_re_ucontext,
+						      ib_uctx);
+	struct bnxt_re_pd *pd;
+	int rc;
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return ERR_PTR(-ENOMEM);
+
+	pd->rdev = rdev;
+	if (bnxt_qplib_alloc_pd(&rdev->qplib_res.pd_tbl, &pd->qplib_pd)) {
+		dev_err(rdev_to_dev(rdev), "Failed to allocate HW PD");
+		rc = -ENOMEM;
+		goto fail;
+	}
+
+	if (udata) {
+		struct bnxt_re_pd_resp resp;
+
+		if (!ucntx->dpi) {
+			/* 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,
+						 &pd->dpi, ucntx)) {
+				rc = -ENOMEM;
+				goto dbfail;
+			}
+			ucntx->dpi = &pd->dpi;
+		}
+
+		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) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to copy user response\n");
+			goto dbfail;
+		}
+	}
+
+	return &pd->ib_pd;
+dbfail:
+	(void)bnxt_qplib_dealloc_pd(&rdev->qplib_res, &rdev->qplib_res.pd_tbl,
+				    &pd->qplib_pd);
+fail:
+	kfree(pd);
+	return ERR_PTR(rc);
+}
+
+/* Address Handles */
+int bnxt_re_destroy_ah(struct ib_ah *ib_ah)
+{
+	struct bnxt_re_ah *ah = container_of(ib_ah, struct bnxt_re_ah, ib_ah);
+	struct bnxt_re_dev *rdev = ah->rdev;
+	int rc;
+
+	rc = bnxt_qplib_destroy_ah(&rdev->qplib_res, &ah->qplib_ah);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to destroy HW AH");
+		return rc;
+	}
+	kfree(ah);
+	return 0;
+}
+
+struct ib_ah *bnxt_re_create_ah(struct ib_pd *ib_pd,
+				struct ib_ah_attr *ah_attr,
+				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_ah *ah;
+	int rc;
+	u16 vlan_tag;
+	u8 nw_type;
+
+	struct ib_gid_attr sgid_attr;
+
+	if (!(ah_attr->ah_flags & IB_AH_GRH)) {
+		dev_err(rdev_to_dev(rdev), "Failed to alloc AH: GRH not set");
+		return ERR_PTR(-EINVAL);
+	}
+	ah = kzalloc(sizeof(*ah), GFP_ATOMIC);
+	if (!ah)
+		return ERR_PTR(-ENOMEM);
+
+	ah->rdev = rdev;
+	ah->qplib_ah.pd = &pd->qplib_pd;
+
+	/* Supply the configuration for the HW */
+	memcpy(ah->qplib_ah.dgid.data, ah_attr->grh.dgid.raw,
+	       sizeof(union ib_gid));
+	/*
+	 * If RoCE V2 is enabled, stack will have two entries for
+	 * each GID entry. Avoiding this duplicte entry in HW. Dividing
+	 * the GID index by 2 for RoCE V2
+	 */
+	ah->qplib_ah.sgid_index = ah_attr->grh.sgid_index / 2;
+	ah->qplib_ah.host_sgid_index = ah_attr->grh.sgid_index;
+	ah->qplib_ah.traffic_class = ah_attr->grh.traffic_class;
+	ah->qplib_ah.flow_label = ah_attr->grh.flow_label;
+	ah->qplib_ah.hop_limit = ah_attr->grh.hop_limit;
+	ah->qplib_ah.sl = ah_attr->sl;
+	if (ib_pd->uobject &&
+	    !rdma_is_multicast_addr((struct in6_addr *)
+				    ah_attr->grh.dgid.raw) &&
+	    !rdma_link_local_addr((struct in6_addr *)
+				  ah_attr->grh.dgid.raw)) {
+		union ib_gid sgid;
+
+		rc = ib_get_cached_gid(&rdev->ibdev, 1,
+				       ah_attr->grh.sgid_index, &sgid,
+				       &sgid_attr);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to query gid at index %d",
+				ah_attr->grh.sgid_index);
+			goto fail;
+		}
+		if (sgid_attr.ndev) {
+			if (is_vlan_dev(sgid_attr.ndev))
+				vlan_tag = vlan_dev_vlan_id(sgid_attr.ndev);
+			dev_put(sgid_attr.ndev);
+		}
+		/* Get network header type for this GID */
+		nw_type = ib_gid_to_network_type(sgid_attr.gid_type, &sgid);
+		switch (nw_type) {
+		case RDMA_NETWORK_IPV4:
+			ah->qplib_ah.nw_type = CMDQ_CREATE_AH_TYPE_V2IPV4;
+			break;
+		case RDMA_NETWORK_IPV6:
+			ah->qplib_ah.nw_type = CMDQ_CREATE_AH_TYPE_V2IPV6;
+			break;
+		default:
+			ah->qplib_ah.nw_type = CMDQ_CREATE_AH_TYPE_V1;
+			break;
+		}
+		rc = rdma_addr_find_l2_eth_by_grh(&sgid, &ah_attr->grh.dgid,
+						  ah_attr->dmac, &vlan_tag,
+						  &sgid_attr.ndev->ifindex,
+						  NULL);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev), "Failed to get dmac\n");
+			goto fail;
+		}
+	}
+
+	memcpy(ah->qplib_ah.dmac, ah_attr->dmac, ETH_ALEN);
+	rc = bnxt_qplib_create_ah(&rdev->qplib_res, &ah->qplib_ah);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to allocate HW AH");
+		goto fail;
+	}
+
+	/* Write AVID to shared page. */
+	if (ib_pd->uobject) {
+		struct ib_ucontext *ib_uctx = ib_pd->uobject->context;
+		struct bnxt_re_ucontext *uctx;
+		unsigned long flag;
+		u32 *wrptr;
+
+		uctx = container_of(ib_uctx, struct bnxt_re_ucontext, ib_uctx);
+		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);
+	}
+
+	return &ah->ib_ah;
+
+fail:
+	kfree(ah);
+	return ERR_PTR(rc);
+}
+
+int bnxt_re_modify_ah(struct ib_ah *ib_ah, struct ib_ah_attr *ah_attr)
+{
+	return 0;
+}
+
+int bnxt_re_query_ah(struct ib_ah *ib_ah, struct ib_ah_attr *ah_attr)
+{
+	struct bnxt_re_ah *ah = container_of(ib_ah, struct bnxt_re_ah, ib_ah);
+
+	memcpy(ah_attr->grh.dgid.raw, ah->qplib_ah.dgid.data,
+	       sizeof(union ib_gid));
+	ah_attr->grh.sgid_index = ah->qplib_ah.host_sgid_index;
+	ah_attr->grh.traffic_class = ah->qplib_ah.traffic_class;
+	ah_attr->sl = ah->qplib_ah.sl;
+	memcpy(ah_attr->dmac, ah->qplib_ah.dmac, ETH_ALEN);
+	ah_attr->ah_flags = IB_AH_GRH;
+	ah_attr->port_num = 1;
+	ah_attr->static_rate = 0;
+	return 0;
+}
+
+/* Queue Pairs */
+int bnxt_re_destroy_qp(struct ib_qp *ib_qp)
+{
+	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
+	struct bnxt_re_dev *rdev = qp->rdev;
+	int rc;
+
+	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to destroy HW QP");
+		return rc;
+	}
+	if (ib_qp->qp_type == IB_QPT_GSI && rdev->qp1_sqp) {
+		rc = bnxt_qplib_destroy_ah(&rdev->qplib_res,
+					   &rdev->sqp_ah->qplib_ah);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to destroy HW AH for shadow QP");
+			return rc;
+		}
+
+		rc = bnxt_qplib_destroy_qp(&rdev->qplib_res,
+					   &rdev->qp1_sqp->qplib_qp);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to destroy Shadow QP");
+			return rc;
+		}
+		mutex_lock(&rdev->qp_lock);
+		list_del(&rdev->qp1_sqp->list);
+		atomic_dec(&rdev->qp_count);
+		mutex_unlock(&rdev->qp_lock);
+
+		kfree(rdev->sqp_ah);
+		kfree(rdev->qp1_sqp);
+	}
+
+	if (qp->rumem && !IS_ERR(qp->rumem))
+		ib_umem_release(qp->rumem);
+	if (qp->sumem && !IS_ERR(qp->sumem))
+		ib_umem_release(qp->sumem);
+
+	mutex_lock(&rdev->qp_lock);
+	list_del(&qp->list);
+	atomic_dec(&rdev->qp_count);
+	mutex_unlock(&rdev->qp_lock);
+	kfree(qp);
+	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 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_re_qp_req ureq;
+	struct bnxt_qplib_qp *qplib_qp = &qp->qplib_qp;
+	struct ib_umem *umem;
+	int bytes = 0;
+	struct ib_ucontext *context = pd->ib_pd.uobject->context;
+	struct bnxt_re_ucontext *cntx = container_of(context,
+						     struct bnxt_re_ucontext,
+						     ib_uctx);
+	if (ib_copy_from_udata(&ureq, udata, sizeof(ureq)))
+		return -EFAULT;
+
+	bytes = (qplib_qp->sq.max_wqe * BNXT_QPLIB_MAX_SQE_ENTRY_SIZE);
+	/* Consider mapping PSN search memory only for RC QPs. */
+	if (qplib_qp->type == CMDQ_CREATE_QP_TYPE_RC)
+		bytes += (qplib_qp->sq.max_wqe * sizeof(struct sq_psn_search));
+	bytes = PAGE_ALIGN(bytes);
+	umem = ib_umem_get(context, ureq.qpsva, bytes,
+			   IB_ACCESS_LOCAL_WRITE, 1);
+	if (IS_ERR(umem))
+		return PTR_ERR(umem);
+
+	qp->sumem = umem;
+	qplib_qp->sq.sglist = umem->sg_head.sgl;
+	qplib_qp->sq.nmap = umem->nmap;
+	qplib_qp->qp_handle = ureq.qp_handle;
+
+	if (!qp->qplib_qp.srq) {
+		bytes = (qplib_qp->rq.max_wqe * BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);
+		bytes = PAGE_ALIGN(bytes);
+		umem = ib_umem_get(context, ureq.qprva, bytes,
+				   IB_ACCESS_LOCAL_WRITE, 1);
+		if (IS_ERR(umem))
+			goto rqfail;
+		qp->rumem = umem;
+		qplib_qp->rq.sglist = umem->sg_head.sgl;
+		qplib_qp->rq.nmap = umem->nmap;
+	}
+
+	qplib_qp->dpi = cntx->dpi;
+	return 0;
+rqfail:
+	ib_umem_release(qp->sumem);
+	qp->sumem = NULL;
+	qplib_qp->sq.sglist = NULL;
+	qplib_qp->sq.nmap = 0;
+
+	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;
+
+	memset(ah, 0, sizeof(*ah));
+	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);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev),
+			"Failed to allocate HW AH for Shadow QP");
+		goto fail;
+	}
+
+	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;
+
+	memset(qp, 0, sizeof(*qp));
+	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.max_wqe = qp1_qp->rq.max_wqe;
+	qp->qplib_qp.sq.max_sge = 2;
+
+	qp->qplib_qp.scq = qp1_qp->scq;
+	qp->qplib_qp.rcq = qp1_qp->rcq;
+
+	qp->qplib_qp.rq.max_wqe = qp1_qp->rq.max_wqe;
+	qp->qplib_qp.rq.max_sge = qp1_qp->rq.max_sge;
+
+	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;
+
+	rdev->sqp_id = qp->qplib_qp.id;
+
+	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;
+}
+
+struct ib_qp *bnxt_re_create_qp(struct ib_pd *ib_pd,
+				struct ib_qp_init_attr *qp_init_attr,
+				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_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_re_qp *qp;
+	struct bnxt_re_cq *cq;
+	int rc, entries;
+
+	if ((qp_init_attr->cap.max_send_wr > dev_attr->max_qp_wqes) ||
+	    (qp_init_attr->cap.max_recv_wr > dev_attr->max_qp_wqes) ||
+	    (qp_init_attr->cap.max_send_sge > dev_attr->max_qp_sges) ||
+	    (qp_init_attr->cap.max_recv_sge > dev_attr->max_qp_sges) ||
+	    (qp_init_attr->cap.max_inline_data > dev_attr->max_inline_data))
+		return ERR_PTR(-EINVAL);
+
+	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+	if (!qp)
+		return ERR_PTR(-ENOMEM);
+
+	qp->rdev = rdev;
+	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 = __from_ib_qp_type(qp_init_attr->qp_type);
+	if (qp->qplib_qp.type == IB_QPT_MAX) {
+		dev_err(rdev_to_dev(rdev), "QP type 0x%x not supported",
+			qp->qplib_qp.type);
+		rc = -EINVAL;
+		goto fail;
+	}
+	qp->qplib_qp.max_inline_data = qp_init_attr->cap.max_inline_data;
+	qp->qplib_qp.sig_type = ((qp_init_attr->sq_sig_type ==
+				  IB_SIGNAL_ALL_WR) ? true : false);
+
+	entries = roundup_pow_of_two(qp_init_attr->cap.max_send_wr + 1);
+	qp->qplib_qp.sq.max_wqe = min_t(u32, entries,
+					dev_attr->max_qp_wqes + 1);
+
+	qp->qplib_qp.sq.max_sge = qp_init_attr->cap.max_send_sge;
+	if (qp->qplib_qp.sq.max_sge > dev_attr->max_qp_sges)
+		qp->qplib_qp.sq.max_sge = dev_attr->max_qp_sges;
+
+	if (qp_init_attr->send_cq) {
+		cq = container_of(qp_init_attr->send_cq, struct bnxt_re_cq,
+				  ib_cq);
+		if (!cq) {
+			dev_err(rdev_to_dev(rdev), "Send CQ not found");
+			rc = -EINVAL;
+			goto fail;
+		}
+		qp->qplib_qp.scq = &cq->qplib_cq;
+	}
+
+	if (qp_init_attr->recv_cq) {
+		cq = container_of(qp_init_attr->recv_cq, struct bnxt_re_cq,
+				  ib_cq);
+		if (!cq) {
+			dev_err(rdev_to_dev(rdev), "Receive CQ not found");
+			rc = -EINVAL;
+			goto fail;
+		}
+		qp->qplib_qp.rcq = &cq->qplib_cq;
+	}
+
+	if (qp_init_attr->srq) {
+		dev_err(rdev_to_dev(rdev), "SRQ not supported");
+		rc = -ENOTSUPP;
+		goto fail;
+	} else {
+		/* Allocate 1 more than what's provided so posting max doesn't
+		 * mean empty
+		 */
+		entries = roundup_pow_of_two(qp_init_attr->cap.max_recv_wr + 1);
+		qp->qplib_qp.rq.max_wqe = min_t(u32, entries,
+						dev_attr->max_qp_wqes + 1);
+
+		qp->qplib_qp.rq.max_sge = qp_init_attr->cap.max_recv_sge;
+		if (qp->qplib_qp.rq.max_sge > dev_attr->max_qp_sges)
+			qp->qplib_qp.rq.max_sge = dev_attr->max_qp_sges;
+	}
+
+	qp->qplib_qp.mtu = ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
+
+	if (qp_init_attr->qp_type == IB_QPT_GSI) {
+		qp->qplib_qp.rq.max_sge = dev_attr->max_qp_sges;
+		if (qp->qplib_qp.rq.max_sge > dev_attr->max_qp_sges)
+			qp->qplib_qp.rq.max_sge = dev_attr->max_qp_sges;
+		qp->qplib_qp.sq.max_sge++;
+		if (qp->qplib_qp.sq.max_sge > dev_attr->max_qp_sges)
+			qp->qplib_qp.sq.max_sge = dev_attr->max_qp_sges;
+
+		qp->qplib_qp.rq_hdr_buf_size =
+					BNXT_QPLIB_MAX_QP1_RQ_HDR_SIZE_V2;
+
+		qp->qplib_qp.sq_hdr_buf_size =
+					BNXT_QPLIB_MAX_QP1_SQ_HDR_SIZE_V2;
+		qp->qplib_qp.dpi = &rdev->dpi_privileged;
+		rc = bnxt_qplib_create_qp1(&rdev->qplib_res, &qp->qplib_qp);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev), "Failed to create HW QP1");
+			goto fail;
+		}
+		/* Create a shadow QP to handle the QP1 traffic */
+		rdev->qp1_sqp = bnxt_re_create_shadow_qp(pd, &rdev->qplib_res,
+							 &qp->qplib_qp);
+		if (!rdev->qp1_sqp) {
+			rc = -EINVAL;
+			dev_err(rdev_to_dev(rdev),
+				"Failed to create Shadow QP for QP1");
+			goto qp_destroy;
+		}
+		rdev->sqp_ah = bnxt_re_create_shadow_qp_ah(pd, &rdev->qplib_res,
+							   &qp->qplib_qp);
+		if (!rdev->sqp_ah) {
+			bnxt_qplib_destroy_qp(&rdev->qplib_res,
+					      &rdev->qp1_sqp->qplib_qp);
+			rc = -EINVAL;
+			dev_err(rdev_to_dev(rdev),
+				"Failed to create AH entry for ShadowQP");
+			goto qp_destroy;
+		}
+
+	} else {
+		qp->qplib_qp.max_rd_atomic = dev_attr->max_qp_rd_atom;
+		qp->qplib_qp.max_dest_rd_atomic = dev_attr->max_qp_init_rd_atom;
+		if (udata) {
+			rc = bnxt_re_init_user_qp(rdev, pd, qp, udata);
+			if (rc)
+				goto fail;
+		} else {
+			qp->qplib_qp.dpi = &rdev->dpi_privileged;
+		}
+
+		rc = bnxt_qplib_create_qp(&rdev->qplib_res, &qp->qplib_qp);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev), "Failed to create HW QP");
+			goto fail;
+		}
+	}
+
+	qp->ib_qp.qp_num = qp->qplib_qp.id;
+	spin_lock_init(&qp->sq_lock);
+
+	if (udata) {
+		struct bnxt_re_qp_resp resp;
+
+		resp.qpid = qp->ib_qp.qp_num;
+		resp.rsvd = 0;
+		rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		if (rc) {
+			dev_err(rdev_to_dev(rdev), "Failed to copy QP udata");
+			goto qp_destroy;
+		}
+	}
+	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->ib_qp;
+qp_destroy:
+	bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
+fail:
+	kfree(qp);
+	return ERR_PTR(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;
+	}
+}
+
+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_modify_shadow_qp(struct bnxt_re_dev *rdev,
+				    struct bnxt_re_qp *qp1_qp,
+				    int qp_attr_mask)
+{
+	struct bnxt_re_qp *qp = rdev->qp1_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)
+		dev_err(rdev_to_dev(rdev),
+			"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;
+	int status;
+	union ib_gid sgid;
+	struct ib_gid_attr sgid_attr;
+	u8 nw_type;
+
+	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,
+					IB_LINK_LAYER_ETHERNET)) {
+			dev_err(rdev_to_dev(rdev),
+				"Invalid attribute mask: %#x specified ",
+				qp_attr_mask);
+			dev_err(rdev_to_dev(rdev),
+				"for qpn: %#x type: %#x",
+				ib_qp->qp_num, ib_qp->qp_type);
+			dev_err(rdev_to_dev(rdev),
+				"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_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;
+	}
+	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) {
+		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, qp_attr->ah_attr.grh.dgid.raw,
+		       sizeof(qp->qplib_qp.ah.dgid.data));
+		qp->qplib_qp.ah.flow_label = qp_attr->ah_attr.grh.flow_label;
+		/* If RoCE V2 is enabled, stack will have two entries for
+		 * each GID entry. Avoiding this duplicte entry in HW. Dividing
+		 * the GID index by 2 for RoCE V2
+		 */
+		qp->qplib_qp.ah.sgid_index =
+					qp_attr->ah_attr.grh.sgid_index / 2;
+		qp->qplib_qp.ah.host_sgid_index =
+					qp_attr->ah_attr.grh.sgid_index;
+		qp->qplib_qp.ah.hop_limit = qp_attr->ah_attr.grh.hop_limit;
+		qp->qplib_qp.ah.traffic_class =
+					qp_attr->ah_attr.grh.traffic_class;
+		qp->qplib_qp.ah.sl = qp_attr->ah_attr.sl;
+		ether_addr_copy(qp->qplib_qp.ah.dmac, qp_attr->ah_attr.dmac);
+
+		status = ib_get_cached_gid(&rdev->ibdev, 1,
+					   qp_attr->ah_attr.grh.sgid_index,
+					   &sgid, &sgid_attr);
+		if (!status && sgid_attr.ndev) {
+			memcpy(qp->qplib_qp.smac, sgid_attr.ndev->dev_addr,
+			       ETH_ALEN);
+			dev_put(sgid_attr.ndev);
+			nw_type = ib_gid_to_network_type(sgid_attr.gid_type,
+							 &sgid);
+			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);
+	} 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));
+	}
+
+	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;
+		qp->qplib_qp.max_rd_atomic = qp_attr->max_rd_atomic;
+	}
+	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) {
+		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)) {
+			dev_err(rdev_to_dev(rdev),
+				"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.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.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) {
+		dev_err(rdev_to_dev(rdev), "Failed to modify HW QP");
+		return rc;
+	}
+	if (ib_qp->qp_type == IB_QPT_GSI && rdev->qp1_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;
+
+	memset(&qplib_qp, 0, sizeof(struct bnxt_qplib_qp));
+	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) {
+		dev_err(rdev_to_dev(rdev), "Failed to query HW QP");
+		return rc;
+	}
+	qp_attr->qp_state = __to_ib_qp_state(qplib_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;
+	memcpy(qp_attr->ah_attr.grh.dgid.raw, qplib_qp.ah.dgid.data,
+	       sizeof(qplib_qp.ah.dgid.data));
+	qp_attr->ah_attr.grh.flow_label = qplib_qp.ah.flow_label;
+	qp_attr->ah_attr.grh.sgid_index = qplib_qp.ah.host_sgid_index;
+	qp_attr->ah_attr.grh.hop_limit = qplib_qp.ah.hop_limit;
+	qp_attr->ah_attr.grh.traffic_class = qplib_qp.ah.traffic_class;
+	qp_attr->ah_attr.sl = qplib_qp.ah.sl;
+	ether_addr_copy(qp_attr->ah_attr.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;
+
+	return 0;
+}
+
+/* Routine for sending QP1 packets for RoCE V1 an V2
+ */
+static int bnxt_re_build_qp1_send_v2(struct bnxt_re_qp *qp,
+				     struct ib_send_wr *wr,
+				     struct bnxt_qplib_swqe *wqe,
+				     int payload_size)
+{
+	struct ib_device *ibdev = &qp->rdev->ibdev;
+	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;
+	struct bnxt_qplib_sge sge;
+	union ib_gid sgid;
+	u8 nw_type;
+	u16 ether_type;
+	struct ib_gid_attr sgid_attr;
+	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, size;
+
+	memset(&qp->qp1_hdr, 0, sizeof(qp->qp1_hdr));
+
+	rc = ib_get_cached_gid(ibdev, 1,
+			       qplib_ah->host_sgid_index, &sgid,
+			       &sgid_attr);
+	if (rc) {
+		dev_err(rdev_to_dev(qp->rdev),
+			"Failed to query gid at index %d",
+			qplib_ah->host_sgid_index);
+		return rc;
+	}
+	if (sgid_attr.ndev) {
+		if (is_vlan_dev(sgid_attr.ndev))
+			vlan_id = vlan_dev_vlan_id(sgid_attr.ndev);
+		dev_put(sgid_attr.ndev);
+	}
+	/* Get network header type for this GID */
+	nw_type = ib_gid_to_network_type(sgid_attr.gid_type, &sgid);
+	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)) {
+			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.raw, sizeof(sgid));
+		memcpy(qp->qp1_hdr.grh.destination_gid.raw, qplib_ah->dgid.data,
+		       sizeof(sgid));
+		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.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) {
+		size = 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 {
+		dev_err(rdev_to_dev(qp->rdev), "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,
+					    struct ib_recv_wr *wr,
+					    struct bnxt_qplib_swqe *wqe,
+					    int payload_size)
+{
+	struct bnxt_qplib_sge ref, sge;
+	u32 rq_prod_index;
+	struct bnxt_re_sqp_entries *sqp_entry;
+
+	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 = &qp->rdev->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;
+}
+
+static int bnxt_re_build_send_wqe(struct bnxt_re_qp *qp,
+				  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(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(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.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(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;
+
+	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_reg_wqe(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 + 1;
+	wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR;
+
+	if (wr->wr.send_flags & IB_SEND_FENCE)
+		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 = (wr->mr->page_size >> PAGE_SHIFT_4K) - 1;
+	wqe->frmr.va = wr->mr->iova;
+	return 0;
+}
+
+static int bnxt_re_copy_inline_data(struct bnxt_re_dev *rdev,
+				    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) {
+			dev_err(rdev_to_dev(rdev),
+				"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,
+				   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 int bnxt_re_post_send_shadow_qp(struct bnxt_re_dev *rdev,
+				       struct bnxt_re_qp *qp,
+				struct ib_send_wr *wr)
+{
+	struct bnxt_qplib_swqe wqe;
+	int rc = 0, payload_sz = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->sq_lock, flags);
+	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.sq.max_sge) {
+			dev_err(rdev_to_dev(rdev),
+				"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) {
+			dev_err(rdev_to_dev(rdev),
+				"Post send failed opcode = %#x rc = %d",
+				wr->opcode, rc);
+			break;
+		}
+		wr = wr->next;
+	}
+	bnxt_qplib_post_send_db(&qp->qplib_qp);
+	spin_unlock_irqrestore(&qp->sq_lock, flags);
+	return rc;
+}
+
+int bnxt_re_post_send(struct ib_qp *ib_qp, struct ib_send_wr *wr,
+		      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) {
+			dev_err(rdev_to_dev(qp->rdev),
+				"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 (ib_qp->qp_type == IB_QPT_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;
+			}
+			/* Fall thru to build the wqe */
+		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:
+			dev_err(rdev_to_dev(qp->rdev),
+				"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 */
+			dev_err(rdev_to_dev(qp->rdev),
+				"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) {
+			dev_err(rdev_to_dev(qp->rdev),
+				"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);
+	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,
+				       struct ib_recv_wr *wr)
+{
+	struct bnxt_qplib_swqe wqe;
+	int rc = 0, payload_sz = 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) {
+			dev_err(rdev_to_dev(rdev),
+				"Limit exceeded for Receive SGEs");
+			rc = -EINVAL;
+			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;
+
+		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, struct ib_recv_wr *wr,
+		      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;
+
+	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) {
+			dev_err(rdev_to_dev(qp->rdev),
+				"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)
+			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;
+		}
+		wr = wr->next;
+	}
+	bnxt_qplib_post_recv_db(&qp->qplib_qp);
+	return rc;
+}
+
+/* Completion Queues */
+int bnxt_re_destroy_cq(struct ib_cq *ib_cq)
+{
+	struct bnxt_re_cq *cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
+	struct bnxt_re_dev *rdev = cq->rdev;
+	int rc;
+
+	rc = bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to destroy HW CQ");
+		return rc;
+	}
+	if (cq->umem && !IS_ERR(cq->umem))
+		ib_umem_release(cq->umem);
+
+	if (cq) {
+		kfree(cq->cql);
+		kfree(cq);
+	}
+	atomic_dec(&rdev->cq_count);
+	rdev->nq.budget--;
+	return 0;
+}
+
+struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
+				struct ib_ucontext *context,
+				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;
+	struct bnxt_re_cq *cq = NULL;
+	int rc, entries;
+	int cqe = attr->cqe;
+
+	/* Validate CQ fields */
+	if (cqe < 1 || cqe > dev_attr->max_cq_wqes) {
+		dev_err(rdev_to_dev(rdev), "Failed to create CQ -max exceeded");
+		return ERR_PTR(-EINVAL);
+	}
+	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+	if (!cq)
+		return ERR_PTR(-ENOMEM);
+
+	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;
+
+	if (context) {
+		struct bnxt_re_cq_req req;
+		struct bnxt_re_ucontext *uctx = container_of
+						(context,
+						 struct bnxt_re_ucontext,
+						 ib_uctx);
+		if (ib_copy_from_udata(&req, udata, sizeof(req))) {
+			rc = -EFAULT;
+			goto fail;
+		}
+
+		cq->umem = ib_umem_get(context, req.cq_va,
+				       entries * sizeof(struct cq_base),
+				       IB_ACCESS_LOCAL_WRITE, 1);
+		if (IS_ERR(cq->umem)) {
+			rc = PTR_ERR(cq->umem);
+			goto fail;
+		}
+		cq->qplib_cq.sghead = cq->umem->sg_head.sgl;
+		cq->qplib_cq.nmap = cq->umem->nmap;
+		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;
+		cq->qplib_cq.sghead = NULL;
+		cq->qplib_cq.nmap = 0;
+	}
+	cq->qplib_cq.max_wqe = entries;
+	cq->qplib_cq.cnq_hw_ring_id = rdev->nq.ring_id;
+
+	rc = bnxt_qplib_create_cq(&rdev->qplib_res, &cq->qplib_cq);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to create HW CQ");
+		goto fail;
+	}
+
+	cq->ib_cq.cqe = entries;
+	cq->cq_period = cq->qplib_cq.period;
+	rdev->nq.budget++;
+
+	atomic_inc(&rdev->cq_count);
+
+	if (context) {
+		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) {
+			dev_err(rdev_to_dev(rdev), "Failed to copy CQ udata");
+			bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
+			goto c2fail;
+		}
+	}
+
+	return &cq->ib_cq;
+
+c2fail:
+	if (context)
+		ib_umem_release(cq->umem);
+fail:
+	kfree(cq->cql);
+	kfree(cq);
+	return ERR_PTR(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_udp = false, 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) {
+		is_udp = true;
+		/* 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 *qp1_qp,
+					 struct bnxt_qplib_cqe *cqe)
+{
+	struct bnxt_re_dev *rdev = qp1_qp->rdev;
+	struct bnxt_re_sqp_entries *sqp_entry = NULL;
+	struct bnxt_re_qp *qp = rdev->qp1_sqp;
+	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 = qp1_qp->qplib_qp.rq_hdr_buf +
+			(tbl_idx * qp1_qp->qplib_qp.rq_hdr_buf_size);
+	rq_hdr_buf_map = bnxt_qplib_get_qp_buf_from_index(&qp1_qp->qplib_qp,
+							  tbl_idx);
+
+	/* Shadow QP header buffer */
+	shrq_hdr_buf_map = bnxt_qplib_get_qp_buf_from_index(&qp->qplib_qp,
+							    tbl_idx);
+	sqp_entry = &rdev->sqp_tbl[tbl_idx];
+
+	/* Store this cqe */
+	memcpy(&sqp_entry->cqe, cqe, sizeof(struct bnxt_qplib_cqe));
+	sqp_entry->qp1_qp = qp1_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) {
+		dev_err(rdev_to_dev(rdev), "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, qp, &rwr);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev),
+			"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;
+
+	udwr.ah = &rdev->sqp_ah->ib_ah;
+	udwr.remote_qpn = rdev->qp1_sqp->qplib_qp.id;
+	udwr.remote_qkey = rdev->qp1_sqp->qplib_qp.qkey;
+
+	/* post data received  in the send queue */
+	rc = bnxt_re_post_send_shadow_qp(rdev, qp, swr);
+
+	return 0;
+}
+
+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 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 *qp,
+					     struct ib_wc *wc,
+					     struct bnxt_qplib_cqe *cqe)
+{
+	u32 tbl_idx;
+	struct bnxt_re_dev *rdev = qp->rdev;
+	struct bnxt_re_qp *qp1_qp = NULL;
+	struct bnxt_qplib_cqe *orig_cqe = NULL;
+	struct bnxt_re_sqp_entries *sqp_entry = NULL;
+	int nw_type;
+
+	tbl_idx = cqe->wr_id;
+
+	sqp_entry = &rdev->sqp_tbl[tbl_idx];
+	qp1_qp = sqp_entry->qp1_qp;
+	orig_cqe = &sqp_entry->cqe;
+
+	wc->wr_id = sqp_entry->wrid;
+	wc->byte_len = orig_cqe->length;
+	wc->qp = &qp1_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);
+	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 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;
+}
+
+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;
+	struct bnxt_qplib_cqe *cqe;
+	int i, ncqe, budget;
+	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);
+	if (!cq->cql) {
+		dev_err(rdev_to_dev(cq->rdev), "POLL CQ : no CQL to use");
+		goto exit;
+	}
+	cqe = &cq->cql[0];
+	while (budget) {
+		ncqe = bnxt_qplib_poll_cq(&cq->qplib_cq, cqe, budget);
+		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);
+			if (!qp) {
+				dev_err(rdev_to_dev(cq->rdev),
+					"POLL CQ : bad QP handle");
+				continue;
+			}
+			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:
+				if (qp->qplib_qp.id ==
+				    qp->rdev->qp1_sqp->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->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:
+				if (qp->qplib_qp.id ==
+				    qp->rdev->qp1_sqp->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(wc, cqe);
+				break;
+			default:
+				dev_err(rdev_to_dev(cq->rdev),
+					"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;
+
+	/* Trigger on the very next completion */
+	if (ib_cqn_flags & IB_CQ_NEXT_COMP)
+		type = DBR_DBR_TYPE_CQ_ARMALL;
+	/* Trigger on the next solicited completion */
+	else if (ib_cqn_flags & IB_CQ_SOLICITED)
+		type = DBR_DBR_TYPE_CQ_ARMSE;
+
+	bnxt_qplib_req_notify_cq(&cq->qplib_cq, type);
+
+	return 0;
+}
+
+/* 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;
+	u64 pbl = 0;
+	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, &pbl, 0, false);
+	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 bnxt_re_mr *mr = container_of(ib_mr, struct bnxt_re_mr, ib_mr);
+	struct bnxt_re_dev *rdev = mr->rdev;
+	int rc = 0;
+
+	if (mr->npages && 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;
+	}
+	rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+
+	if (!IS_ERR(mr->ib_umem) && mr->ib_umem)
+		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) {
+		dev_dbg(rdev_to_dev(rdev), "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 fail;
+
+	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) {
+		dev_err(rdev_to_dev(rdev),
+			"Failed to allocate HW FR page list");
+		goto fail_mr;
+	}
+
+	atomic_inc(&rdev->mr_count);
+	return &mr->ib_mr;
+
+fail_mr:
+	bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+fail:
+	kfree(mr->pages);
+	kfree(mr);
+	return ERR_PTR(rc);
+}
+
+/* Fast Memory Regions */
+struct ib_fmr *bnxt_re_alloc_fmr(struct ib_pd *ib_pd, int mr_access_flags,
+				 struct ib_fmr_attr *fmr_attr)
+{
+	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_fmr *fmr;
+	int rc;
+
+	if (fmr_attr->max_pages > MAX_PBL_LVL_2_PGS ||
+	    fmr_attr->max_maps > rdev->dev_attr.max_map_per_fmr) {
+		dev_err(rdev_to_dev(rdev), "Allocate FMR exceeded Max limit");
+		return ERR_PTR(-ENOMEM);
+	}
+	fmr = kzalloc(sizeof(*fmr), GFP_KERNEL);
+	if (!fmr)
+		return ERR_PTR(-ENOMEM);
+
+	fmr->rdev = rdev;
+	fmr->qplib_fmr.pd = &pd->qplib_pd;
+	fmr->qplib_fmr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR;
+
+	rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &fmr->qplib_fmr);
+	if (rc)
+		goto fail;
+
+	fmr->qplib_fmr.flags = __from_ib_access_flags(mr_access_flags);
+	fmr->ib_fmr.lkey = fmr->qplib_fmr.lkey;
+	fmr->ib_fmr.rkey = fmr->ib_fmr.lkey;
+
+	atomic_inc(&rdev->mr_count);
+	return &fmr->ib_fmr;
+fail:
+	kfree(fmr);
+	return ERR_PTR(rc);
+}
+
+int bnxt_re_map_phys_fmr(struct ib_fmr *ib_fmr, u64 *page_list, int list_len,
+			 u64 iova)
+{
+	struct bnxt_re_fmr *fmr = container_of(ib_fmr, struct bnxt_re_fmr,
+					     ib_fmr);
+	struct bnxt_re_dev *rdev = fmr->rdev;
+	int rc;
+
+	fmr->qplib_fmr.va = iova;
+	fmr->qplib_fmr.total_size = list_len * PAGE_SIZE;
+
+	rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &fmr->qplib_fmr, page_list,
+			       list_len, true);
+	if (rc)
+		dev_err(rdev_to_dev(rdev), "Failed to map FMR for lkey = 0x%x!",
+			fmr->ib_fmr.lkey);
+	return rc;
+}
+
+int bnxt_re_unmap_fmr(struct list_head *fmr_list)
+{
+	struct bnxt_re_dev *rdev;
+	struct bnxt_re_fmr *fmr;
+	struct ib_fmr *ib_fmr;
+	int rc = 0;
+
+	/* Validate each FMRs inside the fmr_list */
+	list_for_each_entry(ib_fmr, fmr_list, list) {
+		fmr = container_of(ib_fmr, struct bnxt_re_fmr, ib_fmr);
+		rdev = fmr->rdev;
+
+		if (rdev) {
+			rc = bnxt_qplib_dereg_mrw(&rdev->qplib_res,
+						  &fmr->qplib_fmr, true);
+			if (rc)
+				break;
+		}
+	}
+	return rc;
+}
+
+int bnxt_re_dealloc_fmr(struct ib_fmr *ib_fmr)
+{
+	struct bnxt_re_fmr *fmr = container_of(ib_fmr, struct bnxt_re_fmr,
+					       ib_fmr);
+	struct bnxt_re_dev *rdev = fmr->rdev;
+	int rc;
+
+	rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &fmr->qplib_fmr);
+	if (rc)
+		dev_err(rdev_to_dev(rdev), "Failed to free FMR");
+
+	kfree(fmr);
+	atomic_dec(&rdev->mr_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;
+	u64 *pbl_tbl, *pbl_tbl_orig;
+	int i, umem_pgs, pages, page_shift, rc;
+	struct scatterlist *sg;
+	int entry;
+
+	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;
+
+	umem = ib_umem_get(ib_pd->uobject->context, start, length,
+			   mr_access_flags, 0);
+	if (IS_ERR(umem)) {
+		dev_err(rdev_to_dev(rdev), "Failed to get umem");
+		rc = -EFAULT;
+		goto free_mr;
+	}
+	mr->ib_umem = umem;
+
+	rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to allocate MR");
+		goto release_umem;
+	}
+	/* The fixed portion of the rkey is the same as the lkey */
+	mr->ib_mr.rkey = mr->qplib_mr.rkey;
+
+	mr->qplib_mr.va = virt_addr;
+	umem_pgs = ib_umem_page_count(umem);
+	if (!umem_pgs) {
+		dev_err(rdev_to_dev(rdev), "umem is invalid!");
+		rc = -EINVAL;
+		goto free_mrw;
+	}
+	mr->qplib_mr.total_size = length;
+
+	pbl_tbl = kcalloc(umem_pgs, sizeof(u64 *), GFP_KERNEL);
+	if (!pbl_tbl) {
+		rc = -EINVAL;
+		goto free_mrw;
+	}
+	pbl_tbl_orig = pbl_tbl;
+
+	page_shift = ilog2(umem->page_size);
+	if (umem->hugetlb) {
+		dev_err(rdev_to_dev(rdev), "umem hugetlb not supported!");
+		rc = -EFAULT;
+		goto fail;
+	}
+	if (umem->page_size != PAGE_SIZE) {
+		dev_err(rdev_to_dev(rdev), "umem page size unsupported!");
+		rc = -EFAULT;
+		goto fail;
+	}
+	/* Map umem buf ptrs to the PBL */
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+		pages = sg_dma_len(sg) >> page_shift;
+		for (i = 0; i < pages; i++, pbl_tbl++)
+			*pbl_tbl = sg_dma_address(sg) + (i << page_shift);
+	}
+	rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, pbl_tbl_orig,
+			       umem_pgs, false);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to register user MR");
+		goto fail;
+	}
+
+	kfree(pbl_tbl_orig);
+
+	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;
+fail:
+	kfree(pbl_tbl_orig);
+free_mrw:
+	bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
+release_umem:
+	ib_umem_release(umem);
+free_mr:
+	kfree(mr);
+	return ERR_PTR(rc);
+}
+
+struct ib_ucontext *bnxt_re_alloc_ucontext(struct ib_device *ibdev,
+					   struct ib_udata *udata)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct bnxt_re_uctx_resp resp;
+	struct bnxt_re_ucontext *uctx;
+	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	int rc;
+
+	dev_dbg(rdev_to_dev(rdev), "ABI version requested %d",
+		ibdev->uverbs_abi_ver);
+
+	if (ibdev->uverbs_abi_ver != BNXT_RE_ABI_VERSION) {
+		dev_dbg(rdev_to_dev(rdev), " is different from the device %d ",
+			BNXT_RE_ABI_VERSION);
+		return ERR_PTR(-EPERM);
+	}
+
+	uctx = kzalloc(sizeof(*uctx), GFP_KERNEL);
+	if (!uctx)
+		return ERR_PTR(-ENOMEM);
+
+	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.dev_id = rdev->en_dev->pdev->devfn; /*Temp, Use idr_alloc instead*/
+	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.rsvd    = 0;
+
+	rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+	if (rc) {
+		dev_err(rdev_to_dev(rdev), "Failed to copy user context");
+		rc = -EFAULT;
+		goto cfail;
+	}
+
+	return &uctx->ib_uctx;
+cfail:
+	free_page((unsigned long)uctx->shpg);
+	uctx->shpg = NULL;
+fail:
+	kfree(uctx);
+	return ERR_PTR(rc);
+}
+
+int bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
+{
+	struct bnxt_re_ucontext *uctx = container_of(ib_uctx,
+						   struct bnxt_re_ucontext,
+						   ib_uctx);
+	if (uctx->shpg)
+		free_page((unsigned long)uctx->shpg);
+	kfree(uctx);
+	return 0;
+}
+
+/* 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)) {
+			dev_err(rdev_to_dev(rdev), "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)) {
+			dev_err(rdev_to_dev(rdev),
+				"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 000000000000..b4084c252f06
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -0,0 +1,197 @@
+/*
+ * 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;
+};
+
+struct bnxt_re_pd {
+	struct bnxt_re_dev	*rdev;
+	struct ib_pd		ib_pd;
+	struct bnxt_qplib_pd	qplib_pd;
+	struct bnxt_qplib_dpi	dpi;
+};
+
+struct bnxt_re_ah {
+	struct bnxt_re_dev	*rdev;
+	struct ib_ah		ib_ah;
+	struct bnxt_qplib_ah	qplib_ah;
+};
+
+struct bnxt_re_qp {
+	struct list_head	list;
+	struct bnxt_re_dev	*rdev;
+	struct ib_qp		ib_qp;
+	spinlock_t		sq_lock;	/* protect sq */
+	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 {
+	struct bnxt_re_dev	*rdev;
+	spinlock_t              cq_lock;	/* protect cq */
+	u16			cq_count;
+	u16			cq_period;
+	struct ib_cq		ib_cq;
+	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_fmr {
+	struct bnxt_re_dev	*rdev;
+	struct ib_fmr		ib_fmr;
+	struct bnxt_qplib_mrw	qplib_fmr;
+};
+
+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 bnxt_re_dev	*rdev;
+	struct ib_ucontext	ib_uctx;
+	struct bnxt_qplib_dpi	*dpi;
+	void			*shpg;
+	spinlock_t		sh_lock;	/* protect shpg */
+};
+
+struct net_device *bnxt_re_get_netdev(struct ib_device *ibdev, u8 port_num);
+
+int bnxt_re_query_device(struct ib_device *ibdev,
+			 struct ib_device_attr *ib_attr,
+			 struct ib_udata *udata);
+int bnxt_re_modify_device(struct ib_device *ibdev,
+			  int device_modify_mask,
+			  struct ib_device_modify *device_modify);
+int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num,
+		       struct ib_port_attr *port_attr);
+int bnxt_re_modify_port(struct ib_device *ibdev, u8 port_num,
+			int port_modify_mask,
+			struct ib_port_modify *port_modify);
+int bnxt_re_get_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable);
+int bnxt_re_query_pkey(struct ib_device *ibdev, u8 port_num,
+		       u16 index, u16 *pkey);
+int bnxt_re_del_gid(struct ib_device *ibdev, u8 port_num,
+		    unsigned int index, void **context);
+int bnxt_re_add_gid(struct ib_device *ibdev, u8 port_num,
+		    unsigned int index, const union ib_gid *gid,
+		    const struct ib_gid_attr *attr, void **context);
+int bnxt_re_query_gid(struct ib_device *ibdev, u8 port_num,
+		      int index, union ib_gid *gid);
+enum rdma_link_layer bnxt_re_get_link_layer(struct ib_device *ibdev,
+					    u8 port_num);
+struct ib_pd *bnxt_re_alloc_pd(struct ib_device *ibdev,
+			       struct ib_ucontext *context,
+			       struct ib_udata *udata);
+int bnxt_re_dealloc_pd(struct ib_pd *pd);
+struct ib_ah *bnxt_re_create_ah(struct ib_pd *pd,
+				struct ib_ah_attr *ah_attr,
+				struct ib_udata *udata);
+int bnxt_re_modify_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr);
+int bnxt_re_query_ah(struct ib_ah *ah, struct ib_ah_attr *ah_attr);
+int bnxt_re_destroy_ah(struct ib_ah *ah);
+struct ib_qp *bnxt_re_create_qp(struct ib_pd *pd,
+				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);
+int bnxt_re_post_send(struct ib_qp *qp, struct ib_send_wr *send_wr,
+		      struct ib_send_wr **bad_send_wr);
+int bnxt_re_post_recv(struct ib_qp *qp, struct ib_recv_wr *recv_wr,
+		      struct ib_recv_wr **bad_recv_wr);
+struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
+				struct ib_ucontext *context,
+				struct ib_udata *udata);
+int bnxt_re_destroy_cq(struct ib_cq *cq);
+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_fmr *bnxt_re_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
+				 struct ib_fmr_attr *fmr_attr);
+int bnxt_re_map_phys_fmr(struct ib_fmr *fmr, u64 *page_list, int list_len,
+			 u64 iova);
+int bnxt_re_unmap_fmr(struct list_head *fmr_list);
+int bnxt_re_dealloc_fmr(struct ib_fmr *fmr);
+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);
+struct ib_ucontext *bnxt_re_alloc_ucontext(struct ib_device *ibdev,
+					   struct ib_udata *udata);
+int bnxt_re_dealloc_ucontext(struct ib_ucontext *context);
+int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
+#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 000000000000..5d355401179b
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -0,0 +1,1315 @@
+/*
+ * 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"
+static char version[] =
+		BNXT_RE_DESC " v" ROCE_DRV_MODULE_VERSION "\n";
+
+MODULE_AUTHOR("Eddie Wai <eddie.wai@broadcom.com>");
+MODULE_DESCRIPTION(BNXT_RE_DESC " Driver");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(ROCE_DRV_MODULE_VERSION);
+
+/* 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;
+
+/* for handling bnxt_en callbacks later */
+static void bnxt_re_stop(void *p)
+{
+}
+
+static void bnxt_re_start(void *p)
+{
+}
+
+static void bnxt_re_sriov_config(void *p, int num_vfs)
+{
+}
+
+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
+};
+
+/* 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, bool lock_wait)
+{
+	struct bnxt_en_dev *en_dev;
+	int rc;
+
+	if (!rdev)
+		return -EINVAL;
+
+	en_dev = rdev->en_dev;
+	/* Acquire rtnl lock if it is not invokded from netdev event */
+	if (lock_wait)
+		rtnl_lock();
+
+	rc = en_dev->en_ops->bnxt_unregister_device(rdev->en_dev,
+						    BNXT_ROCE_ULP);
+	if (lock_wait)
+		rtnl_unlock();
+	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;
+
+	rtnl_lock();
+	rc = en_dev->en_ops->bnxt_register_device(en_dev, BNXT_ROCE_ULP,
+						  &bnxt_re_ulp_ops, rdev);
+	rtnl_unlock();
+	return rc;
+}
+
+static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait)
+{
+	struct bnxt_en_dev *en_dev;
+	int rc;
+
+	if (!rdev)
+		return -EINVAL;
+
+	en_dev = rdev->en_dev;
+
+	if (lock_wait)
+		rtnl_lock();
+
+	rc = en_dev->en_ops->bnxt_free_msix(rdev->en_dev, BNXT_ROCE_ULP);
+
+	if (lock_wait)
+		rtnl_unlock();
+	return rc;
+}
+
+static int bnxt_re_request_msix(struct bnxt_re_dev *rdev)
+{
+	int rc = 0, num_msix_want = BNXT_RE_MIN_MSIX, num_msix_got;
+	struct bnxt_en_dev *en_dev;
+
+	if (!rdev)
+		return -EINVAL;
+
+	en_dev = rdev->en_dev;
+
+	rtnl_lock();
+	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) {
+		dev_warn(rdev_to_dev(rdev),
+			 "Requested %d MSI-X vectors, got %d\n",
+			 num_msix_want, num_msix_got);
+	}
+	rdev->num_msix = num_msix_got;
+done:
+	rtnl_unlock();
+	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,
+				 bool lock_wait)
+{
+	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;
+	bool do_unlock = false;
+	int rc = -EINVAL;
+
+	if (!en_dev)
+		return rc;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+	if (lock_wait) {
+		rtnl_lock();
+		do_unlock = true;
+	}
+
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_FREE, -1, -1);
+	req.ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
+	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)
+		dev_err(rdev_to_dev(rdev),
+			"Failed to free HW ring:%d :%#x", req.ring_id, rc);
+	if (do_unlock)
+		rtnl_unlock();
+	return rc;
+}
+
+static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, dma_addr_t *dma_arr,
+				  int pages, int type, u32 ring_mask,
+				  u32 map_index, 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));
+	rtnl_lock();
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_ALLOC, -1, -1);
+	req.enables = 0;
+	req.page_tbl_addr =  cpu_to_le64(dma_arr[0]);
+	if (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(map_index);
+	req.length = cpu_to_le32(ring_mask + 1);
+	req.ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
+	req.int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
+	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);
+
+	rtnl_unlock();
+	return rc;
+}
+
+static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev,
+				      u32 fw_stats_ctx_id, bool lock_wait)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct hwrm_stat_ctx_free_input req = {0};
+	struct bnxt_fw_msg fw_msg;
+	bool do_unlock = false;
+	int rc = -EINVAL;
+
+	if (!en_dev)
+		return rc;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+	if (lock_wait) {
+		rtnl_lock();
+		do_unlock = true;
+	}
+
+	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 *)&req,
+			    sizeof(req), DFLT_HWRM_CMD_TIMEOUT);
+	rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg);
+	if (rc)
+		dev_err(rdev_to_dev(rdev),
+			"Failed to free HW stats context %#x", rc);
+
+	if (do_unlock)
+		rtnl_unlock();
+	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 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));
+	rtnl_lock();
+
+	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);
+	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);
+
+	rtnl_unlock();
+	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 bnxt_re_dev *rdev;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(rdev, &bnxt_re_dev_list, list) {
+		if (rdev->netdev == netdev) {
+			rcu_read_unlock();
+			return rdev;
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
+}
+
+static void bnxt_re_dev_unprobe(struct net_device *netdev,
+				struct bnxt_en_dev *en_dev)
+{
+	dev_put(netdev);
+	module_put(en_dev->pdev->driver->driver.owner);
+}
+
+static struct bnxt_en_dev *bnxt_re_dev_probe(struct net_device *netdev)
+{
+	struct bnxt *bp = netdev_priv(netdev);
+	struct bnxt_en_dev *en_dev;
+	struct pci_dev *pdev;
+
+	/* Call bnxt_en's RoCE probe via indirect API */
+	if (!bp->ulp_probe)
+		return ERR_PTR(-EINVAL);
+
+	en_dev = bp->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_dbg(&pdev->dev,
+			"%s: probe error: RoCE is not supported on this device",
+			ROCE_DRV_MODULE_NAME);
+		return ERR_PTR(-ENODEV);
+	}
+
+	/* Bump net device reference count */
+	if (!try_module_get(pdev->driver->driver.owner))
+		return ERR_PTR(-ENODEV);
+
+	dev_hold(netdev);
+
+	return en_dev;
+}
+
+static void bnxt_re_unregister_ib(struct bnxt_re_dev *rdev)
+{
+	ib_unregister_device(&rdev->ibdev);
+}
+
+static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
+{
+	struct ib_device *ibdev = &rdev->ibdev;
+
+	/* ib device init */
+	ibdev->owner = THIS_MODULE;
+	ibdev->node_type = RDMA_NODE_IB_CA;
+	strlcpy(ibdev->name, "bnxt_re%d", IB_DEVICE_NAME_MAX);
+	strlcpy(ibdev->node_desc, BNXT_RE_DESC " HCA",
+		strlen(BNXT_RE_DESC) + 5);
+	ibdev->phys_port_cnt = 1;
+
+	bnxt_qplib_get_guid(rdev->netdev->dev_addr, (u8 *)&ibdev->node_guid);
+
+	ibdev->num_comp_vectors	= 1;
+	ibdev->dev.parent = &rdev->en_dev->pdev->dev;
+	ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;
+
+	/* User space */
+	ibdev->uverbs_abi_ver = BNXT_RE_ABI_VERSION;
+	ibdev->uverbs_cmd_mask =
+			(1ull << IB_USER_VERBS_CMD_GET_CONTEXT)		|
+			(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE)	|
+			(1ull << IB_USER_VERBS_CMD_QUERY_PORT)		|
+			(1ull << IB_USER_VERBS_CMD_ALLOC_PD)		|
+			(1ull << IB_USER_VERBS_CMD_DEALLOC_PD)		|
+			(1ull << IB_USER_VERBS_CMD_REG_MR)		|
+			(1ull << IB_USER_VERBS_CMD_REREG_MR)		|
+			(1ull << IB_USER_VERBS_CMD_DEREG_MR)		|
+			(1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) |
+			(1ull << IB_USER_VERBS_CMD_CREATE_CQ)		|
+			(1ull << IB_USER_VERBS_CMD_RESIZE_CQ)		|
+			(1ull << IB_USER_VERBS_CMD_DESTROY_CQ)		|
+			(1ull << IB_USER_VERBS_CMD_CREATE_QP)		|
+			(1ull << IB_USER_VERBS_CMD_MODIFY_QP)		|
+			(1ull << IB_USER_VERBS_CMD_QUERY_QP)		|
+			(1ull << IB_USER_VERBS_CMD_DESTROY_QP)		|
+			(1ull << IB_USER_VERBS_CMD_CREATE_SRQ)		|
+			(1ull << IB_USER_VERBS_CMD_MODIFY_SRQ)		|
+			(1ull << IB_USER_VERBS_CMD_QUERY_SRQ)		|
+			(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ)		|
+			(1ull << IB_USER_VERBS_CMD_CREATE_AH)		|
+			(1ull << IB_USER_VERBS_CMD_MODIFY_AH)		|
+			(1ull << IB_USER_VERBS_CMD_QUERY_AH)		|
+			(1ull << IB_USER_VERBS_CMD_DESTROY_AH);
+	/* POLL_CQ and REQ_NOTIFY_CQ is directly handled in libbnxt_re */
+
+	/* Kernel verbs */
+	ibdev->query_device		= bnxt_re_query_device;
+	ibdev->modify_device		= bnxt_re_modify_device;
+
+	ibdev->query_port		= bnxt_re_query_port;
+	ibdev->modify_port		= bnxt_re_modify_port;
+	ibdev->get_port_immutable	= bnxt_re_get_port_immutable;
+	ibdev->query_pkey		= bnxt_re_query_pkey;
+	ibdev->query_gid		= bnxt_re_query_gid;
+	ibdev->get_netdev		= bnxt_re_get_netdev;
+	ibdev->add_gid			= bnxt_re_add_gid;
+	ibdev->del_gid			= bnxt_re_del_gid;
+	ibdev->get_link_layer		= bnxt_re_get_link_layer;
+
+	ibdev->alloc_pd			= bnxt_re_alloc_pd;
+	ibdev->dealloc_pd		= bnxt_re_dealloc_pd;
+
+	ibdev->create_ah		= bnxt_re_create_ah;
+	ibdev->modify_ah		= bnxt_re_modify_ah;
+	ibdev->query_ah			= bnxt_re_query_ah;
+	ibdev->destroy_ah		= bnxt_re_destroy_ah;
+
+	ibdev->create_qp		= bnxt_re_create_qp;
+	ibdev->modify_qp		= bnxt_re_modify_qp;
+	ibdev->query_qp			= bnxt_re_query_qp;
+	ibdev->destroy_qp		= bnxt_re_destroy_qp;
+
+	ibdev->post_send		= bnxt_re_post_send;
+	ibdev->post_recv		= bnxt_re_post_recv;
+
+	ibdev->create_cq		= bnxt_re_create_cq;
+	ibdev->destroy_cq		= bnxt_re_destroy_cq;
+	ibdev->poll_cq			= bnxt_re_poll_cq;
+	ibdev->req_notify_cq		= bnxt_re_req_notify_cq;
+
+	ibdev->get_dma_mr		= bnxt_re_get_dma_mr;
+	ibdev->dereg_mr			= bnxt_re_dereg_mr;
+	ibdev->alloc_mr			= bnxt_re_alloc_mr;
+	ibdev->map_mr_sg		= bnxt_re_map_mr_sg;
+	ibdev->alloc_fmr		= bnxt_re_alloc_fmr;
+	ibdev->map_phys_fmr		= bnxt_re_map_phys_fmr;
+	ibdev->unmap_fmr		= bnxt_re_unmap_fmr;
+	ibdev->dealloc_fmr		= bnxt_re_dealloc_fmr;
+
+	ibdev->reg_user_mr		= bnxt_re_reg_user_mr;
+	ibdev->alloc_ucontext		= bnxt_re_alloc_ucontext;
+	ibdev->dealloc_ucontext		= bnxt_re_dealloc_ucontext;
+	ibdev->mmap			= bnxt_re_mmap;
+
+	return ib_register_device(ibdev, NULL);
+}
+
+static ssize_t show_rev(struct device *device, struct device_attribute *attr,
+			char *buf)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(device, ibdev.dev);
+
+	return scnprintf(buf, PAGE_SIZE, "0x%x\n", rdev->en_dev->pdev->vendor);
+}
+
+static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
+			   char *buf)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(device, ibdev.dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n", rdev->dev_attr.fw_ver);
+}
+
+static ssize_t show_hca(struct device *device, struct device_attribute *attr,
+			char *buf)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(device, ibdev.dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n", rdev->ibdev.node_desc);
+}
+
+static DEVICE_ATTR(hw_rev, 0444, show_rev, NULL);
+static DEVICE_ATTR(fw_rev, 0444, show_fw_ver, NULL);
+static DEVICE_ATTR(hca_type, 0444, show_hca, NULL);
+
+static struct device_attribute *bnxt_re_attributes[] = {
+	&dev_attr_hw_rev,
+	&dev_attr_fw_rev,
+	&dev_attr_hca_type
+};
+
+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();
+	flush_workqueue(bnxt_re_wq);
+
+	ib_dealloc_device(&rdev->ibdev);
+	/* rdev is gone */
+}
+
+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 = (struct bnxt_re_dev *)ib_alloc_device(sizeof(*rdev));
+	if (!rdev) {
+		dev_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);
+	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_aeq_handler(struct bnxt_qplib_rcfw *rcfw,
+			       struct creq_func_event *aeqe)
+{
+	switch (aeqe->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_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) {
+		dev_err(NULL, "%s: CQ is NULL, CQN not handled",
+			ROCE_DRV_MODULE_NAME);
+		return -EINVAL;
+	}
+	if (cq->ib_cq.comp_handler) {
+		/* Lock comp_handler? */
+		(*cq->ib_cq.comp_handler)(&cq->ib_cq, cq->ib_cq.cq_context);
+	}
+
+	return 0;
+}
+
+static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
+{
+	if (rdev->nq.hwq.max_elements)
+		bnxt_qplib_disable_nq(&rdev->nq);
+
+	if (rdev->qplib_res.rcfw)
+		bnxt_qplib_cleanup_res(&rdev->qplib_res);
+}
+
+static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
+{
+	int rc = 0;
+
+	bnxt_qplib_init_res(&rdev->qplib_res);
+
+	if (rdev->msix_entries[BNXT_RE_NQ_IDX].vector <= 0)
+		return -EINVAL;
+
+	rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq,
+				  rdev->msix_entries[BNXT_RE_NQ_IDX].vector,
+				  rdev->msix_entries[BNXT_RE_NQ_IDX].db_offset,
+				  &bnxt_re_cqn_handler,
+				  NULL);
+
+	if (rc)
+		dev_err(rdev_to_dev(rdev), "Failed to enable NQ: %#x", rc);
+
+	return rc;
+}
+
+static void bnxt_re_free_res(struct bnxt_re_dev *rdev, bool lock_wait)
+{
+	if (rdev->nq.hwq.max_elements) {
+		bnxt_re_net_ring_free(rdev, rdev->nq.ring_id, lock_wait);
+		bnxt_qplib_free_nq(&rdev->nq);
+	}
+	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)
+{
+	int rc = 0;
+
+	/* Configure and allocate resources for qplib */
+	rdev->qplib_res.rcfw = &rdev->rcfw;
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr);
+	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 fail;
+
+	rdev->nq.hwq.max_elements = BNXT_RE_MAX_CQ_COUNT +
+				    BNXT_RE_MAX_SRQC_COUNT + 2;
+	rc = bnxt_qplib_alloc_nq(rdev->en_dev->pdev, &rdev->nq);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev),
+			"Failed to allocate NQ memory: %#x", rc);
+		goto fail;
+	}
+	rc = bnxt_re_net_ring_alloc
+			(rdev, rdev->nq.hwq.pbl[PBL_LVL_0].pg_map_arr,
+			 rdev->nq.hwq.pbl[rdev->nq.hwq.level].pg_count,
+			 HWRM_RING_ALLOC_CMPL, BNXT_QPLIB_NQE_MAX_CNT - 1,
+			 rdev->msix_entries[BNXT_RE_NQ_IDX].ring_idx,
+			 &rdev->nq.ring_id);
+	if (rc) {
+		dev_err(rdev_to_dev(rdev),
+			"Failed to allocate NQ ring: %#x", rc);
+		goto free_nq;
+	}
+	return 0;
+free_nq:
+	bnxt_qplib_free_nq(&rdev->nq);
+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;
+	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) {
+		dev_warn(rdev_to_dev(rdev),
+			 "Asymmetric cos queue configuration detected");
+		dev_warn(rdev_to_dev(rdev),
+			 " 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->qp1_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 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;
+
+	if (!prio_map)
+		prio_map = -EFAULT;
+	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 */
+	rc = bnxt_re_get_priority_mask(rdev);
+	if (rc < 0)
+		return rc;
+	prio_map = (u8)rc;
+
+	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) {
+		dev_warn(rdev_to_dev(rdev), "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) {
+		dev_warn(rdev_to_dev(rdev), "no tc for cos{%x, %x}\n",
+			 rdev->cosq[0], rdev->cosq[1]);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait)
+{
+	int i, rc;
+
+	if (test_and_clear_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags)) {
+		for (i = 0; i < ARRAY_SIZE(bnxt_re_attributes); i++)
+			device_remove_file(&rdev->ibdev.dev,
+					   bnxt_re_attributes[i]);
+		/* Cleanup ib dev */
+		bnxt_re_unregister_ib(rdev);
+	}
+	if (test_and_clear_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags))
+		cancel_delayed_work(&rdev->worker);
+
+	bnxt_re_cleanup_res(rdev);
+	bnxt_re_free_res(rdev, lock_wait);
+
+	if (test_and_clear_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags)) {
+		rc = bnxt_qplib_deinit_rcfw(&rdev->rcfw);
+		if (rc)
+			dev_warn(rdev_to_dev(rdev),
+				 "Failed to deinitialize RCFW: %#x", rc);
+		bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id,
+					   lock_wait);
+		bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx);
+		bnxt_qplib_disable_rcfw_channel(&rdev->rcfw);
+		bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, lock_wait);
+		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, lock_wait);
+		if (rc)
+			dev_warn(rdev_to_dev(rdev),
+				 "Failed to free MSI-X vectors: %#x", rc);
+	}
+	if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) {
+		rc = bnxt_re_unregister_netdev(rdev, lock_wait);
+		if (rc)
+			dev_warn(rdev_to_dev(rdev),
+				 "Failed to unregister with netdev: %#x", rc);
+	}
+}
+
+static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
+{
+	u32 i;
+
+	rdev->qplib_ctx.qpc_count = BNXT_RE_MAX_QPC_COUNT;
+	rdev->qplib_ctx.mrw_count = BNXT_RE_MAX_MRW_COUNT;
+	rdev->qplib_ctx.srqc_count = BNXT_RE_MAX_SRQC_COUNT;
+	rdev->qplib_ctx.cq_count = BNXT_RE_MAX_CQ_COUNT;
+	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
+		rdev->qplib_ctx.tqm_count[i] =
+		rdev->dev_attr.tqm_alloc_reqs[i];
+}
+
+/* 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_ib_reg(struct bnxt_re_dev *rdev)
+{
+	int i, j, rc;
+
+	/* Registered a new RoCE device instance to netdev */
+	rc = bnxt_re_register_netdev(rdev);
+	if (rc) {
+		pr_err("Failed to register with netedev: %#x\n", rc);
+		return -EINVAL;
+	}
+	set_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
+
+	rc = bnxt_re_request_msix(rdev);
+	if (rc) {
+		pr_err("Failed to get MSI-X vectors: %#x\n", rc);
+		rc = -EINVAL;
+		goto fail;
+	}
+	set_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags);
+
+	/* Establish RCFW Communication Channel to initialize the context
+	 * memory for the function and all child VFs
+	 */
+	rc = bnxt_qplib_alloc_rcfw_channel(rdev->en_dev->pdev, &rdev->rcfw);
+	if (rc)
+		goto fail;
+
+	rc = bnxt_re_net_ring_alloc
+			(rdev, rdev->rcfw.creq.pbl[PBL_LVL_0].pg_map_arr,
+			 rdev->rcfw.creq.pbl[rdev->rcfw.creq.level].pg_count,
+			 HWRM_RING_ALLOC_CMPL, BNXT_QPLIB_CREQE_MAX_CNT - 1,
+			 rdev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx,
+			 &rdev->rcfw.creq_ring_id);
+	if (rc) {
+		pr_err("Failed to allocate CREQ: %#x\n", rc);
+		goto free_rcfw;
+	}
+	rc = bnxt_qplib_enable_rcfw_channel
+				(rdev->en_dev->pdev, &rdev->rcfw,
+				 rdev->msix_entries[BNXT_RE_AEQ_IDX].vector,
+				 rdev->msix_entries[BNXT_RE_AEQ_IDX].db_offset,
+				 0, &bnxt_re_aeq_handler);
+	if (rc) {
+		pr_err("Failed to enable RCFW channel: %#x\n", rc);
+		goto free_ring;
+	}
+
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr);
+	if (rc)
+		goto disable_rcfw;
+	bnxt_re_set_resource_limits(rdev);
+
+	rc = bnxt_qplib_alloc_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx, 0);
+	if (rc) {
+		pr_err("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) {
+		pr_err("Failed to allocate stats context: %#x\n", rc);
+		goto free_ctx;
+	}
+
+	rc = bnxt_qplib_init_rcfw(&rdev->rcfw, &rdev->qplib_ctx, 0);
+	if (rc) {
+		pr_err("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) {
+		pr_err("Failed to allocate resources: %#x\n", rc);
+		goto fail;
+	}
+	rc = bnxt_re_init_res(rdev);
+	if (rc) {
+		pr_err("Failed to initialize resources: %#x\n", rc);
+		goto fail;
+	}
+
+	rc = bnxt_re_setup_qos(rdev);
+	if (rc)
+		pr_info("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));
+
+	/* Register ib dev */
+	rc = bnxt_re_register_ib(rdev);
+	if (rc) {
+		pr_err("Failed to register with IB: %#x\n", rc);
+		goto fail;
+	}
+	dev_info(rdev_to_dev(rdev), "Device registered successfully");
+	for (i = 0; i < ARRAY_SIZE(bnxt_re_attributes); i++) {
+		rc = device_create_file(&rdev->ibdev.dev,
+					bnxt_re_attributes[i]);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to create IB sysfs: %#x", rc);
+			/* Must clean up all created device files */
+			for (j = 0; j < i; j++)
+				device_remove_file(&rdev->ibdev.dev,
+						   bnxt_re_attributes[j]);
+			bnxt_re_unregister_ib(rdev);
+			goto fail;
+		}
+	}
+	set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags);
+	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE);
+	bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_GID_CHANGE);
+
+	return 0;
+free_sctx:
+	bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id, true);
+free_ctx:
+	bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx);
+disable_rcfw:
+	bnxt_qplib_disable_rcfw_channel(&rdev->rcfw);
+free_ring:
+	bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, true);
+free_rcfw:
+	bnxt_qplib_free_rcfw_channel(&rdev->rcfw);
+fail:
+	bnxt_re_ib_unreg(rdev, true);
+	return rc;
+}
+
+static void bnxt_re_dev_unreg(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct net_device *netdev = rdev->netdev;
+
+	bnxt_re_dev_remove(rdev);
+
+	if (netdev)
+		bnxt_re_dev_unprobe(netdev, en_dev);
+}
+
+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))
+			pr_err("%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;
+		bnxt_re_dev_unprobe(netdev, en_dev);
+		goto exit;
+	}
+exit:
+	return rc;
+}
+
+static void bnxt_re_remove_one(struct bnxt_re_dev *rdev)
+{
+	pci_dev_put(rdev->en_dev->pdev);
+}
+
+/* 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 &&
+	    !test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
+		return;
+
+	switch (re_work->event) {
+	case NETDEV_REGISTER:
+		rc = bnxt_re_ib_reg(rdev);
+		if (rc)
+			dev_err(rdev_to_dev(rdev),
+				"Failed to register with IB: %#x", rc);
+		break;
+	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);
+		break;
+	default:
+		break;
+	}
+	kfree(re_work);
+}
+
+static void bnxt_re_init_one(struct bnxt_re_dev *rdev)
+{
+	pci_dev_get(rdev->en_dev->pdev);
+}
+
+/*
+ * "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;
+
+	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)
+		goto exit;
+	if (real_dev != netdev)
+		goto exit;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		if (rdev)
+			break;
+		rc = bnxt_re_dev_reg(&rdev, real_dev);
+		if (rc == -ENODEV)
+			break;
+		if (rc) {
+			pr_err("Failed to register with the device %s: %#x\n",
+			       real_dev->name, rc);
+			break;
+		}
+		bnxt_re_init_one(rdev);
+		sch_work = true;
+		break;
+
+	case NETDEV_UNREGISTER:
+		bnxt_re_ib_unreg(rdev, false);
+		bnxt_re_remove_one(rdev);
+		bnxt_re_dev_unreg(rdev);
+		break;
+
+	default:
+		sch_work = true;
+		break;
+	}
+	if (sch_work) {
+		/* Allocate for the deferred task */
+		re_work = kzalloc(sizeof(*re_work), GFP_ATOMIC);
+		if (re_work) {
+			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:
+	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)
+{
+	unregister_netdevice_notifier(&bnxt_re_netdev_notifier);
+	if (bnxt_re_wq)
+		destroy_workqueue(bnxt_re_wq);
+}
+
+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 000000000000..43d08b5e9085
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -0,0 +1,2167 @@
+/*
+ * 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
+ */
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/prefetch.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_arm_cq_enable(struct bnxt_qplib_cq *cq);
+
+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->hwq.max_elements * 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->hwq.max_elements * 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->rq;
+	int rc = 0;
+
+	if (qp->sq_hdr_buf_size && sq->hwq.max_elements) {
+		qp->sq_hdr_buf = dma_alloc_coherent(&res->pdev->dev,
+					sq->hwq.max_elements *
+					qp->sq_hdr_buf_size,
+					&qp->sq_hdr_buf_map, GFP_KERNEL);
+		if (!qp->sq_hdr_buf) {
+			rc = -ENOMEM;
+			dev_err(&res->pdev->dev,
+				"QPLIB: Failed to create sq_hdr_buf");
+			goto fail;
+		}
+	}
+
+	if (qp->rq_hdr_buf_size && rq->hwq.max_elements) {
+		qp->rq_hdr_buf = dma_alloc_coherent(&res->pdev->dev,
+						    rq->hwq.max_elements *
+						    qp->rq_hdr_buf_size,
+						    &qp->rq_hdr_buf_map,
+						    GFP_KERNEL);
+		if (!qp->rq_hdr_buf) {
+			rc = -ENOMEM;
+			dev_err(&res->pdev->dev,
+				"QPLIB: Failed to create rq_hdr_buf");
+			goto fail;
+		}
+	}
+	return 0;
+
+fail:
+	bnxt_qplib_free_qp_hdr_buf(res, qp);
+	return rc;
+}
+
+static void bnxt_qplib_service_nq(unsigned long data)
+{
+	struct bnxt_qplib_nq *nq = (struct bnxt_qplib_nq *)data;
+	struct bnxt_qplib_hwq *hwq = &nq->hwq;
+	struct nq_base *nqe, **nq_ptr;
+	int num_cqne_processed = 0;
+	u32 sw_cons, raw_cons;
+	u16 type;
+	int budget = nq->budget;
+	u64 q_handle;
+
+	/* 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;
+
+		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;
+			bnxt_qplib_arm_cq_enable((struct bnxt_qplib_cq *)
+						 ((unsigned long)q_handle));
+			if (!nq->cqn_handler(nq, (struct bnxt_qplib_cq *)
+						 ((unsigned long)q_handle)))
+				num_cqne_processed++;
+			else
+				dev_warn(&nq->pdev->dev,
+					 "QPLIB: cqn - type 0x%x not handled",
+					 type);
+			break;
+		}
+		case NQ_BASE_TYPE_DBQ_EVENT:
+			break;
+		default:
+			dev_warn(&nq->pdev->dev,
+				 "QPLIB: nqe with type = 0x%x not handled",
+				 type);
+			break;
+		}
+		raw_cons++;
+	}
+	if (hwq->cons != raw_cons) {
+		hwq->cons = raw_cons;
+		NQ_DB_REARM(nq->bar_reg_iomem, hwq->cons, hwq->max_elements);
+	}
+}
+
+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;
+	struct nq_base **nq_ptr;
+	u32 sw_cons;
+
+	/* Prefetch the NQ element */
+	sw_cons = HWQ_CMP(hwq->cons, hwq);
+	nq_ptr = (struct nq_base **)nq->hwq.pbl_ptr;
+	prefetch(&nq_ptr[NQE_PG(sw_cons)][NQE_IDX(sw_cons)]);
+
+	/* Fan out to CPU affinitized kthreads? */
+	tasklet_schedule(&nq->worker);
+
+	return IRQ_HANDLED;
+}
+
+void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
+{
+	/* Make sure the HW is stopped! */
+	synchronize_irq(nq->vector);
+	tasklet_disable(&nq->worker);
+	tasklet_kill(&nq->worker);
+
+	if (nq->requested) {
+		free_irq(nq->vector, nq);
+		nq->requested = false;
+	}
+	if (nq->bar_reg_iomem)
+		iounmap(nq->bar_reg_iomem);
+	nq->bar_reg_iomem = NULL;
+
+	nq->cqn_handler = NULL;
+	nq->srqn_handler = NULL;
+	nq->vector = 0;
+}
+
+int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
+			 int msix_vector, int bar_reg_offset,
+			 int (*cqn_handler)(struct bnxt_qplib_nq *nq,
+					    struct bnxt_qplib_cq *),
+			 int (*srqn_handler)(struct bnxt_qplib_nq *nq,
+					     void *, u8 event))
+{
+	resource_size_t nq_base;
+	int rc;
+
+	nq->pdev = pdev;
+	nq->vector = msix_vector;
+
+	nq->cqn_handler = cqn_handler;
+
+	nq->srqn_handler = srqn_handler;
+
+	tasklet_init(&nq->worker, bnxt_qplib_service_nq, (unsigned long)nq);
+
+	nq->requested = false;
+	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, "bnxt_qplib_nq", nq);
+	if (rc) {
+		dev_err(&nq->pdev->dev,
+			"Failed to request IRQ for NQ: %#x", rc);
+		bnxt_qplib_disable_nq(nq);
+		goto fail;
+	}
+	nq->requested = true;
+	nq->bar_reg = NQ_CONS_PCI_BAR_REGION;
+	nq->bar_reg_off = bar_reg_offset;
+	nq_base = pci_resource_start(pdev, nq->bar_reg);
+	if (!nq_base) {
+		rc = -ENOMEM;
+		goto fail;
+	}
+	nq->bar_reg_iomem = ioremap_nocache(nq_base + nq->bar_reg_off, 4);
+	if (!nq->bar_reg_iomem) {
+		rc = -ENOMEM;
+		goto fail;
+	}
+	NQ_DB_REARM(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);
+
+	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->pdev, &nq->hwq);
+}
+
+int bnxt_qplib_alloc_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq)
+{
+	nq->pdev = pdev;
+	if (!nq->hwq.max_elements ||
+	    nq->hwq.max_elements > BNXT_QPLIB_NQE_MAX_CNT)
+		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;
+
+	if (bnxt_qplib_alloc_init_hwq(nq->pdev, &nq->hwq, NULL, 0,
+				      &nq->hwq.max_elements,
+				      BNXT_QPLIB_MAX_NQE_ENTRY_SIZE, 0,
+				      PAGE_SIZE, HWQ_TYPE_L2_CMPL))
+		return -ENOMEM;
+
+	nq->budget = 8;
+	return 0;
+}
+
+/* QP */
+int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_create_qp1 req;
+	struct creq_create_qp1_resp *resp;
+	struct bnxt_qplib_pbl *pbl;
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct bnxt_qplib_q *rq = &qp->rq;
+	int rc;
+	u16 cmd_flags = 0;
+	u32 qp_flags = 0;
+
+	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 */
+	sq->hwq.max_elements = sq->max_wqe;
+	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &sq->hwq, NULL, 0,
+				       &sq->hwq.max_elements,
+				       BNXT_QPLIB_MAX_SQE_ENTRY_SIZE, 0,
+				       PAGE_SIZE, HWQ_TYPE_QUEUE);
+	if (rc)
+		goto exit;
+
+	sq->swq = kcalloc(sq->hwq.max_elements, sizeof(*sq->swq), GFP_KERNEL);
+	if (!sq->swq) {
+		rc = -ENOMEM;
+		goto fail_sq;
+	}
+	pbl = &sq->hwq.pbl[PBL_LVL_0];
+	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+	req.sq_pg_size_sq_lvl =
+		((sq->hwq.level & CMDQ_CREATE_QP1_SQ_LVL_MASK)
+				<<  CMDQ_CREATE_QP1_SQ_LVL_SFT) |
+		(pbl->pg_size == ROCE_PG_SIZE_4K ?
+				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_4K :
+		 pbl->pg_size == ROCE_PG_SIZE_8K ?
+				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8K :
+		 pbl->pg_size == ROCE_PG_SIZE_64K ?
+				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_64K :
+		 pbl->pg_size == ROCE_PG_SIZE_2M ?
+				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_2M :
+		 pbl->pg_size == ROCE_PG_SIZE_8M ?
+				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8M :
+		 pbl->pg_size == ROCE_PG_SIZE_1G ?
+				CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_1G :
+		 CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_4K);
+
+	if (qp->scq)
+		req.scq_cid = cpu_to_le32(qp->scq->id);
+
+	qp_flags |= CMDQ_CREATE_QP1_QP_FLAGS_RESERVED_LKEY_ENABLE;
+
+	/* RQ */
+	if (rq->max_wqe) {
+		rq->hwq.max_elements = qp->rq.max_wqe;
+		rc = bnxt_qplib_alloc_init_hwq(res->pdev, &rq->hwq, NULL, 0,
+					       &rq->hwq.max_elements,
+					       BNXT_QPLIB_MAX_RQE_ENTRY_SIZE, 0,
+					       PAGE_SIZE, HWQ_TYPE_QUEUE);
+		if (rc)
+			goto fail_sq;
+
+		rq->swq = kcalloc(rq->hwq.max_elements, sizeof(*rq->swq),
+				  GFP_KERNEL);
+		if (!rq->swq) {
+			rc = -ENOMEM;
+			goto fail_rq;
+		}
+		pbl = &rq->hwq.pbl[PBL_LVL_0];
+		req.rq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+		req.rq_pg_size_rq_lvl =
+			((rq->hwq.level & CMDQ_CREATE_QP1_RQ_LVL_MASK) <<
+			 CMDQ_CREATE_QP1_RQ_LVL_SFT) |
+				(pbl->pg_size == ROCE_PG_SIZE_4K ?
+					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_4K :
+				 pbl->pg_size == ROCE_PG_SIZE_8K ?
+					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8K :
+				 pbl->pg_size == ROCE_PG_SIZE_64K ?
+					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_64K :
+				 pbl->pg_size == ROCE_PG_SIZE_2M ?
+					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_2M :
+				 pbl->pg_size == ROCE_PG_SIZE_8M ?
+					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8M :
+				 pbl->pg_size == ROCE_PG_SIZE_1G ?
+					CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_1G :
+				 CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_4K);
+		if (qp->rcq)
+			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 fail;
+	}
+	req.qp_flags = cpu_to_le32(qp_flags);
+	req.sq_size = cpu_to_le32(sq->hwq.max_elements);
+	req.rq_size = cpu_to_le32(rq->hwq.max_elements);
+
+	req.sq_fwo_sq_sge =
+		cpu_to_le16((sq->max_sge & CMDQ_CREATE_QP1_SQ_SGE_MASK) <<
+			    CMDQ_CREATE_QP1_SQ_SGE_SFT);
+	req.rq_fwo_rq_sge =
+		cpu_to_le16((rq->max_sge & CMDQ_CREATE_QP1_RQ_SGE_MASK) <<
+			    CMDQ_CREATE_QP1_RQ_SGE_SFT);
+
+	req.pd_id = cpu_to_le32(qp->pd->id);
+
+	resp = (struct creq_create_qp1_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&res->pdev->dev, "QPLIB: FP: CREATE_QP1 send failed");
+		rc = -EINVAL;
+		goto fail;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_QP1 timed out");
+		rc = -ETIMEDOUT;
+		goto fail;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_QP1 failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		rc = -EINVAL;
+		goto fail;
+	}
+	qp->id = le32_to_cpu(resp->xid);
+	qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET;
+	sq->flush_in_progress = false;
+	rq->flush_in_progress = false;
+
+	return 0;
+
+fail:
+	bnxt_qplib_free_qp_hdr_buf(res, qp);
+fail_rq:
+	bnxt_qplib_free_hwq(res->pdev, &rq->hwq);
+	kfree(rq->swq);
+fail_sq:
+	bnxt_qplib_free_hwq(res->pdev, &sq->hwq);
+	kfree(sq->swq);
+exit:
+	return rc;
+}
+
+int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct sq_send *hw_sq_send_hdr, **hw_sq_send_ptr;
+	struct cmdq_create_qp req;
+	struct creq_create_qp_resp *resp;
+	struct bnxt_qplib_pbl *pbl;
+	struct sq_psn_search **psn_search_ptr;
+	unsigned long int psn_search, poff = 0;
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct bnxt_qplib_hwq *xrrq;
+	int i, rc, req_size, psn_sz;
+	u16 cmd_flags = 0, max_ssge;
+	u32 sw_prod, qp_flags = 0;
+
+	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 */
+	psn_sz = (qp->type == CMDQ_CREATE_QP_TYPE_RC) ?
+		 sizeof(struct sq_psn_search) : 0;
+	sq->hwq.max_elements = sq->max_wqe;
+	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &sq->hwq, sq->sglist,
+				       sq->nmap, &sq->hwq.max_elements,
+				       BNXT_QPLIB_MAX_SQE_ENTRY_SIZE,
+				       psn_sz,
+				       PAGE_SIZE, HWQ_TYPE_QUEUE);
+	if (rc)
+		goto exit;
+
+	sq->swq = kcalloc(sq->hwq.max_elements, sizeof(*sq->swq), GFP_KERNEL);
+	if (!sq->swq) {
+		rc = -ENOMEM;
+		goto fail_sq;
+	}
+	hw_sq_send_ptr = (struct sq_send **)sq->hwq.pbl_ptr;
+	if (psn_sz) {
+		psn_search_ptr = (struct sq_psn_search **)
+				  &hw_sq_send_ptr[get_sqe_pg
+					(sq->hwq.max_elements)];
+		psn_search = (unsigned long int)
+			      &hw_sq_send_ptr[get_sqe_pg(sq->hwq.max_elements)]
+			      [get_sqe_idx(sq->hwq.max_elements)];
+		if (psn_search & ~PAGE_MASK) {
+			/* If the psn_search does not start on a page boundary,
+			 * then calculate the offset
+			 */
+			poff = (psn_search & ~PAGE_MASK) /
+				BNXT_QPLIB_MAX_PSNE_ENTRY_SIZE;
+		}
+		for (i = 0; i < sq->hwq.max_elements; i++)
+			sq->swq[i].psn_search =
+				&psn_search_ptr[get_psne_pg(i + poff)]
+					       [get_psne_idx(i + poff)];
+	}
+	pbl = &sq->hwq.pbl[PBL_LVL_0];
+	req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+	req.sq_pg_size_sq_lvl =
+		((sq->hwq.level & CMDQ_CREATE_QP_SQ_LVL_MASK)
+				 <<  CMDQ_CREATE_QP_SQ_LVL_SFT) |
+		(pbl->pg_size == ROCE_PG_SIZE_4K ?
+				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_4K :
+		 pbl->pg_size == ROCE_PG_SIZE_8K ?
+				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8K :
+		 pbl->pg_size == ROCE_PG_SIZE_64K ?
+				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_64K :
+		 pbl->pg_size == ROCE_PG_SIZE_2M ?
+				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_2M :
+		 pbl->pg_size == ROCE_PG_SIZE_8M ?
+				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8M :
+		 pbl->pg_size == ROCE_PG_SIZE_1G ?
+				CMDQ_CREATE_QP_SQ_PG_SIZE_PG_1G :
+		 CMDQ_CREATE_QP_SQ_PG_SIZE_PG_4K);
+
+	/* initialize all SQ WQEs to LOCAL_INVALID (sq prep for hw fetch) */
+	hw_sq_send_ptr = (struct sq_send **)sq->hwq.pbl_ptr;
+	for (sw_prod = 0; sw_prod < sq->hwq.max_elements; sw_prod++) {
+		hw_sq_send_hdr = &hw_sq_send_ptr[get_sqe_pg(sw_prod)]
+						[get_sqe_idx(sw_prod)];
+		hw_sq_send_hdr->wqe_type = SQ_BASE_WQE_TYPE_LOCAL_INVALID;
+	}
+
+	if (qp->scq)
+		req.scq_cid = cpu_to_le32(qp->scq->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;
+
+	/* RQ */
+	if (rq->max_wqe) {
+		rq->hwq.max_elements = rq->max_wqe;
+		rc = bnxt_qplib_alloc_init_hwq(res->pdev, &rq->hwq, rq->sglist,
+					       rq->nmap, &rq->hwq.max_elements,
+					       BNXT_QPLIB_MAX_RQE_ENTRY_SIZE, 0,
+					       PAGE_SIZE, HWQ_TYPE_QUEUE);
+		if (rc)
+			goto fail_sq;
+
+		rq->swq = kcalloc(rq->hwq.max_elements, sizeof(*rq->swq),
+				  GFP_KERNEL);
+		if (!rq->swq) {
+			rc = -ENOMEM;
+			goto fail_rq;
+		}
+		pbl = &rq->hwq.pbl[PBL_LVL_0];
+		req.rq_pbl = cpu_to_le64(pbl->pg_map_arr[0]);
+		req.rq_pg_size_rq_lvl =
+			((rq->hwq.level & CMDQ_CREATE_QP_RQ_LVL_MASK) <<
+			 CMDQ_CREATE_QP_RQ_LVL_SFT) |
+				(pbl->pg_size == ROCE_PG_SIZE_4K ?
+					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_4K :
+				 pbl->pg_size == ROCE_PG_SIZE_8K ?
+					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8K :
+				 pbl->pg_size == ROCE_PG_SIZE_64K ?
+					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_64K :
+				 pbl->pg_size == ROCE_PG_SIZE_2M ?
+					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_2M :
+				 pbl->pg_size == ROCE_PG_SIZE_8M ?
+					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8M :
+				 pbl->pg_size == ROCE_PG_SIZE_1G ?
+					CMDQ_CREATE_QP_RQ_PG_SIZE_PG_1G :
+				 CMDQ_CREATE_QP_RQ_PG_SIZE_PG_4K);
+	}
+
+	if (qp->rcq)
+		req.rcq_cid = cpu_to_le32(qp->rcq->id);
+	req.qp_flags = cpu_to_le32(qp_flags);
+	req.sq_size = cpu_to_le32(sq->hwq.max_elements);
+	req.rq_size = cpu_to_le32(rq->hwq.max_elements);
+	qp->sq_hdr_buf = NULL;
+	qp->rq_hdr_buf = NULL;
+
+	rc = bnxt_qplib_alloc_qp_hdr_buf(res, qp);
+	if (rc)
+		goto fail_rq;
+
+	/* CTRL-22434: Irrespective of the requested SGE count on the SQ
+	 * always create the QP with max send sges possible if the requested
+	 * inline size is greater than 0.
+	 */
+	max_ssge = qp->max_inline_data ? 6 : sq->max_sge;
+	req.sq_fwo_sq_sge = cpu_to_le16(
+				((max_ssge & CMDQ_CREATE_QP_SQ_SGE_MASK)
+				 << CMDQ_CREATE_QP_SQ_SGE_SFT) | 0);
+	req.rq_fwo_rq_sge = cpu_to_le16(
+				((rq->max_sge & CMDQ_CREATE_QP_RQ_SGE_MASK)
+				 << CMDQ_CREATE_QP_RQ_SGE_SFT) | 0);
+	/* 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);
+		rc = bnxt_qplib_alloc_init_hwq(res->pdev, xrrq, NULL, 0,
+					       &xrrq->max_elements,
+					       BNXT_QPLIB_MAX_ORRQE_ENTRY_SIZE,
+					       0, req_size, HWQ_TYPE_CTX);
+		if (rc)
+			goto fail_buf_free;
+		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);
+
+		rc = bnxt_qplib_alloc_init_hwq(res->pdev, xrrq, NULL, 0,
+					       &xrrq->max_elements,
+					       BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE,
+					       0, req_size, HWQ_TYPE_CTX);
+		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);
+
+	resp = (struct creq_create_qp_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_QP send failed");
+		rc = -EINVAL;
+		goto fail;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_QP timed out");
+		rc = -ETIMEDOUT;
+		goto fail;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_QP failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		rc = -EINVAL;
+		goto fail;
+	}
+	qp->id = le32_to_cpu(resp->xid);
+	qp->cur_qp_state = CMDQ_MODIFY_QP_NEW_STATE_RESET;
+	sq->flush_in_progress = false;
+	rq->flush_in_progress = false;
+
+	return 0;
+
+fail:
+	if (qp->irrq.max_elements)
+		bnxt_qplib_free_hwq(res->pdev, &qp->irrq);
+fail_orrq:
+	if (qp->orrq.max_elements)
+		bnxt_qplib_free_hwq(res->pdev, &qp->orrq);
+fail_buf_free:
+	bnxt_qplib_free_qp_hdr_buf(res, qp);
+fail_rq:
+	bnxt_qplib_free_hwq(res->pdev, &rq->hwq);
+	kfree(rq->swq);
+fail_sq:
+	bnxt_qplib_free_hwq(res->pdev, &sq->hwq);
+	kfree(sq->swq);
+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, pkey;
+	u32 temp32[4];
+	u32 bmask;
+
+	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) {
+		if (!bnxt_qplib_get_pkey(res, &res->pkey_tbl,
+					 qp->pkey_index, &pkey))
+			req.pkey = cpu_to_le16(pkey);
+	}
+	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);
+
+	resp = (struct creq_modify_qp_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: MODIFY_QP send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: MODIFY_QP timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: MODIFY_QP failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	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 creq_query_qp_resp_sb *sb;
+	u16 cmd_flags = 0;
+	u32 temp32[4];
+	int i;
+
+	RCFW_CMD_PREP(req, QUERY_QP, cmd_flags);
+
+	req.qp_cid = cpu_to_le32(qp->id);
+	req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS;
+	resp = (struct creq_query_qp_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     (void **)&sb, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: QUERY_QP send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: QUERY_QP timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: QUERY_QP failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	/* 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, "QPLIB: SGID not found??");
+
+	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);
+	return 0;
+}
+
+static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp)
+{
+	struct bnxt_qplib_hwq *cq_hwq = &cq->hwq;
+	struct cq_base *hw_cqe, **hw_cqe_ptr;
+	int i;
+
+	for (i = 0; i < cq_hwq->max_elements; i++) {
+		hw_cqe_ptr = (struct cq_base **)cq_hwq->pbl_ptr;
+		hw_cqe = &hw_cqe_ptr[CQE_PG(i)][CQE_IDX(i)];
+		if (!CQE_CMP_VALID(hw_cqe, i, cq_hwq->max_elements))
+			continue;
+		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;
+	unsigned long flags;
+	u16 cmd_flags = 0;
+
+	RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags);
+
+	req.qp_cid = cpu_to_le32(qp->id);
+	resp = (struct creq_destroy_qp_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: DESTROY_QP send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: DESTROY_QP timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: DESTROY_QP failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+
+	/* Must walk the associated CQs to nullified the QP ptr */
+	spin_lock_irqsave(&qp->scq->hwq.lock, flags);
+
+	__clean_cq(qp->scq, (u64)(unsigned long)qp);
+
+	if (qp->rcq && qp->rcq != qp->scq) {
+		spin_lock(&qp->rcq->hwq.lock);
+		__clean_cq(qp->rcq, (u64)(unsigned long)qp);
+		spin_unlock(&qp->rcq->hwq.lock);
+	}
+
+	spin_unlock_irqrestore(&qp->scq->hwq.lock, flags);
+
+	bnxt_qplib_free_qp_hdr_buf(res, qp);
+	bnxt_qplib_free_hwq(res->pdev, &qp->sq.hwq);
+	kfree(qp->sq.swq);
+
+	bnxt_qplib_free_hwq(res->pdev, &qp->rq.hwq);
+	kfree(qp->rq.swq);
+
+	if (qp->irrq.max_elements)
+		bnxt_qplib_free_hwq(res->pdev, &qp->irrq);
+	if (qp->orrq.max_elements)
+		bnxt_qplib_free_hwq(res->pdev, &qp->orrq);
+
+	return 0;
+}
+
+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 = HWQ_CMP(sq->hwq.prod, &sq->hwq);
+		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 HWQ_CMP(rq->hwq.prod, &rq->hwq);
+}
+
+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 = HWQ_CMP(rq->hwq.prod, &rq->hwq);
+		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;
+}
+
+void bnxt_qplib_post_send_db(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct dbr_dbr db_msg = { 0 };
+	u32 sw_prod;
+
+	sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);
+
+	db_msg.index = cpu_to_le32((sw_prod << DBR_DBR_INDEX_SFT) &
+				   DBR_DBR_INDEX_MASK);
+	db_msg.type_xid =
+		cpu_to_le32(((qp->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
+			    DBR_DBR_TYPE_SQ);
+	/* Flush all the WQE writes to HW */
+	wmb();
+	__iowrite64_copy(qp->dpi->dbr, &db_msg, sizeof(db_msg) / sizeof(u64));
+}
+
+int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
+			 struct bnxt_qplib_swqe *wqe)
+{
+	struct bnxt_qplib_q *sq = &qp->sq;
+	struct bnxt_qplib_swq *swq;
+	struct sq_send *hw_sq_send_hdr, **hw_sq_send_ptr;
+	struct sq_sge *hw_sge;
+	u32 sw_prod;
+	u8 wqe_size16;
+	int i, rc = 0, data_len = 0, pkt_num = 0;
+	__le32 temp32;
+
+	if (qp->state != CMDQ_MODIFY_QP_NEW_STATE_RTS) {
+		rc = -EINVAL;
+		goto done;
+	}
+	if (HWQ_CMP((sq->hwq.prod + 1), &sq->hwq) ==
+	    HWQ_CMP(sq->hwq.cons, &sq->hwq)) {
+		rc = -ENOMEM;
+		goto done;
+	}
+	sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);
+	swq = &sq->swq[sw_prod];
+	swq->wr_id = wqe->wr_id;
+	swq->type = wqe->type;
+	swq->flags = wqe->flags;
+	if (qp->sig_type)
+		swq->flags |= SQ_SEND_FLAGS_SIGNAL_COMP;
+	swq->start_psn = sq->psn & BTH_PSN_MASK;
+
+	hw_sq_send_ptr = (struct sq_send **)sq->hwq.pbl_ptr;
+	hw_sq_send_hdr = &hw_sq_send_ptr[get_sqe_pg(sw_prod)]
+					[get_sqe_idx(sw_prod)];
+
+	memset(hw_sq_send_hdr, 0, BNXT_QPLIB_MAX_SQE_ENTRY_SIZE);
+
+	if (wqe->flags & BNXT_QPLIB_SWQE_FLAGS_INLINE) {
+		/* Copy the inline data */
+		if (wqe->inline_len > BNXT_QPLIB_SWQE_MAX_INLINE_LENGTH) {
+			dev_warn(&sq->hwq.pdev->dev,
+				 "QPLIB: Inline data length > 96 detected");
+			data_len = BNXT_QPLIB_SWQE_MAX_INLINE_LENGTH;
+		} else {
+			data_len = wqe->inline_len;
+		}
+		memcpy(hw_sq_send_hdr->data, wqe->inline_data, data_len);
+		wqe_size16 = (data_len + 15) >> 4;
+	} else {
+		for (i = 0, hw_sge = (struct sq_sge *)hw_sq_send_hdr->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);
+			data_len += wqe->sg_list[i].size;
+		}
+		/* Each SGE entry = 1 WQE size16 */
+		wqe_size16 = wqe->num_sge;
+	}
+
+	/* Specifics */
+	switch (wqe->type) {
+	case BNXT_QPLIB_SWQE_TYPE_SEND:
+		if (qp->type == CMDQ_CREATE_QP1_TYPE_GSI) {
+			/* Assemble info for Raw Ethertype QPs */
+			struct sq_send_raweth_qp1 *sqe =
+				(struct sq_send_raweth_qp1 *)hw_sq_send_hdr;
+
+			sqe->wqe_type = wqe->type;
+			sqe->flags = wqe->flags;
+			sqe->wqe_size = wqe_size16 +
+				((offsetof(typeof(*sqe), data) + 15) >> 4);
+			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);
+			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;
+		}
+		/* else, just fall thru */
+	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM:
+	case BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV:
+	{
+		struct sq_send *sqe = (struct sq_send *)hw_sq_send_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->wqe_size = wqe_size16 +
+				((offsetof(typeof(*sqe), data) + 15) >> 4);
+		sqe->inv_key_or_imm_data = cpu_to_le32(
+						wqe->send.inv_key);
+		if (qp->type == CMDQ_CREATE_QP_TYPE_UD) {
+			sqe->q_key = cpu_to_le32(wqe->send.q_key);
+			sqe->dst_qp = cpu_to_le32(
+					wqe->send.dst_qp & SQ_SEND_DST_QP_MASK);
+			sqe->length = cpu_to_le32(data_len);
+			sqe->avid = cpu_to_le32(wqe->send.avid &
+						SQ_SEND_AVID_MASK);
+			sq->psn = (sq->psn + 1) & BTH_PSN_MASK;
+		} else {
+			sqe->length = cpu_to_le32(data_len);
+			sqe->dst_qp = 0;
+			sqe->avid = 0;
+			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 *sqe = (struct sq_rdma *)hw_sq_send_hdr;
+
+		sqe->wqe_type = wqe->type;
+		sqe->flags = wqe->flags;
+		sqe->wqe_size = wqe_size16 +
+				((offsetof(typeof(*sqe), data) + 15) >> 4);
+		sqe->imm_data = cpu_to_le32(wqe->rdma.inv_key);
+		sqe->length = cpu_to_le32((u32)data_len);
+		sqe->remote_va = cpu_to_le64(wqe->rdma.remote_va);
+		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 *sqe = (struct sq_atomic *)hw_sq_send_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);
+		sqe->swap_data = cpu_to_le64(wqe->atomic.swap_data);
+		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 =
+				(struct sq_localinvalidate *)hw_sq_send_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 *sqe = (struct sq_fr_pmr *)hw_sq_send_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);
+		sqe->pblptr = cpu_to_le64(wqe->frmr.pbl_dma_ptr);
+		sqe->va = cpu_to_le64(wqe->frmr.va);
+
+		break;
+	}
+	case BNXT_QPLIB_SWQE_TYPE_BIND_MW:
+	{
+		struct sq_bind *sqe = (struct sq_bind *)hw_sq_send_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);
+		sqe->va = cpu_to_le64(wqe->bind.va);
+		temp32 = cpu_to_le32(wqe->bind.length);
+		memcpy(&sqe->length, &temp32, sizeof(wqe->bind.length));
+		break;
+	}
+	default:
+		/* Bad wqe, return error */
+		rc = -EINVAL;
+		goto done;
+	}
+	swq->next_psn = sq->psn & BTH_PSN_MASK;
+	if (swq->psn_search) {
+		swq->psn_search->opcode_start_psn = cpu_to_le32(
+			((swq->start_psn << SQ_PSN_SEARCH_START_PSN_SFT) &
+			 SQ_PSN_SEARCH_START_PSN_MASK) |
+			((wqe->type << SQ_PSN_SEARCH_OPCODE_SFT) &
+			 SQ_PSN_SEARCH_OPCODE_MASK));
+		swq->psn_search->flags_next_psn = cpu_to_le32(
+			((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) &
+			 SQ_PSN_SEARCH_NEXT_PSN_MASK));
+	}
+
+	sq->hwq.prod++;
+done:
+	return rc;
+}
+
+void bnxt_qplib_post_recv_db(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct dbr_dbr db_msg = { 0 };
+	u32 sw_prod;
+
+	sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
+	db_msg.index = cpu_to_le32((sw_prod << DBR_DBR_INDEX_SFT) &
+				   DBR_DBR_INDEX_MASK);
+	db_msg.type_xid =
+		cpu_to_le32(((qp->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
+			    DBR_DBR_TYPE_RQ);
+
+	/* Flush the writes to HW Rx WQE before the ringing Rx DB */
+	wmb();
+	__iowrite64_copy(qp->dpi->dbr, &db_msg, sizeof(db_msg) / sizeof(u64));
+}
+
+int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp,
+			 struct bnxt_qplib_swqe *wqe)
+{
+	struct bnxt_qplib_q *rq = &qp->rq;
+	struct rq_wqe *rqe, **rqe_ptr;
+	struct sq_sge *hw_sge;
+	u32 sw_prod;
+	int i, rc = 0;
+
+	if (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+		dev_err(&rq->hwq.pdev->dev,
+			"QPLIB: FP: QP (0x%x) is in the 0x%x state",
+			qp->id, qp->state);
+		rc = -EINVAL;
+		goto done;
+	}
+	if (HWQ_CMP((rq->hwq.prod + 1), &rq->hwq) ==
+	    HWQ_CMP(rq->hwq.cons, &rq->hwq)) {
+		dev_err(&rq->hwq.pdev->dev,
+			"QPLIB: FP: QP (0x%x) RQ is full!", qp->id);
+		rc = -EINVAL;
+		goto done;
+	}
+	sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
+	rq->swq[sw_prod].wr_id = wqe->wr_id;
+
+	rqe_ptr = (struct rq_wqe **)rq->hwq.pbl_ptr;
+	rqe = &rqe_ptr[RQE_PG(sw_prod)][RQE_IDX(sw_prod)];
+
+	memset(rqe, 0, BNXT_QPLIB_MAX_RQE_ENTRY_SIZE);
+
+	/* Calculate wqe_size16 and data_len */
+	for (i = 0, hw_sge = (struct sq_sge *)rqe->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);
+	}
+	rqe->wqe_type = wqe->type;
+	rqe->flags = wqe->flags;
+	rqe->wqe_size = wqe->num_sge +
+			((offsetof(typeof(*rqe), data) + 15) >> 4);
+
+	/* Supply the rqe->wr_id index to the wr_id_tbl for now */
+	rqe->wr_id[0] = cpu_to_le32(sw_prod);
+
+	rq->hwq.prod++;
+done:
+	return rc;
+}
+
+/* CQ */
+
+/* Spinlock must be held */
+static void bnxt_qplib_arm_cq_enable(struct bnxt_qplib_cq *cq)
+{
+	struct dbr_dbr db_msg = { 0 };
+
+	db_msg.type_xid =
+		cpu_to_le32(((cq->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
+			    DBR_DBR_TYPE_CQ_ARMENA);
+	/* Flush memory writes before enabling the CQ */
+	wmb();
+	__iowrite64_copy(cq->dbr_base, &db_msg, sizeof(db_msg) / sizeof(u64));
+}
+
+static void bnxt_qplib_arm_cq(struct bnxt_qplib_cq *cq, u32 arm_type)
+{
+	struct bnxt_qplib_hwq *cq_hwq = &cq->hwq;
+	struct dbr_dbr db_msg = { 0 };
+	u32 sw_cons;
+
+	/* Ring DB */
+	sw_cons = HWQ_CMP(cq_hwq->cons, cq_hwq);
+	db_msg.index = cpu_to_le32((sw_cons << DBR_DBR_INDEX_SFT) &
+				    DBR_DBR_INDEX_MASK);
+	db_msg.type_xid =
+		cpu_to_le32(((cq->id << DBR_DBR_XID_SFT) & DBR_DBR_XID_MASK) |
+			    arm_type);
+	/* flush memory writes before arming the CQ */
+	wmb();
+	__iowrite64_copy(cq->dpi->dbr, &db_msg, sizeof(db_msg) / sizeof(u64));
+}
+
+int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_create_cq req;
+	struct creq_create_cq_resp *resp;
+	struct bnxt_qplib_pbl *pbl;
+	u16 cmd_flags = 0;
+	int rc;
+
+	cq->hwq.max_elements = cq->max_wqe;
+	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &cq->hwq, cq->sghead,
+				       cq->nmap, &cq->hwq.max_elements,
+				       BNXT_QPLIB_MAX_CQE_ENTRY_SIZE, 0,
+				       PAGE_SIZE, HWQ_TYPE_QUEUE);
+	if (rc)
+		goto exit;
+
+	RCFW_CMD_PREP(req, CREATE_CQ, cmd_flags);
+
+	if (!cq->dpi) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: FP: CREATE_CQ failed due to NULL DPI");
+		return -EINVAL;
+	}
+	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];
+	req.pg_size_lvl = cpu_to_le32(
+	    ((cq->hwq.level & CMDQ_CREATE_CQ_LVL_MASK) <<
+						CMDQ_CREATE_CQ_LVL_SFT) |
+	    (pbl->pg_size == ROCE_PG_SIZE_4K ? CMDQ_CREATE_CQ_PG_SIZE_PG_4K :
+	     pbl->pg_size == ROCE_PG_SIZE_8K ? CMDQ_CREATE_CQ_PG_SIZE_PG_8K :
+	     pbl->pg_size == ROCE_PG_SIZE_64K ? CMDQ_CREATE_CQ_PG_SIZE_PG_64K :
+	     pbl->pg_size == ROCE_PG_SIZE_2M ? CMDQ_CREATE_CQ_PG_SIZE_PG_2M :
+	     pbl->pg_size == ROCE_PG_SIZE_8M ? CMDQ_CREATE_CQ_PG_SIZE_PG_8M :
+	     pbl->pg_size == ROCE_PG_SIZE_1G ? CMDQ_CREATE_CQ_PG_SIZE_PG_1G :
+	     CMDQ_CREATE_CQ_PG_SIZE_PG_4K));
+
+	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);
+
+	resp = (struct creq_create_cq_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_CQ send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_CQ timed out");
+		rc = -ETIMEDOUT;
+		goto fail;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: CREATE_CQ failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		rc = -EINVAL;
+		goto fail;
+	}
+	cq->id = le32_to_cpu(resp->xid);
+	cq->dbr_base = res->dpi_tbl.dbr_bar_reg_iomem;
+	cq->period = BNXT_QPLIB_QUEUE_START_PERIOD;
+	init_waitqueue_head(&cq->waitq);
+
+	bnxt_qplib_arm_cq_enable(cq);
+	return 0;
+
+fail:
+	bnxt_qplib_free_hwq(res->pdev, &cq->hwq);
+exit:
+	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 cmd_flags = 0;
+
+	RCFW_CMD_PREP(req, DESTROY_CQ, cmd_flags);
+
+	req.cq_cid = cpu_to_le32(cq->id);
+	resp = (struct creq_destroy_cq_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: DESTROY_CQ send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: DESTROY_CQ timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: FP: DESTROY_CQ failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	bnxt_qplib_free_hwq(res->pdev, &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)
+{
+	u32 sw_prod, sw_cons;
+	struct bnxt_qplib_cqe *cqe;
+	int rc = 0;
+
+	/* Now complete all outstanding SQEs with FLUSHED_ERR */
+	sw_prod = HWQ_CMP(sq->hwq.prod, &sq->hwq);
+	cqe = *pcqe;
+	while (*budget) {
+		sw_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq);
+		if (sw_cons == sw_prod) {
+			sq->flush_in_progress = false;
+			break;
+		}
+		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[sw_cons].wr_id;
+		cqe->src_qp = qp->id;
+		cqe->type = sq->swq[sw_cons].type;
+		cqe++;
+		(*budget)--;
+		sq->hwq.cons++;
+	}
+	*pcqe = cqe;
+	if (!(*budget) && HWQ_CMP(sq->hwq.cons, &sq->hwq) != sw_prod)
+		/* Out of budget */
+		rc = -EAGAIN;
+
+	return rc;
+}
+
+static int __flush_rq(struct bnxt_qplib_q *rq, struct bnxt_qplib_qp *qp,
+		      int opcode, struct bnxt_qplib_cqe **pcqe, int *budget)
+{
+	struct bnxt_qplib_cqe *cqe;
+	u32 sw_prod, sw_cons;
+	int rc = 0;
+
+	/* Flush the rest of the RQ */
+	sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
+	cqe = *pcqe;
+	while (*budget) {
+		sw_cons = HWQ_CMP(rq->hwq.cons, &rq->hwq);
+		if (sw_cons == sw_prod)
+			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[sw_cons].wr_id;
+		cqe++;
+		(*budget)--;
+		rq->hwq.cons++;
+	}
+	*pcqe = cqe;
+	if (!*budget && HWQ_CMP(rq->hwq.cons, &rq->hwq) != sw_prod)
+		/* Out of budget */
+		rc = -EAGAIN;
+
+	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)
+{
+	struct bnxt_qplib_qp *qp;
+	struct bnxt_qplib_q *sq;
+	struct bnxt_qplib_cqe *cqe;
+	u32 sw_cons, cqe_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,
+			"QPLIB: FP: Process Req qp is NULL");
+		return -EINVAL;
+	}
+	sq = &qp->sq;
+
+	cqe_cons = HWQ_CMP(le16_to_cpu(hwcqe->sq_cons_idx), &sq->hwq);
+	if (cqe_cons > sq->hwq.max_elements) {
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: FP: CQ Process req reported ");
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: sq_cons_idx 0x%x which exceeded max 0x%x",
+			cqe_cons, sq->hwq.max_elements);
+		return -EINVAL;
+	}
+	/* If we were in the middle of flushing the SQ, continue */
+	if (sq->flush_in_progress)
+		goto flush;
+
+	/* 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_cons
+	 */
+	cqe = *pcqe;
+	while (*budget) {
+		sw_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq);
+		if (sw_cons == cqe_cons)
+			break;
+		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 = sq->swq[sw_cons].wr_id;
+		cqe->type = sq->swq[sw_cons].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 (HWQ_CMP((sw_cons + 1), &sq->hwq) == cqe_cons &&
+		    hwcqe->status != CQ_REQ_STATUS_OK) {
+			cqe->status = hwcqe->status;
+			dev_err(&cq->hwq.pdev->dev,
+				"QPLIB: FP: CQ Processed Req ");
+			dev_err(&cq->hwq.pdev->dev,
+				"QPLIB: wr_id[%d] = 0x%llx with status 0x%x",
+				sw_cons, cqe->wr_id, cqe->status);
+			cqe++;
+			(*budget)--;
+			sq->flush_in_progress = true;
+			/* Must block new posting of SQ and RQ */
+			qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
+		} else {
+			if (sq->swq[sw_cons].flags &
+			    SQ_SEND_FLAGS_SIGNAL_COMP) {
+				cqe->status = CQ_REQ_STATUS_OK;
+				cqe++;
+				(*budget)--;
+			}
+		}
+		sq->hwq.cons++;
+	}
+	*pcqe = cqe;
+	if (!*budget && HWQ_CMP(sq->hwq.cons, &sq->hwq) != cqe_cons) {
+		/* Out of budget */
+		rc = -EAGAIN;
+		goto done;
+	}
+	if (!sq->flush_in_progress)
+		goto done;
+flush:
+	/* Require to walk the sq's swq to fabricate CQEs for all
+	 * previously posted SWQEs due to the error CQE received
+	 */
+	rc = __flush_sq(sq, qp, pcqe, budget);
+	if (!rc)
+		sq->flush_in_progress = false;
+done:
+	return rc;
+}
+
+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_qp *qp;
+	struct bnxt_qplib_q *rq;
+	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, "QPLIB: process_cq RC qp is NULL");
+		return -EINVAL;
+	}
+	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;
+	rq = &qp->rq;
+	if (wr_id_idx > rq->hwq.max_elements) {
+		dev_err(&cq->hwq.pdev->dev, "QPLIB: FP: CQ Process RC ");
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: wr_id idx 0x%x exceeded RQ max 0x%x",
+			wr_id_idx, rq->hwq.max_elements);
+		return -EINVAL;
+	}
+	if (rq->flush_in_progress)
+		goto flush_rq;
+
+	cqe->wr_id = rq->swq[wr_id_idx].wr_id;
+	cqe++;
+	(*budget)--;
+	rq->hwq.cons++;
+	*pcqe = cqe;
+
+	if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
+		rq->flush_in_progress = true;
+flush_rq:
+		rc = __flush_rq(rq, qp, CQ_BASE_CQE_TYPE_RES_RC, pcqe, budget);
+		if (!rc)
+			rq->flush_in_progress = false;
+	}
+	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_qp *qp;
+	struct bnxt_qplib_q *rq;
+	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, "QPLIB: process_cq UD qp is NULL");
+		return -EINVAL;
+	}
+	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);
+	cqe->flags = le16_to_cpu(hwcqe->flags);
+	cqe->status = hwcqe->status;
+	cqe->qp_handle = (u64)(unsigned long)qp;
+	memcpy(cqe->smac, hwcqe->src_mac, 6);
+	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);
+
+	rq = &qp->rq;
+	if (wr_id_idx > rq->hwq.max_elements) {
+		dev_err(&cq->hwq.pdev->dev, "QPLIB: FP: CQ Process UD ");
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: wr_id idx %#x exceeded RQ max %#x",
+			wr_id_idx, rq->hwq.max_elements);
+		return -EINVAL;
+	}
+	if (rq->flush_in_progress)
+		goto flush_rq;
+
+	cqe->wr_id = rq->swq[wr_id_idx].wr_id;
+	cqe++;
+	(*budget)--;
+	rq->hwq.cons++;
+	*pcqe = cqe;
+
+	if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
+		rq->flush_in_progress = true;
+flush_rq:
+		rc = __flush_rq(rq, qp, CQ_BASE_CQE_TYPE_RES_UD, pcqe, budget);
+		if (!rc)
+			rq->flush_in_progress = false;
+	}
+	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_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,
+			"QPLIB: process_cq Raw/QP1 qp is NULL");
+		return -EINVAL;
+	}
+	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);
+
+	rq = &qp->rq;
+	if (wr_id_idx > rq->hwq.max_elements) {
+		dev_err(&cq->hwq.pdev->dev, "QPLIB: FP: CQ Process Raw/QP1 RQ wr_id ");
+		dev_err(&cq->hwq.pdev->dev, "QPLIB: ix 0x%x exceeded RQ max 0x%x",
+			wr_id_idx, rq->hwq.max_elements);
+		return -EINVAL;
+	}
+	if (rq->flush_in_progress)
+		goto flush_rq;
+
+	cqe->wr_id = rq->swq[wr_id_idx].wr_id;
+	cqe++;
+	(*budget)--;
+	rq->hwq.cons++;
+	*pcqe = cqe;
+
+	if (hwcqe->status != CQ_RES_RC_STATUS_OK) {
+		rq->flush_in_progress = true;
+flush_rq:
+		rc = __flush_rq(rq, qp, CQ_BASE_CQE_TYPE_RES_RAWETH_QP1, pcqe,
+				budget);
+		if (!rc)
+			rq->flush_in_progress = false;
+	}
+	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 sw_cons = 0, cqe_cons;
+	int rc = 0;
+	u8 opcode = 0;
+
+	/* Check the Status */
+	if (hwcqe->status != CQ_TERMINAL_STATUS_OK)
+		dev_warn(&cq->hwq.pdev->dev,
+			 "QPLIB: FP: CQ Process Terminal Error status = 0x%x",
+			 hwcqe->status);
+
+	qp = (struct bnxt_qplib_qp *)((unsigned long)
+				      le64_to_cpu(hwcqe->qp_handle));
+	if (!qp) {
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: FP: CQ Process terminal qp is NULL");
+		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;
+
+	if (cqe_cons > sq->hwq.max_elements) {
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: FP: CQ Process terminal reported ");
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: sq_cons_idx 0x%x which exceeded max 0x%x",
+			cqe_cons, sq->hwq.max_elements);
+		goto do_rq;
+	}
+	/* If we were in the middle of flushing, continue */
+	if (sq->flush_in_progress)
+		goto flush_sq;
+
+	/* 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) {
+		sw_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq);
+		if (sw_cons == cqe_cons)
+			break;
+		if (sq->swq[sw_cons].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[sw_cons].wr_id;
+			cqe->type = sq->swq[sw_cons].type;
+			cqe++;
+			(*budget)--;
+		}
+		sq->hwq.cons++;
+	}
+	*pcqe = cqe;
+	if (!(*budget) && sw_cons != cqe_cons) {
+		/* Out of budget */
+		rc = -EAGAIN;
+		goto sq_done;
+	}
+	sq->flush_in_progress = true;
+flush_sq:
+	rc = __flush_sq(sq, qp, pcqe, budget);
+	if (!rc)
+		sq->flush_in_progress = false;
+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->hwq.max_elements) {
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: FP: CQ Processed terminal ");
+		dev_err(&cq->hwq.pdev->dev,
+			"QPLIB: reported rq_cons_idx 0x%x exceeds max 0x%x",
+			cqe_cons, rq->hwq.max_elements);
+		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
+	 */
+	rq->flush_in_progress = true;
+	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:
+		opcode = CQ_BASE_CQE_TYPE_RES_UD;
+		break;
+	}
+
+	rc = __flush_rq(rq, qp, opcode, pcqe, budget);
+	if (!rc)
+		rq->flush_in_progress = false;
+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,
+			"QPLIB: FP: CQ Process Cutoff Error status = 0x%x",
+			hwcqe->status);
+		return -EINVAL;
+	}
+	clear_bit(CQ_FLAGS_RESIZE_IN_PROG, &cq->flags);
+	wake_up_interruptible(&cq->waitq);
+
+	return 0;
+}
+
+int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe,
+		       int num_cqes)
+{
+	struct cq_base *hw_cqe, **hw_cqe_ptr;
+	unsigned long flags;
+	u32 sw_cons, raw_cons;
+	int budget, rc = 0;
+
+	spin_lock_irqsave(&cq->hwq.lock, flags);
+	raw_cons = cq->hwq.cons;
+	budget = num_cqes;
+
+	while (budget) {
+		sw_cons = HWQ_CMP(raw_cons, &cq->hwq);
+		hw_cqe_ptr = (struct cq_base **)cq->hwq.pbl_ptr;
+		hw_cqe = &hw_cqe_ptr[CQE_PG(sw_cons)][CQE_IDX(sw_cons)];
+
+		/* Check for Valid bit */
+		if (!CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements))
+			break;
+
+		/* From the device's respective CQE format to qplib_wc*/
+		switch (hw_cqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK) {
+		case CQ_BASE_CQE_TYPE_REQ:
+			rc = bnxt_qplib_cq_process_req(cq,
+						       (struct cq_req *)hw_cqe,
+						       &cqe, &budget);
+			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,
+				"QPLIB: process_cq unknown type 0x%lx",
+				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
+			 */
+			dev_err(&cq->hwq.pdev->dev,
+				"QPLIB: process_cqe error rc = 0x%x", rc);
+		}
+		raw_cons++;
+	}
+	if (cq->hwq.cons != raw_cons) {
+		cq->hwq.cons = raw_cons;
+		bnxt_qplib_arm_cq(cq, DBR_DBR_TYPE_CQ);
+	}
+exit:
+	spin_unlock_irqrestore(&cq->hwq.lock, flags);
+	return num_cqes - budget;
+}
+
+void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cq->hwq.lock, flags);
+	if (arm_type)
+		bnxt_qplib_arm_cq(cq, arm_type);
+
+	spin_unlock_irqrestore(&cq->hwq.lock, flags);
+}
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 000000000000..f0150f8da1e3
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -0,0 +1,439 @@
+/*
+ * 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__
+
+struct bnxt_qplib_sge {
+	u64				addr;
+	u32				lkey;
+	u32				size;
+};
+
+#define BNXT_QPLIB_MAX_SQE_ENTRY_SIZE	sizeof(struct sq_send)
+
+#define SQE_CNT_PER_PG		(PAGE_SIZE / BNXT_QPLIB_MAX_SQE_ENTRY_SIZE)
+#define SQE_MAX_IDX_PER_PG	(SQE_CNT_PER_PG - 1)
+
+static inline u32 get_sqe_pg(u32 val)
+{
+	return ((val & ~SQE_MAX_IDX_PER_PG) / SQE_CNT_PER_PG);
+}
+
+static inline u32 get_sqe_idx(u32 val)
+{
+	return (val & SQE_MAX_IDX_PER_PG);
+}
+
+#define BNXT_QPLIB_MAX_PSNE_ENTRY_SIZE	sizeof(struct sq_psn_search)
+
+#define PSNE_CNT_PER_PG		(PAGE_SIZE / BNXT_QPLIB_MAX_PSNE_ENTRY_SIZE)
+#define PSNE_MAX_IDX_PER_PG	(PSNE_CNT_PER_PG - 1)
+
+static inline u32 get_psne_pg(u32 val)
+{
+	return ((val & ~PSNE_MAX_IDX_PER_PG) / PSNE_CNT_PER_PG);
+}
+
+static inline u32 get_psne_idx(u32 val)
+{
+	return (val & PSNE_MAX_IDX_PER_PG);
+}
+
+#define BNXT_QPLIB_QP_MAX_SGL	6
+
+struct bnxt_qplib_swq {
+	u64				wr_id;
+	u8				type;
+	u8				flags;
+	u32				start_psn;
+	u32				next_psn;
+	struct sq_psn_search		*psn_search;
+};
+
+struct bnxt_qplib_swqe {
+	/* General */
+	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;
+	};
+};
+
+#define BNXT_QPLIB_MAX_RQE_ENTRY_SIZE	sizeof(struct rq_wqe)
+
+#define RQE_CNT_PER_PG		(PAGE_SIZE / BNXT_QPLIB_MAX_RQE_ENTRY_SIZE)
+#define RQE_MAX_IDX_PER_PG	(RQE_CNT_PER_PG - 1)
+#define RQE_PG(x)		(((x) & ~RQE_MAX_IDX_PER_PG) / RQE_CNT_PER_PG)
+#define RQE_IDX(x)		((x) & RQE_MAX_IDX_PER_PG)
+
+struct bnxt_qplib_q {
+	struct bnxt_qplib_hwq		hwq;
+	struct bnxt_qplib_swq		*swq;
+	struct scatterlist		*sglist;
+	u32				nmap;
+	u32				max_wqe;
+	u16				max_sge;
+	u32				psn;
+	bool				flush_in_progress;
+};
+
+struct bnxt_qplib_qp {
+	struct bnxt_qplib_pd		*pd;
+	struct bnxt_qplib_dpi		*dpi;
+	u64				qp_handle;
+	u32				id;
+	u8				type;
+	u8				sig_type;
+	u32				modify_flags;
+	u8				state;
+	u8				cur_qp_state;
+	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;
+	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;
+};
+
+#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)))
+
+struct bnxt_qplib_cqe {
+	u8				status;
+	u8				type;
+	u8				opcode;
+	u32				length;
+	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;
+	void __iomem			*dbr_base;
+	u32				max_wqe;
+	u32				id;
+	u16				count;
+	u16				period;
+	struct bnxt_qplib_hwq		hwq;
+	u32				cnq_hw_ring_id;
+	bool				resize_in_progress;
+	struct scatterlist		*sghead;
+	u32				nmap;
+	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;
+};
+
+#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)
+#define NQ_DB_REARM(db, raw_cons, cp_bit)			\
+	writel(NQ_DB_CP_FLAGS_REARM | ((raw_cons) & ((cp_bit) - 1)), db)
+#define NQ_DB(db, raw_cons, cp_bit)				\
+	writel(NQ_DB_CP_FLAGS | ((raw_cons) & ((cp_bit) - 1)), db)
+
+struct bnxt_qplib_nq {
+	struct pci_dev			*pdev;
+
+	int				vector;
+	int				budget;
+	bool				requested;
+	struct tasklet_struct		worker;
+	struct bnxt_qplib_hwq		hwq;
+
+	u16				bar_reg;
+	u16				bar_reg_off;
+	u16				ring_id;
+	void __iomem			*bar_reg_iomem;
+
+	int				(*cqn_handler)
+						(struct bnxt_qplib_nq *nq,
+						 struct bnxt_qplib_cq *cq);
+	int				(*srqn_handler)
+						(struct bnxt_qplib_nq *nq,
+						 void *srq,
+						 u8 event);
+};
+
+void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq);
+int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
+			 int msix_vector, int bar_reg_offset,
+			 int (*cqn_handler)(struct bnxt_qplib_nq *nq,
+					    struct bnxt_qplib_cq *cq),
+			 int (*srqn_handler)(struct bnxt_qplib_nq *nq,
+					     void *srq,
+					     u8 event));
+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_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);
+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 pci_dev *pdev, struct bnxt_qplib_nq *nq);
+#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 000000000000..23fb7260662b
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -0,0 +1,694 @@
+/*
+ * 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
+ */
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/prefetch.h>
+#include "roce_hsi.h"
+#include "qplib_res.h"
+#include "qplib_rcfw.h"
+static void bnxt_qplib_service_creq(unsigned long data);
+
+/* Hardware communication channel */
+int bnxt_qplib_rcfw_wait_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie)
+{
+	u16 cbit;
+	int rc;
+
+	cookie &= RCFW_MAX_COOKIE_VALUE;
+	cbit = cookie % RCFW_MAX_OUTSTANDING_CMD;
+	if (!test_bit(cbit, rcfw->cmdq_bitmap))
+		dev_warn(&rcfw->pdev->dev,
+			 "QPLIB: CMD bit %d for cookie 0x%x is not set?",
+			 cbit, cookie);
+
+	rc = wait_event_timeout(rcfw->waitq,
+				!test_bit(cbit, rcfw->cmdq_bitmap),
+				msecs_to_jiffies(RCFW_CMD_WAIT_TIME_MS));
+	if (!rc) {
+		dev_warn(&rcfw->pdev->dev,
+			 "QPLIB: Bono Error: timeout %d msec, msg {0x%x}\n",
+			 RCFW_CMD_WAIT_TIME_MS, cookie);
+	}
+
+	return rc;
+};
+
+int bnxt_qplib_rcfw_block_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie)
+{
+	u32 count = -1;
+	u16 cbit;
+
+	cookie &= RCFW_MAX_COOKIE_VALUE;
+	cbit = cookie % RCFW_MAX_OUTSTANDING_CMD;
+	if (!test_bit(cbit, rcfw->cmdq_bitmap))
+		goto done;
+	do {
+		bnxt_qplib_service_creq((unsigned long)rcfw);
+	} while (test_bit(cbit, rcfw->cmdq_bitmap) && --count);
+done:
+	return count;
+};
+
+void *bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
+				   struct cmdq_base *req, void **crsbe,
+				   u8 is_block)
+{
+	struct bnxt_qplib_crsq *crsq = &rcfw->crsq;
+	struct bnxt_qplib_cmdqe *cmdqe, **cmdq_ptr;
+	struct bnxt_qplib_hwq *cmdq = &rcfw->cmdq;
+	struct bnxt_qplib_hwq *crsb = &rcfw->crsb;
+	struct bnxt_qplib_crsqe *crsqe = NULL;
+	struct bnxt_qplib_crsbe **crsb_ptr;
+	u32 sw_prod, cmdq_prod;
+	u8 retry_cnt = 0xFF;
+	dma_addr_t dma_addr;
+	unsigned long flags;
+	u32 size, opcode;
+	u16 cookie, cbit;
+	int pg, idx;
+	u8 *preq;
+
+retry:
+	opcode = req->opcode;
+	if (!test_bit(FIRMWARE_INITIALIZED_FLAG, &rcfw->flags) &&
+	    (opcode != CMDQ_BASE_OPCODE_QUERY_FUNC &&
+	     opcode != CMDQ_BASE_OPCODE_INITIALIZE_FW)) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: RCFW not initialized, reject opcode 0x%x",
+			opcode);
+		return NULL;
+	}
+
+	if (test_bit(FIRMWARE_INITIALIZED_FLAG, &rcfw->flags) &&
+	    opcode == CMDQ_BASE_OPCODE_INITIALIZE_FW) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: RCFW already initialized!");
+		return NULL;
+	}
+
+	/* Cmdq are in 16-byte units, each request can consume 1 or more
+	 * cmdqe
+	 */
+	spin_lock_irqsave(&cmdq->lock, flags);
+	if (req->cmd_size > cmdq->max_elements -
+	    ((HWQ_CMP(cmdq->prod, cmdq) - HWQ_CMP(cmdq->cons, cmdq)) &
+	     (cmdq->max_elements - 1))) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: RCFW: CMDQ is full!");
+		spin_unlock_irqrestore(&cmdq->lock, flags);
+
+		if (!retry_cnt--)
+			return NULL;
+		goto retry;
+	}
+
+	retry_cnt = 0xFF;
+
+	cookie = atomic_inc_return(&rcfw->seq_num) & RCFW_MAX_COOKIE_VALUE;
+	cbit = cookie % RCFW_MAX_OUTSTANDING_CMD;
+	if (is_block)
+		cookie |= RCFW_CMD_IS_BLOCKING;
+	req->cookie = cpu_to_le16(cookie);
+	if (test_and_set_bit(cbit, rcfw->cmdq_bitmap)) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: RCFW MAX outstanding cmd reached!");
+		atomic_dec(&rcfw->seq_num);
+		spin_unlock_irqrestore(&cmdq->lock, flags);
+
+		if (!retry_cnt--)
+			return NULL;
+		goto retry;
+	}
+	/* Reserve a resp buffer slot if requested */
+	if (req->resp_size && crsbe) {
+		spin_lock(&crsb->lock);
+		sw_prod = HWQ_CMP(crsb->prod, crsb);
+		crsb_ptr = (struct bnxt_qplib_crsbe **)crsb->pbl_ptr;
+		*crsbe = (void *)&crsb_ptr[get_crsb_pg(sw_prod)]
+					  [get_crsb_idx(sw_prod)];
+		bnxt_qplib_crsb_dma_next(crsb->pbl_dma_ptr, sw_prod, &dma_addr);
+		req->resp_addr = cpu_to_le64(dma_addr);
+		crsb->prod++;
+		spin_unlock(&crsb->lock);
+
+		req->resp_size = (sizeof(struct bnxt_qplib_crsbe) +
+				  BNXT_QPLIB_CMDQE_UNITS - 1) /
+				 BNXT_QPLIB_CMDQE_UNITS;
+	}
+	cmdq_ptr = (struct bnxt_qplib_cmdqe **)cmdq->pbl_ptr;
+	preq = (u8 *)req;
+	size = req->cmd_size * BNXT_QPLIB_CMDQE_UNITS;
+	do {
+		pg = 0;
+		idx = 0;
+
+		/* Locate the next cmdq slot */
+		sw_prod = HWQ_CMP(cmdq->prod, cmdq);
+		cmdqe = &cmdq_ptr[get_cmdq_pg(sw_prod)][get_cmdq_idx(sw_prod)];
+		if (!cmdqe) {
+			dev_err(&rcfw->pdev->dev,
+				"QPLIB: RCFW request failed with no cmdqe!");
+			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));
+		cmdq->prod++;
+	} while (size > 0);
+
+	cmdq_prod = cmdq->prod;
+	if (rcfw->flags & FIRMWARE_FIRST_FLAG) {
+		/* The very first doorbell write is required to set this flag
+		 * which prompts the FW to reset its internal pointers
+		 */
+		cmdq_prod |= FIRMWARE_FIRST_FLAG;
+		rcfw->flags &= ~FIRMWARE_FIRST_FLAG;
+	}
+	sw_prod = HWQ_CMP(crsq->prod, crsq);
+	crsqe = &crsq->crsq[sw_prod];
+	memset(crsqe, 0, sizeof(*crsqe));
+	crsq->prod++;
+	crsqe->req_size = req->cmd_size;
+
+	/* ring CMDQ DB */
+	writel(cmdq_prod, rcfw->cmdq_bar_reg_iomem +
+	       rcfw->cmdq_bar_reg_prod_off);
+	writel(RCFW_CMDQ_TRIG_VAL, rcfw->cmdq_bar_reg_iomem +
+	       rcfw->cmdq_bar_reg_trig_off);
+done:
+	spin_unlock_irqrestore(&cmdq->lock, flags);
+	/* Return the CREQ response pointer */
+	return crsqe ? &crsqe->qp_event : NULL;
+}
+
+/* Completions */
+static int bnxt_qplib_process_func_event(struct bnxt_qplib_rcfw *rcfw,
+					 struct creq_func_event *func_event)
+{
+	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;
+	}
+	return 0;
+}
+
+static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
+				       struct creq_qp_event *qp_event)
+{
+	struct bnxt_qplib_crsq *crsq = &rcfw->crsq;
+	struct bnxt_qplib_hwq *cmdq = &rcfw->cmdq;
+	struct bnxt_qplib_crsqe *crsqe;
+	u16 cbit, cookie, blocked = 0;
+	unsigned long flags;
+	u32 sw_cons;
+
+	switch (qp_event->event) {
+	case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION:
+		dev_dbg(&rcfw->pdev->dev,
+			"QPLIB: Received QP error notification");
+		break;
+	default:
+		/* Command Response */
+		spin_lock_irqsave(&cmdq->lock, flags);
+		sw_cons = HWQ_CMP(crsq->cons, crsq);
+		crsqe = &crsq->crsq[sw_cons];
+		crsq->cons++;
+		memcpy(&crsqe->qp_event, qp_event, sizeof(crsqe->qp_event));
+
+		cookie = le16_to_cpu(crsqe->qp_event.cookie);
+		blocked = cookie & RCFW_CMD_IS_BLOCKING;
+		cookie &= RCFW_MAX_COOKIE_VALUE;
+		cbit = cookie % RCFW_MAX_OUTSTANDING_CMD;
+		if (!test_and_clear_bit(cbit, rcfw->cmdq_bitmap))
+			dev_warn(&rcfw->pdev->dev,
+				 "QPLIB: CMD bit %d was not requested", cbit);
+
+		cmdq->cons += crsqe->req_size;
+		spin_unlock_irqrestore(&cmdq->lock, flags);
+		if (!blocked)
+			wake_up(&rcfw->waitq);
+		break;
+	}
+	return 0;
+}
+
+/* SP - CREQ Completion handlers */
+static void bnxt_qplib_service_creq(unsigned long data)
+{
+	struct bnxt_qplib_rcfw *rcfw = (struct bnxt_qplib_rcfw *)data;
+	struct bnxt_qplib_hwq *creq = &rcfw->creq;
+	struct creq_base *creqe, **creq_ptr;
+	u32 sw_cons, raw_cons;
+	unsigned long flags;
+	u32 type;
+
+	/* Service the CREQ until empty */
+	spin_lock_irqsave(&creq->lock, flags);
+	raw_cons = creq->cons;
+	while (1) {
+		sw_cons = HWQ_CMP(raw_cons, creq);
+		creq_ptr = (struct creq_base **)creq->pbl_ptr;
+		creqe = &creq_ptr[get_creq_pg(sw_cons)][get_creq_idx(sw_cons)];
+		if (!CREQ_CMP_VALID(creqe, raw_cons, creq->max_elements))
+			break;
+
+		type = creqe->type & CREQ_BASE_TYPE_MASK;
+		switch (type) {
+		case CREQ_BASE_TYPE_QP_EVENT:
+			if (!bnxt_qplib_process_qp_event
+			    (rcfw, (struct creq_qp_event *)creqe))
+				rcfw->creq_qp_event_processed++;
+			else {
+				dev_warn(&rcfw->pdev->dev, "QPLIB: crsqe with");
+				dev_warn(&rcfw->pdev->dev,
+					 "QPLIB: type = 0x%x not handled",
+					 type);
+			}
+			break;
+		case CREQ_BASE_TYPE_FUNC_EVENT:
+			if (!bnxt_qplib_process_func_event
+			    (rcfw, (struct creq_func_event *)creqe))
+				rcfw->creq_func_event_processed++;
+			else
+				dev_warn
+				(&rcfw->pdev->dev, "QPLIB:aeqe:%#x Not handled",
+				 type);
+			break;
+		default:
+			dev_warn(&rcfw->pdev->dev, "QPLIB: creqe with ");
+			dev_warn(&rcfw->pdev->dev,
+				 "QPLIB: op_event = 0x%x not handled", type);
+			break;
+		}
+		raw_cons++;
+	}
+	if (creq->cons != raw_cons) {
+		creq->cons = raw_cons;
+		CREQ_DB_REARM(rcfw->creq_bar_reg_iomem, raw_cons,
+			      creq->max_elements);
+	}
+	spin_unlock_irqrestore(&creq->lock, flags);
+}
+
+static irqreturn_t bnxt_qplib_creq_irq(int irq, void *dev_instance)
+{
+	struct bnxt_qplib_rcfw *rcfw = dev_instance;
+	struct bnxt_qplib_hwq *creq = &rcfw->creq;
+	struct creq_base **creq_ptr;
+	u32 sw_cons;
+
+	/* Prefetch the CREQ element */
+	sw_cons = HWQ_CMP(creq->cons, creq);
+	creq_ptr = (struct creq_base **)rcfw->creq.pbl_ptr;
+	prefetch(&creq_ptr[get_creq_pg(sw_cons)][get_creq_idx(sw_cons)]);
+
+	tasklet_schedule(&rcfw->worker);
+
+	return IRQ_HANDLED;
+}
+
+/* RCFW */
+int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw)
+{
+	struct creq_deinitialize_fw_resp *resp;
+	struct cmdq_deinitialize_fw req;
+	u16 cmd_flags = 0;
+
+	RCFW_CMD_PREP(req, DEINITIALIZE_FW, cmd_flags);
+	resp = (struct creq_deinitialize_fw_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp)
+		return -EINVAL;
+
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie)))
+		return -ETIMEDOUT;
+
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie))
+		return -EFAULT;
+
+	clear_bit(FIRMWARE_INITIALIZED_FLAG, &rcfw->flags);
+	return 0;
+}
+
+static int __get_pbl_pg_idx(struct bnxt_qplib_pbl *pbl)
+{
+	return (pbl->pg_size == ROCE_PG_SIZE_4K ?
+				      CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_4K :
+		pbl->pg_size == ROCE_PG_SIZE_8K ?
+				      CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8K :
+		pbl->pg_size == ROCE_PG_SIZE_64K ?
+				      CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_64K :
+		pbl->pg_size == ROCE_PG_SIZE_2M ?
+				      CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_2M :
+		pbl->pg_size == ROCE_PG_SIZE_8M ?
+				      CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8M :
+		pbl->pg_size == ROCE_PG_SIZE_1G ?
+				      CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_1G :
+				      CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_4K);
+}
+
+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, level;
+
+	RCFW_CMD_PREP(req, INITIALIZE_FW, cmd_flags);
+
+	/*
+	 * 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;
+
+	level = ctx->qpc_tbl.level;
+	req.qpc_pg_size_qpc_lvl = (level << CMDQ_INITIALIZE_FW_QPC_LVL_SFT) |
+				__get_pbl_pg_idx(&ctx->qpc_tbl.pbl[level]);
+	level = ctx->mrw_tbl.level;
+	req.mrw_pg_size_mrw_lvl = (level << CMDQ_INITIALIZE_FW_MRW_LVL_SFT) |
+				__get_pbl_pg_idx(&ctx->mrw_tbl.pbl[level]);
+	level = ctx->srqc_tbl.level;
+	req.srq_pg_size_srq_lvl = (level << CMDQ_INITIALIZE_FW_SRQ_LVL_SFT) |
+				__get_pbl_pg_idx(&ctx->srqc_tbl.pbl[level]);
+	level = ctx->cq_tbl.level;
+	req.cq_pg_size_cq_lvl = (level << CMDQ_INITIALIZE_FW_CQ_LVL_SFT) |
+				__get_pbl_pg_idx(&ctx->cq_tbl.pbl[level]);
+	level = ctx->srqc_tbl.level;
+	req.srq_pg_size_srq_lvl = (level << CMDQ_INITIALIZE_FW_SRQ_LVL_SFT) |
+				__get_pbl_pg_idx(&ctx->srqc_tbl.pbl[level]);
+	level = ctx->cq_tbl.level;
+	req.cq_pg_size_cq_lvl = (level << CMDQ_INITIALIZE_FW_CQ_LVL_SFT) |
+				__get_pbl_pg_idx(&ctx->cq_tbl.pbl[level]);
+	level = ctx->tim_tbl.level;
+	req.tim_pg_size_tim_lvl = (level << CMDQ_INITIALIZE_FW_TIM_LVL_SFT) |
+				  __get_pbl_pg_idx(&ctx->tim_tbl.pbl[level]);
+	level = ctx->tqm_pde_level;
+	req.tqm_pg_size_tqm_lvl = (level << CMDQ_INITIALIZE_FW_TQM_LVL_SFT) |
+				  __get_pbl_pg_idx(&ctx->tqm_pde.pbl[level]);
+
+	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_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);
+
+	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);
+	resp = (struct creq_initialize_fw_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: RCFW: INITIALIZE_FW send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: RCFW: INITIALIZE_FW timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: RCFW: INITIALIZE_FW failed");
+		return -EINVAL;
+	}
+	set_bit(FIRMWARE_INITIALIZED_FLAG, &rcfw->flags);
+	return 0;
+}
+
+void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+{
+	bnxt_qplib_free_hwq(rcfw->pdev, &rcfw->crsb);
+	kfree(rcfw->crsq.crsq);
+	bnxt_qplib_free_hwq(rcfw->pdev, &rcfw->cmdq);
+	bnxt_qplib_free_hwq(rcfw->pdev, &rcfw->creq);
+
+	rcfw->pdev = NULL;
+}
+
+int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev,
+				  struct bnxt_qplib_rcfw *rcfw)
+{
+	rcfw->pdev = pdev;
+	rcfw->creq.max_elements = BNXT_QPLIB_CREQE_MAX_CNT;
+	if (bnxt_qplib_alloc_init_hwq(rcfw->pdev, &rcfw->creq, NULL, 0,
+				      &rcfw->creq.max_elements,
+				      BNXT_QPLIB_CREQE_UNITS, 0, PAGE_SIZE,
+				      HWQ_TYPE_L2_CMPL)) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: HW channel CREQ allocation failed");
+		goto fail;
+	}
+	rcfw->cmdq.max_elements = BNXT_QPLIB_CMDQE_MAX_CNT;
+	if (bnxt_qplib_alloc_init_hwq(rcfw->pdev, &rcfw->cmdq, NULL, 0,
+				      &rcfw->cmdq.max_elements,
+				      BNXT_QPLIB_CMDQE_UNITS, 0, PAGE_SIZE,
+				      HWQ_TYPE_CTX)) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: HW channel CMDQ allocation failed");
+		goto fail;
+	}
+
+	rcfw->crsq.max_elements = rcfw->cmdq.max_elements;
+	rcfw->crsq.crsq = kcalloc(rcfw->crsq.max_elements,
+				  sizeof(*rcfw->crsq.crsq), GFP_KERNEL);
+	if (!rcfw->crsq.crsq)
+		goto fail;
+
+	rcfw->crsb.max_elements = BNXT_QPLIB_CRSBE_MAX_CNT;
+	if (bnxt_qplib_alloc_init_hwq(rcfw->pdev, &rcfw->crsb, NULL, 0,
+				      &rcfw->crsb.max_elements,
+				      BNXT_QPLIB_CRSBE_UNITS, 0, PAGE_SIZE,
+				      HWQ_TYPE_CTX)) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: HW channel CRSB allocation failed");
+		goto fail;
+	}
+	return 0;
+
+fail:
+	bnxt_qplib_free_rcfw_channel(rcfw);
+	return -ENOMEM;
+}
+
+void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+{
+	unsigned long indx;
+
+	/* Make sure the HW channel is stopped! */
+	synchronize_irq(rcfw->vector);
+	tasklet_disable(&rcfw->worker);
+	tasklet_kill(&rcfw->worker);
+
+	if (rcfw->requested) {
+		free_irq(rcfw->vector, rcfw);
+		rcfw->requested = false;
+	}
+	if (rcfw->cmdq_bar_reg_iomem)
+		iounmap(rcfw->cmdq_bar_reg_iomem);
+	rcfw->cmdq_bar_reg_iomem = NULL;
+
+	if (rcfw->creq_bar_reg_iomem)
+		iounmap(rcfw->creq_bar_reg_iomem);
+	rcfw->creq_bar_reg_iomem = NULL;
+
+	indx = find_first_bit(rcfw->cmdq_bitmap, rcfw->bmap_size);
+	if (indx != rcfw->bmap_size)
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: disabling RCFW with pending cmd-bit %lx", indx);
+	kfree(rcfw->cmdq_bitmap);
+	rcfw->bmap_size = 0;
+
+	rcfw->aeq_handler = NULL;
+	rcfw->vector = 0;
+}
+
+int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
+				   struct bnxt_qplib_rcfw *rcfw,
+				   int msix_vector,
+				   int cp_bar_reg_off, int virt_fn,
+				   int (*aeq_handler)(struct bnxt_qplib_rcfw *,
+						      struct creq_func_event *))
+{
+	resource_size_t res_base;
+	struct cmdq_init init;
+	u16 bmap_size;
+	int rc;
+
+	/* General */
+	atomic_set(&rcfw->seq_num, 0);
+	rcfw->flags = FIRMWARE_FIRST_FLAG;
+	bmap_size = BITS_TO_LONGS(RCFW_MAX_OUTSTANDING_CMD *
+				  sizeof(unsigned long));
+	rcfw->cmdq_bitmap = kzalloc(bmap_size, GFP_KERNEL);
+	if (!rcfw->cmdq_bitmap)
+		return -ENOMEM;
+	rcfw->bmap_size = bmap_size;
+
+	/* CMDQ */
+	rcfw->cmdq_bar_reg = RCFW_COMM_PCI_BAR_REGION;
+	res_base = pci_resource_start(pdev, rcfw->cmdq_bar_reg);
+	if (!res_base)
+		return -ENOMEM;
+
+	rcfw->cmdq_bar_reg_iomem = ioremap_nocache(res_base +
+					      RCFW_COMM_BASE_OFFSET,
+					      RCFW_COMM_SIZE);
+	if (!rcfw->cmdq_bar_reg_iomem) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: CMDQ BAR region %d mapping failed",
+			rcfw->cmdq_bar_reg);
+		return -ENOMEM;
+	}
+
+	rcfw->cmdq_bar_reg_prod_off = virt_fn ? RCFW_VF_COMM_PROD_OFFSET :
+					RCFW_PF_COMM_PROD_OFFSET;
+
+	rcfw->cmdq_bar_reg_trig_off = RCFW_COMM_TRIG_OFFSET;
+
+	/* CRSQ */
+	rcfw->crsq.prod = 0;
+	rcfw->crsq.cons = 0;
+
+	/* CREQ */
+	rcfw->creq_bar_reg = RCFW_COMM_CONS_PCI_BAR_REGION;
+	res_base = pci_resource_start(pdev, rcfw->creq_bar_reg);
+	if (!res_base)
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: CREQ BAR region %d resc start is 0!",
+			rcfw->creq_bar_reg);
+	rcfw->creq_bar_reg_iomem = ioremap_nocache(res_base + cp_bar_reg_off,
+						   4);
+	if (!rcfw->creq_bar_reg_iomem) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: CREQ BAR region %d mapping failed",
+			rcfw->creq_bar_reg);
+		return -ENOMEM;
+	}
+	rcfw->creq_qp_event_processed = 0;
+	rcfw->creq_func_event_processed = 0;
+
+	rcfw->vector = msix_vector;
+	if (aeq_handler)
+		rcfw->aeq_handler = aeq_handler;
+
+	tasklet_init(&rcfw->worker, bnxt_qplib_service_creq,
+		     (unsigned long)rcfw);
+
+	rcfw->requested = false;
+	rc = request_irq(rcfw->vector, bnxt_qplib_creq_irq, 0,
+			 "bnxt_qplib_creq", rcfw);
+	if (rc) {
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: Failed to request IRQ for CREQ rc = 0x%x", rc);
+		bnxt_qplib_disable_rcfw_channel(rcfw);
+		return rc;
+	}
+	rcfw->requested = true;
+
+	init_waitqueue_head(&rcfw->waitq);
+
+	CREQ_DB_REARM(rcfw->creq_bar_reg_iomem, 0, rcfw->creq.max_elements);
+
+	init.cmdq_pbl = cpu_to_le64(rcfw->cmdq.pbl[PBL_LVL_0].pg_map_arr[0]);
+	init.cmdq_size_cmdq_lvl = cpu_to_le16(
+		((BNXT_QPLIB_CMDQE_MAX_CNT << CMDQ_INIT_CMDQ_SIZE_SFT) &
+		 CMDQ_INIT_CMDQ_SIZE_MASK) |
+		((rcfw->cmdq.level << CMDQ_INIT_CMDQ_LVL_SFT) &
+		 CMDQ_INIT_CMDQ_LVL_MASK));
+	init.creq_ring_id = cpu_to_le16(rcfw->creq_ring_id);
+
+	/* Write to the Bono mailbox register */
+	__iowrite32_copy(rcfw->cmdq_bar_reg_iomem, &init, sizeof(init) / 4);
+	return 0;
+}
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 000000000000..d3567d75bf58
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -0,0 +1,231 @@
+/*
+ * 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_CMD_PREP(req, CMD, cmd_flags)				\
+	do {								\
+		memset(&(req), 0, sizeof((req)));			\
+		(req).opcode = CMDQ_BASE_OPCODE_##CMD;			\
+		(req).cmd_size = (sizeof((req)) +			\
+				BNXT_QPLIB_CMDQE_UNITS - 1) /		\
+				BNXT_QPLIB_CMDQE_UNITS;			\
+		(req).flags = cpu_to_le16(cmd_flags);			\
+	} while (0)
+
+#define RCFW_CMD_WAIT_TIME_MS		20000 /* 20 Seconds timeout */
+
+/* CMDQ elements */
+#define BNXT_QPLIB_CMDQE_MAX_CNT	256
+#define BNXT_QPLIB_CMDQE_UNITS		sizeof(struct bnxt_qplib_cmdqe)
+#define BNXT_QPLIB_CMDQE_CNT_PER_PG	(PAGE_SIZE / BNXT_QPLIB_CMDQE_UNITS)
+
+#define MAX_CMDQ_IDX			(BNXT_QPLIB_CMDQE_MAX_CNT - 1)
+#define MAX_CMDQ_IDX_PER_PG		(BNXT_QPLIB_CMDQE_CNT_PER_PG - 1)
+
+#define RCFW_MAX_OUTSTANDING_CMD	BNXT_QPLIB_CMDQE_MAX_CNT
+#define RCFW_MAX_COOKIE_VALUE		0x7FFF
+#define RCFW_CMD_IS_BLOCKING		0x8000
+
+/* Cmdq contains a fix number of a 16-Byte slots */
+struct bnxt_qplib_cmdqe {
+	u8		data[16];
+};
+
+static inline u32 get_cmdq_pg(u32 val)
+{
+	return (val & ~MAX_CMDQ_IDX_PER_PG) / BNXT_QPLIB_CMDQE_CNT_PER_PG;
+}
+
+static inline u32 get_cmdq_idx(u32 val)
+{
+	return val & MAX_CMDQ_IDX_PER_PG;
+}
+
+/* Crsq buf is 1024-Byte */
+struct bnxt_qplib_crsbe {
+	u8			data[1024];
+};
+
+/* CRSQ SB */
+#define BNXT_QPLIB_CRSBE_MAX_CNT	4
+#define BNXT_QPLIB_CRSBE_UNITS		sizeof(struct bnxt_qplib_crsbe)
+#define BNXT_QPLIB_CRSBE_CNT_PER_PG	(PAGE_SIZE / BNXT_QPLIB_CRSBE_UNITS)
+
+#define MAX_CRSB_IDX			(BNXT_QPLIB_CRSBE_MAX_CNT - 1)
+#define MAX_CRSB_IDX_PER_PG		(BNXT_QPLIB_CRSBE_CNT_PER_PG - 1)
+
+static inline u32 get_crsb_pg(u32 val)
+{
+	return (val & ~MAX_CRSB_IDX_PER_PG) / BNXT_QPLIB_CRSBE_CNT_PER_PG;
+}
+
+static inline u32 get_crsb_idx(u32 val)
+{
+	return val & MAX_CRSB_IDX_PER_PG;
+}
+
+static inline void bnxt_qplib_crsb_dma_next(dma_addr_t *pg_map_arr,
+					    u32 prod, dma_addr_t *dma_addr)
+{
+		*dma_addr = pg_map_arr[(prod) / BNXT_QPLIB_CRSBE_CNT_PER_PG];
+		*dma_addr += ((prod) % BNXT_QPLIB_CRSBE_CNT_PER_PG) *
+			      BNXT_QPLIB_CRSBE_UNITS;
+}
+
+/* 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 BNXT_QPLIB_CREQE_CNT_PER_PG	(PAGE_SIZE / BNXT_QPLIB_CREQE_UNITS)
+
+#define MAX_CREQ_IDX			(BNXT_QPLIB_CREQE_MAX_CNT - 1)
+#define MAX_CREQ_IDX_PER_PG		(BNXT_QPLIB_CREQE_CNT_PER_PG - 1)
+
+static inline u32 get_creq_pg(u32 val)
+{
+	return (val & ~MAX_CREQ_IDX_PER_PG) / BNXT_QPLIB_CREQE_CNT_PER_PG;
+}
+
+static inline u32 get_creq_idx(u32 val)
+{
+	return val & MAX_CREQ_IDX_PER_PG;
+}
+
+#define BNXT_QPLIB_CREQE_PER_PG	(PAGE_SIZE / sizeof(struct creq_base))
+
+#define CREQ_CMP_VALID(hdr, raw_cons, cp_bit)			\
+	(!!((hdr)->v & CREQ_BASE_V) ==				\
+	   !((raw_cons) & (cp_bit)))
+
+#define CREQ_DB_KEY_CP			(0x2 << CMPL_DOORBELL_KEY_SFT)
+#define CREQ_DB_IDX_VALID		CMPL_DOORBELL_IDX_VALID
+#define CREQ_DB_IRQ_DIS			CMPL_DOORBELL_MASK
+#define CREQ_DB_CP_FLAGS_REARM		(CREQ_DB_KEY_CP |	\
+					 CREQ_DB_IDX_VALID)
+#define CREQ_DB_CP_FLAGS		(CREQ_DB_KEY_CP |	\
+					 CREQ_DB_IDX_VALID |	\
+					 CREQ_DB_IRQ_DIS)
+#define CREQ_DB_REARM(db, raw_cons, cp_bit)			\
+	writel(CREQ_DB_CP_FLAGS_REARM | ((raw_cons) & ((cp_bit) - 1)), db)
+#define CREQ_DB(db, raw_cons, cp_bit)				\
+	writel(CREQ_DB_CP_FLAGS | ((raw_cons) & ((cp_bit) - 1)), db)
+
+/* HWQ */
+struct bnxt_qplib_crsqe {
+	struct creq_qp_event	qp_event;
+	u32			req_size;
+};
+
+struct bnxt_qplib_crsq {
+	struct bnxt_qplib_crsqe	*crsq;
+	u32			prod;
+	u32			cons;
+	u32			max_elements;
+};
+
+/* RCFW Communication Channels */
+struct bnxt_qplib_rcfw {
+	struct pci_dev		*pdev;
+	int			vector;
+	struct tasklet_struct	worker;
+	bool			requested;
+	unsigned long		*cmdq_bitmap;
+	u32			bmap_size;
+	unsigned long		flags;
+#define FIRMWARE_INITIALIZED_FLAG	1
+#define FIRMWARE_FIRST_FLAG		BIT(31)
+	wait_queue_head_t	waitq;
+	int			(*aeq_handler)(struct bnxt_qplib_rcfw *,
+					       struct creq_func_event *);
+	atomic_t		seq_num;
+
+	/* Bar region info */
+	void __iomem		*cmdq_bar_reg_iomem;
+	u16			cmdq_bar_reg;
+	u16			cmdq_bar_reg_prod_off;
+	u16			cmdq_bar_reg_trig_off;
+	u16			creq_ring_id;
+	u16			creq_bar_reg;
+	void __iomem		*creq_bar_reg_iomem;
+
+	/* Cmd-Resp and Async Event notification queue */
+	struct bnxt_qplib_hwq	creq;
+	u64			creq_qp_event_processed;
+	u64			creq_func_event_processed;
+
+	/* Actual Cmd and Resp Queues */
+	struct bnxt_qplib_hwq	cmdq;
+	struct bnxt_qplib_crsq	crsq;
+	struct bnxt_qplib_hwq	crsb;
+};
+
+void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
+int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev,
+				  struct bnxt_qplib_rcfw *rcfw);
+void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
+int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
+				   struct bnxt_qplib_rcfw *rcfw,
+				   int msix_vector,
+				   int cp_bar_reg_off, int virt_fn,
+				   int (*aeq_handler)
+					(struct bnxt_qplib_rcfw *,
+					 struct creq_func_event *));
+
+int bnxt_qplib_rcfw_block_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie);
+int bnxt_qplib_rcfw_wait_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie);
+void *bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
+				   struct cmdq_base *req, void **crsbe,
+				   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);
+#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 000000000000..62447b3badec
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -0,0 +1,825 @@
+/*
+ * 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
+ */
+
+#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 "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_stats *stats);
+
+/* PBL */
+static void __free_pbl(struct pci_dev *pdev, struct bnxt_qplib_pbl *pbl,
+		       bool is_umem)
+{
+	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,
+					 "QPLIB: PBL free pg_arr[%d] empty?!",
+					 i);
+			pbl->pg_arr[i] = NULL;
+		}
+	}
+	kfree(pbl->pg_arr);
+	pbl->pg_arr = NULL;
+	kfree(pbl->pg_map_arr);
+	pbl->pg_map_arr = NULL;
+	pbl->pg_count = 0;
+	pbl->pg_size = 0;
+}
+
+static int __alloc_pbl(struct pci_dev *pdev, struct bnxt_qplib_pbl *pbl,
+		       struct scatterlist *sghead, u32 pages, u32 pg_size)
+{
+	struct scatterlist *sg;
+	bool is_umem = false;
+	int i;
+
+	/* page ptr arrays */
+	pbl->pg_arr = kcalloc(pages, sizeof(void *), GFP_KERNEL);
+	if (!pbl->pg_arr)
+		return -ENOMEM;
+
+	pbl->pg_map_arr = kcalloc(pages, sizeof(dma_addr_t), GFP_KERNEL);
+	if (!pbl->pg_map_arr) {
+		kfree(pbl->pg_arr);
+		pbl->pg_arr = NULL;
+		return -ENOMEM;
+	}
+	pbl->pg_count = 0;
+	pbl->pg_size = pg_size;
+
+	if (!sghead) {
+		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;
+			memset(pbl->pg_arr[i], 0, pbl->pg_size);
+			pbl->pg_count++;
+		}
+	} else {
+		i = 0;
+		is_umem = true;
+		for_each_sg(sghead, sg, pages, i) {
+			pbl->pg_map_arr[i] = sg_dma_address(sg);
+			pbl->pg_arr[i] = sg_virt(sg);
+			if (!pbl->pg_arr[i])
+				goto fail;
+
+			pbl->pg_count++;
+		}
+	}
+
+	return 0;
+
+fail:
+	__free_pbl(pdev, pbl, is_umem);
+	return -ENOMEM;
+}
+
+/* HWQ */
+void bnxt_qplib_free_hwq(struct pci_dev *pdev, 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(pdev, &hwq->pbl[i], hwq->is_user);
+		else
+			__free_pbl(pdev, &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 pci_dev *pdev, struct bnxt_qplib_hwq *hwq,
+			      struct scatterlist *sghead, int nmap,
+			      u32 *elements, u32 element_size, u32 aux,
+			      u32 pg_size, enum bnxt_qplib_hwq_type hwq_type)
+{
+	u32 pages, slots, size, aux_pages = 0, aux_size = 0;
+	dma_addr_t *src_phys_ptr, **dst_virt_ptr;
+	int i, rc;
+
+	hwq->level = PBL_LVL_MAX;
+
+	slots = roundup_pow_of_two(*elements);
+	if (aux) {
+		aux_size = roundup_pow_of_two(aux);
+		aux_pages = (slots * aux_size) / pg_size;
+		if ((slots * aux_size) % pg_size)
+			aux_pages++;
+	}
+	size = roundup_pow_of_two(element_size);
+
+	if (!sghead) {
+		hwq->is_user = false;
+		pages = (slots * size) / pg_size + aux_pages;
+		if ((slots * size) % pg_size)
+			pages++;
+		if (!pages)
+			return -EINVAL;
+	} else {
+		hwq->is_user = true;
+		pages = nmap;
+	}
+
+	/* Alloc the 1st memory block; can be a PDL/PTL/PBL */
+	if (sghead && (pages == MAX_PBL_LVL_0_PGS))
+		rc = __alloc_pbl(pdev, &hwq->pbl[PBL_LVL_0], sghead,
+				 pages, pg_size);
+	else
+		rc = __alloc_pbl(pdev, &hwq->pbl[PBL_LVL_0], NULL, 1, pg_size);
+	if (rc)
+		goto fail;
+
+	hwq->level = PBL_LVL_0;
+
+	if (pages > MAX_PBL_LVL_0_PGS) {
+		if (pages > MAX_PBL_LVL_1_PGS) {
+			/* 2 levels of indirection */
+			rc = __alloc_pbl(pdev, &hwq->pbl[PBL_LVL_1], NULL,
+					 MAX_PBL_LVL_1_PGS_FOR_LVL_2, pg_size);
+			if (rc)
+				goto fail;
+			/* Fill in lvl0 PBL */
+			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] | PTU_PDE_VALID;
+			hwq->level = PBL_LVL_1;
+
+			rc = __alloc_pbl(pdev, &hwq->pbl[PBL_LVL_2], sghead,
+					 pages, pg_size);
+			if (rc)
+				goto fail;
+
+			/* Fill in lvl1 PBL */
+			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_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;
+			}
+			hwq->level = PBL_LVL_2;
+		} else {
+			u32 flag = hwq_type == HWQ_TYPE_L2_CMPL ? 0 :
+						PTU_PTE_VALID;
+
+			/* 1 level of indirection */
+			rc = __alloc_pbl(pdev, &hwq->pbl[PBL_LVL_1], sghead,
+					 pages, pg_size);
+			if (rc)
+				goto fail;
+			/* Fill in lvl0 PBL */
+			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_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;
+			}
+			hwq->level = PBL_LVL_1;
+		}
+	}
+	hwq->pdev = pdev;
+	spin_lock_init(&hwq->lock);
+	hwq->prod = 0;
+	hwq->cons = 0;
+	*elements = hwq->max_elements = slots;
+	hwq->element_size = size;
+
+	/* For direct access to the elements */
+	hwq->pbl_ptr = hwq->pbl[hwq->level].pg_arr;
+	hwq->pbl_dma_ptr = hwq->pbl[hwq->level].pg_map_arr;
+
+	return 0;
+
+fail:
+	bnxt_qplib_free_hwq(pdev, hwq);
+	return -ENOMEM;
+}
+
+/* Context Tables */
+void bnxt_qplib_free_ctx(struct pci_dev *pdev,
+			 struct bnxt_qplib_ctx *ctx)
+{
+	int i;
+
+	bnxt_qplib_free_hwq(pdev, &ctx->qpc_tbl);
+	bnxt_qplib_free_hwq(pdev, &ctx->mrw_tbl);
+	bnxt_qplib_free_hwq(pdev, &ctx->srqc_tbl);
+	bnxt_qplib_free_hwq(pdev, &ctx->cq_tbl);
+	bnxt_qplib_free_hwq(pdev, &ctx->tim_tbl);
+	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
+		bnxt_qplib_free_hwq(pdev, &ctx->tqm_tbl[i]);
+	bnxt_qplib_free_hwq(pdev, &ctx->tqm_pde);
+	bnxt_qplib_free_stats_ctx(pdev, &ctx->stats);
+}
+
+/*
+ * 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 pci_dev *pdev,
+			 struct bnxt_qplib_ctx *ctx,
+			 bool virt_fn)
+{
+	int i, j, k, rc = 0;
+	int fnz_idx = -1;
+	__le64 **pbl_ptr;
+
+	if (virt_fn)
+		goto stats_alloc;
+
+	/* QPC Tables */
+	ctx->qpc_tbl.max_elements = ctx->qpc_count;
+	rc = bnxt_qplib_alloc_init_hwq(pdev, &ctx->qpc_tbl, NULL, 0,
+				       &ctx->qpc_tbl.max_elements,
+				       BNXT_QPLIB_MAX_QP_CTX_ENTRY_SIZE, 0,
+				       PAGE_SIZE, HWQ_TYPE_CTX);
+	if (rc)
+		goto fail;
+
+	/* MRW Tables */
+	ctx->mrw_tbl.max_elements = ctx->mrw_count;
+	rc = bnxt_qplib_alloc_init_hwq(pdev, &ctx->mrw_tbl, NULL, 0,
+				       &ctx->mrw_tbl.max_elements,
+				       BNXT_QPLIB_MAX_MRW_CTX_ENTRY_SIZE, 0,
+				       PAGE_SIZE, HWQ_TYPE_CTX);
+	if (rc)
+		goto fail;
+
+	/* SRQ Tables */
+	ctx->srqc_tbl.max_elements = ctx->srqc_count;
+	rc = bnxt_qplib_alloc_init_hwq(pdev, &ctx->srqc_tbl, NULL, 0,
+				       &ctx->srqc_tbl.max_elements,
+				       BNXT_QPLIB_MAX_SRQ_CTX_ENTRY_SIZE, 0,
+				       PAGE_SIZE, HWQ_TYPE_CTX);
+	if (rc)
+		goto fail;
+
+	/* CQ Tables */
+	ctx->cq_tbl.max_elements = ctx->cq_count;
+	rc = bnxt_qplib_alloc_init_hwq(pdev, &ctx->cq_tbl, NULL, 0,
+				       &ctx->cq_tbl.max_elements,
+				       BNXT_QPLIB_MAX_CQ_CTX_ENTRY_SIZE, 0,
+				       PAGE_SIZE, HWQ_TYPE_CTX);
+	if (rc)
+		goto fail;
+
+	/* TQM Buffer */
+	ctx->tqm_pde.max_elements = 512;
+	rc = bnxt_qplib_alloc_init_hwq(pdev, &ctx->tqm_pde, NULL, 0,
+				       &ctx->tqm_pde.max_elements, sizeof(u64),
+				       0, PAGE_SIZE, HWQ_TYPE_CTX);
+	if (rc)
+		goto fail;
+
+	for (i = 0; i < MAX_TQM_ALLOC_REQ; i++) {
+		if (!ctx->tqm_count[i])
+			continue;
+		ctx->tqm_tbl[i].max_elements = ctx->qpc_count *
+					       ctx->tqm_count[i];
+		rc = bnxt_qplib_alloc_init_hwq(pdev, &ctx->tqm_tbl[i], NULL, 0,
+					       &ctx->tqm_tbl[i].max_elements, 1,
+					       0, PAGE_SIZE, HWQ_TYPE_CTX);
+		if (rc)
+			goto fail;
+	}
+	pbl_ptr = (__le64 **)ctx->tqm_pde.pbl_ptr;
+	for (i = 0, j = 0; i < MAX_TQM_ALLOC_REQ;
+	     i++, j += MAX_TQM_ALLOC_BLK_SIZE) {
+		if (!ctx->tqm_tbl[i].max_elements)
+			continue;
+		if (fnz_idx == -1)
+			fnz_idx = i;
+		switch (ctx->tqm_tbl[i].level) {
+		case PBL_LVL_2:
+			for (k = 0; k < ctx->tqm_tbl[i].pbl[PBL_LVL_1].pg_count;
+			     k++)
+				pbl_ptr[PTR_PG(j + k)][PTR_IDX(j + k)] =
+				  cpu_to_le64(
+				    ctx->tqm_tbl[i].pbl[PBL_LVL_1].pg_map_arr[k]
+				    | PTU_PTE_VALID);
+			break;
+		case PBL_LVL_1:
+		case PBL_LVL_0:
+		default:
+			pbl_ptr[PTR_PG(j)][PTR_IDX(j)] = cpu_to_le64(
+				ctx->tqm_tbl[i].pbl[PBL_LVL_0].pg_map_arr[0] |
+				PTU_PTE_VALID);
+			break;
+		}
+	}
+	if (fnz_idx == -1)
+		fnz_idx = 0;
+	ctx->tqm_pde_level = ctx->tqm_tbl[fnz_idx].level == PBL_LVL_2 ?
+			     PBL_LVL_2 : ctx->tqm_tbl[fnz_idx].level + 1;
+
+	/* TIM Buffer */
+	ctx->tim_tbl.max_elements = ctx->qpc_count * 16;
+	rc = bnxt_qplib_alloc_init_hwq(pdev, &ctx->tim_tbl, NULL, 0,
+				       &ctx->tim_tbl.max_elements, 1,
+				       0, PAGE_SIZE, HWQ_TYPE_CTX);
+	if (rc)
+		goto fail;
+
+stats_alloc:
+	/* Stats */
+	rc = bnxt_qplib_alloc_stats_ctx(pdev, &ctx->stats);
+	if (rc)
+		goto fail;
+
+	return 0;
+
+fail:
+	bnxt_qplib_free_ctx(pdev, ctx);
+	return rc;
+}
+
+/* GUID */
+void bnxt_qplib_get_guid(u8 *dev_addr, u8 *guid)
+{
+	u8 mac[ETH_ALEN];
+
+	/* MAC-48 to EUI-64 mapping */
+	memcpy(mac, dev_addr, ETH_ALEN);
+	guid[0] = mac[0] ^ 2;
+	guid[1] = mac[1];
+	guid[2] = mac[2];
+	guid[3] = 0xff;
+	guid[4] = 0xfe;
+	guid[5] = mac[3];
+	guid[6] = mac[4];
+	guid[7] = mac[5];
+}
+
+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);
+	sgid_tbl->tbl = NULL;
+	sgid_tbl->hw_id = NULL;
+	sgid_tbl->ctx = 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(struct bnxt_qplib_gid), 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->max = max;
+	return 0;
+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], true);
+	}
+	memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max);
+	memset(sgid_tbl->hw_id, -1, sizeof(u16) * 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)
+{
+	memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max);
+	memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
+}
+
+static void bnxt_qplib_free_pkey_tbl(struct bnxt_qplib_res *res,
+				     struct bnxt_qplib_pkey_tbl *pkey_tbl)
+{
+	if (!pkey_tbl->tbl)
+		dev_dbg(&res->pdev->dev, "QPLIB: PKEY tbl not present");
+	else
+		kfree(pkey_tbl->tbl);
+
+	pkey_tbl->tbl = NULL;
+	pkey_tbl->max = 0;
+	pkey_tbl->active = 0;
+}
+
+static int bnxt_qplib_alloc_pkey_tbl(struct bnxt_qplib_res *res,
+				     struct bnxt_qplib_pkey_tbl *pkey_tbl,
+				     u16 max)
+{
+	pkey_tbl->tbl = kcalloc(max, sizeof(u16), GFP_KERNEL);
+	if (!pkey_tbl->tbl)
+		return -ENOMEM;
+
+	pkey_tbl->max = max;
+	return 0;
+};
+
+/* 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",
+			 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", dpi->dpi);
+		return -EINVAL;
+	}
+	if (test_and_set_bit(dpi->dpi, dpit->tbl)) {
+		dev_warn(&res->pdev->dev, "Freeing an unused DPI? dpi = %d",
+			 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,
+			"QPLIB: DBR BAR region %d already mapped", 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,
+			"QPLIB: BAR region %d resc start failed", 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, "QPLIB: Invalid DBR length %d",
+			dbr_len);
+		return -ENOMEM;
+	}
+
+	dpit->dbr_bar_reg_iomem = ioremap_nocache(bar_reg_base + dbr_offset,
+						  dbr_len);
+	if (!dpit->dbr_bar_reg_iomem) {
+		dev_err(&res->pdev->dev,
+			"QPLIB: FP: DBR BAR region %d mapping failed",
+			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) {
+		pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
+		dev_err(&res->pdev->dev,
+			"QPLIB: DPI app tbl allocation failed");
+		return -ENOMEM;
+	}
+
+	bytes = dpit->max >> 3;
+	if (!bytes)
+		bytes = 1;
+
+	dpit->tbl = kmalloc(bytes, GFP_KERNEL);
+	if (!dpit->tbl) {
+		pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
+		kfree(dpit->app_tbl);
+		dpit->app_tbl = NULL;
+		dev_err(&res->pdev->dev,
+			"QPLIB: DPI tbl allocation failed for size = %d",
+			bytes);
+		return -ENOMEM;
+	}
+
+	memset((u8 *)dpit->tbl, 0xFF, bytes);
+
+	return 0;
+}
+
+/* PKEYs */
+static void bnxt_qplib_cleanup_pkey_tbl(struct bnxt_qplib_pkey_tbl *pkey_tbl)
+{
+	memset(pkey_tbl->tbl, 0, sizeof(u16) * pkey_tbl->max);
+	pkey_tbl->active = 0;
+}
+
+static void bnxt_qplib_init_pkey_tbl(struct bnxt_qplib_res *res,
+				     struct bnxt_qplib_pkey_tbl *pkey_tbl)
+{
+	u16 pkey = 0xFFFF;
+
+	memset(pkey_tbl->tbl, 0, sizeof(u16) * pkey_tbl->max);
+
+	/* pkey default = 0xFFFF */
+	bnxt_qplib_add_pkey(res, pkey_tbl, &pkey, false);
+}
+
+/* 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_stats *stats)
+{
+	memset(stats, 0, sizeof(*stats));
+	stats->fw_id = -1;
+	stats->size = sizeof(struct ctx_hw_stats);
+	stats->dma = dma_alloc_coherent(&pdev->dev, stats->size,
+					&stats->dma_map, GFP_KERNEL);
+	if (!stats->dma) {
+		dev_err(&pdev->dev, "QPLIB: Stats DMA allocation failed");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void bnxt_qplib_cleanup_res(struct bnxt_qplib_res *res)
+{
+	bnxt_qplib_cleanup_pkey_tbl(&res->pkey_tbl);
+	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);
+	bnxt_qplib_init_pkey_tbl(res, &res->pkey_tbl);
+
+	return 0;
+}
+
+void bnxt_qplib_free_res(struct bnxt_qplib_res *res)
+{
+	bnxt_qplib_free_pkey_tbl(res, &res->pkey_tbl);
+	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);
+
+	res->netdev = NULL;
+	res->pdev = NULL;
+}
+
+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_pkey_tbl(res, &res->pkey_tbl, dev_attr->max_pkey);
+	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;
+}
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 000000000000..6277d802ca4b
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -0,0 +1,223 @@
+/*
+ * 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 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))
+
+enum bnxt_qplib_hwq_type {
+	HWQ_TYPE_CTX,
+	HWQ_TYPE_QUEUE,
+	HWQ_TYPE_L2_CMPL
+};
+
+#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)
+
+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)
+
+struct bnxt_qplib_pbl {
+	u32				pg_count;
+	u32				pg_size;
+	void				**pg_arr;
+	dma_addr_t			*pg_map_arr;
+};
+
+struct bnxt_qplib_hwq {
+	struct pci_dev			*pdev;
+	/* lock to protect qplib_hwq */
+	spinlock_t			lock;
+	struct bnxt_qplib_pbl		pbl[PBL_LVL_MAX];
+	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;
+	u16				element_size;	/* Size of each entry */
+
+	u32				prod;		/* raw */
+	u32				cons;		/* raw */
+	u8				cp_bit;
+	u8				is_user;
+};
+
+/* Tables */
+struct bnxt_qplib_pd_tbl {
+	unsigned long			*tbl;
+	u32				max;
+};
+
+struct bnxt_qplib_sgid_tbl {
+	struct bnxt_qplib_gid		*tbl;
+	u16				*hw_id;
+	u16				max;
+	u16				active;
+	void				*ctx;
+};
+
+struct bnxt_qplib_pkey_tbl {
+	u16				*tbl;
+	u16				max;
+	u16				active;
+};
+
+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
+
+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;
+#define MAX_TQM_ALLOC_REQ		32
+#define MAX_TQM_ALLOC_BLK_SIZE		8
+	u8				tqm_count[MAX_TQM_ALLOC_REQ];
+	struct bnxt_qplib_hwq		tqm_pde;
+	u32				tqm_pde_level;
+	struct bnxt_qplib_hwq		tqm_tbl[MAX_TQM_ALLOC_REQ];
+	struct bnxt_qplib_stats		stats;
+	struct bnxt_qplib_vf_res	vf_res;
+};
+
+struct bnxt_qplib_res {
+	struct pci_dev			*pdev;
+	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_pkey_tbl	pkey_tbl;
+	struct bnxt_qplib_dpi_tbl	dpi_tbl;
+};
+
+#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 pci_dev *pdev, struct bnxt_qplib_hwq *hwq);
+int bnxt_qplib_alloc_init_hwq(struct pci_dev *pdev, struct bnxt_qplib_hwq *hwq,
+			      struct scatterlist *sl, int nmap, u32 *elements,
+			      u32 elements_per_page, u32 aux, u32 pg_size,
+			      enum bnxt_qplib_hwq_type hwq_type);
+void bnxt_qplib_get_guid(u8 *dev_addr, u8 *guid);
+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 pci_dev *pdev,
+			 struct bnxt_qplib_ctx *ctx);
+int bnxt_qplib_alloc_ctx(struct pci_dev *pdev,
+			 struct bnxt_qplib_ctx *ctx,
+			 bool virt_fn);
+#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 000000000000..7b31eccedf11
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -0,0 +1,838 @@
+/*
+ * 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
+ */
+
+#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 */
+int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
+			    struct bnxt_qplib_dev_attr *attr)
+{
+	struct cmdq_query_func req;
+	struct creq_query_func_resp *resp;
+	struct creq_query_func_resp_sb *sb;
+	u16 cmd_flags = 0;
+	u32 temp;
+	u8 *tqm_alloc;
+	int i;
+
+	RCFW_CMD_PREP(req, QUERY_FUNC, cmd_flags);
+
+	req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS;
+	resp = (struct creq_query_func_resp *)
+		bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void **)&sb,
+					     0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: QUERY_FUNC send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: QUERY_FUNC timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: QUERY_FUNC failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	/* Extract the context from the side buffer */
+	attr->max_qp = le32_to_cpu(sb->max_qp);
+	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);
+	attr->max_qp_sges = 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_fmr = le32_to_cpu(sb->max_fmr);
+	attr->max_map_per_fmr = sb->max_map_per_fmr;
+
+	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;
+	/* Bono only reports 1 PKEY for now, but it can support > 1 */
+	attr->max_pkey = le32_to_cpu(sb->max_pkeys);
+
+	attr->max_inline_data = le32_to_cpu(sb->max_inline_data);
+	attr->l2_db_size = (sb->l2_db_space_size + 1) * PAGE_SIZE;
+	attr->max_sgid = le32_to_cpu(sb->max_gid);
+
+	strlcpy(attr->fw_ver, "20.6.28.0", sizeof(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);
+	}
+	return 0;
+}
+
+/* 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,
+			"QPLIB: Index %d exceeded SGID table max (%d)",
+			index, sgid_tbl->max);
+		return -EINVAL;
+	}
+	memcpy(gid, &sgid_tbl->tbl[index], sizeof(*gid));
+	return 0;
+}
+
+int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			struct bnxt_qplib_gid *gid, 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, "QPLIB: SGID table not allocated");
+		return -EINVAL;
+	}
+	/* Do we need a sgid_lock here? */
+	if (!sgid_tbl->active) {
+		dev_err(&res->pdev->dev,
+			"QPLIB: SGID table has no active entries");
+		return -ENOMEM;
+	}
+	for (index = 0; index < sgid_tbl->max; index++) {
+		if (!memcmp(&sgid_tbl->tbl[index], gid, sizeof(*gid)))
+			break;
+	}
+	if (index == sgid_tbl->max) {
+		dev_warn(&res->pdev->dev, "GID not found in the SGID table");
+		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;
+
+		RCFW_CMD_PREP(req, DELETE_GID, cmd_flags);
+		if (sgid_tbl->hw_id[index] == 0xFFFF) {
+			dev_err(&res->pdev->dev,
+				"QPLIB: GID entry contains an invalid HW id");
+			return -EINVAL;
+		}
+		req.gid_index = cpu_to_le16(sgid_tbl->hw_id[index]);
+		resp = (struct creq_delete_gid_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, NULL,
+						     0);
+		if (!resp) {
+			dev_err(&res->pdev->dev,
+				"QPLIB: SP: DELETE_GID send failed");
+			return -EINVAL;
+		}
+		if (!bnxt_qplib_rcfw_wait_for_resp(rcfw,
+						   le16_to_cpu(req.cookie))) {
+			/* Cmd timed out */
+			dev_err(&res->pdev->dev,
+				"QPLIB: SP: DELETE_GID timed out");
+			return -ETIMEDOUT;
+		}
+		if (resp->status ||
+		    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+			dev_err(&res->pdev->dev,
+				"QPLIB: SP: DELETE_GID failed ");
+			dev_err(&res->pdev->dev,
+				"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+				resp->status, le16_to_cpu(req.cookie),
+				le16_to_cpu(resp->cookie));
+			return -EINVAL;
+		}
+	}
+	memcpy(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero,
+	       sizeof(bnxt_qplib_gid_zero));
+	sgid_tbl->active--;
+	dev_dbg(&res->pdev->dev,
+		"QPLIB: SGID deleted hw_id[0x%x] = 0x%x active = 0x%x",
+		 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, 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, rc = 0;
+
+	if (!sgid_tbl) {
+		dev_err(&res->pdev->dev, "QPLIB: SGID table not allocated");
+		return -EINVAL;
+	}
+	/* Do we need a sgid_lock here? */
+	if (sgid_tbl->active == sgid_tbl->max) {
+		dev_err(&res->pdev->dev, "QPLIB: SGID table is full");
+		return -ENOMEM;
+	}
+	free_idx = sgid_tbl->max;
+	for (i = 0; i < sgid_tbl->max; i++) {
+		if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid))) {
+			dev_dbg(&res->pdev->dev,
+				"QPLIB: SGID entry already exist in entry %d!",
+				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,
+			"QPLIB: SGID table is FULL but count is not MAX??");
+		return -ENOMEM;
+	}
+	if (update) {
+		struct cmdq_add_gid req;
+		struct creq_add_gid_resp *resp;
+		u16 cmd_flags = 0;
+		u32 temp32[4];
+		u16 temp16[3];
+
+		RCFW_CMD_PREP(req, ADD_GID, cmd_flags);
+
+		memcpy(temp32, gid->data, sizeof(struct bnxt_qplib_gid));
+		req.gid[0] = cpu_to_be32(temp32[3]);
+		req.gid[1] = cpu_to_be32(temp32[2]);
+		req.gid[2] = cpu_to_be32(temp32[1]);
+		req.gid[3] = cpu_to_be32(temp32[0]);
+		if (vlan_id != 0xFFFF)
+			req.vlan = cpu_to_le16((vlan_id &
+					CMDQ_ADD_GID_VLAN_VLAN_ID_MASK) |
+					CMDQ_ADD_GID_VLAN_TPID_TPID_8100 |
+					CMDQ_ADD_GID_VLAN_VLAN_EN);
+
+		/* MAC in network format */
+		memcpy(temp16, smac, 6);
+		req.src_mac[0] = cpu_to_be16(temp16[0]);
+		req.src_mac[1] = cpu_to_be16(temp16[1]);
+		req.src_mac[2] = cpu_to_be16(temp16[2]);
+
+		resp = (struct creq_add_gid_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+		if (!resp) {
+			dev_err(&res->pdev->dev,
+				"QPLIB: SP: ADD_GID send failed");
+			return -EINVAL;
+		}
+		if (!bnxt_qplib_rcfw_wait_for_resp(rcfw,
+						   le16_to_cpu(req.cookie))) {
+			/* Cmd timed out */
+			dev_err(&res->pdev->dev,
+				"QPIB: SP: ADD_GID timed out");
+			return -ETIMEDOUT;
+		}
+		if (resp->status ||
+		    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+			dev_err(&res->pdev->dev, "QPLIB: SP: ADD_GID failed ");
+			dev_err(&res->pdev->dev,
+				"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+				resp->status, le16_to_cpu(req.cookie),
+				le16_to_cpu(resp->cookie));
+			return -EINVAL;
+		}
+		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->active++;
+	dev_dbg(&res->pdev->dev,
+		"QPLIB: SGID added hw_id[0x%x] = 0x%x active = 0x%x",
+		 free_idx, sgid_tbl->hw_id[free_idx], sgid_tbl->active);
+
+	*index = free_idx;
+	/* unlock */
+	return rc;
+}
+
+/* pkeys */
+int bnxt_qplib_get_pkey(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 index,
+			u16 *pkey)
+{
+	if (index == 0xFFFF) {
+		*pkey = 0xFFFF;
+		return 0;
+	}
+	if (index > pkey_tbl->max) {
+		dev_err(&res->pdev->dev,
+			"QPLIB: Index %d exceeded PKEY table max (%d)",
+			index, pkey_tbl->max);
+		return -EINVAL;
+	}
+	memcpy(pkey, &pkey_tbl->tbl[index], sizeof(*pkey));
+	return 0;
+}
+
+int bnxt_qplib_del_pkey(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 *pkey,
+			bool update)
+{
+	int i, rc = 0;
+
+	if (!pkey_tbl) {
+		dev_err(&res->pdev->dev, "QPLIB: PKEY table not allocated");
+		return -EINVAL;
+	}
+
+	/* Do we need a pkey_lock here? */
+	if (!pkey_tbl->active) {
+		dev_err(&res->pdev->dev,
+			"QPLIB: PKEY table has no active entries");
+		return -ENOMEM;
+	}
+	for (i = 0; i < pkey_tbl->max; i++) {
+		if (!memcmp(&pkey_tbl->tbl[i], pkey, sizeof(*pkey)))
+			break;
+	}
+	if (i == pkey_tbl->max) {
+		dev_err(&res->pdev->dev,
+			"QPLIB: PKEY 0x%04x not found in the pkey table",
+			*pkey);
+		return -ENOMEM;
+	}
+	memset(&pkey_tbl->tbl[i], 0, sizeof(*pkey));
+	pkey_tbl->active--;
+
+	/* unlock */
+	return rc;
+}
+
+int bnxt_qplib_add_pkey(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 *pkey,
+			bool update)
+{
+	int i, free_idx, rc = 0;
+
+	if (!pkey_tbl) {
+		dev_err(&res->pdev->dev, "QPLIB: PKEY table not allocated");
+		return -EINVAL;
+	}
+
+	/* Do we need a pkey_lock here? */
+	if (pkey_tbl->active == pkey_tbl->max) {
+		dev_err(&res->pdev->dev, "QPLIB: PKEY table is full");
+		return -ENOMEM;
+	}
+	free_idx = pkey_tbl->max;
+	for (i = 0; i < pkey_tbl->max; i++) {
+		if (!memcmp(&pkey_tbl->tbl[i], pkey, sizeof(*pkey)))
+			return -EALREADY;
+		else if (!pkey_tbl->tbl[i] && free_idx == pkey_tbl->max)
+			free_idx = i;
+	}
+	if (free_idx == pkey_tbl->max) {
+		dev_err(&res->pdev->dev,
+			"QPLIB: PKEY table is FULL but count is not MAX??");
+		return -ENOMEM;
+	}
+	/* Add PKEY to the pkey_tbl */
+	memcpy(&pkey_tbl->tbl[free_idx], pkey, sizeof(*pkey));
+	pkey_tbl->active++;
+
+	/* unlock */
+	return rc;
+}
+
+/* AH */
+int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah)
+{
+	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];
+
+	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]);
+
+	resp = (struct creq_create_ah_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 1);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: CREATE_AH send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_block_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: CREATE_AH timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: CREATE_AH failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	ah->id = le32_to_cpu(resp->xid);
+	return 0;
+}
+
+int bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah)
+{
+	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);
+
+	resp = (struct creq_destroy_ah_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 1);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: DESTROY_AH send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_block_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: DESTROY_AH timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: DESTROY_AH failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* 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;
+
+	if (mrw->lkey == 0xFFFFFFFF) {
+		dev_info(&res->pdev->dev,
+			 "QPLIB: SP: Free a reserved lkey MRW");
+		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);
+
+	resp = (struct creq_deallocate_key_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&res->pdev->dev, "QPLIB: SP: FREE_MR send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&res->pdev->dev, "QPLIB: SP: FREE_MR timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&res->pdev->dev, "QPLIB: SP: FREE_MR failed ");
+		dev_err(&res->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	/* Free the qplib's MRW memory */
+	if (mrw->hwq.max_elements)
+		bnxt_qplib_free_hwq(res->pdev, &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;
+
+	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);
+
+	resp = (struct creq_allocate_mrw_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, 0);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: ALLOC_MRW send failed");
+		return -EINVAL;
+	}
+	if (!bnxt_qplib_rcfw_wait_for_resp(rcfw, le16_to_cpu(req.cookie))) {
+		/* Cmd timed out */
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: ALLOC_MRW timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: ALLOC_MRW failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+	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);
+	resp = (struct creq_deregister_mr_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, block);
+	if (!resp) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: DEREG_MR send failed");
+		return -EINVAL;
+	}
+	if (block)
+		rc = bnxt_qplib_rcfw_block_for_resp(rcfw,
+						    le16_to_cpu(req.cookie));
+	else
+		rc = bnxt_qplib_rcfw_wait_for_resp(rcfw,
+						   le16_to_cpu(req.cookie));
+	if (!rc) {
+		/* Cmd timed out */
+		dev_err(&res->pdev->dev, "QPLIB: SP: DEREG_MR timed out");
+		return -ETIMEDOUT;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&rcfw->pdev->dev, "QPLIB: SP: DEREG_MR failed ");
+		dev_err(&rcfw->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+
+	/* Free the qplib's MR memory */
+	if (mrw->hwq.max_elements) {
+		mrw->va = 0;
+		mrw->total_size = 0;
+		bnxt_qplib_free_hwq(res->pdev, &mrw->hwq);
+	}
+
+	return 0;
+}
+
+int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr,
+		      u64 *pbl_tbl, int num_pbls, bool block)
+{
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct cmdq_register_mr req;
+	struct creq_register_mr_resp *resp;
+	u16 cmd_flags = 0, level;
+	int pg_ptrs, pages, i, rc;
+	dma_addr_t **pbl_ptr;
+	u32 pg_size;
+
+	if (num_pbls) {
+		pg_ptrs = roundup_pow_of_two(num_pbls);
+		pages = pg_ptrs >> MAX_PBL_LVL_1_PGS_SHIFT;
+		if (!pages)
+			pages++;
+
+		if (pages > MAX_PBL_LVL_1_PGS) {
+			dev_err(&res->pdev->dev, "QPLIB: SP: Reg MR pages ");
+			dev_err(&res->pdev->dev,
+				"requested (0x%x) exceeded max (0x%x)",
+				pages, MAX_PBL_LVL_1_PGS);
+			return -ENOMEM;
+		}
+		/* Free the hwq if it already exist, must be a rereg */
+		if (mr->hwq.max_elements)
+			bnxt_qplib_free_hwq(res->pdev, &mr->hwq);
+
+		mr->hwq.max_elements = pages;
+		rc = bnxt_qplib_alloc_init_hwq(res->pdev, &mr->hwq, NULL, 0,
+					       &mr->hwq.max_elements,
+					       PAGE_SIZE, 0, PAGE_SIZE,
+					       HWQ_TYPE_CTX);
+		if (rc) {
+			dev_err(&res->pdev->dev,
+				"SP: Reg MR memory allocation failed");
+			return -ENOMEM;
+		}
+		/* Write to the hwq */
+		pbl_ptr = (dma_addr_t **)mr->hwq.pbl_ptr;
+		for (i = 0; i < num_pbls; i++)
+			pbl_ptr[PTR_PG(i)][PTR_IDX(i)] =
+				(pbl_tbl[i] & PAGE_MASK) | PTU_PTE_VALID;
+	}
+
+	RCFW_CMD_PREP(req, REGISTER_MR, cmd_flags);
+
+	/* Configure the request */
+	if (mr->hwq.level == PBL_LVL_MAX) {
+		level = 0;
+		req.pbl = 0;
+		pg_size = PAGE_SIZE;
+	} else {
+		level = mr->hwq.level + 1;
+		req.pbl = cpu_to_le64(mr->hwq.pbl[PBL_LVL_0].pg_map_arr[0]);
+		pg_size = mr->hwq.pbl[PBL_LVL_0].pg_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.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);
+
+	resp = (struct creq_register_mr_resp *)
+			bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+						     NULL, block);
+	if (!resp) {
+		dev_err(&res->pdev->dev, "SP: REG_MR send failed");
+		rc = -EINVAL;
+		goto fail;
+	}
+	if (block)
+		rc = bnxt_qplib_rcfw_block_for_resp(rcfw,
+						    le16_to_cpu(req.cookie));
+	else
+		rc = bnxt_qplib_rcfw_wait_for_resp(rcfw,
+						   le16_to_cpu(req.cookie));
+	if (!rc) {
+		/* Cmd timed out */
+		dev_err(&res->pdev->dev, "SP: REG_MR timed out");
+		rc = -ETIMEDOUT;
+		goto fail;
+	}
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&res->pdev->dev, "QPLIB: SP: REG_MR failed ");
+		dev_err(&res->pdev->dev,
+			"QPLIB: SP: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		rc = -EINVAL;
+		goto fail;
+	}
+	return 0;
+
+fail:
+	if (mr->hwq.max_elements)
+		bnxt_qplib_free_hwq(res->pdev, &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)
+{
+	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;
+
+	frpl->hwq.max_elements = pages;
+	rc = bnxt_qplib_alloc_init_hwq(res->pdev, &frpl->hwq, NULL, 0,
+				       &frpl->hwq.max_elements, PAGE_SIZE, 0,
+				       PAGE_SIZE, HWQ_TYPE_CTX);
+	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->pdev, &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;
+	int tleft;
+
+	RCFW_CMD_PREP(req, MAP_TC_TO_COS, cmd_flags);
+	req.cos0 = cpu_to_le16(cids[0]);
+	req.cos1 = cpu_to_le16(cids[1]);
+
+	resp = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, NULL, 0);
+	if (!resp) {
+		dev_err(&res->pdev->dev, "QPLIB: SP: MAP_TC2COS send failed");
+		return -EINVAL;
+	}
+
+	tleft = bnxt_qplib_rcfw_block_for_resp(rcfw, le16_to_cpu(req.cookie));
+	if (!tleft) {
+		dev_err(&res->pdev->dev, "QPLIB: SP: MAP_TC2COS timed out");
+		return -ETIMEDOUT;
+	}
+
+	if (resp->status ||
+	    le16_to_cpu(resp->cookie) != le16_to_cpu(req.cookie)) {
+		dev_err(&res->pdev->dev, "QPLIB: SP: MAP_TC2COS failed ");
+		dev_err(&res->pdev->dev,
+			"QPLIB: with status 0x%x cmdq 0x%x resp 0x%x",
+			resp->status, le16_to_cpu(req.cookie),
+			le16_to_cpu(resp->cookie));
+		return -EINVAL;
+	}
+
+	return 0;
+}
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 000000000000..1442a617e968
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -0,0 +1,160 @@
+/*
+ * 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__
+
+struct bnxt_qplib_dev_attr {
+	char				fw_ver[32];
+	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_fmr;
+	u32				max_map_per_fmr;
+	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];
+};
+
+struct bnxt_qplib_pd {
+	u32				id;
+};
+
+struct bnxt_qplib_gid {
+	u8				data[16];
+};
+
+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)
+
+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, bool update);
+int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			struct bnxt_qplib_gid *gid, u8 *mac, u16 vlan_id,
+			bool update, u32 *index);
+int bnxt_qplib_get_pkey(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 index,
+			u16 *pkey);
+int bnxt_qplib_del_pkey(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 *pkey,
+			bool update);
+int bnxt_qplib_add_pkey(struct bnxt_qplib_res *res,
+			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 *pkey,
+			bool update);
+int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
+			    struct bnxt_qplib_dev_attr *attr);
+int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah);
+int bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah);
+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,
+		      u64 *pbl_tbl, int num_pbls, bool block);
+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);
+#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 000000000000..fc23477ac52f
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -0,0 +1,2821 @@
+/*
+ * 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 */
+/* 64b Doorbell Format (8 bytes) */
+struct dbr_dbr {
+	__le32 index;
+	#define DBR_DBR_INDEX_MASK				    0xfffffUL
+	#define DBR_DBR_INDEX_SFT				    0
+	#define DBR_DBR_RESERVED12_MASK			    0xfff00000UL
+	#define DBR_DBR_RESERVED12_SFT				    20
+	__le32 type_xid;
+	#define DBR_DBR_XID_MASK				    0xfffffUL
+	#define DBR_DBR_XID_SFT				    0
+	#define DBR_DBR_RESERVED8_MASK				    0xff00000UL
+	#define DBR_DBR_RESERVED8_SFT				    20
+	#define DBR_DBR_TYPE_MASK				    0xf0000000UL
+	#define DBR_DBR_TYPE_SFT				    28
+	#define DBR_DBR_TYPE_SQ				   (0x0UL << 28)
+	#define DBR_DBR_TYPE_RQ				   (0x1UL << 28)
+	#define DBR_DBR_TYPE_SRQ				   (0x2UL << 28)
+	#define DBR_DBR_TYPE_SRQ_ARM				   (0x3UL << 28)
+	#define DBR_DBR_TYPE_CQ				   (0x4UL << 28)
+	#define DBR_DBR_TYPE_CQ_ARMSE				   (0x5UL << 28)
+	#define DBR_DBR_TYPE_CQ_ARMALL				   (0x6UL << 28)
+	#define DBR_DBR_TYPE_CQ_ARMENA				   (0x7UL << 28)
+	#define DBR_DBR_TYPE_SRQ_ARMENA			   (0x8UL << 28)
+	#define DBR_DBR_TYPE_CQ_CUTOFF_ACK			   (0x9UL << 28)
+	#define DBR_DBR_TYPE_NULL				   (0xfUL << 28)
+};
+
+/* 32b Doorbell Format (4 bytes) */
+struct dbr_dbr32 {
+	__le32 type_abs_incr_xid;
+	#define DBR_DBR32_XID_MASK				    0xfffffUL
+	#define DBR_DBR32_XID_SFT				    0
+	#define DBR_DBR32_RESERVED4_MASK			    0xf00000UL
+	#define DBR_DBR32_RESERVED4_SFT			    20
+	#define DBR_DBR32_INCR_MASK				    0xf000000UL
+	#define DBR_DBR32_INCR_SFT				    24
+	#define DBR_DBR32_ABS					    0x10000000UL
+	#define DBR_DBR32_TYPE_MASK				    0xe0000000UL
+	#define DBR_DBR32_TYPE_SFT				    29
+	#define DBR_DBR32_TYPE_SQ				   (0x0UL << 29)
+};
+
+/* 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
+};
+
+/* 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];
+};
+
+/* 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];
+};
+
+/* 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];
+};
+
+/* 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];
+};
+
+/* 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];
+};
+
+/* 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];
+};
+
+/* 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
+};
+
+/* 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];
+};
+
+/* 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 {
+	__le32 length;
+	#define CQ_RES_UD_LENGTH_MASK				    0x3fffUL
+	#define CQ_RES_UD_LENGTH_SFT				    0
+	#define CQ_RES_UD_RESERVED18_MASK			    0xffffc000UL
+	#define CQ_RES_UD_RESERVED18_SFT			    14
+	__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)
+	#define CQ_RES_UD_RESERVED3_MASK			    0xe0UL
+	#define CQ_RES_UD_RESERVED3_SFT			    5
+	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_ROCE_IP_VER_MASK		    0xcUL
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_SFT		    2
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_V1			   (0x0UL << 2)
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV4		   (0x2UL << 2)
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6		   (0x3UL << 2)
+	#define CQ_RES_UD_FLAGS_ROCE_IP_VER_LAST		\
+					CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6
+	__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_RESERVED4_MASK			    0xf00000UL
+	#define CQ_RES_UD_RESERVED4_SFT			    20
+	#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
+	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
+	u8 type;
+	#define CMDQ_CREATE_QP_TYPE_RC				   0x2UL
+	#define CMDQ_CREATE_QP_TYPE_UD				   0x4UL
+	#define CMDQ_CREATE_QP_TYPE_RAW_ETHERTYPE		   0x6UL
+	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_LOG2_PG_SIZE_MASK		    0x7cUL
+	#define CMDQ_REGISTER_MR_LOG2_PG_SIZE_SFT		    2
+	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 unused_1;
+	__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;
+	__le32 gid[4];
+	__le16 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)
+	__le16 reserved16;
+	__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;
+};
+
+/* 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];
+};
+
+/* 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
+	__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[8];
+};
+
+/* 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;
+};
+
+/* 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__ */
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.h b/drivers/infiniband/hw/cxgb3/iwch_cm.h
index b9efadfffb4f..e66e75921797 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.h
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.h
@@ -55,14 +55,14 @@
 
 #define put_ep(ep) { \
 	PDBG("put_ep (via %s:%u) ep %p refcnt %d\n", __func__, __LINE__,  \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
-	WARN_ON(atomic_read(&((ep)->kref.refcount)) < 1); \
+	     ep, kref_read(&((ep)->kref))); \
+	WARN_ON(kref_read(&((ep)->kref)) < 1); \
 	kref_put(&((ep)->kref), __free_ep); \
 }
 
 #define get_ep(ep) { \
 	PDBG("get_ep (via %s:%u) ep %p, refcnt %d\n", __func__, __LINE__, \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
+	     ep, kref_read(&((ep)->kref))); \
 	kref_get(&((ep)->kref));  \
 }
 
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 6262dc035f3c..86ecd3ea6a4b 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -37,7 +37,7 @@
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/list.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/spinlock.h>
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
@@ -1133,7 +1133,7 @@ static int iwch_query_port(struct ib_device *ibdev,
 	dev = to_iwch_dev(ibdev);
 	netdev = dev->rdev.port_info.lldevs[port-1];
 
-	memset(props, 0, sizeof(struct ib_port_attr));
+	/* props being zeroed by the caller, avoid zeroing it here */
 	props->max_mtu = IB_MTU_4096;
 	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
@@ -1329,13 +1329,14 @@ static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
-	err = iwch_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
 
 	return 0;
 }
@@ -1392,7 +1393,7 @@ int iwch_register_device(struct iwch_dev *dev)
 	memcpy(dev->ibdev.node_desc, IWCH_NODE_DESC, sizeof(IWCH_NODE_DESC));
 	dev->ibdev.phys_port_cnt = dev->rdev.port_info.nports;
 	dev->ibdev.num_comp_vectors = 1;
-	dev->ibdev.dma_device = &(dev->rdev.rnic_info.pdev->dev);
+	dev->ibdev.dev.parent = &dev->rdev.rnic_info.pdev->dev;
 	dev->ibdev.query_device = iwch_query_device;
 	dev->ibdev.query_port = iwch_query_port;
 	dev->ibdev.query_pkey = iwch_query_pkey;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c
index d939980a708f..a9194db7f9b8 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_qp.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c
@@ -961,7 +961,7 @@ int iwch_modify_qp(struct iwch_dev *rhp, struct iwch_qp *qhp,
 	case IWCH_QP_STATE_RTS:
 		switch (attrs->next_state) {
 		case IWCH_QP_STATE_CLOSING:
-			BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
+			BUG_ON(kref_read(&qhp->ep->com.kref) < 2);
 			qhp->attr.state = IWCH_QP_STATE_CLOSING;
 			if (!internal) {
 				abort=0;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 9398143d7c5e..03a1b0e64fc3 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -692,6 +692,10 @@ static int send_connect(struct c4iw_ep *ep)
 	int ret;
 	enum chip_type adapter_type = ep->com.dev->rdev.lldi.adapter_type;
 	u32 isn = (prandom_u32() & ~7UL) - 1;
+	struct net_device *netdev;
+	u64 params;
+
+	netdev = ep->com.dev->rdev.lldi.ports[0];
 
 	switch (CHELSIO_CHIP_VERSION(adapter_type)) {
 	case CHELSIO_T4:
@@ -768,6 +772,8 @@ static int send_connect(struct c4iw_ep *ep)
 		opt2 |= T5_ISS_F;
 	}
 
+	params = cxgb4_select_ntuple(netdev, ep->l2t);
+
 	if (ep->com.remote_addr.ss_family == AF_INET6)
 		cxgb4_clip_get(ep->com.dev->rdev.lldi.ports[0],
 			       (const u32 *)&la6->sin6_addr.s6_addr, 1);
@@ -809,18 +815,22 @@ static int send_connect(struct c4iw_ep *ep)
 		req->opt0 = cpu_to_be64(opt0);
 
 		if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) {
-			req->params = cpu_to_be32(cxgb4_select_ntuple(
-						ep->com.dev->rdev.lldi.ports[0],
-						ep->l2t));
+			req->params = cpu_to_be32(params);
 			req->opt2 = cpu_to_be32(opt2);
 		} else {
-			t5req->params = cpu_to_be64(FILTER_TUPLE_V(
-						cxgb4_select_ntuple(
-						ep->com.dev->rdev.lldi.ports[0],
-						ep->l2t)));
-			t5req->rsvd = cpu_to_be32(isn);
-			PDBG("%s snd_isn %u\n", __func__, t5req->rsvd);
-			t5req->opt2 = cpu_to_be32(opt2);
+			if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+				t5req->params =
+					  cpu_to_be64(FILTER_TUPLE_V(params));
+				t5req->rsvd = cpu_to_be32(isn);
+				PDBG("%s snd_isn %u\n", __func__, t5req->rsvd);
+				t5req->opt2 = cpu_to_be32(opt2);
+			} else {
+				t6req->params =
+					  cpu_to_be64(FILTER_TUPLE_V(params));
+				t6req->rsvd = cpu_to_be32(isn);
+				PDBG("%s snd_isn %u\n", __func__, t6req->rsvd);
+				t6req->opt2 = cpu_to_be32(opt2);
+			}
 		}
 	} else {
 		switch (CHELSIO_CHIP_VERSION(adapter_type)) {
@@ -859,18 +869,24 @@ static int send_connect(struct c4iw_ep *ep)
 		req6->opt0 = cpu_to_be64(opt0);
 
 		if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) {
-			req6->params = cpu_to_be32(cxgb4_select_ntuple(
-						ep->com.dev->rdev.lldi.ports[0],
-						ep->l2t));
+			req6->params = cpu_to_be32(cxgb4_select_ntuple(netdev,
+								      ep->l2t));
 			req6->opt2 = cpu_to_be32(opt2);
 		} else {
-			t5req6->params = cpu_to_be64(FILTER_TUPLE_V(
-						cxgb4_select_ntuple(
-						ep->com.dev->rdev.lldi.ports[0],
-						ep->l2t)));
-			t5req6->rsvd = cpu_to_be32(isn);
-			PDBG("%s snd_isn %u\n", __func__, t5req6->rsvd);
-			t5req6->opt2 = cpu_to_be32(opt2);
+			if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+				t5req6->params =
+					    cpu_to_be64(FILTER_TUPLE_V(params));
+				t5req6->rsvd = cpu_to_be32(isn);
+				PDBG("%s snd_isn %u\n", __func__, t5req6->rsvd);
+				t5req6->opt2 = cpu_to_be32(opt2);
+			} else {
+				t6req6->params =
+					    cpu_to_be64(FILTER_TUPLE_V(params));
+				t6req6->rsvd = cpu_to_be32(isn);
+				PDBG("%s snd_isn %u\n", __func__, t6req6->rsvd);
+				t6req6->opt2 = cpu_to_be32(opt2);
+			}
+
 		}
 	}
 
@@ -2517,18 +2533,18 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 		struct sockaddr_in *sin = (struct sockaddr_in *)
 			&child_ep->com.local_addr;
 
-		sin->sin_family = PF_INET;
+		sin->sin_family = AF_INET;
 		sin->sin_port = local_port;
 		sin->sin_addr.s_addr = *(__be32 *)local_ip;
 
 		sin = (struct sockaddr_in *)&child_ep->com.local_addr;
-		sin->sin_family = PF_INET;
+		sin->sin_family = AF_INET;
 		sin->sin_port = ((struct sockaddr_in *)
 				 &parent_ep->com.local_addr)->sin_port;
 		sin->sin_addr.s_addr = *(__be32 *)local_ip;
 
 		sin = (struct sockaddr_in *)&child_ep->com.remote_addr;
-		sin->sin_family = PF_INET;
+		sin->sin_family = AF_INET;
 		sin->sin_port = peer_port;
 		sin->sin_addr.s_addr = *(__be32 *)peer_ip;
 	} else {
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 40c0e7b9fc6e..4e4f1a732b01 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -214,6 +214,52 @@ static const struct file_operations wr_log_debugfs_fops = {
 	.write   = wr_log_clear,
 };
 
+static struct sockaddr_in zero_sin = {
+	.sin_family = AF_INET,
+};
+
+static struct sockaddr_in6 zero_sin6 = {
+	.sin6_family = AF_INET6,
+};
+
+static void set_ep_sin_addrs(struct c4iw_ep *ep,
+			     struct sockaddr_in **lsin,
+			     struct sockaddr_in **rsin,
+			     struct sockaddr_in **m_lsin,
+			     struct sockaddr_in **m_rsin)
+{
+	struct iw_cm_id *id = ep->com.cm_id;
+
+	*lsin = (struct sockaddr_in *)&ep->com.local_addr;
+	*rsin = (struct sockaddr_in *)&ep->com.remote_addr;
+	if (id) {
+		*m_lsin = (struct sockaddr_in *)&id->m_local_addr;
+		*m_rsin = (struct sockaddr_in *)&id->m_remote_addr;
+	} else {
+		*m_lsin = &zero_sin;
+		*m_rsin = &zero_sin;
+	}
+}
+
+static void set_ep_sin6_addrs(struct c4iw_ep *ep,
+			      struct sockaddr_in6 **lsin6,
+			      struct sockaddr_in6 **rsin6,
+			      struct sockaddr_in6 **m_lsin6,
+			      struct sockaddr_in6 **m_rsin6)
+{
+	struct iw_cm_id *id = ep->com.cm_id;
+
+	*lsin6 = (struct sockaddr_in6 *)&ep->com.local_addr;
+	*rsin6 = (struct sockaddr_in6 *)&ep->com.remote_addr;
+	if (id) {
+		*m_lsin6 = (struct sockaddr_in6 *)&id->m_local_addr;
+		*m_rsin6 = (struct sockaddr_in6 *)&id->m_remote_addr;
+	} else {
+		*m_lsin6 = &zero_sin6;
+		*m_rsin6 = &zero_sin6;
+	}
+}
+
 static int dump_qp(int id, void *p, void *data)
 {
 	struct c4iw_qp *qp = p;
@@ -229,16 +275,15 @@ static int dump_qp(int id, void *p, void *data)
 		return 1;
 
 	if (qp->ep) {
-		if (qp->ep->com.local_addr.ss_family == AF_INET) {
-			struct sockaddr_in *lsin = (struct sockaddr_in *)
-				&qp->ep->com.cm_id->local_addr;
-			struct sockaddr_in *rsin = (struct sockaddr_in *)
-				&qp->ep->com.cm_id->remote_addr;
-			struct sockaddr_in *mapped_lsin = (struct sockaddr_in *)
-				&qp->ep->com.cm_id->m_local_addr;
-			struct sockaddr_in *mapped_rsin = (struct sockaddr_in *)
-				&qp->ep->com.cm_id->m_remote_addr;
+		struct c4iw_ep *ep = qp->ep;
+
+		if (ep->com.local_addr.ss_family == AF_INET) {
+			struct sockaddr_in *lsin;
+			struct sockaddr_in *rsin;
+			struct sockaddr_in *m_lsin;
+			struct sockaddr_in *m_rsin;
 
+			set_ep_sin_addrs(ep, &lsin, &rsin, &m_lsin, &m_rsin);
 			cc = snprintf(qpd->buf + qpd->pos, space,
 				      "rc qp sq id %u rq id %u state %u "
 				      "onchip %u ep tid %u state %u "
@@ -246,23 +291,19 @@ static int dump_qp(int id, void *p, void *data)
 				      qp->wq.sq.qid, qp->wq.rq.qid,
 				      (int)qp->attr.state,
 				      qp->wq.sq.flags & T4_SQ_ONCHIP,
-				      qp->ep->hwtid, (int)qp->ep->com.state,
+				      ep->hwtid, (int)ep->com.state,
 				      &lsin->sin_addr, ntohs(lsin->sin_port),
-				      ntohs(mapped_lsin->sin_port),
+				      ntohs(m_lsin->sin_port),
 				      &rsin->sin_addr, ntohs(rsin->sin_port),
-				      ntohs(mapped_rsin->sin_port));
+				      ntohs(m_rsin->sin_port));
 		} else {
-			struct sockaddr_in6 *lsin6 = (struct sockaddr_in6 *)
-				&qp->ep->com.cm_id->local_addr;
-			struct sockaddr_in6 *rsin6 = (struct sockaddr_in6 *)
-				&qp->ep->com.cm_id->remote_addr;
-			struct sockaddr_in6 *mapped_lsin6 =
-				(struct sockaddr_in6 *)
-				&qp->ep->com.cm_id->m_local_addr;
-			struct sockaddr_in6 *mapped_rsin6 =
-				(struct sockaddr_in6 *)
-				&qp->ep->com.cm_id->m_remote_addr;
+			struct sockaddr_in6 *lsin6;
+			struct sockaddr_in6 *rsin6;
+			struct sockaddr_in6 *m_lsin6;
+			struct sockaddr_in6 *m_rsin6;
 
+			set_ep_sin6_addrs(ep, &lsin6, &rsin6, &m_lsin6,
+					  &m_rsin6);
 			cc = snprintf(qpd->buf + qpd->pos, space,
 				      "rc qp sq id %u rq id %u state %u "
 				      "onchip %u ep tid %u state %u "
@@ -270,13 +311,13 @@ static int dump_qp(int id, void *p, void *data)
 				      qp->wq.sq.qid, qp->wq.rq.qid,
 				      (int)qp->attr.state,
 				      qp->wq.sq.flags & T4_SQ_ONCHIP,
-				      qp->ep->hwtid, (int)qp->ep->com.state,
+				      ep->hwtid, (int)ep->com.state,
 				      &lsin6->sin6_addr,
 				      ntohs(lsin6->sin6_port),
-				      ntohs(mapped_lsin6->sin6_port),
+				      ntohs(m_lsin6->sin6_port),
 				      &rsin6->sin6_addr,
 				      ntohs(rsin6->sin6_port),
-				      ntohs(mapped_rsin6->sin6_port));
+				      ntohs(m_rsin6->sin6_port));
 		}
 	} else
 		cc = snprintf(qpd->buf + qpd->pos, space,
@@ -533,15 +574,12 @@ static int dump_ep(int id, void *p, void *data)
 		return 1;
 
 	if (ep->com.local_addr.ss_family == AF_INET) {
-		struct sockaddr_in *lsin = (struct sockaddr_in *)
-			&ep->com.cm_id->local_addr;
-		struct sockaddr_in *rsin = (struct sockaddr_in *)
-			&ep->com.cm_id->remote_addr;
-		struct sockaddr_in *mapped_lsin = (struct sockaddr_in *)
-			&ep->com.cm_id->m_local_addr;
-		struct sockaddr_in *mapped_rsin = (struct sockaddr_in *)
-			&ep->com.cm_id->m_remote_addr;
+		struct sockaddr_in *lsin;
+		struct sockaddr_in *rsin;
+		struct sockaddr_in *m_lsin;
+		struct sockaddr_in *m_rsin;
 
+		set_ep_sin_addrs(ep, &lsin, &rsin, &m_lsin, &m_rsin);
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
@@ -553,19 +591,16 @@ static int dump_ep(int id, void *p, void *data)
 			      ep->stats.connect_neg_adv,
 			      ep->stats.abort_neg_adv,
 			      &lsin->sin_addr, ntohs(lsin->sin_port),
-			      ntohs(mapped_lsin->sin_port),
+			      ntohs(m_lsin->sin_port),
 			      &rsin->sin_addr, ntohs(rsin->sin_port),
-			      ntohs(mapped_rsin->sin_port));
+			      ntohs(m_rsin->sin_port));
 	} else {
-		struct sockaddr_in6 *lsin6 = (struct sockaddr_in6 *)
-			&ep->com.cm_id->local_addr;
-		struct sockaddr_in6 *rsin6 = (struct sockaddr_in6 *)
-			&ep->com.cm_id->remote_addr;
-		struct sockaddr_in6 *mapped_lsin6 = (struct sockaddr_in6 *)
-			&ep->com.cm_id->m_local_addr;
-		struct sockaddr_in6 *mapped_rsin6 = (struct sockaddr_in6 *)
-			&ep->com.cm_id->m_remote_addr;
+		struct sockaddr_in6 *lsin6;
+		struct sockaddr_in6 *rsin6;
+		struct sockaddr_in6 *m_lsin6;
+		struct sockaddr_in6 *m_rsin6;
 
+		set_ep_sin6_addrs(ep, &lsin6, &rsin6, &m_lsin6, &m_rsin6);
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
@@ -577,9 +612,9 @@ static int dump_ep(int id, void *p, void *data)
 			      ep->stats.connect_neg_adv,
 			      ep->stats.abort_neg_adv,
 			      &lsin6->sin6_addr, ntohs(lsin6->sin6_port),
-			      ntohs(mapped_lsin6->sin6_port),
+			      ntohs(m_lsin6->sin6_port),
 			      &rsin6->sin6_addr, ntohs(rsin6->sin6_port),
-			      ntohs(mapped_rsin6->sin6_port));
+			      ntohs(m_rsin6->sin6_port));
 	}
 	if (cc < space)
 		epd->pos += cc;
@@ -600,7 +635,7 @@ static int dump_listen_ep(int id, void *p, void *data)
 	if (ep->com.local_addr.ss_family == AF_INET) {
 		struct sockaddr_in *lsin = (struct sockaddr_in *)
 			&ep->com.cm_id->local_addr;
-		struct sockaddr_in *mapped_lsin = (struct sockaddr_in *)
+		struct sockaddr_in *m_lsin = (struct sockaddr_in *)
 			&ep->com.cm_id->m_local_addr;
 
 		cc = snprintf(epd->buf + epd->pos, space,
@@ -609,11 +644,11 @@ static int dump_listen_ep(int id, void *p, void *data)
 			      ep, ep->com.cm_id, (int)ep->com.state,
 			      ep->com.flags, ep->stid, ep->backlog,
 			      &lsin->sin_addr, ntohs(lsin->sin_port),
-			      ntohs(mapped_lsin->sin_port));
+			      ntohs(m_lsin->sin_port));
 	} else {
 		struct sockaddr_in6 *lsin6 = (struct sockaddr_in6 *)
 			&ep->com.cm_id->local_addr;
-		struct sockaddr_in6 *mapped_lsin6 = (struct sockaddr_in6 *)
+		struct sockaddr_in6 *m_lsin6 = (struct sockaddr_in6 *)
 			&ep->com.cm_id->m_local_addr;
 
 		cc = snprintf(epd->buf + epd->pos, space,
@@ -622,7 +657,7 @@ static int dump_listen_ep(int id, void *p, void *data)
 			      ep, ep->com.cm_id, (int)ep->com.state,
 			      ep->com.flags, ep->stid, ep->backlog,
 			      &lsin6->sin6_addr, ntohs(lsin6->sin6_port),
-			      ntohs(mapped_lsin6->sin6_port));
+			      ntohs(m_lsin6->sin6_port));
 	}
 	if (cc < space)
 		epd->pos += cc;
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 8cd4d054a87e..5846c47c8d55 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -37,7 +37,7 @@
 #include <linux/idr.h>
 #include <linux/completion.h>
 #include <linux/netdevice.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/inet.h>
@@ -672,14 +672,14 @@ enum c4iw_mmid_state {
 
 #define c4iw_put_ep(ep) { \
 	PDBG("put_ep (via %s:%u) ep %p refcnt %d\n", __func__, __LINE__,  \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
-	WARN_ON(atomic_read(&((ep)->kref.refcount)) < 1); \
+	     ep, kref_read(&((ep)->kref))); \
+	WARN_ON(kref_read(&((ep)->kref)) < 1); \
 	kref_put(&((ep)->kref), _c4iw_free_ep); \
 }
 
 #define c4iw_get_ep(ep) { \
 	PDBG("get_ep (via %s:%u) ep %p, refcnt %d\n", __func__, __LINE__, \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
+	     ep, kref_read(&((ep)->kref))); \
 	kref_get(&((ep)->kref));  \
 }
 void _c4iw_free_ep(struct kref *kref);
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 3345e1c312f7..df64417ab6f2 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -370,8 +370,7 @@ static int c4iw_query_port(struct ib_device *ibdev, u8 port,
 
 	dev = to_c4iw_dev(ibdev);
 	netdev = dev->rdev.lldi.ports[port-1];
-
-	memset(props, 0, sizeof(struct ib_port_attr));
+	/* props being zeroed by the caller, avoid zeroing it here */
 	props->max_mtu = IB_MTU_4096;
 	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
@@ -508,13 +507,14 @@ static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
-	err = c4iw_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
 
 	return 0;
 }
@@ -572,7 +572,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	memcpy(dev->ibdev.node_desc, C4IW_NODE_DESC, sizeof(C4IW_NODE_DESC));
 	dev->ibdev.phys_port_cnt = dev->rdev.lldi.nports;
 	dev->ibdev.num_comp_vectors =  dev->rdev.lldi.nciq;
-	dev->ibdev.dma_device = &(dev->rdev.lldi.pdev->dev);
+	dev->ibdev.dev.parent = &dev->rdev.lldi.pdev->dev;
 	dev->ibdev.query_device = c4iw_query_device;
 	dev->ibdev.query_port = c4iw_query_port;
 	dev->ibdev.query_pkey = c4iw_query_pkey;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 04c1c382dedb..d4fd2f5c8326 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1580,7 +1580,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	case C4IW_QP_STATE_RTS:
 		switch (attrs->next_state) {
 		case C4IW_QP_STATE_CLOSING:
-			BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
+			BUG_ON(kref_read(&qhp->ep->com.kref) < 2);
 			t4_set_wq_in_error(&qhp->wq);
 			set_state(qhp, C4IW_QP_STATE_CLOSING);
 			ep = qhp->ep;
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 7a3d906b3671..e2cd2cd3b28a 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -576,7 +576,7 @@ int hfi1_get_proc_affinity(int node)
 	struct hfi1_affinity_node *entry;
 	cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask;
 	const struct cpumask *node_mask,
-		*proc_mask = tsk_cpus_allowed(current);
+		*proc_mask = &current->cpus_allowed;
 	struct hfi1_affinity_node_list *affinity = &node_affinity;
 	struct cpu_mask_set *set = &affinity->proc;
 
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index ef72bc2a9e1d..121a4c920f1b 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -7827,7 +7827,8 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg)
 		}
 
 		/* just report this */
-		dd_dev_info(dd, "DCC Error: fmconfig error: %s\n", extra);
+		dd_dev_info_ratelimited(dd, "DCC Error: fmconfig error: %s\n",
+					extra);
 		reg &= ~DCC_ERR_FLG_FMCONFIG_ERR_SMASK;
 	}
 
@@ -7878,34 +7879,35 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg)
 		}
 
 		/* just report this */
-		dd_dev_info(dd, "DCC Error: PortRcv error: %s\n", extra);
-		dd_dev_info(dd, "           hdr0 0x%llx, hdr1 0x%llx\n",
-			    hdr0, hdr1);
+		dd_dev_info_ratelimited(dd, "DCC Error: PortRcv error: %s\n"
+					"               hdr0 0x%llx, hdr1 0x%llx\n",
+					extra, hdr0, hdr1);
 
 		reg &= ~DCC_ERR_FLG_RCVPORT_ERR_SMASK;
 	}
 
 	if (reg & DCC_ERR_FLG_EN_CSR_ACCESS_BLOCKED_UC_SMASK) {
 		/* informative only */
-		dd_dev_info(dd, "8051 access to LCB blocked\n");
+		dd_dev_info_ratelimited(dd, "8051 access to LCB blocked\n");
 		reg &= ~DCC_ERR_FLG_EN_CSR_ACCESS_BLOCKED_UC_SMASK;
 	}
 	if (reg & DCC_ERR_FLG_EN_CSR_ACCESS_BLOCKED_HOST_SMASK) {
 		/* informative only */
-		dd_dev_info(dd, "host access to LCB blocked\n");
+		dd_dev_info_ratelimited(dd, "host access to LCB blocked\n");
 		reg &= ~DCC_ERR_FLG_EN_CSR_ACCESS_BLOCKED_HOST_SMASK;
 	}
 
 	/* report any remaining errors */
 	if (reg)
-		dd_dev_info(dd, "DCC Error: %s\n",
-			    dcc_err_string(buf, sizeof(buf), reg));
+		dd_dev_info_ratelimited(dd, "DCC Error: %s\n",
+					dcc_err_string(buf, sizeof(buf), reg));
 
 	if (lcl_reason == 0)
 		lcl_reason = OPA_LINKDOWN_REASON_UNKNOWN;
 
 	if (do_bounce) {
-		dd_dev_info(dd, "%s: PortErrorAction bounce\n", __func__);
+		dd_dev_info_ratelimited(dd, "%s: PortErrorAction bounce\n",
+					__func__);
 		set_link_down_reason(ppd, lcl_reason, 0, lcl_reason);
 		queue_work(ppd->hfi1_wq, &ppd->link_bounce_work);
 	}
@@ -10508,16 +10510,18 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 			ppd->remote_link_down_reason = 0;
 		}
 
-		ret1 = set_physical_link_state(dd, PLS_DISABLED);
-		if (ret1 != HCMD_SUCCESS) {
-			dd_dev_err(dd,
-				   "Failed to transition to Disabled link state, return 0x%x\n",
-				   ret1);
-			ret = -EINVAL;
-			break;
+		if (!dd->dc_shutdown) {
+			ret1 = set_physical_link_state(dd, PLS_DISABLED);
+			if (ret1 != HCMD_SUCCESS) {
+				dd_dev_err(dd,
+					   "Failed to transition to Disabled link state, return 0x%x\n",
+					   ret1);
+				ret = -EINVAL;
+				break;
+			}
+			dc_shutdown(dd);
 		}
 		ppd->host_link_state = HLS_DN_DISABLE;
-		dc_shutdown(dd);
 		break;
 	case HLS_DN_OFFLINE:
 		if (ppd->host_link_state == HLS_DN_DISABLE)
diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h
index da7be21bedb4..1b783bbee4bb 100644
--- a/drivers/infiniband/hw/hfi1/common.h
+++ b/drivers/infiniband/hw/hfi1/common.h
@@ -331,10 +331,6 @@ struct diag_pkt {
 #define FULL_MGMT_P_KEY      0xFFFF
 
 #define DEFAULT_P_KEY LIM_MGMT_P_KEY
-#define HFI1_AETH_CREDIT_SHIFT 24
-#define HFI1_AETH_CREDIT_MASK 0x1F
-#define HFI1_AETH_CREDIT_INVAL 0x1F
-#define HFI1_MSN_MASK 0xFFFFFF
 #define HFI1_FECN_SHIFT 31
 #define HFI1_FECN_MASK 1
 #define HFI1_FECN_SMASK BIT(HFI1_FECN_SHIFT)
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index 8725f4c086cf..7fe9dd885746 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -50,6 +50,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/module.h>
+#include <linux/string.h>
 
 #include "hfi.h"
 #include "debugfs.h"
@@ -503,18 +504,11 @@ static ssize_t asic_flags_write(struct file *file, const char __user *buf,
 	ppd = private2ppd(file);
 	dd = ppd->dd;
 
-	buff = kmalloc(count + 1, GFP_KERNEL);
-	if (!buff)
-		return -ENOMEM;
-
-	ret = copy_from_user(buff, buf, count);
-	if (ret > 0) {
-		ret = -EFAULT;
-		goto do_free;
-	}
-
 	/* zero terminate and read the expected integer */
-	buff[count] = 0;
+	buff = memdup_user_nul(buf, count);
+	if (IS_ERR(buff))
+		return PTR_ERR(buff);
+
 	ret = kstrtoull(buff, 0, &value);
 	if (ret)
 		goto do_free;
@@ -692,15 +686,9 @@ static ssize_t __i2c_debugfs_write(struct file *file, const char __user *buf,
 	if (i2c_addr == 0)
 		return -EINVAL;
 
-	buff = kmalloc(count, GFP_KERNEL);
-	if (!buff)
-		return -ENOMEM;
-
-	ret = copy_from_user(buff, buf, count);
-	if (ret > 0) {
-		ret = -EFAULT;
-		goto _free;
-	}
+	buff = memdup_user(buf, count);
+	if (IS_ERR(buff))
+		return PTR_ERR(buff);
 
 	total_written = i2c_write(ppd, target, i2c_addr, offset, buff, count);
 	if (total_written < 0) {
@@ -805,15 +793,10 @@ static ssize_t __qsfp_debugfs_write(struct file *file, const char __user *buf,
 
 	ppd = private2ppd(file);
 
-	buff = kmalloc(count, GFP_KERNEL);
-	if (!buff)
-		return -ENOMEM;
+	buff = memdup_user(buf, count);
+	if (IS_ERR(buff))
+		return PTR_ERR(buff);
 
-	ret = copy_from_user(buff, buf, count);
-	if (ret > 0) {
-		ret = -EFAULT;
-		goto _free;
-	}
 	total_written = qsfp_write(ppd, target, *ppos, buff, count);
 	if (total_written < 0) {
 		ret = total_written;
diff --git a/drivers/infiniband/hw/hfi1/dma.c b/drivers/infiniband/hw/hfi1/dma.c
deleted file mode 100644
index 7e8dab892848..000000000000
--- a/drivers/infiniband/hw/hfi1/dma.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * Copyright(c) 2015, 2016 Intel Corporation.
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *  - Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- *  - Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in
- *    the documentation and/or other materials provided with the
- *    distribution.
- *  - Neither the name of Intel Corporation nor the names of its
- *    contributors may be used to endorse or promote products derived
- *    from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER 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.
- *
- */
-#include <linux/types.h>
-#include <linux/scatterlist.h>
-
-#include "verbs.h"
-
-#define BAD_DMA_ADDRESS ((u64)0)
-
-/*
- * The following functions implement driver specific replacements
- * for the ib_dma_*() functions.
- *
- * These functions return kernel virtual addresses instead of
- * device bus addresses since the driver uses the CPU to copy
- * data instead of using hardware DMA.
- */
-
-static int hfi1_mapping_error(struct ib_device *dev, u64 dma_addr)
-{
-	return dma_addr == BAD_DMA_ADDRESS;
-}
-
-static u64 hfi1_dma_map_single(struct ib_device *dev, void *cpu_addr,
-			       size_t size, enum dma_data_direction direction)
-{
-	if (WARN_ON(!valid_dma_direction(direction)))
-		return BAD_DMA_ADDRESS;
-
-	return (u64)cpu_addr;
-}
-
-static void hfi1_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size,
-				  enum dma_data_direction direction)
-{
-	/* This is a stub, nothing to be done here */
-}
-
-static u64 hfi1_dma_map_page(struct ib_device *dev, struct page *page,
-			     unsigned long offset, size_t size,
-			    enum dma_data_direction direction)
-{
-	u64 addr;
-
-	if (WARN_ON(!valid_dma_direction(direction)))
-		return BAD_DMA_ADDRESS;
-
-	if (offset + size > PAGE_SIZE)
-		return BAD_DMA_ADDRESS;
-
-	addr = (u64)page_address(page);
-	if (addr)
-		addr += offset;
-
-	return addr;
-}
-
-static void hfi1_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size,
-				enum dma_data_direction direction)
-{
-	/* This is a stub, nothing to be done here */
-}
-
-static int hfi1_map_sg(struct ib_device *dev, struct scatterlist *sgl,
-		       int nents, enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	u64 addr;
-	int i;
-	int ret = nents;
-
-	if (WARN_ON(!valid_dma_direction(direction)))
-		return BAD_DMA_ADDRESS;
-
-	for_each_sg(sgl, sg, nents, i) {
-		addr = (u64)page_address(sg_page(sg));
-		if (!addr) {
-			ret = 0;
-			break;
-		}
-		sg->dma_address = addr + sg->offset;
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-	}
-	return ret;
-}
-
-static void hfi1_unmap_sg(struct ib_device *dev,
-			  struct scatterlist *sg, int nents,
-			 enum dma_data_direction direction)
-{
-	/* This is a stub, nothing to be done here */
-}
-
-static void hfi1_sync_single_for_cpu(struct ib_device *dev, u64 addr,
-				     size_t size, enum dma_data_direction dir)
-{
-}
-
-static void hfi1_sync_single_for_device(struct ib_device *dev, u64 addr,
-					size_t size,
-					enum dma_data_direction dir)
-{
-}
-
-static void *hfi1_dma_alloc_coherent(struct ib_device *dev, size_t size,
-				     u64 *dma_handle, gfp_t flag)
-{
-	struct page *p;
-	void *addr = NULL;
-
-	p = alloc_pages(flag, get_order(size));
-	if (p)
-		addr = page_address(p);
-	if (dma_handle)
-		*dma_handle = (u64)addr;
-	return addr;
-}
-
-static void hfi1_dma_free_coherent(struct ib_device *dev, size_t size,
-				   void *cpu_addr, u64 dma_handle)
-{
-	free_pages((unsigned long)cpu_addr, get_order(size));
-}
-
-struct ib_dma_mapping_ops hfi1_dma_mapping_ops = {
-	.mapping_error = hfi1_mapping_error,
-	.map_single = hfi1_dma_map_single,
-	.unmap_single = hfi1_dma_unmap_single,
-	.map_page = hfi1_dma_map_page,
-	.unmap_page = hfi1_dma_unmap_page,
-	.map_sg = hfi1_map_sg,
-	.unmap_sg = hfi1_unmap_sg,
-	.sync_single_for_cpu = hfi1_sync_single_for_cpu,
-	.sync_single_for_device = hfi1_sync_single_for_device,
-	.alloc_coherent = hfi1_dma_alloc_coherent,
-	.free_coherent = hfi1_dma_free_coherent
-};
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 4fbaee68012b..3881c951f6af 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -100,6 +100,11 @@ MODULE_VERSION(HFI1_DRIVER_VERSION);
  * MAX_PKT_RCV is the max # if packets processed per receive interrupt.
  */
 #define MAX_PKT_RECV 64
+/*
+ * MAX_PKT_THREAD_RCV is the max # of packets processed before
+ * the qp_wait_list queue is flushed.
+ */
+#define MAX_PKT_RECV_THREAD (MAX_PKT_RECV * 4)
 #define EGR_HEAD_UPDATE_THRESHOLD 16
 
 struct hfi1_ib_stats hfi1_stats;
@@ -259,7 +264,7 @@ static inline void *get_egrbuf(const struct hfi1_ctxtdata *rcd, u64 rhf,
  * allowed size ranges for the respective type and, optionally,
  * return the proper encoding.
  */
-inline int hfi1_rcvbuf_validate(u32 size, u8 type, u16 *encoded)
+int hfi1_rcvbuf_validate(u32 size, u8 type, u16 *encoded)
 {
 	if (unlikely(!PAGE_ALIGNED(size)))
 		return 0;
@@ -279,7 +284,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 	struct ib_header *rhdr = packet->hdr;
 	u32 rte = rhf_rcv_type_err(packet->rhf);
 	int lnh = be16_to_cpu(rhdr->lrh[0]) & 3;
-	struct hfi1_ibport *ibp = &ppd->ibport_data;
+	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_devdata *dd = ppd->dd;
 	struct rvt_dev_info *rdi = &dd->verbs_dev.rdi;
 
@@ -594,7 +599,7 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 
 	while (1) {
 		struct hfi1_devdata *dd = rcd->dd;
-		struct hfi1_ibport *ibp = &rcd->ppd->ibport_data;
+		struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 		__le32 *rhf_addr = (__le32 *)rcd->rcvhdrq + mdata.ps_head +
 					 dd->rhf_offset;
 		struct rvt_qp *qp;
@@ -654,24 +659,68 @@ next:
 	}
 }
 
-static inline int skip_rcv_packet(struct hfi1_packet *packet, int thread)
+static void process_rcv_qp_work(struct hfi1_ctxtdata *rcd)
+{
+	struct rvt_qp *qp, *nqp;
+
+	/*
+	 * Iterate over all QPs waiting to respond.
+	 * The list won't change since the IRQ is only run on one CPU.
+	 */
+	list_for_each_entry_safe(qp, nqp, &rcd->qp_wait_list, rspwait) {
+		list_del_init(&qp->rspwait);
+		if (qp->r_flags & RVT_R_RSP_NAK) {
+			qp->r_flags &= ~RVT_R_RSP_NAK;
+			hfi1_send_rc_ack(rcd, qp, 0);
+		}
+		if (qp->r_flags & RVT_R_RSP_SEND) {
+			unsigned long flags;
+
+			qp->r_flags &= ~RVT_R_RSP_SEND;
+			spin_lock_irqsave(&qp->s_lock, flags);
+			if (ib_rvt_state_ops[qp->state] &
+					RVT_PROCESS_OR_FLUSH_SEND)
+				hfi1_schedule_send(qp);
+			spin_unlock_irqrestore(&qp->s_lock, flags);
+		}
+		rvt_put_qp(qp);
+	}
+}
+
+static noinline int max_packet_exceeded(struct hfi1_packet *packet, int thread)
+{
+	if (thread) {
+		if ((packet->numpkt & (MAX_PKT_RECV_THREAD - 1)) == 0)
+			/* allow defered processing */
+			process_rcv_qp_work(packet->rcd);
+		cond_resched();
+		return RCV_PKT_OK;
+	} else {
+		this_cpu_inc(*packet->rcd->dd->rcv_limit);
+		return RCV_PKT_LIMIT;
+	}
+}
+
+static inline int check_max_packet(struct hfi1_packet *packet, int thread)
 {
 	int ret = RCV_PKT_OK;
 
+	if (unlikely((packet->numpkt & (MAX_PKT_RECV - 1)) == 0))
+		ret = max_packet_exceeded(packet, thread);
+	return ret;
+}
+
+static noinline int skip_rcv_packet(struct hfi1_packet *packet, int thread)
+{
+	int ret;
+
 	/* Set up for the next packet */
 	packet->rhqoff += packet->rsize;
 	if (packet->rhqoff >= packet->maxcnt)
 		packet->rhqoff = 0;
 
 	packet->numpkt++;
-	if (unlikely((packet->numpkt & (MAX_PKT_RECV - 1)) == 0)) {
-		if (thread) {
-			cond_resched();
-		} else {
-			ret = RCV_PKT_LIMIT;
-			this_cpu_inc(*packet->rcd->dd->rcv_limit);
-		}
-	}
+	ret = check_max_packet(packet, thread);
 
 	packet->rhf_addr = (__le32 *)packet->rcd->rcvhdrq + packet->rhqoff +
 				     packet->rcd->dd->rhf_offset;
@@ -682,7 +731,7 @@ static inline int skip_rcv_packet(struct hfi1_packet *packet, int thread)
 
 static inline int process_rcv_packet(struct hfi1_packet *packet, int thread)
 {
-	int ret = RCV_PKT_OK;
+	int ret;
 
 	packet->hdr = hfi1_get_msgheader(packet->rcd->dd,
 					 packet->rhf_addr);
@@ -723,14 +772,7 @@ static inline int process_rcv_packet(struct hfi1_packet *packet, int thread)
 	if (packet->rhqoff >= packet->maxcnt)
 		packet->rhqoff = 0;
 
-	if (unlikely((packet->numpkt & (MAX_PKT_RECV - 1)) == 0)) {
-		if (thread) {
-			cond_resched();
-		} else {
-			ret = RCV_PKT_LIMIT;
-			this_cpu_inc(*packet->rcd->dd->rcv_limit);
-		}
-	}
+	ret = check_max_packet(packet, thread);
 
 	packet->rhf_addr = (__le32 *)packet->rcd->rcvhdrq + packet->rhqoff +
 				      packet->rcd->dd->rhf_offset;
@@ -767,38 +809,6 @@ static inline void finish_packet(struct hfi1_packet *packet)
 		       packet->etail, rcv_intr_dynamic, packet->numpkt);
 }
 
-static inline void process_rcv_qp_work(struct hfi1_packet *packet)
-{
-	struct hfi1_ctxtdata *rcd;
-	struct rvt_qp *qp, *nqp;
-
-	rcd = packet->rcd;
-	rcd->head = packet->rhqoff;
-
-	/*
-	 * Iterate over all QPs waiting to respond.
-	 * The list won't change since the IRQ is only run on one CPU.
-	 */
-	list_for_each_entry_safe(qp, nqp, &rcd->qp_wait_list, rspwait) {
-		list_del_init(&qp->rspwait);
-		if (qp->r_flags & RVT_R_RSP_NAK) {
-			qp->r_flags &= ~RVT_R_RSP_NAK;
-			hfi1_send_rc_ack(rcd, qp, 0);
-		}
-		if (qp->r_flags & RVT_R_RSP_SEND) {
-			unsigned long flags;
-
-			qp->r_flags &= ~RVT_R_RSP_SEND;
-			spin_lock_irqsave(&qp->s_lock, flags);
-			if (ib_rvt_state_ops[qp->state] &
-					RVT_PROCESS_OR_FLUSH_SEND)
-				hfi1_schedule_send(qp);
-			spin_unlock_irqrestore(&qp->s_lock, flags);
-		}
-		rvt_put_qp(qp);
-	}
-}
-
 /*
  * Handle receive interrupts when using the no dma rtail option.
  */
@@ -826,7 +836,8 @@ int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
-	process_rcv_qp_work(&packet);
+	process_rcv_qp_work(rcd);
+	rcd->head = packet.rhqoff;
 bail:
 	finish_packet(&packet);
 	return last;
@@ -854,7 +865,8 @@ int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
-	process_rcv_qp_work(&packet);
+	process_rcv_qp_work(rcd);
+	rcd->head = packet.rhqoff;
 bail:
 	finish_packet(&packet);
 	return last;
@@ -1024,7 +1036,8 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 		process_rcv_update(last, &packet);
 	}
 
-	process_rcv_qp_work(&packet);
+	process_rcv_qp_work(rcd);
+	rcd->head = packet.rhqoff;
 
 bail:
 	/*
diff --git a/drivers/infiniband/hw/hfi1/efivar.c b/drivers/infiniband/hw/hfi1/efivar.c
index 106349fc1fb9..d106d23016ba 100644
--- a/drivers/infiniband/hw/hfi1/efivar.c
+++ b/drivers/infiniband/hw/hfi1/efivar.c
@@ -45,6 +45,7 @@
  *
  */
 
+#include <linux/ctype.h>
 #include "efivar.h"
 
 /* GUID for HFI1 variables in EFI */
@@ -150,15 +151,32 @@ fail:
 int read_hfi1_efi_var(struct hfi1_devdata *dd, const char *kind,
 		      unsigned long *size, void **return_data)
 {
+	char prefix_name[64];
 	char name[64];
+	int result;
+	int i;
 
 	/* create a common prefix */
-	snprintf(name, sizeof(name), "%04x:%02x:%02x.%x-%s",
+	snprintf(prefix_name, sizeof(prefix_name), "%04x:%02x:%02x.%x",
 		 pci_domain_nr(dd->pcidev->bus),
 		 dd->pcidev->bus->number,
 		 PCI_SLOT(dd->pcidev->devfn),
-		 PCI_FUNC(dd->pcidev->devfn),
-		 kind);
+		 PCI_FUNC(dd->pcidev->devfn));
+	snprintf(name, sizeof(name), "%s-%s", prefix_name, kind);
+	result = read_efi_var(name, size, return_data);
+
+	/*
+	 * If reading the lowercase EFI variable fail, read the uppercase
+	 * variable.
+	 */
+	if (result) {
+		/* Converting to uppercase */
+		for (i = 0; prefix_name[i]; i++)
+			if (isalpha(prefix_name[i]))
+				prefix_name[i] = toupper(prefix_name[i]);
+		snprintf(name, sizeof(name), "%s-%s", prefix_name, kind);
+		result = read_efi_var(name, size, return_data);
+	}
 
-	return read_efi_var(name, size, return_data);
+	return result;
 }
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index bd786b7bd30b..f78c739b330a 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -48,6 +48,7 @@
 #include <linux/cdev.h>
 #include <linux/vmalloc.h>
 #include <linux/io.h>
+#include <linux/sched/mm.h>
 
 #include <rdma/ib.h>
 
@@ -92,7 +93,7 @@ static unsigned int poll_next(struct file *, struct poll_table_struct *);
 static int user_event_ack(struct hfi1_ctxtdata *, int, unsigned long);
 static int set_ctxt_pkey(struct hfi1_ctxtdata *, unsigned, u16);
 static int manage_rcvq(struct hfi1_ctxtdata *, unsigned, int);
-static int vma_fault(struct vm_area_struct *, struct vm_fault *);
+static int vma_fault(struct vm_fault *);
 static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
 			    unsigned long arg);
 
@@ -185,7 +186,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 	if (fd) {
 		fd->rec_cpu_num = -1; /* no cpu affinity by default */
 		fd->mm = current->mm;
-		atomic_inc(&fd->mm->mm_count);
+		mmgrab(fd->mm);
 		fp->private_data = fd;
 	} else {
 		fp->private_data = NULL;
@@ -695,7 +696,7 @@ done:
  * Local (non-chip) user memory is not mapped right away but as it is
  * accessed by the user-level code.
  */
-static int vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int vma_fault(struct vm_fault *vmf)
 {
 	struct page *page;
 
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 751a0fb29fa5..0808e3c3ba39 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -356,12 +356,11 @@ struct hfi1_packet {
 	u64 rhf;
 	u32 maxcnt;
 	u32 rhqoff;
-	u32 hdrqtail;
-	int numpkt;
 	u16 tlen;
-	u16 hlen;
 	s16 etail;
-	u16 rsize;
+	u8 hlen;
+	u8 numpkt;
+	u8 rsize;
 	u8 updegr;
 	u8 rcv_flags;
 	u8 etype;
@@ -1584,6 +1583,11 @@ static inline struct hfi1_ibport *to_iport(struct ib_device *ibdev, u8 port)
 	return &dd->pport[pidx].ibport_data;
 }
 
+static inline struct hfi1_ibport *rcd_to_iport(struct hfi1_ctxtdata *rcd)
+{
+	return &rcd->ppd->ibport_data;
+}
+
 void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp);
 static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
@@ -1793,8 +1797,6 @@ int kdeth_process_expected(struct hfi1_packet *packet);
 int kdeth_process_eager(struct hfi1_packet *packet);
 int process_receive_invalid(struct hfi1_packet *packet);
 
-void update_sge(struct rvt_sge_state *ss, u32 length);
-
 /* global module parameter variables */
 extern unsigned int hfi1_max_mtu;
 extern unsigned int hfi1_cu;
@@ -1940,6 +1942,10 @@ static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd)
 	dev_info(&(dd)->pcidev->dev, "%s: " fmt, \
 			get_unit_name((dd)->unit), ##__VA_ARGS__)
 
+#define dd_dev_info_ratelimited(dd, fmt, ...) \
+	dev_info_ratelimited(&(dd)->pcidev->dev, "%s: " fmt, \
+			get_unit_name((dd)->unit), ##__VA_ARGS__)
+
 #define dd_dev_dbg(dd, fmt, ...) \
 	dev_dbg(&(dd)->pcidev->dev, "%s: " fmt, \
 		get_unit_name((dd)->unit), ##__VA_ARGS__)
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index e3b5bc93bc70..f40864e9a3b2 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -297,14 +297,15 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 		 * The resulting value will be rounded down to the closest
 		 * multiple of dd->rcv_entries.group_size.
 		 */
-		rcd->egrbufs.buffers = kcalloc(rcd->egrbufs.count,
-					       sizeof(*rcd->egrbufs.buffers),
-					       GFP_KERNEL);
+		rcd->egrbufs.buffers = kzalloc_node(
+			rcd->egrbufs.count * sizeof(*rcd->egrbufs.buffers),
+			GFP_KERNEL, numa);
 		if (!rcd->egrbufs.buffers)
 			goto bail;
-		rcd->egrbufs.rcvtids = kcalloc(rcd->egrbufs.count,
-					       sizeof(*rcd->egrbufs.rcvtids),
-					       GFP_KERNEL);
+		rcd->egrbufs.rcvtids = kzalloc_node(
+				rcd->egrbufs.count *
+				sizeof(*rcd->egrbufs.rcvtids),
+				GFP_KERNEL, numa);
 		if (!rcd->egrbufs.rcvtids)
 			goto bail;
 		rcd->egrbufs.size = eager_buffer_size;
@@ -322,8 +323,8 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 		rcd->egrbufs.rcvtid_size = HFI1_MAX_EAGER_BUFFER_SIZE;
 
 		if (ctxt < dd->first_user_ctxt) { /* N/A for PSM contexts */
-			rcd->opstats = kzalloc(sizeof(*rcd->opstats),
-				GFP_KERNEL);
+			rcd->opstats = kzalloc_node(sizeof(*rcd->opstats),
+						    GFP_KERNEL, numa);
 			if (!rcd->opstats)
 				goto bail;
 		}
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 6e595afca24c..09cda3c35e82 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -4406,7 +4406,7 @@ int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 	switch (in_mad->base_version) {
 	case OPA_MGMT_BASE_VERSION:
 		if (unlikely(in_mad_size != sizeof(struct opa_mad))) {
-			dev_err(ibdev->dma_device, "invalid in_mad_size\n");
+			dev_err(ibdev->dev.parent, "invalid in_mad_size\n");
 			return IB_MAD_RESULT_FAILURE;
 		}
 		return hfi1_process_opa_mad(ibdev, mad_flags, port,
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 4ac8f330c5cb..0829fce06172 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -598,15 +598,6 @@ pci_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_CAN_RECOVER;
 }
 
-static pci_ers_result_t
-pci_link_reset(struct pci_dev *pdev)
-{
-	struct hfi1_devdata *dd = pci_get_drvdata(pdev);
-
-	dd_dev_info(dd, "HFI1 link_reset function called, ignored\n");
-	return PCI_ERS_RESULT_CAN_RECOVER;
-}
-
 static void
 pci_resume(struct pci_dev *pdev)
 {
@@ -625,7 +616,6 @@ pci_resume(struct pci_dev *pdev)
 const struct pci_error_handlers hfi1_pci_err_handler = {
 	.error_detected = pci_error_detected,
 	.mmio_enabled = pci_mmio_enabled,
-	.link_reset = pci_link_reset,
 	.slot_reset = pci_slot_reset,
 	.resume = pci_resume,
 };
@@ -673,12 +663,12 @@ MODULE_PARM_DESC(pcie_retry, "Driver will try this many times to reach requested
 
 #define UNSET_PSET 255
 #define DEFAULT_DISCRETE_PSET 2	/* discrete HFI */
-#define DEFAULT_MCP_PSET 4	/* MCP HFI */
+#define DEFAULT_MCP_PSET 6	/* MCP HFI */
 static uint pcie_pset = UNSET_PSET;
 module_param(pcie_pset, uint, S_IRUGO);
 MODULE_PARM_DESC(pcie_pset, "PCIe Eq Pset value to use, range is 0-10");
 
-static uint pcie_ctle = 1; /* discrete on, integrated off */
+static uint pcie_ctle = 3; /* discrete on, integrated on */
 module_param(pcie_ctle, uint, S_IRUGO);
 MODULE_PARM_DESC(pcie_ctle, "PCIe static CTLE mode, bit 0 - discrete on/off, bit 1 - integrated on/off");
 
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index d752d6768a49..c4ebd097b20f 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -79,43 +79,6 @@ static inline unsigned mk_qpn(struct rvt_qpn_table *qpt,
 	return (map - qpt->map) * RVT_BITS_PER_PAGE + off;
 }
 
-/*
- * Convert the AETH credit code into the number of credits.
- */
-static const u16 credit_table[31] = {
-	0,                      /* 0 */
-	1,                      /* 1 */
-	2,                      /* 2 */
-	3,                      /* 3 */
-	4,                      /* 4 */
-	6,                      /* 5 */
-	8,                      /* 6 */
-	12,                     /* 7 */
-	16,                     /* 8 */
-	24,                     /* 9 */
-	32,                     /* A */
-	48,                     /* B */
-	64,                     /* C */
-	96,                     /* D */
-	128,                    /* E */
-	192,                    /* F */
-	256,                    /* 10 */
-	384,                    /* 11 */
-	512,                    /* 12 */
-	768,                    /* 13 */
-	1024,                   /* 14 */
-	1536,                   /* 15 */
-	2048,                   /* 16 */
-	3072,                   /* 17 */
-	4096,                   /* 18 */
-	6144,                   /* 19 */
-	8192,                   /* 1A */
-	12288,                  /* 1B */
-	16384,                  /* 1C */
-	24576,                  /* 1D */
-	32768                   /* 1E */
-};
-
 const struct rvt_operation_params hfi1_post_parms[RVT_OPERATION_MAX] = {
 [IB_WR_RDMA_WRITE] = {
 	.length = sizeof(struct ib_rdma_wr),
@@ -340,68 +303,6 @@ int hfi1_check_send_wqe(struct rvt_qp *qp,
 }
 
 /**
- * hfi1_compute_aeth - compute the AETH (syndrome + MSN)
- * @qp: the queue pair to compute the AETH for
- *
- * Returns the AETH.
- */
-__be32 hfi1_compute_aeth(struct rvt_qp *qp)
-{
-	u32 aeth = qp->r_msn & HFI1_MSN_MASK;
-
-	if (qp->ibqp.srq) {
-		/*
-		 * Shared receive queues don't generate credits.
-		 * Set the credit field to the invalid value.
-		 */
-		aeth |= HFI1_AETH_CREDIT_INVAL << HFI1_AETH_CREDIT_SHIFT;
-	} else {
-		u32 min, max, x;
-		u32 credits;
-		struct rvt_rwq *wq = qp->r_rq.wq;
-		u32 head;
-		u32 tail;
-
-		/* sanity check pointers before trusting them */
-		head = wq->head;
-		if (head >= qp->r_rq.size)
-			head = 0;
-		tail = wq->tail;
-		if (tail >= qp->r_rq.size)
-			tail = 0;
-		/*
-		 * Compute the number of credits available (RWQEs).
-		 * There is a small chance that the pair of reads are
-		 * not atomic, which is OK, since the fuzziness is
-		 * resolved as further ACKs go out.
-		 */
-		credits = head - tail;
-		if ((int)credits < 0)
-			credits += qp->r_rq.size;
-		/*
-		 * Binary search the credit table to find the code to
-		 * use.
-		 */
-		min = 0;
-		max = 31;
-		for (;;) {
-			x = (min + max) / 2;
-			if (credit_table[x] == credits)
-				break;
-			if (credit_table[x] > credits) {
-				max = x;
-			} else {
-				if (min == x)
-					break;
-				min = x;
-			}
-		}
-		aeth |= x << HFI1_AETH_CREDIT_SHIFT;
-	}
-	return cpu_to_be32(aeth);
-}
-
-/**
  * _hfi1_schedule_send - schedule progress
  * @qp: the QP
  *
@@ -457,44 +358,6 @@ void hfi1_schedule_send(struct rvt_qp *qp)
 		_hfi1_schedule_send(qp);
 }
 
-/**
- * hfi1_get_credit - handle credit in aeth
- * @qp: the qp
- * @aeth: the Acknowledge Extended Transport Header
- *
- * The QP s_lock should be held.
- */
-void hfi1_get_credit(struct rvt_qp *qp, u32 aeth)
-{
-	u32 credit = (aeth >> HFI1_AETH_CREDIT_SHIFT) & HFI1_AETH_CREDIT_MASK;
-
-	lockdep_assert_held(&qp->s_lock);
-	/*
-	 * If the credit is invalid, we can send
-	 * as many packets as we like.  Otherwise, we have to
-	 * honor the credit field.
-	 */
-	if (credit == HFI1_AETH_CREDIT_INVAL) {
-		if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT)) {
-			qp->s_flags |= RVT_S_UNLIMITED_CREDIT;
-			if (qp->s_flags & RVT_S_WAIT_SSN_CREDIT) {
-				qp->s_flags &= ~RVT_S_WAIT_SSN_CREDIT;
-				hfi1_schedule_send(qp);
-			}
-		}
-	} else if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT)) {
-		/* Compute new LSN (i.e., MSN + credit) */
-		credit = (aeth + credit_table[credit]) & HFI1_MSN_MASK;
-		if (cmp_msn(credit, qp->s_lsn) > 0) {
-			qp->s_lsn = credit;
-			if (qp->s_flags & RVT_S_WAIT_SSN_CREDIT) {
-				qp->s_flags &= ~RVT_S_WAIT_SSN_CREDIT;
-				hfi1_schedule_send(qp);
-			}
-		}
-	}
-}
-
 void hfi1_qp_wakeup(struct rvt_qp *qp, u32 flag)
 {
 	unsigned long flags;
@@ -744,7 +607,7 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
 	wqe = rvt_get_swqe_ptr(qp, qp->s_last);
 	send_context = qp_to_send_context(qp, priv->s_sc);
 	seq_printf(s,
-		   "N %d %s QP %x R %u %s %u %u %u f=%x %u %u %u %u %u %u PSN %x %x %x %x %x (%u %u %u %u %u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d\n",
+		   "N %d %s QP %x R %u %s %u %u %u f=%x %u %u %u %u %u %u SPSN %x %x %x %x %x RPSN %x (%u %u %u %u %u %u %u) RQP %x LID %x SL %u MTU %u %u %u %u %u SDE %p,%u SC %p,%u SCQ %u %u PID %d\n",
 		   iter->n,
 		   qp_idle(qp) ? "I" : "B",
 		   qp->ibqp.qp_num,
@@ -763,6 +626,7 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
 		   qp->s_last_psn,
 		   qp->s_psn, qp->s_next_psn,
 		   qp->s_sending_psn, qp->s_sending_hpsn,
+		   qp->r_psn,
 		   qp->s_last, qp->s_acked, qp->s_cur,
 		   qp->s_tail, qp->s_head, qp->s_size,
 		   qp->s_avail,
@@ -773,6 +637,7 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
 		   qp->s_retry,
 		   qp->s_retry_cnt,
 		   qp->s_rnr_retry_cnt,
+		   qp->s_rnr_retry,
 		   sde,
 		   sde ? sde->this_idx : 0,
 		   send_context,
@@ -782,19 +647,6 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
 		   qp->pid);
 }
 
-void qp_comm_est(struct rvt_qp *qp)
-{
-	qp->r_flags |= RVT_R_COMM_EST;
-	if (qp->ibqp.event_handler) {
-		struct ib_event ev;
-
-		ev.device = qp->ibqp.device;
-		ev.element.qp = &qp->ibqp;
-		ev.event = IB_EVENT_COMM_EST;
-		qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
-	}
-}
-
 void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 		    gfp_t gfp)
 {
@@ -819,8 +671,6 @@ void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 		iowait_sleep,
 		iowait_wakeup,
 		iowait_sdma_drained);
-	setup_timer(&priv->s_rnr_timer, hfi1_rc_rnr_retry, (unsigned long)qp);
-	qp->s_timer.function = hfi1_rc_timeout;
 	return priv;
 }
 
@@ -861,7 +711,6 @@ void flush_qp_waiters(struct rvt_qp *qp)
 {
 	lockdep_assert_held(&qp->s_lock);
 	flush_iowait(qp);
-	hfi1_stop_rc_timers(qp);
 }
 
 void stop_send_queue(struct rvt_qp *qp)
@@ -869,7 +718,6 @@ void stop_send_queue(struct rvt_qp *qp)
 	struct hfi1_qp_priv *priv = qp->priv;
 
 	cancel_work_sync(&priv->s_iowait.iowork);
-	hfi1_del_timers_sync(qp);
 }
 
 void quiesce_qp(struct rvt_qp *qp)
@@ -961,17 +809,20 @@ int get_pmtu_from_attr(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 
 void notify_error_qp(struct rvt_qp *qp)
 {
-	struct hfi1_ibdev *dev = to_idev(qp->ibqp.device);
 	struct hfi1_qp_priv *priv = qp->priv;
+	seqlock_t *lock = priv->s_iowait.lock;
 
-	write_seqlock(&dev->iowait_lock);
-	if (!list_empty(&priv->s_iowait.list) && !(qp->s_flags & RVT_S_BUSY)) {
-		qp->s_flags &= ~RVT_S_ANY_WAIT_IO;
-		list_del_init(&priv->s_iowait.list);
-		priv->s_iowait.lock = NULL;
-		rvt_put_qp(qp);
+	if (lock) {
+		write_seqlock(lock);
+		if (!list_empty(&priv->s_iowait.list) &&
+		    !(qp->s_flags & RVT_S_BUSY)) {
+			qp->s_flags &= ~RVT_S_ANY_WAIT_IO;
+			list_del_init(&priv->s_iowait.list);
+			priv->s_iowait.lock = NULL;
+			rvt_put_qp(qp);
+		}
+		write_sequnlock(lock);
 	}
-	write_sequnlock(&dev->iowait_lock);
 
 	if (!(qp->s_flags & RVT_S_BUSY)) {
 		qp->s_hdrwords = 0;
diff --git a/drivers/infiniband/hw/hfi1/qp.h b/drivers/infiniband/hw/hfi1/qp.h
index 587d84d65bb8..1eb9cd7b8c19 100644
--- a/drivers/infiniband/hw/hfi1/qp.h
+++ b/drivers/infiniband/hw/hfi1/qp.h
@@ -71,14 +71,6 @@ static inline void clear_ahg(struct rvt_qp *qp)
 }
 
 /**
- * hfi1_compute_aeth - compute the AETH (syndrome + MSN)
- * @qp: the queue pair to compute the AETH for
- *
- * Returns the AETH.
- */
-__be32 hfi1_compute_aeth(struct rvt_qp *qp);
-
-/**
  * hfi1_create_qp - create a queue pair for a device
  * @ibpd: the protection domain who's device we create the queue pair for
  * @init_attr: the attributes of the queue pair
@@ -91,14 +83,6 @@ __be32 hfi1_compute_aeth(struct rvt_qp *qp);
 struct ib_qp *hfi1_create_qp(struct ib_pd *ibpd,
 			     struct ib_qp_init_attr *init_attr,
 			     struct ib_udata *udata);
-/**
- * hfi1_get_credit - flush the send work queue of a QP
- * @qp: the qp who's send work queue to flush
- * @aeth: the Acknowledge Extended Transport Header
- *
- * The QP s_lock should be held.
- */
-void hfi1_get_credit(struct rvt_qp *qp, u32 aeth);
 
 /**
  * hfi1_qp_wakeup - wake up on the indicated event
@@ -131,12 +115,6 @@ int qp_iter_next(struct qp_iter *iter);
  */
 void qp_iter_print(struct seq_file *s, struct qp_iter *iter);
 
-/**
- * qp_comm_est - handle trap with QP established
- * @qp: the QP
- */
-void qp_comm_est(struct rvt_qp *qp);
-
 void _hfi1_schedule_send(struct rvt_qp *qp);
 void hfi1_schedule_send(struct rvt_qp *qp);
 
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 809b26eb6d3c..7382be11afca 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -57,133 +57,6 @@
 /* cut down ridiculously long IB macro names */
 #define OP(x) RC_OP(x)
 
-/**
- * hfi1_add_retry_timer - add/start a retry timer
- * @qp - the QP
- *
- * add a retry timer on the QP
- */
-static inline void hfi1_add_retry_timer(struct rvt_qp *qp)
-{
-	struct ib_qp *ibqp = &qp->ibqp;
-	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
-
-	lockdep_assert_held(&qp->s_lock);
-	qp->s_flags |= RVT_S_TIMER;
-	/* 4.096 usec. * (1 << qp->timeout) */
-	qp->s_timer.expires = jiffies + qp->timeout_jiffies +
-			      rdi->busy_jiffies;
-	add_timer(&qp->s_timer);
-}
-
-/**
- * hfi1_add_rnr_timer - add/start an rnr timer
- * @qp - the QP
- * @to - timeout in usecs
- *
- * add an rnr timer on the QP
- */
-void hfi1_add_rnr_timer(struct rvt_qp *qp, u32 to)
-{
-	struct hfi1_qp_priv *priv = qp->priv;
-
-	lockdep_assert_held(&qp->s_lock);
-	qp->s_flags |= RVT_S_WAIT_RNR;
-	priv->s_rnr_timer.expires = jiffies + usecs_to_jiffies(to);
-	add_timer(&priv->s_rnr_timer);
-}
-
-/**
- * hfi1_mod_retry_timer - mod a retry timer
- * @qp - the QP
- *
- * Modify a potentially already running retry
- * timer
- */
-static inline void hfi1_mod_retry_timer(struct rvt_qp *qp)
-{
-	struct ib_qp *ibqp = &qp->ibqp;
-	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
-
-	lockdep_assert_held(&qp->s_lock);
-	qp->s_flags |= RVT_S_TIMER;
-	/* 4.096 usec. * (1 << qp->timeout) */
-	mod_timer(&qp->s_timer, jiffies + qp->timeout_jiffies +
-		  rdi->busy_jiffies);
-}
-
-/**
- * hfi1_stop_retry_timer - stop a retry timer
- * @qp - the QP
- *
- * stop a retry timer and return if the timer
- * had been pending.
- */
-static inline int hfi1_stop_retry_timer(struct rvt_qp *qp)
-{
-	int rval = 0;
-
-	lockdep_assert_held(&qp->s_lock);
-	/* Remove QP from retry */
-	if (qp->s_flags & RVT_S_TIMER) {
-		qp->s_flags &= ~RVT_S_TIMER;
-		rval = del_timer(&qp->s_timer);
-	}
-	return rval;
-}
-
-/**
- * hfi1_stop_rc_timers - stop all timers
- * @qp - the QP
- *
- * stop any pending timers
- */
-void hfi1_stop_rc_timers(struct rvt_qp *qp)
-{
-	struct hfi1_qp_priv *priv = qp->priv;
-
-	lockdep_assert_held(&qp->s_lock);
-	/* Remove QP from all timers */
-	if (qp->s_flags & (RVT_S_TIMER | RVT_S_WAIT_RNR)) {
-		qp->s_flags &= ~(RVT_S_TIMER | RVT_S_WAIT_RNR);
-		del_timer(&qp->s_timer);
-		del_timer(&priv->s_rnr_timer);
-	}
-}
-
-/**
- * hfi1_stop_rnr_timer - stop an rnr timer
- * @qp - the QP
- *
- * stop an rnr timer and return if the timer
- * had been pending.
- */
-static inline int hfi1_stop_rnr_timer(struct rvt_qp *qp)
-{
-	int rval = 0;
-	struct hfi1_qp_priv *priv = qp->priv;
-
-	lockdep_assert_held(&qp->s_lock);
-	/* Remove QP from rnr timer */
-	if (qp->s_flags & RVT_S_WAIT_RNR) {
-		qp->s_flags &= ~RVT_S_WAIT_RNR;
-		rval = del_timer(&priv->s_rnr_timer);
-	}
-	return rval;
-}
-
-/**
- * hfi1_del_timers_sync - wait for any timeout routines to exit
- * @qp - the QP
- */
-void hfi1_del_timers_sync(struct rvt_qp *qp)
-{
-	struct hfi1_qp_priv *priv = qp->priv;
-
-	del_timer_sync(&qp->s_timer);
-	del_timer_sync(&priv->s_rnr_timer);
-}
-
 static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe,
 		       u32 psn, u32 pmtu)
 {
@@ -194,7 +67,7 @@ static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe,
 	ss->sg_list = wqe->sg_list + 1;
 	ss->num_sge = wqe->wr.num_sge;
 	ss->total_len = wqe->length;
-	hfi1_skip_sge(ss, len, 0);
+	rvt_skip_sge(ss, len, false);
 	return wqe->length - len;
 }
 
@@ -284,7 +157,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 				qp->s_ack_state = OP(RDMA_READ_RESPONSE_ONLY);
 				e->sent = 1;
 			}
-			ohdr->u.aeth = hfi1_compute_aeth(qp);
+			ohdr->u.aeth = rvt_compute_aeth(qp);
 			hwords++;
 			qp->s_ack_rdma_psn = e->psn;
 			bth2 = mask_psn(qp->s_ack_rdma_psn++);
@@ -293,7 +166,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 			ps->s_txreq->ss = NULL;
 			len = 0;
 			qp->s_ack_state = OP(ATOMIC_ACKNOWLEDGE);
-			ohdr->u.at.aeth = hfi1_compute_aeth(qp);
+			ohdr->u.at.aeth = rvt_compute_aeth(qp);
 			ib_u64_put(e->atomic_data, &ohdr->u.at.atomic_ack_eth);
 			hwords += sizeof(ohdr->u.at) / sizeof(u32);
 			bth2 = mask_psn(e->psn);
@@ -315,7 +188,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 			len = pmtu;
 			middle = HFI1_CAP_IS_KSET(SDMA_AHG);
 		} else {
-			ohdr->u.aeth = hfi1_compute_aeth(qp);
+			ohdr->u.aeth = rvt_compute_aeth(qp);
 			hwords++;
 			qp->s_ack_state = OP(RDMA_READ_RESPONSE_LAST);
 			e = &qp->s_ack_queue[qp->s_tail_ack_queue];
@@ -338,11 +211,11 @@ normal:
 		ps->s_txreq->ss = NULL;
 		if (qp->s_nak_state)
 			ohdr->u.aeth =
-				cpu_to_be32((qp->r_msn & HFI1_MSN_MASK) |
+				cpu_to_be32((qp->r_msn & IB_MSN_MASK) |
 					    (qp->s_nak_state <<
-					     HFI1_AETH_CREDIT_SHIFT));
+					     IB_AETH_CREDIT_SHIFT));
 		else
-			ohdr->u.aeth = hfi1_compute_aeth(qp);
+			ohdr->u.aeth = rvt_compute_aeth(qp);
 		hwords++;
 		len = 0;
 		bth0 = OP(ACKNOWLEDGE) << 24;
@@ -414,7 +287,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 			goto bail;
 		/* We are in the error state, flush the work request. */
 		smp_read_barrier_depends(); /* see post_one_send() */
-		if (qp->s_last == ACCESS_ONCE(qp->s_head))
+		if (qp->s_last == READ_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (iowait_sdma_pending(&priv->s_iowait)) {
@@ -457,7 +330,8 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		newreq = 0;
 		if (qp->s_cur == qp->s_tail) {
 			/* Check if send work queue is empty. */
-			if (qp->s_tail == qp->s_head) {
+			smp_read_barrier_depends(); /* see post_one_send() */
+			if (qp->s_tail == READ_ONCE(qp->s_head)) {
 				clear_ahg(qp);
 				goto bail;
 			}
@@ -518,7 +392,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		case IB_WR_SEND_WITH_INV:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
+			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
@@ -555,7 +429,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
+			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
@@ -840,7 +714,7 @@ bail_no_tx:
 void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 		      int is_fecn)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	u64 pbc, pbc_flags = 0;
 	u16 lrh0;
@@ -853,6 +727,10 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 	struct ib_header hdr;
 	struct ib_other_headers *ohdr;
 	unsigned long flags;
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	/* clear the defer count */
+	priv->r_adefered = 0;
 
 	/* Don't send ACK or NAK if a RDMA read or atomic is pending. */
 	if (qp->s_flags & RVT_S_RESP_PENDING)
@@ -880,11 +758,11 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 	if (qp->s_mig_state == IB_MIG_MIGRATED)
 		bth0 |= IB_BTH_MIG_REQ;
 	if (qp->r_nak_state)
-		ohdr->u.aeth = cpu_to_be32((qp->r_msn & HFI1_MSN_MASK) |
+		ohdr->u.aeth = cpu_to_be32((qp->r_msn & IB_MSN_MASK) |
 					    (qp->r_nak_state <<
-					     HFI1_AETH_CREDIT_SHIFT));
+					     IB_AETH_CREDIT_SHIFT));
 	else
-		ohdr->u.aeth = hfi1_compute_aeth(qp);
+		ohdr->u.aeth = rvt_compute_aeth(qp);
 	sc5 = ibp->sl_to_sc[qp->remote_ah_attr.sl];
 	/* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */
 	pbc_flags |= ((!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT);
@@ -1038,7 +916,7 @@ done:
  * Back up requester to resend the last un-ACKed request.
  * The QP r_lock and s_lock should be held and interrupts disabled.
  */
-static void restart_rc(struct rvt_qp *qp, u32 psn, int wait)
+void hfi1_restart_rc(struct rvt_qp *qp, u32 psn, int wait)
 {
 	struct rvt_swqe *wqe = rvt_get_swqe_ptr(qp, qp->s_acked);
 	struct hfi1_ibport *ibp;
@@ -1075,44 +953,6 @@ static void restart_rc(struct rvt_qp *qp, u32 psn, int wait)
 }
 
 /*
- * This is called from s_timer for missing responses.
- */
-void hfi1_rc_timeout(unsigned long arg)
-{
-	struct rvt_qp *qp = (struct rvt_qp *)arg;
-	struct hfi1_ibport *ibp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&qp->r_lock, flags);
-	spin_lock(&qp->s_lock);
-	if (qp->s_flags & RVT_S_TIMER) {
-		ibp = to_iport(qp->ibqp.device, qp->port_num);
-		ibp->rvp.n_rc_timeouts++;
-		qp->s_flags &= ~RVT_S_TIMER;
-		del_timer(&qp->s_timer);
-		trace_hfi1_timeout(qp, qp->s_last_psn + 1);
-		restart_rc(qp, qp->s_last_psn + 1, 1);
-		hfi1_schedule_send(qp);
-	}
-	spin_unlock(&qp->s_lock);
-	spin_unlock_irqrestore(&qp->r_lock, flags);
-}
-
-/*
- * This is called from s_timer for RNR timeouts.
- */
-void hfi1_rc_rnr_retry(unsigned long arg)
-{
-	struct rvt_qp *qp = (struct rvt_qp *)arg;
-	unsigned long flags;
-
-	spin_lock_irqsave(&qp->s_lock, flags);
-	hfi1_stop_rnr_timer(qp);
-	hfi1_schedule_send(qp);
-	spin_unlock_irqrestore(&qp->s_lock, flags);
-}
-
-/*
  * Set qp->s_sending_psn to the next PSN after the given one.
  * This would be psn+1 except when RDMA reads are present.
  */
@@ -1150,7 +990,7 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 	u32 psn;
 
 	lockdep_assert_held(&qp->s_lock);
-	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_OR_FLUSH_SEND))
+	if (!(ib_rvt_state_ops[qp->state] & RVT_SEND_OR_FLUSH_OR_RECV_OK))
 		return;
 
 	/* Find out where the BTH is */
@@ -1178,7 +1018,7 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 	    !(qp->s_flags &
 		(RVT_S_TIMER | RVT_S_WAIT_RNR | RVT_S_WAIT_PSN)) &&
 		(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
-		hfi1_add_retry_timer(qp);
+		rvt_add_retry_timer(qp);
 
 	while (qp->s_last != qp->s_acked) {
 		u32 s_last;
@@ -1308,7 +1148,6 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 	int ret = 0;
 	u32 ack_psn;
 	int diff;
-	unsigned long to;
 
 	lockdep_assert_held(&qp->s_lock);
 	/*
@@ -1318,10 +1157,10 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 	 * request but will include an ACK'ed request(s).
 	 */
 	ack_psn = psn;
-	if (aeth >> 29)
+	if (aeth >> IB_AETH_NAK_SHIFT)
 		ack_psn--;
 	wqe = rvt_get_swqe_ptr(qp, qp->s_acked);
-	ibp = to_iport(qp->ibqp.device, qp->port_num);
+	ibp = rcd_to_iport(rcd);
 
 	/*
 	 * The MSN might be for a later WQE than the PSN indicates so
@@ -1357,7 +1196,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			/* Retry this request. */
 			if (!(qp->r_flags & RVT_R_RDMAR_SEQ)) {
 				qp->r_flags |= RVT_R_RDMAR_SEQ;
-				restart_rc(qp, qp->s_last_psn + 1, 0);
+				hfi1_restart_rc(qp, qp->s_last_psn + 1, 0);
 				if (list_empty(&qp->rspwait)) {
 					qp->r_flags |= RVT_R_RSP_SEND;
 					rvt_get_qp(qp);
@@ -1398,7 +1237,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			break;
 	}
 
-	switch (aeth >> 29) {
+	switch (aeth >> IB_AETH_NAK_SHIFT) {
 	case 0:         /* ACK */
 		this_cpu_inc(*ibp->rvp.rc_acks);
 		if (qp->s_acked != qp->s_tail) {
@@ -1406,7 +1245,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			 * We are expecting more ACKs so
 			 * mod the retry timer.
 			 */
-			hfi1_mod_retry_timer(qp);
+			rvt_mod_retry_timer(qp);
 			/*
 			 * We can stop re-sending the earlier packets and
 			 * continue with the next packet the receiver wants.
@@ -1415,7 +1254,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 				reset_psn(qp, psn + 1);
 		} else {
 			/* No more acks - kill all timers */
-			hfi1_stop_rc_timers(qp);
+			rvt_stop_rc_timers(qp);
 			if (cmp_psn(qp->s_psn, psn) <= 0) {
 				qp->s_state = OP(SEND_LAST);
 				qp->s_psn = psn + 1;
@@ -1425,7 +1264,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			qp->s_flags &= ~RVT_S_WAIT_ACK;
 			hfi1_schedule_send(qp);
 		}
-		hfi1_get_credit(qp, aeth);
+		rvt_get_credit(qp, aeth);
 		qp->s_rnr_retry = qp->s_rnr_retry_cnt;
 		qp->s_retry = qp->s_retry_cnt;
 		update_last_psn(qp, psn);
@@ -1452,11 +1291,8 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 		reset_psn(qp, psn);
 
 		qp->s_flags &= ~(RVT_S_WAIT_SSN_CREDIT | RVT_S_WAIT_ACK);
-		hfi1_stop_rc_timers(qp);
-		to =
-			ib_hfi1_rnr_table[(aeth >> HFI1_AETH_CREDIT_SHIFT) &
-					   HFI1_AETH_CREDIT_MASK];
-		hfi1_add_rnr_timer(qp, to);
+		rvt_stop_rc_timers(qp);
+		rvt_add_rnr_timer(qp, aeth);
 		return 0;
 
 	case 3:         /* NAK */
@@ -1464,8 +1300,8 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			goto bail_stop;
 		/* The last valid PSN is the previous PSN. */
 		update_last_psn(qp, psn - 1);
-		switch ((aeth >> HFI1_AETH_CREDIT_SHIFT) &
-			HFI1_AETH_CREDIT_MASK) {
+		switch ((aeth >> IB_AETH_CREDIT_SHIFT) &
+			IB_AETH_CREDIT_MASK) {
 		case 0: /* PSN sequence error */
 			ibp->rvp.n_seq_naks++;
 			/*
@@ -1474,7 +1310,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			 * RDMA READ response which terminates the RDMA
 			 * READ.
 			 */
-			restart_rc(qp, psn, 0);
+			hfi1_restart_rc(qp, psn, 0);
 			hfi1_schedule_send(qp);
 			break;
 
@@ -1513,7 +1349,7 @@ reserved:
 	}
 	/* cannot be reached  */
 bail_stop:
-	hfi1_stop_rc_timers(qp);
+	rvt_stop_rc_timers(qp);
 	return ret;
 }
 
@@ -1528,7 +1364,7 @@ static void rdma_seq_err(struct rvt_qp *qp, struct hfi1_ibport *ibp, u32 psn,
 
 	lockdep_assert_held(&qp->s_lock);
 	/* Remove QP from retry timer */
-	hfi1_stop_rc_timers(qp);
+	rvt_stop_rc_timers(qp);
 
 	wqe = rvt_get_swqe_ptr(qp, qp->s_acked);
 
@@ -1542,7 +1378,7 @@ static void rdma_seq_err(struct rvt_qp *qp, struct hfi1_ibport *ibp, u32 psn,
 
 	ibp->rvp.n_rdma_seq++;
 	qp->r_flags |= RVT_R_RDMAR_SEQ;
-	restart_rc(qp, qp->s_last_psn + 1, 0);
+	hfi1_restart_rc(qp, qp->s_last_psn + 1, 0);
 	if (list_empty(&qp->rspwait)) {
 		qp->r_flags |= RVT_R_RSP_SEND;
 		rvt_get_qp(qp);
@@ -1586,7 +1422,7 @@ static void rc_rcv_resp(struct hfi1_ibport *ibp,
 
 	/* Ignore invalid responses. */
 	smp_read_barrier_depends(); /* see post_one_send */
-	if (cmp_psn(psn, ACCESS_ONCE(qp->s_next_psn)) >= 0)
+	if (cmp_psn(psn, READ_ONCE(qp->s_next_psn)) >= 0)
 		goto ack_done;
 
 	/* Ignore duplicate responses. */
@@ -1595,8 +1431,8 @@ static void rc_rcv_resp(struct hfi1_ibport *ibp,
 		/* Update credits for "ghost" ACKs */
 		if (diff == 0 && opcode == OP(ACKNOWLEDGE)) {
 			aeth = be32_to_cpu(ohdr->u.aeth);
-			if ((aeth >> 29) == 0)
-				hfi1_get_credit(qp, aeth);
+			if ((aeth >> IB_AETH_NAK_SHIFT) == 0)
+				rvt_get_credit(qp, aeth);
 		}
 		goto ack_done;
 	}
@@ -1656,8 +1492,7 @@ read_middle:
 		 * We got a response so update the timeout.
 		 * 4.096 usec. * (1 << qp->timeout)
 		 */
-		qp->s_flags |= RVT_S_TIMER;
-		mod_timer(&qp->s_timer, jiffies + qp->timeout_jiffies);
+		rvt_mod_retry_timer(qp);
 		if (qp->s_flags & RVT_S_WAIT_ACK) {
 			qp->s_flags &= ~RVT_S_WAIT_ACK;
 			hfi1_schedule_send(qp);
@@ -1673,7 +1508,7 @@ read_middle:
 		qp->s_rdma_read_len -= pmtu;
 		update_last_psn(qp, psn);
 		spin_unlock_irqrestore(&qp->s_lock, flags);
-		hfi1_copy_sge(&qp->s_rdma_read_sge, data, pmtu, 0, 0);
+		hfi1_copy_sge(&qp->s_rdma_read_sge, data, pmtu, false, false);
 		goto bail;
 
 	case OP(RDMA_READ_RESPONSE_ONLY):
@@ -1717,7 +1552,7 @@ read_last:
 		if (unlikely(tlen != qp->s_rdma_read_len))
 			goto ack_len_err;
 		aeth = be32_to_cpu(ohdr->u.aeth);
-		hfi1_copy_sge(&qp->s_rdma_read_sge, data, tlen, 0, 0);
+		hfi1_copy_sge(&qp->s_rdma_read_sge, data, tlen, false, false);
 		WARN_ON(qp->s_rdma_read_sge.num_sge);
 		(void)do_rc_ack(qp, aeth, psn,
 				 OP(RDMA_READ_RESPONSE_LAST), 0, rcd);
@@ -1786,7 +1621,7 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data,
 				 struct rvt_qp *qp, u32 opcode, u32 psn,
 				 int diff, struct hfi1_ctxtdata *rcd)
 {
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct rvt_ack_entry *e;
 	unsigned long flags;
 	u8 i, prev;
@@ -1961,25 +1796,6 @@ send_ack:
 	return 0;
 }
 
-void hfi1_rc_error(struct rvt_qp *qp, enum ib_wc_status err)
-{
-	unsigned long flags;
-	int lastwqe;
-
-	spin_lock_irqsave(&qp->s_lock, flags);
-	lastwqe = rvt_error_qp(qp, err);
-	spin_unlock_irqrestore(&qp->s_lock, flags);
-
-	if (lastwqe) {
-		struct ib_event ev;
-
-		ev.device = qp->ibqp.device;
-		ev.element.qp = &qp->ibqp;
-		ev.event = IB_EVENT_QP_LAST_WQE_REACHED;
-		qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
-	}
-}
-
 static inline void update_ack_queue(struct rvt_qp *qp, unsigned n)
 {
 	unsigned next;
@@ -2095,7 +1911,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	void *data = packet->ebuf;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct ib_other_headers *ohdr = packet->ohdr;
 	u32 bth0, opcode;
 	u32 hdrsize = packet->hlen;
@@ -2107,7 +1923,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	struct ib_reth *reth;
 	unsigned long flags;
 	int ret, is_fecn = 0;
-	int copy_last = 0;
+	bool copy_last = false;
 	u32 rkey;
 
 	lockdep_assert_held(&qp->r_lock);
@@ -2180,7 +1996,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	}
 
 	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST))
-		qp_comm_est(qp);
+		rvt_comm_est(qp);
 
 	/* OK, process the packet. */
 	switch (opcode) {
@@ -2201,7 +2017,7 @@ send_middle:
 		qp->r_rcv_len += pmtu;
 		if (unlikely(qp->r_rcv_len > qp->r_len))
 			goto nack_inv;
-		hfi1_copy_sge(&qp->r_sge, data, pmtu, 1, 0);
+		hfi1_copy_sge(&qp->r_sge, data, pmtu, true, false);
 		break;
 
 	case OP(RDMA_WRITE_LAST_WITH_IMMEDIATE):
@@ -2241,7 +2057,7 @@ send_last_inv:
 		wc.wc_flags = IB_WC_WITH_INVALIDATE;
 		goto send_last;
 	case OP(RDMA_WRITE_LAST):
-		copy_last = ibpd_to_rvtpd(qp->ibqp.pd)->user;
+		copy_last = rvt_is_user_qp(qp);
 		/* fall through */
 	case OP(SEND_LAST):
 no_immediate_data:
@@ -2259,7 +2075,7 @@ send_last:
 		wc.byte_len = tlen + qp->r_rcv_len;
 		if (unlikely(wc.byte_len > qp->r_len))
 			goto nack_inv;
-		hfi1_copy_sge(&qp->r_sge, data, tlen, 1, copy_last);
+		hfi1_copy_sge(&qp->r_sge, data, tlen, true, copy_last);
 		rvt_put_ss(&qp->r_sge);
 		qp->r_msn++;
 		if (!__test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags))
@@ -2297,7 +2113,7 @@ send_last:
 		break;
 
 	case OP(RDMA_WRITE_ONLY):
-		copy_last = 1;
+		copy_last = rvt_is_user_qp(qp);
 		/* fall through */
 	case OP(RDMA_WRITE_FIRST):
 	case OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE):
@@ -2512,7 +2328,7 @@ rnr_nak:
 	return;
 
 nack_op_err:
-	hfi1_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 	qp->r_nak_state = IB_NAK_REMOTE_OPERATIONAL_ERROR;
 	qp->r_ack_psn = qp->r_psn;
 	/* Queue NAK for later */
@@ -2522,7 +2338,7 @@ nack_op_err:
 nack_inv_unlck:
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 nack_inv:
-	hfi1_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 	qp->r_nak_state = IB_NAK_INVALID_REQUEST;
 	qp->r_ack_psn = qp->r_psn;
 	/* Queue NAK for later */
@@ -2532,7 +2348,7 @@ nack_inv:
 nack_acc_unlck:
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 nack_acc:
-	hfi1_rc_error(qp, IB_WC_LOC_PROT_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_PROT_ERR);
 	qp->r_nak_state = IB_NAK_REMOTE_ACCESS_ERROR;
 	qp->r_ack_psn = qp->r_psn;
 send_ack:
@@ -2547,7 +2363,7 @@ void hfi1_rc_hdrerr(
 {
 	int has_grh = rcv_flags & HFI1_HAS_GRH;
 	struct ib_other_headers *ohdr;
-	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	int diff;
 	u32 opcode;
 	u32 psn, bth0;
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 717ed4b159d3..aa15bcbfb079 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -54,44 +54,6 @@
 #include "trace.h"
 
 /*
- * Convert the AETH RNR timeout code into the number of microseconds.
- */
-const u32 ib_hfi1_rnr_table[32] = {
-	655360,	/* 00: 655.36 */
-	10,	/* 01:    .01 */
-	20,	/* 02     .02 */
-	30,	/* 03:    .03 */
-	40,	/* 04:    .04 */
-	60,	/* 05:    .06 */
-	80,	/* 06:    .08 */
-	120,	/* 07:    .12 */
-	160,	/* 08:    .16 */
-	240,	/* 09:    .24 */
-	320,	/* 0A:    .32 */
-	480,	/* 0B:    .48 */
-	640,	/* 0C:    .64 */
-	960,	/* 0D:    .96 */
-	1280,	/* 0E:   1.28 */
-	1920,	/* 0F:   1.92 */
-	2560,	/* 10:   2.56 */
-	3840,	/* 11:   3.84 */
-	5120,	/* 12:   5.12 */
-	7680,	/* 13:   7.68 */
-	10240,	/* 14:  10.24 */
-	15360,	/* 15:  15.36 */
-	20480,	/* 16:  20.48 */
-	30720,	/* 17:  30.72 */
-	40960,	/* 18:  40.96 */
-	61440,	/* 19:  61.44 */
-	81920,	/* 1A:  81.92 */
-	122880,	/* 1B: 122.88 */
-	163840,	/* 1C: 163.84 */
-	245760,	/* 1D: 245.76 */
-	327680,	/* 1E: 327.68 */
-	491520	/* 1F: 491.52 */
-};
-
-/*
  * Validate a RWQE and fill in the SGE state.
  * Return 1 if OK.
  */
@@ -358,10 +320,9 @@ static void ruc_loopback(struct rvt_qp *sqp)
 	u64 sdata;
 	atomic64_t *maddr;
 	enum ib_wc_status send_status;
-	int release;
+	bool release;
 	int ret;
-	int copy_last = 0;
-	u32 to;
+	bool copy_last = false;
 	int local_ops = 0;
 
 	rcu_read_lock();
@@ -425,7 +386,7 @@ again:
 	memset(&wc, 0, sizeof(wc));
 	send_status = IB_WC_SUCCESS;
 
-	release = 1;
+	release = true;
 	sqp->s_sge.sge = wqe->sg_list[0];
 	sqp->s_sge.sg_list = wqe->sg_list + 1;
 	sqp->s_sge.num_sge = wqe->wr.num_sge;
@@ -476,7 +437,7 @@ send:
 		/* skip copy_last set and qp_access_flags recheck */
 		goto do_write;
 	case IB_WR_RDMA_WRITE:
-		copy_last = ibpd_to_rvtpd(qp->ibqp.pd)->user;
+		copy_last = rvt_is_user_qp(qp);
 		if (unlikely(!(qp->qp_access_flags & IB_ACCESS_REMOTE_WRITE)))
 			goto inv_err;
 do_write:
@@ -500,7 +461,7 @@ do_write:
 					  wqe->rdma_wr.rkey,
 					  IB_ACCESS_REMOTE_READ)))
 			goto acc_err;
-		release = 0;
+		release = false;
 		sqp->s_sge.sg_list = NULL;
 		sqp->s_sge.num_sge = 1;
 		qp->r_sge.sge = wqe->sg_list[0];
@@ -618,8 +579,8 @@ rnr_nak:
 	spin_lock_irqsave(&sqp->s_lock, flags);
 	if (!(ib_rvt_state_ops[sqp->state] & RVT_PROCESS_RECV_OK))
 		goto clr_busy;
-	to = ib_hfi1_rnr_table[qp->r_min_rnr_timer];
-	hfi1_add_rnr_timer(sqp, to);
+	rvt_add_rnr_timer(sqp, qp->r_min_rnr_timer <<
+				IB_AETH_CREDIT_SHIFT);
 	goto clr_busy;
 
 op_err:
@@ -637,7 +598,7 @@ acc_err:
 	wc.status = IB_WC_LOC_PROT_ERR;
 err:
 	/* responder goes to error state */
-	hfi1_rc_error(qp, wc.status);
+	rvt_rc_error(qp, wc.status);
 
 serr:
 	spin_lock_irqsave(&sqp->s_lock, flags);
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 1d81cac1fa6c..5cde1ecda0fe 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -856,7 +856,7 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd,
 {
 	struct sdma_rht_node *rht_node;
 	struct sdma_engine *sde = NULL;
-	const struct cpumask *current_mask = tsk_cpus_allowed(current);
+	const struct cpumask *current_mask = &current->cpus_allowed;
 	unsigned long cpu_id;
 
 	/*
diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c
index 01f525cd985a..e86798af6903 100644
--- a/drivers/infiniband/hw/hfi1/trace.c
+++ b/drivers/infiniband/hw/hfi1/trace.c
@@ -130,14 +130,14 @@ const char *parse_everbs_hdrs(
 	case OP(RC, ACKNOWLEDGE):
 		trace_seq_printf(p, AETH_PRN, be32_to_cpu(eh->aeth) >> 24,
 				 parse_syndrome(be32_to_cpu(eh->aeth) >> 24),
-				 be32_to_cpu(eh->aeth) & HFI1_MSN_MASK);
+				 be32_to_cpu(eh->aeth) & IB_MSN_MASK);
 		break;
 	/* aeth + atomicacketh */
 	case OP(RC, ATOMIC_ACKNOWLEDGE):
 		trace_seq_printf(p, AETH_PRN " " ATOMICACKETH_PRN,
 				 be32_to_cpu(eh->at.aeth) >> 24,
 				 parse_syndrome(be32_to_cpu(eh->at.aeth) >> 24),
-				 be32_to_cpu(eh->at.aeth) & HFI1_MSN_MASK,
+				 be32_to_cpu(eh->at.aeth) & IB_MSN_MASK,
 				 ib_u64_get(&eh->at.atomic_ack_eth));
 		break;
 	/* atomiceth */
diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index b141a78ae38b..4b2a8400c823 100644
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -296,7 +296,7 @@ bail_no_tx:
  */
 void hfi1_uc_rcv(struct hfi1_packet *packet)
 {
-	struct hfi1_ibport *ibp = &packet->rcd->ppd->ibport_data;
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct ib_header *hdr = packet->hdr;
 	u32 rcv_flags = packet->rcv_flags;
 	void *data = packet->ebuf;
@@ -384,7 +384,7 @@ inv:
 	}
 
 	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST))
-		qp_comm_est(qp);
+		rvt_comm_est(qp);
 
 	/* OK, process the packet. */
 	switch (opcode) {
@@ -419,7 +419,7 @@ send_first:
 		qp->r_rcv_len += pmtu;
 		if (unlikely(qp->r_rcv_len > qp->r_len))
 			goto rewind;
-		hfi1_copy_sge(&qp->r_sge, data, pmtu, 0, 0);
+		hfi1_copy_sge(&qp->r_sge, data, pmtu, false, false);
 		break;
 
 	case OP(SEND_LAST_WITH_IMMEDIATE):
@@ -444,7 +444,7 @@ send_last:
 		if (unlikely(wc.byte_len > qp->r_len))
 			goto rewind;
 		wc.opcode = IB_WC_RECV;
-		hfi1_copy_sge(&qp->r_sge, data, tlen, 0, 0);
+		hfi1_copy_sge(&qp->r_sge, data, tlen, false, false);
 		rvt_put_ss(&qp->s_rdma_read_sge);
 last_imm:
 		wc.wr_id = qp->r_wr_id;
@@ -519,7 +519,7 @@ rdma_first:
 		qp->r_rcv_len += pmtu;
 		if (unlikely(qp->r_rcv_len > qp->r_len))
 			goto drop;
-		hfi1_copy_sge(&qp->r_sge, data, pmtu, 1, 0);
+		hfi1_copy_sge(&qp->r_sge, data, pmtu, true, false);
 		break;
 
 	case OP(RDMA_WRITE_LAST_WITH_IMMEDIATE):
@@ -548,7 +548,7 @@ rdma_last_imm:
 		}
 		wc.byte_len = qp->r_len;
 		wc.opcode = IB_WC_RECV_RDMA_WITH_IMM;
-		hfi1_copy_sge(&qp->r_sge, data, tlen, 1, 0);
+		hfi1_copy_sge(&qp->r_sge, data, tlen, true, false);
 		rvt_put_ss(&qp->r_sge);
 		goto last_imm;
 
@@ -564,7 +564,7 @@ rdma_last:
 		tlen -= (hdrsize + pad + 4);
 		if (unlikely(tlen + qp->r_rcv_len != qp->r_len))
 			goto drop;
-		hfi1_copy_sge(&qp->r_sge, data, tlen, 1, 0);
+		hfi1_copy_sge(&qp->r_sge, data, tlen, true, false);
 		rvt_put_ss(&qp->r_sge);
 		break;
 
@@ -584,5 +584,5 @@ drop:
 	return;
 
 op_err:
-	hfi1_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 }
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index c071955c0272..13ea4eb6ef3d 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -167,7 +167,7 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 
 		ret = hfi1_rvt_get_rwqe(qp, 0);
 		if (ret < 0) {
-			hfi1_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			goto bail_unlock;
 		}
 		if (!ret) {
@@ -189,10 +189,10 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 
 		hfi1_make_grh(ibp, &grh, &grd, 0, 0);
 		hfi1_copy_sge(&qp->r_sge, &grh,
-			      sizeof(grh), 1, 0);
+			      sizeof(grh), true, false);
 		wc.wc_flags |= IB_WC_GRH;
 	} else {
-		hfi1_skip_sge(&qp->r_sge, sizeof(struct ib_grh), 1);
+		rvt_skip_sge(&qp->r_sge, sizeof(struct ib_grh), true);
 	}
 	ssge.sg_list = swqe->sg_list + 1;
 	ssge.sge = *swqe->sg_list;
@@ -206,7 +206,7 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 		if (len > sge->sge_length)
 			len = sge->sge_length;
 		WARN_ON_ONCE(len == 0);
-		hfi1_copy_sge(&qp->r_sge, sge->vaddr, len, 1, 0);
+		hfi1_copy_sge(&qp->r_sge, sge->vaddr, len, true, false);
 		sge->vaddr += len;
 		sge->length -= len;
 		sge->sge_length -= len;
@@ -672,7 +672,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	u32 src_qp;
 	u16 dlid, pkey;
 	int mgmt_pkey_idx = -1;
-	struct hfi1_ibport *ibp = &packet->rcd->ppd->ibport_data;
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct ib_header *hdr = packet->hdr;
 	u32 rcv_flags = packet->rcv_flags;
@@ -796,7 +796,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 
 		ret = hfi1_rvt_get_rwqe(qp, 0);
 		if (ret < 0) {
-			hfi1_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			return;
 		}
 		if (!ret) {
@@ -812,13 +812,13 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	}
 	if (has_grh) {
 		hfi1_copy_sge(&qp->r_sge, &hdr->u.l.grh,
-			      sizeof(struct ib_grh), 1, 0);
+			      sizeof(struct ib_grh), true, false);
 		wc.wc_flags |= IB_WC_GRH;
 	} else {
-		hfi1_skip_sge(&qp->r_sge, sizeof(struct ib_grh), 1);
+		rvt_skip_sge(&qp->r_sge, sizeof(struct ib_grh), true);
 	}
 	hfi1_copy_sge(&qp->r_sge, data, wc.byte_len - sizeof(struct ib_grh),
-		      1, 0);
+		      true, false);
 	rvt_put_ss(&qp->r_sge);
 	if (!test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags))
 		return;
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 64d26525435a..4a8295399e71 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -45,6 +45,7 @@
  *
  */
 #include <asm/page.h>
+#include <linux/string.h>
 
 #include "user_exp_rcv.h"
 #include "trace.h"
@@ -577,16 +578,10 @@ int hfi1_user_exp_rcv_clear(struct file *fp, struct hfi1_tid_info *tinfo)
 	u32 *tidinfo;
 	unsigned tididx;
 
-	tidinfo = kcalloc(tinfo->tidcnt, sizeof(*tidinfo), GFP_KERNEL);
-	if (!tidinfo)
-		return -ENOMEM;
-
-	if (copy_from_user(tidinfo, (void __user *)(unsigned long)
-			   tinfo->tidlist, sizeof(tidinfo[0]) *
-			   tinfo->tidcnt)) {
-		ret = -EFAULT;
-		goto done;
-	}
+	tidinfo = memdup_user((void __user *)(unsigned long)tinfo->tidlist,
+			      sizeof(tidinfo[0]) * tinfo->tidcnt);
+	if (IS_ERR(tidinfo))
+		return PTR_ERR(tidinfo);
 
 	mutex_lock(&uctxt->exp_lock);
 	for (tididx = 0; tididx < tinfo->tidcnt; tididx++) {
@@ -602,7 +597,7 @@ int hfi1_user_exp_rcv_clear(struct file *fp, struct hfi1_tid_info *tinfo)
 	spin_unlock(&fd->tid_lock);
 	tinfo->tidcnt = tididx;
 	mutex_unlock(&uctxt->exp_lock);
-done:
+
 	kfree(tidinfo);
 	return ret;
 }
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 20f4ddcac3b0..68295a12b771 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -46,7 +46,7 @@
  */
 
 #include <linux/mm.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/device.h>
 #include <linux/module.h>
 
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index 7d22f8ee98ef..e6811c4edc73 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -60,6 +60,7 @@
 #include <linux/mmu_context.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
+#include <linux/string.h>
 
 #include "hfi.h"
 #include "sdma.h"
@@ -725,30 +726,28 @@ int hfi1_user_sdma_process_request(struct file *fp, struct iovec *iovec,
 	 */
 	if (req_opcode(req->info.ctrl) == EXPECTED) {
 		u16 ntids = iovec[idx].iov_len / sizeof(*req->tids);
+		u32 *tmp;
 
 		if (!ntids || ntids > MAX_TID_PAIR_ENTRIES) {
 			ret = -EINVAL;
 			goto free_req;
 		}
-		req->tids = kcalloc(ntids, sizeof(*req->tids), GFP_KERNEL);
-		if (!req->tids) {
-			ret = -ENOMEM;
-			goto free_req;
-		}
+
 		/*
 		 * We have to copy all of the tids because they may vary
 		 * in size and, therefore, the TID count might not be
 		 * equal to the pkt count. However, there is no way to
 		 * tell at this point.
 		 */
-		ret = copy_from_user(req->tids, iovec[idx].iov_base,
-				     ntids * sizeof(*req->tids));
-		if (ret) {
+		tmp = memdup_user(iovec[idx].iov_base,
+				  ntids * sizeof(*req->tids));
+		if (IS_ERR(tmp)) {
+			ret = PTR_ERR(tmp);
 			SDMA_DBG(req, "Failed to copy %d TIDs (%d)",
 				 ntids, ret);
-			ret = -EFAULT;
 			goto free_req;
 		}
+		req->tids = tmp;
 		req->n_tids = ntids;
 		idx++;
 	}
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 95ed4d6da510..222315fadab1 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -291,7 +291,7 @@ static void wss_insert(void *address)
 /*
  * Is the working set larger than the threshold?
  */
-static inline int wss_exceeds_threshold(void)
+static inline bool wss_exceeds_threshold(void)
 {
 	return atomic_read(&wss.total_count) >= wss.threshold;
 }
@@ -419,18 +419,19 @@ __be64 ib_hfi1_sys_image_guid;
  * @ss: the SGE state
  * @data: the data to copy
  * @length: the length of the data
+ * @release: boolean to release MR
  * @copy_last: do a separate copy of the last 8 bytes
  */
 void hfi1_copy_sge(
 	struct rvt_sge_state *ss,
 	void *data, u32 length,
-	int release,
-	int copy_last)
+	bool release,
+	bool copy_last)
 {
 	struct rvt_sge *sge = &ss->sge;
-	int in_last = 0;
 	int i;
-	int cacheless_copy = 0;
+	bool in_last = false;
+	bool cacheless_copy = false;
 
 	if (sge_copy_mode == COPY_CACHELESS) {
 		cacheless_copy = length >= PAGE_SIZE;
@@ -454,19 +455,15 @@ void hfi1_copy_sge(
 		if (length > 8) {
 			length -= 8;
 		} else {
-			copy_last = 0;
-			in_last = 1;
+			copy_last = false;
+			in_last = true;
 		}
 	}
 
 again:
 	while (length) {
-		u32 len = sge->length;
+		u32 len = rvt_get_sge_length(sge, length);
 
-		if (len > length)
-			len = length;
-		if (len > sge->sge_length)
-			len = sge->sge_length;
 		WARN_ON_ONCE(len == 0);
 		if (unlikely(in_last)) {
 			/* enforce byte transfer ordering */
@@ -477,77 +474,19 @@ again:
 		} else {
 			memcpy(sge->vaddr, data, len);
 		}
-		sge->vaddr += len;
-		sge->length -= len;
-		sge->sge_length -= len;
-		if (sge->sge_length == 0) {
-			if (release)
-				rvt_put_mr(sge->mr);
-			if (--ss->num_sge)
-				*sge = *ss->sg_list++;
-		} else if (sge->length == 0 && sge->mr->lkey) {
-			if (++sge->n >= RVT_SEGSZ) {
-				if (++sge->m >= sge->mr->mapsz)
-					break;
-				sge->n = 0;
-			}
-			sge->vaddr =
-				sge->mr->map[sge->m]->segs[sge->n].vaddr;
-			sge->length =
-				sge->mr->map[sge->m]->segs[sge->n].length;
-		}
+		rvt_update_sge(ss, len, release);
 		data += len;
 		length -= len;
 	}
 
 	if (copy_last) {
-		copy_last = 0;
-		in_last = 1;
+		copy_last = false;
+		in_last = true;
 		length = 8;
 		goto again;
 	}
 }
 
-/**
- * hfi1_skip_sge - skip over SGE memory
- * @ss: the SGE state
- * @length: the number of bytes to skip
- */
-void hfi1_skip_sge(struct rvt_sge_state *ss, u32 length, int release)
-{
-	struct rvt_sge *sge = &ss->sge;
-
-	while (length) {
-		u32 len = sge->length;
-
-		if (len > length)
-			len = length;
-		if (len > sge->sge_length)
-			len = sge->sge_length;
-		WARN_ON_ONCE(len == 0);
-		sge->vaddr += len;
-		sge->length -= len;
-		sge->sge_length -= len;
-		if (sge->sge_length == 0) {
-			if (release)
-				rvt_put_mr(sge->mr);
-			if (--ss->num_sge)
-				*sge = *ss->sg_list++;
-		} else if (sge->length == 0 && sge->mr->lkey) {
-			if (++sge->n >= RVT_SEGSZ) {
-				if (++sge->m >= sge->mr->mapsz)
-					break;
-				sge->n = 0;
-			}
-			sge->vaddr =
-				sge->mr->map[sge->m]->segs[sge->n].vaddr;
-			sge->length =
-				sge->mr->map[sge->m]->segs[sge->n].length;
-		}
-		length -= len;
-	}
-}
-
 /*
  * Make sure the QP is ready and able to accept the given opcode.
  */
@@ -576,7 +515,7 @@ void hfi1_ib_rcv(struct hfi1_packet *packet)
 	struct ib_header *hdr = packet->hdr;
 	u32 tlen = packet->tlen;
 	struct hfi1_pportdata *ppd = rcd->ppd;
-	struct hfi1_ibport *ibp = &ppd->ibport_data;
+	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct rvt_dev_info *rdi = &ppd->dd->verbs_dev.rdi;
 	opcode_handler packet_handler;
 	unsigned long flags;
@@ -689,27 +628,6 @@ static void mem_timer(unsigned long data)
 		hfi1_qp_wakeup(qp, RVT_S_WAIT_KMEM);
 }
 
-void update_sge(struct rvt_sge_state *ss, u32 length)
-{
-	struct rvt_sge *sge = &ss->sge;
-
-	sge->vaddr += length;
-	sge->length -= length;
-	sge->sge_length -= length;
-	if (sge->sge_length == 0) {
-		if (--ss->num_sge)
-			*sge = *ss->sg_list++;
-	} else if (sge->length == 0 && sge->mr->lkey) {
-		if (++sge->n >= RVT_SEGSZ) {
-			if (++sge->m >= sge->mr->mapsz)
-				return;
-			sge->n = 0;
-		}
-		sge->vaddr = sge->mr->map[sge->m]->segs[sge->n].vaddr;
-		sge->length = sge->mr->map[sge->m]->segs[sge->n].length;
-	}
-}
-
 /*
  * This is called with progress side lock held.
  */
@@ -798,7 +716,7 @@ static noinline int build_verbs_ulp_payload(
 			len);
 		if (ret)
 			goto bail_txadd;
-		update_sge(ss, len);
+		rvt_update_sge(ss, len, false);
 		length -= len;
 	}
 	return ret;
@@ -1073,7 +991,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 
 				if (slen > len)
 					slen = len;
-				update_sge(ss, slen);
+				rvt_update_sge(ss, slen, false);
 				seg_pio_copy_mid(pbuf, addr, slen);
 				len -= slen;
 			}
@@ -1384,6 +1302,7 @@ static int query_port(struct rvt_dev_info *rdi, u8 port_num,
 	struct hfi1_pportdata *ppd = &dd->pport[port_num - 1];
 	u16 lid = ppd->lid;
 
+	/* props being zeroed by the caller, avoid zeroing it here */
 	props->lid = lid ? lid : 0;
 	props->lmc = ppd->lmc;
 	/* OPA logical states match IB logical states */
@@ -1618,7 +1537,7 @@ static int cntr_names_initialized;
  * external strings.
  */
 static int init_cntr_names(const char *names_in,
-			   const int names_len,
+			   const size_t names_len,
 			   int num_extra_names,
 			   int *num_cntrs,
 			   const char ***cntr_names)
@@ -1784,7 +1703,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	strlcpy(ibdev->name + lcpysz, "_%d", IB_DEVICE_NAME_MAX - lcpysz);
 	ibdev->owner = THIS_MODULE;
 	ibdev->phys_port_cnt = dd->num_pports;
-	ibdev->dma_device = &dd->pcidev->dev;
+	ibdev->dev.parent = &dd->pcidev->dev;
 	ibdev->modify_device = modify_device;
 	ibdev->alloc_hw_stats = alloc_hw_stats;
 	ibdev->get_hw_stats = get_hw_stats;
@@ -1845,6 +1764,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.mtu_to_path_mtu = mtu_to_path_mtu;
 	dd->verbs_dev.rdi.driver_f.check_modify_qp = hfi1_check_modify_qp;
 	dd->verbs_dev.rdi.driver_f.modify_qp = hfi1_modify_qp;
+	dd->verbs_dev.rdi.driver_f.notify_restart_rc = hfi1_restart_rc;
 	dd->verbs_dev.rdi.driver_f.check_send_wqe = hfi1_check_send_wqe;
 
 	/* completeion queue */
@@ -1910,7 +1830,7 @@ void hfi1_unregister_ib_device(struct hfi1_devdata *dd)
 
 void hfi1_cnp_rcv(struct hfi1_packet *packet)
 {
-	struct hfi1_ibport *ibp = &packet->rcd->ppd->ibport_data;
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct ib_header *hdr = packet->hdr;
 	struct rvt_qp *qp = packet->qp;
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index e6b893010e6d..3a0b589e41c2 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -127,7 +127,6 @@ struct hfi1_qp_priv {
 	u8 s_sc;		                  /* SC[0..4] for next packet */
 	u8 r_adefered;                            /* number of acks defered */
 	struct iowait s_iowait;
-	struct timer_list s_rnr_timer;
 	struct rvt_qp *owner;
 };
 
@@ -260,15 +259,6 @@ int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 #define PSN_MODIFY_MASK 0xFFFFFF
 
 /*
- * Compare the lower 24 bits of the msn values.
- * Returns an integer <, ==, or > than zero.
- */
-static inline int cmp_msn(u32 a, u32 b)
-{
-	return (((int)a) - ((int)b)) << 8;
-}
-
-/*
  * Compare two PSNs
  * Returns an integer <, ==, or > than zero.
  */
@@ -299,9 +289,7 @@ void hfi1_put_txreq(struct verbs_txreq *tx);
 int hfi1_verbs_send(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
 
 void hfi1_copy_sge(struct rvt_sge_state *ss, void *data, u32 length,
-		   int release, int copy_last);
-
-void hfi1_skip_sge(struct rvt_sge_state *ss, u32 length, int release);
+		   bool release, bool copy_last);
 
 void hfi1_cnp_rcv(struct hfi1_packet *packet);
 
@@ -319,16 +307,8 @@ u8 ah_to_sc(struct ib_device *ibdev, struct ib_ah_attr *ah_attr);
 
 struct ib_ah *hfi1_create_qp0_ah(struct hfi1_ibport *ibp, u16 dlid);
 
-void hfi1_rc_rnr_retry(unsigned long arg);
-void hfi1_add_rnr_timer(struct rvt_qp *qp, u32 to);
-void hfi1_rc_timeout(unsigned long arg);
-void hfi1_del_timers_sync(struct rvt_qp *qp);
-void hfi1_stop_rc_timers(struct rvt_qp *qp);
-
 void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr);
 
-void hfi1_rc_error(struct rvt_qp *qp, enum ib_wc_status err);
-
 void hfi1_ud_rcv(struct hfi1_packet *packet);
 
 int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey);
@@ -342,7 +322,7 @@ int hfi1_check_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 
 void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		    int attr_mask, struct ib_udata *udata);
-
+void hfi1_restart_rc(struct rvt_qp *qp, u32 psn, int wait);
 int hfi1_check_send_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe);
 
 extern const u32 rc_only_opcode;
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 4953d9cb83a7..c3b41f95e70a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -32,6 +32,7 @@
  */
 #include <linux/acpi.h>
 #include <linux/of_platform.h>
+#include <linux/module.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
@@ -249,7 +250,7 @@ static int hns_roce_query_port(struct ib_device *ib_dev, u8 port_num,
 	assert(port_num > 0);
 	port = port_num - 1;
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->max_mtu = hr_dev->caps.max_mtu;
 	props->gid_tbl_len = hr_dev->caps.gid_table_len[port];
@@ -400,14 +401,15 @@ static int hns_roce_port_immutable(struct ib_device *ib_dev, u8 port_num,
 	struct ib_port_attr attr;
 	int ret;
 
-	ret = hns_roce_query_port(ib_dev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+
+	ret = ib_query_port(ib_dev, port_num, &attr);
 	if (ret)
 		return ret;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
 
-	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
 	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 
 	return 0;
@@ -437,7 +439,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 
 	ib_dev->owner			= THIS_MODULE;
 	ib_dev->node_type		= RDMA_NODE_IB_CA;
-	ib_dev->dma_device		= dev;
+	ib_dev->dev.parent		= dev;
 
 	ib_dev->phys_port_cnt		= hr_dev->caps.num_ports;
 	ib_dev->local_dma_lkey		= hr_dev->caps.reserved_lkey;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index f036f32f15d3..3f44f2f91f03 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -101,7 +101,7 @@ static void hns_roce_ib_qp_event(struct hns_roce_qp *hr_qp,
 			event.event = IB_EVENT_QP_ACCESS_ERR;
 			break;
 		default:
-			dev_dbg(ibqp->device->dma_device, "roce_ib: Unexpected event type %d on QP %06lx\n",
+			dev_dbg(ibqp->device->dev.parent, "roce_ib: Unexpected event type %d on QP %06lx\n",
 				type, hr_qp->qpn);
 			return;
 		}
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index 98923a8cf86d..f82483b3d1e7 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -450,6 +450,9 @@ static enum i40iw_status_code i40iw_sc_cqp_create(struct i40iw_sc_cqp *cqp,
 	u32 cnt = 0, p1, p2, val = 0, err_code;
 	enum i40iw_status_code ret_code;
 
+	*maj_err = 0;
+	*min_err = 0;
+
 	ret_code = i40iw_allocate_dma_mem(cqp->dev->hw,
 					  &cqp->sdbuf,
 					  128,
@@ -4498,9 +4501,9 @@ void i40iw_sc_vsi_init(struct i40iw_sc_vsi *vsi, struct i40iw_vsi_init_info *inf
 	i40iw_fill_qos_list(info->params->qs_handle_list);
 
 	for (i = 0; i < I40IW_MAX_USER_PRIORITY; i++) {
-		vsi->qos[i].qs_handle =
-			info->params->qs_handle_list[i];
-			i40iw_debug(vsi->dev, I40IW_DEBUG_DCB, "qset[%d]: %d\n", i, vsi->qos[i].qs_handle);
+		vsi->qos[i].qs_handle = info->params->qs_handle_list[i];
+		i40iw_debug(vsi->dev, I40IW_DEBUG_DCB, "qset[%d]: %d\n", i,
+			    vsi->qos[i].qs_handle);
 		spin_lock_init(&vsi->qos[i].lock);
 		INIT_LIST_HEAD(&vsi->qos[i].qplist);
 	}
@@ -4851,46 +4854,46 @@ void i40iw_vsi_stats_free(struct i40iw_sc_vsi *vsi)
 }
 
 static struct i40iw_cqp_ops iw_cqp_ops = {
-	i40iw_sc_cqp_init,
-	i40iw_sc_cqp_create,
-	i40iw_sc_cqp_post_sq,
-	i40iw_sc_cqp_get_next_send_wqe,
-	i40iw_sc_cqp_destroy,
-	i40iw_sc_poll_for_cqp_op_done
+	.cqp_init = i40iw_sc_cqp_init,
+	.cqp_create = i40iw_sc_cqp_create,
+	.cqp_post_sq = i40iw_sc_cqp_post_sq,
+	.cqp_get_next_send_wqe = i40iw_sc_cqp_get_next_send_wqe,
+	.cqp_destroy = i40iw_sc_cqp_destroy,
+	.poll_for_cqp_op_done = i40iw_sc_poll_for_cqp_op_done
 };
 
 static struct i40iw_ccq_ops iw_ccq_ops = {
-	i40iw_sc_ccq_init,
-	i40iw_sc_ccq_create,
-	i40iw_sc_ccq_destroy,
-	i40iw_sc_ccq_create_done,
-	i40iw_sc_ccq_get_cqe_info,
-	i40iw_sc_ccq_arm
+	.ccq_init = i40iw_sc_ccq_init,
+	.ccq_create = i40iw_sc_ccq_create,
+	.ccq_destroy = i40iw_sc_ccq_destroy,
+	.ccq_create_done = i40iw_sc_ccq_create_done,
+	.ccq_get_cqe_info = i40iw_sc_ccq_get_cqe_info,
+	.ccq_arm = i40iw_sc_ccq_arm
 };
 
 static struct i40iw_ceq_ops iw_ceq_ops = {
-	i40iw_sc_ceq_init,
-	i40iw_sc_ceq_create,
-	i40iw_sc_cceq_create_done,
-	i40iw_sc_cceq_destroy_done,
-	i40iw_sc_cceq_create,
-	i40iw_sc_ceq_destroy,
-	i40iw_sc_process_ceq
+	.ceq_init = i40iw_sc_ceq_init,
+	.ceq_create = i40iw_sc_ceq_create,
+	.cceq_create_done = i40iw_sc_cceq_create_done,
+	.cceq_destroy_done = i40iw_sc_cceq_destroy_done,
+	.cceq_create = i40iw_sc_cceq_create,
+	.ceq_destroy = i40iw_sc_ceq_destroy,
+	.process_ceq = i40iw_sc_process_ceq
 };
 
 static struct i40iw_aeq_ops iw_aeq_ops = {
-	i40iw_sc_aeq_init,
-	i40iw_sc_aeq_create,
-	i40iw_sc_aeq_destroy,
-	i40iw_sc_get_next_aeqe,
-	i40iw_sc_repost_aeq_entries,
-	i40iw_sc_aeq_create_done,
-	i40iw_sc_aeq_destroy_done
+	.aeq_init = i40iw_sc_aeq_init,
+	.aeq_create = i40iw_sc_aeq_create,
+	.aeq_destroy = i40iw_sc_aeq_destroy,
+	.get_next_aeqe = i40iw_sc_get_next_aeqe,
+	.repost_aeq_entries = i40iw_sc_repost_aeq_entries,
+	.aeq_create_done = i40iw_sc_aeq_create_done,
+	.aeq_destroy_done = i40iw_sc_aeq_destroy_done
 };
 
 /* iwarp pd ops */
 static struct i40iw_pd_ops iw_pd_ops = {
-	i40iw_sc_pd_init,
+	.pd_init = i40iw_sc_pd_init,
 };
 
 static struct i40iw_priv_qp_ops iw_priv_qp_ops = {
@@ -4909,53 +4912,51 @@ static struct i40iw_priv_qp_ops iw_priv_qp_ops = {
 };
 
 static struct i40iw_priv_cq_ops iw_priv_cq_ops = {
-	i40iw_sc_cq_init,
-	i40iw_sc_cq_create,
-	i40iw_sc_cq_destroy,
-	i40iw_sc_cq_modify,
+	.cq_init = i40iw_sc_cq_init,
+	.cq_create = i40iw_sc_cq_create,
+	.cq_destroy = i40iw_sc_cq_destroy,
+	.cq_modify = i40iw_sc_cq_modify,
 };
 
 static struct i40iw_mr_ops iw_mr_ops = {
-	i40iw_sc_alloc_stag,
-	i40iw_sc_mr_reg_non_shared,
-	i40iw_sc_mr_reg_shared,
-	i40iw_sc_dealloc_stag,
-	i40iw_sc_query_stag,
-	i40iw_sc_mw_alloc
+	.alloc_stag = i40iw_sc_alloc_stag,
+	.mr_reg_non_shared = i40iw_sc_mr_reg_non_shared,
+	.mr_reg_shared = i40iw_sc_mr_reg_shared,
+	.dealloc_stag = i40iw_sc_dealloc_stag,
+	.query_stag = i40iw_sc_query_stag,
+	.mw_alloc = i40iw_sc_mw_alloc
 };
 
 static struct i40iw_cqp_misc_ops iw_cqp_misc_ops = {
-	i40iw_sc_manage_push_page,
-	i40iw_sc_manage_hmc_pm_func_table,
-	i40iw_sc_set_hmc_resource_profile,
-	i40iw_sc_commit_fpm_values,
-	i40iw_sc_query_fpm_values,
-	i40iw_sc_static_hmc_pages_allocated,
-	i40iw_sc_add_arp_cache_entry,
-	i40iw_sc_del_arp_cache_entry,
-	i40iw_sc_query_arp_cache_entry,
-	i40iw_sc_manage_apbvt_entry,
-	i40iw_sc_manage_qhash_table_entry,
-	i40iw_sc_alloc_local_mac_ipaddr_entry,
-	i40iw_sc_add_local_mac_ipaddr_entry,
-	i40iw_sc_del_local_mac_ipaddr_entry,
-	i40iw_sc_cqp_nop,
-	i40iw_sc_commit_fpm_values_done,
-	i40iw_sc_query_fpm_values_done,
-	i40iw_sc_manage_hmc_pm_func_table_done,
-	i40iw_sc_suspend_qp,
-	i40iw_sc_resume_qp
+	.manage_push_page = i40iw_sc_manage_push_page,
+	.manage_hmc_pm_func_table = i40iw_sc_manage_hmc_pm_func_table,
+	.set_hmc_resource_profile = i40iw_sc_set_hmc_resource_profile,
+	.commit_fpm_values = i40iw_sc_commit_fpm_values,
+	.query_fpm_values = i40iw_sc_query_fpm_values,
+	.static_hmc_pages_allocated = i40iw_sc_static_hmc_pages_allocated,
+	.add_arp_cache_entry = i40iw_sc_add_arp_cache_entry,
+	.del_arp_cache_entry = i40iw_sc_del_arp_cache_entry,
+	.query_arp_cache_entry = i40iw_sc_query_arp_cache_entry,
+	.manage_apbvt_entry = i40iw_sc_manage_apbvt_entry,
+	.manage_qhash_table_entry = i40iw_sc_manage_qhash_table_entry,
+	.alloc_local_mac_ipaddr_table_entry = i40iw_sc_alloc_local_mac_ipaddr_entry,
+	.add_local_mac_ipaddr_entry = i40iw_sc_add_local_mac_ipaddr_entry,
+	.del_local_mac_ipaddr_entry = i40iw_sc_del_local_mac_ipaddr_entry,
+	.cqp_nop = i40iw_sc_cqp_nop,
+	.commit_fpm_values_done = i40iw_sc_commit_fpm_values_done,
+	.query_fpm_values_done = i40iw_sc_query_fpm_values_done,
+	.manage_hmc_pm_func_table_done = i40iw_sc_manage_hmc_pm_func_table_done,
+	.update_suspend_qp = i40iw_sc_suspend_qp,
+	.update_resume_qp = i40iw_sc_resume_qp
 };
 
 static struct i40iw_hmc_ops iw_hmc_ops = {
-	i40iw_sc_init_iw_hmc,
-	i40iw_sc_parse_fpm_query_buf,
-	i40iw_sc_configure_iw_fpm,
-	i40iw_sc_parse_fpm_commit_buf,
-	i40iw_sc_create_hmc_obj,
-	i40iw_sc_del_hmc_obj,
-	NULL,
-	NULL
+	.init_iw_hmc = i40iw_sc_init_iw_hmc,
+	.parse_fpm_query_buf = i40iw_sc_parse_fpm_query_buf,
+	.configure_iw_fpm = i40iw_sc_configure_iw_fpm,
+	.parse_fpm_commit_buf = i40iw_sc_parse_fpm_commit_buf,
+	.create_hmc_object = i40iw_sc_create_hmc_obj,
+	.del_hmc_object = i40iw_sc_del_hmc_obj
 };
 
 /**
diff --git a/drivers/infiniband/hw/i40iw/i40iw_uk.c b/drivers/infiniband/hw/i40iw/i40iw_uk.c
index 2800f796271c..b0d3a0e8a9b5 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_uk.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_uk.c
@@ -913,29 +913,29 @@ enum i40iw_status_code i40iw_get_wqe_shift(u32 wqdepth, u32 sge, u32 inline_data
 }
 
 static struct i40iw_qp_uk_ops iw_qp_uk_ops = {
-	i40iw_qp_post_wr,
-	i40iw_qp_ring_push_db,
-	i40iw_rdma_write,
-	i40iw_rdma_read,
-	i40iw_send,
-	i40iw_inline_rdma_write,
-	i40iw_inline_send,
-	i40iw_stag_local_invalidate,
-	i40iw_mw_bind,
-	i40iw_post_receive,
-	i40iw_nop
+	.iw_qp_post_wr = i40iw_qp_post_wr,
+	.iw_qp_ring_push_db = i40iw_qp_ring_push_db,
+	.iw_rdma_write = i40iw_rdma_write,
+	.iw_rdma_read = i40iw_rdma_read,
+	.iw_send = i40iw_send,
+	.iw_inline_rdma_write = i40iw_inline_rdma_write,
+	.iw_inline_send = i40iw_inline_send,
+	.iw_stag_local_invalidate = i40iw_stag_local_invalidate,
+	.iw_mw_bind = i40iw_mw_bind,
+	.iw_post_receive = i40iw_post_receive,
+	.iw_post_nop = i40iw_nop
 };
 
 static struct i40iw_cq_ops iw_cq_ops = {
-	i40iw_cq_request_notification,
-	i40iw_cq_poll_completion,
-	i40iw_cq_post_entries,
-	i40iw_clean_cq
+	.iw_cq_request_notification = i40iw_cq_request_notification,
+	.iw_cq_poll_completion = i40iw_cq_poll_completion,
+	.iw_cq_post_entries = i40iw_cq_post_entries,
+	.iw_cq_clean = i40iw_clean_cq
 };
 
 static struct i40iw_device_uk_ops iw_device_uk_ops = {
-	i40iw_cq_uk_init,
-	i40iw_qp_uk_init,
+	.iwarp_cq_uk_init = i40iw_cq_uk_init,
+	.iwarp_qp_uk_init = i40iw_qp_uk_init,
 };
 
 /**
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 4c000d60d5c6..9b2849979756 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -97,8 +97,7 @@ static int i40iw_query_port(struct ib_device *ibdev,
 	struct i40iw_device *iwdev = to_iwdev(ibdev);
 	struct net_device *netdev = iwdev->netdev;
 
-	memset(props, 0, sizeof(*props));
-
+	/* props being zeroed by the caller, avoid zeroing it here */
 	props->max_mtu = IB_MTU_4096;
 	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
@@ -2497,14 +2496,15 @@ static int i40iw_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
-	err = i40iw_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
 
 	return 0;
 }
@@ -2758,7 +2758,6 @@ static struct i40iw_ib_device *i40iw_init_rdma_device(struct i40iw_device *iwdev
 	    (1ull << IB_USER_VERBS_CMD_POST_SEND);
 	iwibdev->ibdev.phys_port_cnt = 1;
 	iwibdev->ibdev.num_comp_vectors = iwdev->ceqs_count;
-	iwibdev->ibdev.dma_device = &pcidev->dev;
 	iwibdev->ibdev.dev.parent = &pcidev->dev;
 	iwibdev->ibdev.query_port = i40iw_query_port;
 	iwibdev->ibdev.modify_port = i40iw_modify_port;
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index 06020c54db20..ea24230ea0d4 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -499,6 +499,7 @@ static int set_guid_rec(struct ib_device *ibdev,
 	struct list_head *head =
 		&dev->sriov.alias_guid.ports_guid[port - 1].cb_list;
 
+	memset(&attr, 0, sizeof(attr));
 	err = __mlx4_ib_query_port(ibdev, port, &attr, 1);
 	if (err) {
 		pr_debug("mlx4_ib_query_port failed (err: %d), port: %d\n",
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 7031a8dd4d14..fba94df28cf1 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -39,6 +39,9 @@
 #include <linux/inetdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/task.h>
+
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 #include <net/devlink.h>
@@ -678,7 +681,7 @@ static u8 state_to_phys_state(enum ib_port_state state)
 }
 
 static int eth_link_query_port(struct ib_device *ibdev, u8 port,
-			       struct ib_port_attr *props, int netw_view)
+			       struct ib_port_attr *props)
 {
 
 	struct mlx4_ib_dev *mdev = to_mdev(ibdev);
@@ -741,11 +744,11 @@ int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
 {
 	int err;
 
-	memset(props, 0, sizeof *props);
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	err = mlx4_ib_port_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND ?
 		ib_link_query_port(ibdev, port, props, netw_view) :
-				eth_link_query_port(ibdev, port, props, netw_view);
+				eth_link_query_port(ibdev, port, props);
 
 	return err;
 }
@@ -1014,7 +1017,7 @@ static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 
 	mutex_lock(&mdev->cap_mask_mutex);
 
-	err = mlx4_ib_query_port(ibdev, port, &attr);
+	err = ib_query_port(ibdev, port, &attr);
 	if (err)
 		goto out;
 
@@ -2537,24 +2540,27 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct mlx4_ib_dev *mdev = to_mdev(ibdev);
 	int err;
 
-	err = mlx4_ib_query_port(ibdev, port_num, &attr);
-	if (err)
-		return err;
-
-	immutable->pkey_tbl_len = attr.pkey_tbl_len;
-	immutable->gid_tbl_len = attr.gid_tbl_len;
-
 	if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND) {
 		immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+		immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 	} else {
 		if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)
 			immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2)
 			immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE |
 				RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
+		immutable->core_cap_flags |= RDMA_CORE_PORT_RAW_PACKET;
+		if (immutable->core_cap_flags & (RDMA_CORE_PORT_IBA_ROCE |
+		    RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP))
+			immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 	}
 
-	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+	err = ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
 
 	return 0;
 }
@@ -2625,7 +2631,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.phys_port_cnt     = mlx4_is_bonded(dev) ?
 						1 : ibdev->num_ports;
 	ibdev->ib_dev.num_comp_vectors	= dev->caps.num_comp_vectors;
-	ibdev->ib_dev.dma_device	= &dev->persist->pdev->dev;
+	ibdev->ib_dev.dev.parent	= &dev->persist->pdev->dev;
 	ibdev->ib_dev.get_netdev	= mlx4_ib_get_netdev;
 	ibdev->ib_dev.add_gid		= mlx4_ib_add_gid;
 	ibdev->ib_dev.del_gid		= mlx4_ib_del_gid;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 7f3d976d81ed..64fed44b43a6 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -55,7 +55,7 @@
 #define pr_fmt(fmt)	"<" MLX4_IB_DRV_NAME "> %s: " fmt, __func__
 
 #define mlx4_ib_warn(ibdev, format, arg...) \
-	dev_warn((ibdev)->dma_device, MLX4_IB_DRV_NAME ": " format, ## arg)
+	dev_warn((ibdev)->dev.parent, MLX4_IB_DRV_NAME ": " format, ## arg)
 
 enum {
 	MLX4_IB_SQ_MIN_WQE_SHIFT = 6,
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 5d73989d9771..433bcdbdd680 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -292,10 +292,10 @@ mlx4_alloc_priv_pages(struct ib_device *device,
 	if (!mr->pages)
 		return -ENOMEM;
 
-	mr->page_map = dma_map_single(device->dma_device, mr->pages,
+	mr->page_map = dma_map_single(device->dev.parent, mr->pages,
 				      mr->page_map_size, DMA_TO_DEVICE);
 
-	if (dma_mapping_error(device->dma_device, mr->page_map)) {
+	if (dma_mapping_error(device->dev.parent, mr->page_map)) {
 		ret = -ENOMEM;
 		goto err;
 	}
@@ -313,7 +313,7 @@ mlx4_free_priv_pages(struct mlx4_ib_mr *mr)
 	if (mr->pages) {
 		struct ib_device *device = mr->ibmr.device;
 
-		dma_unmap_single(device->dma_device, mr->page_map,
+		dma_unmap_single(device->dev.parent, mr->page_map,
 				 mr->page_map_size, DMA_TO_DEVICE);
 		free_page((unsigned long)mr->pages);
 		mr->pages = NULL;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index c068add8838b..c34eebc7db65 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -76,10 +76,6 @@ enum {
 	MLX4_IB_LSO_HEADER_SPARE	= 128,
 };
 
-enum {
-	MLX4_IB_IBOE_ETHERTYPE		= 0x8915
-};
-
 struct mlx4_ib_sqp {
 	struct mlx4_ib_qp	qp;
 	int			pkey_index;
@@ -2424,11 +2420,31 @@ static u8 sl_to_vl(struct mlx4_ib_dev *dev, u8 sl, int port_num)
 	return vl;
 }
 
+static int fill_gid_by_hw_index(struct mlx4_ib_dev *ibdev, u8 port_num,
+				int index, union ib_gid *gid,
+				enum ib_gid_type *gid_type)
+{
+	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
+	struct mlx4_port_gid_table *port_gid_table;
+	unsigned long flags;
+
+	port_gid_table = &iboe->gids[port_num - 1];
+	spin_lock_irqsave(&iboe->lock, flags);
+	memcpy(gid, &port_gid_table->gids[index].gid, sizeof(*gid));
+	*gid_type = port_gid_table->gids[index].gid_type;
+	spin_unlock_irqrestore(&iboe->lock, flags);
+	if (!memcmp(gid, &zgid, sizeof(*gid)))
+		return -ENOENT;
+
+	return 0;
+}
+
 #define MLX4_ROCEV2_QP1_SPORT 0xC000
 static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
 			    void *wqe, unsigned *mlx_seg_len)
 {
 	struct ib_device *ib_dev = sqp->qp.ibqp.device;
+	struct mlx4_ib_dev *ibdev = to_mdev(ib_dev);
 	struct mlx4_wqe_mlx_seg *mlx = wqe;
 	struct mlx4_wqe_ctrl_seg *ctrl = wqe;
 	struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
@@ -2454,8 +2470,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
 	is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET;
 	is_grh = mlx4_ib_ah_grh_present(ah);
 	if (is_eth) {
-		struct ib_gid_attr gid_attr;
-
+		enum ib_gid_type gid_type;
 		if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
 			/* When multi-function is enabled, the ib_core gid
 			 * indexes don't necessarily match the hw ones, so
@@ -2466,18 +2481,11 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
 			if (err)
 				return err;
 		} else  {
-			err = ib_get_cached_gid(ib_dev,
-						be32_to_cpu(ah->av.ib.port_pd) >> 24,
-						ah->av.ib.gid_index, &sgid,
-						&gid_attr);
-			if (!err) {
-				if (gid_attr.ndev)
-					dev_put(gid_attr.ndev);
-				if (!memcmp(&sgid, &zgid, sizeof(sgid)))
-					err = -ENOENT;
-			}
+			err = fill_gid_by_hw_index(ibdev, sqp->qp.port,
+					    ah->av.ib.gid_index,
+					    &sgid, &gid_type);
 			if (!err) {
-				is_udp = gid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP;
+				is_udp = gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP;
 				if (is_udp) {
 					if (ipv6_addr_v4mapped((struct in6_addr *)&sgid))
 						ip_version = 4;
@@ -2588,7 +2596,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
 		u16 ether_type;
 		u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13;
 
-		ether_type = (!is_udp) ? MLX4_IB_IBOE_ETHERTYPE :
+		ether_type = (!is_udp) ? ETH_P_IBOE:
 			(ip_version == 4 ? ETH_P_IP : ETH_P_IPV6);
 
 		mlx->sched_prio = cpu_to_be16(pcp);
@@ -2955,21 +2963,17 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 
 		if (sqp->roce_v2_gsi) {
 			struct mlx4_ib_ah *ah = to_mah(ud_wr(wr)->ah);
-			struct ib_gid_attr gid_attr;
+			enum ib_gid_type gid_type;
 			union ib_gid gid;
 
-			if (!ib_get_cached_gid(ibqp->device,
-					       be32_to_cpu(ah->av.ib.port_pd) >> 24,
-					       ah->av.ib.gid_index, &gid,
-					       &gid_attr)) {
-				if (gid_attr.ndev)
-					dev_put(gid_attr.ndev);
-				qp = (gid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ?
-					to_mqp(sqp->roce_v2_gsi) : qp;
-			} else {
+			if (!fill_gid_by_hw_index(mdev, sqp->qp.port,
+					   ah->av.ib.gid_index,
+					   &gid, &gid_type))
+				qp = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ?
+						to_mqp(sqp->roce_v2_gsi) : qp;
+			else
 				pr_err("Failed to get gid at index %d. RoCEv2 will not work properly\n",
 				       ah->av.ib.gid_index);
-			}
 		}
 	}
 
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index 69fb5ba94d0f..0ba5ba7540c8 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -226,6 +226,7 @@ static int add_port_entries(struct mlx4_ib_dev *device, int port_num)
 	int ret = 0 ;
 	struct ib_port_attr attr;
 
+	memset(&attr, 0, sizeof(attr));
 	/* get the physical gid and pkey table sizes.*/
 	ret = __mlx4_ib_query_port(&device->ib_dev, port_num, &attr, 1);
 	if (ret)
diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile
index 7493a83acd28..90ad2adc752f 100644
--- a/drivers/infiniband/hw/mlx5/Makefile
+++ b/drivers/infiniband/hw/mlx5/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_MLX5_INFINIBAND)	+= mlx5_ib.o
 
-mlx5_ib-y :=	main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o
+mlx5_ib-y :=	main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o
 mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o
diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
new file mode 100644
index 000000000000..cdc2d3017da7
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -0,0 +1,48 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "cmd.h"
+
+int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey)
+{
+	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)]   = {};
+	int err;
+
+	MLX5_SET(query_special_contexts_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (!err)
+		*null_mkey = MLX5_GET(query_special_contexts_out, out,
+				      null_mkey);
+	return err;
+}
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
new file mode 100644
index 000000000000..7ca8a7b6434d
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef MLX5_IB_CMD_H
+#define MLX5_IB_CMD_H
+
+#include <linux/kernel.h>
+#include <linux/mlx5/driver.h>
+
+int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey);
+#endif /* MLX5_IB_CMD_H */
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index b3ef47c3ab73..31803b367104 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -689,7 +689,7 @@ int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 {
 	struct mlx5_core_dev *mdev = to_mdev(ibcq->device)->mdev;
 	struct mlx5_ib_cq *cq = to_mcq(ibcq);
-	void __iomem *uar_page = mdev->priv.uuari.uars[0].map;
+	void __iomem *uar_page = mdev->priv.uar->map;
 	unsigned long irq_flags;
 	int ret = 0;
 
@@ -704,9 +704,7 @@ int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 	mlx5_cq_arm(&cq->mcq,
 		    (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
 		    MLX5_CQ_DB_REQ_NOT_SOL : MLX5_CQ_DB_REQ_NOT,
-		    uar_page,
-		    MLX5_GET_DOORBELL_LOCK(&mdev->priv.cq_uar_lock),
-		    to_mcq(ibcq)->mcq.cons_index);
+		    uar_page, to_mcq(ibcq)->mcq.cons_index);
 
 	return ret;
 }
@@ -790,7 +788,7 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	MLX5_SET(cqc, cqc, log_page_size,
 		 page_shift - MLX5_ADAPTER_PAGE_SHIFT);
 
-	*index = to_mucontext(context)->uuari.uars[0].index;
+	*index = to_mucontext(context)->bfregi.sys_pages[0];
 
 	if (ucmd.cqe_comp_en == 1) {
 		if (unlikely((*cqe_size != 64) ||
@@ -886,7 +884,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 	MLX5_SET(cqc, cqc, log_page_size,
 		 cq->buf.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
 
-	*index = dev->mdev->priv.uuari.uars[0].index;
+	*index = dev->mdev->priv.uar->index;
 
 	return 0;
 
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 39e58489dcc2..8dacb49eabd9 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -42,12 +42,24 @@ enum {
 	MLX5_IB_VENDOR_CLASS2 = 0xa
 };
 
+static bool can_do_mad_ifc(struct mlx5_ib_dev *dev, u8 port_num,
+			   struct ib_mad *in_mad)
+{
+	if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED &&
+	    in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+		return true;
+	return dev->mdev->port_caps[port_num - 1].has_smi;
+}
+
 int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
 		 u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
 		 const void *in_mad, void *response_mad)
 {
 	u8 op_modifier = 0;
 
+	if (!can_do_mad_ifc(dev, port, (struct ib_mad *)in_mad))
+		return -EPERM;
+
 	/* Key check traps can't be generated unless we have in_wc to
 	 * tell us where to send the trap.
 	 */
@@ -515,7 +527,7 @@ int mlx5_query_mad_ifc_port(struct ib_device *ibdev, u8 port,
 	if (!in_mad || !out_mad)
 		goto out;
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	init_query_mad(in_mad);
 	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d566f6738833..4dc0a8785fe0 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -41,6 +41,8 @@
 #include <asm/pat.h>
 #endif
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/task.h>
 #include <linux/delay.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_addr.h>
@@ -53,6 +55,7 @@
 #include <linux/in.h>
 #include <linux/etherdevice.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/vport.h>
 #include "mlx5_ib.h"
 
 #define DRIVER_NAME "mlx5_ib"
@@ -64,10 +67,6 @@ MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_VERSION(DRIVER_VERSION);
 
-static int deprecated_prof_sel = 2;
-module_param_named(prof_sel, deprecated_prof_sel, int, 0444);
-MODULE_PARM_DESC(prof_sel, "profile selector. Deprecated here. Moved to module mlx5_core");
-
 static char mlx5_version[] =
 	DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v"
 	DRIVER_VERSION " (" DRIVER_RELDATE ")\n";
@@ -174,7 +173,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	enum ib_mtu ndev_ib_mtu;
 	u16 qkey_viol_cntr;
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->port_cap_flags  |= IB_PORT_CM_SUP;
 	props->port_cap_flags  |= IB_PORT_IP_BASED_GIDS;
@@ -325,6 +324,27 @@ __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
 	return cpu_to_be16(MLX5_CAP_ROCE(dev->mdev, r_roce_min_src_udp_port));
 }
 
+int mlx5_get_roce_gid_type(struct mlx5_ib_dev *dev, u8 port_num,
+			   int index, enum ib_gid_type *gid_type)
+{
+	struct ib_gid_attr attr;
+	union ib_gid gid;
+	int ret;
+
+	ret = ib_get_cached_gid(&dev->ib_dev, port_num, index, &gid, &attr);
+	if (ret)
+		return ret;
+
+	if (!attr.ndev)
+		return -ENODEV;
+
+	dev_put(attr.ndev);
+
+	*gid_type = attr.gid_type;
+
+	return 0;
+}
+
 static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_IB)
@@ -564,8 +584,15 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
 
 	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads)) {
-		if (MLX5_CAP_ETH(mdev, csum_cap))
+		if (MLX5_CAP_ETH(mdev, csum_cap)) {
+			/* Legacy bit to support old userspace libraries */
 			props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
+			props->raw_packet_caps |= IB_RAW_PACKET_CAP_IP_CSUM;
+		}
+
+		if (MLX5_CAP_ETH(dev->mdev, vlan_cap))
+			props->raw_packet_caps |=
+				IB_RAW_PACKET_CAP_CVLAN_STRIPPING;
 
 		if (field_avail(typeof(resp), tso_caps, uhw->outlen)) {
 			max_tso = MLX5_CAP_ETH(mdev, max_lso_cap);
@@ -604,8 +631,11 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	}
 
 	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
-	    MLX5_CAP_ETH(dev->mdev, scatter_fcs))
+	    MLX5_CAP_ETH(dev->mdev, scatter_fcs)) {
+		/* Legacy bit to support old userspace libraries */
 		props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS;
+		props->raw_packet_caps |= IB_RAW_PACKET_CAP_SCATTER_FCS;
+	}
 
 	if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS))
 		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
@@ -672,17 +702,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			1 << MLX5_CAP_GEN(dev->mdev, log_max_rq);
 	}
 
-	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
-			uhw->outlen)) {
-		resp.mlx5_ib_support_multi_pkt_send_wqes =
-			MLX5_CAP_ETH(mdev, multi_pkt_send_wqe);
-		resp.response_length +=
-			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
-	}
-
-	if (field_avail(typeof(resp), reserved, uhw->outlen))
-		resp.response_length += sizeof(resp.reserved);
-
 	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
 		resp.cqe_comp_caps.max_num =
 			MLX5_CAP_GEN(dev->mdev, cqe_compression) ?
@@ -706,6 +725,17 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.packet_pacing_caps);
 	}
 
+	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
+			uhw->outlen)) {
+		resp.mlx5_ib_support_multi_pkt_send_wqes =
+			MLX5_CAP_ETH(mdev, multi_pkt_send_wqe);
+		resp.response_length +=
+			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
+	}
+
+	if (field_avail(typeof(resp), reserved, uhw->outlen))
+		resp.response_length += sizeof(resp.reserved);
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
@@ -830,7 +860,7 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 		goto out;
 	}
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	err = mlx5_query_hca_vport_context(mdev, 0, port, 0, rep);
 	if (err)
@@ -968,6 +998,31 @@ static int mlx5_ib_modify_device(struct ib_device *ibdev, int mask,
 	return err;
 }
 
+static int set_port_caps_atomic(struct mlx5_ib_dev *dev, u8 port_num, u32 mask,
+				u32 value)
+{
+	struct mlx5_hca_vport_context ctx = {};
+	int err;
+
+	err = mlx5_query_hca_vport_context(dev->mdev, 0,
+					   port_num, 0, &ctx);
+	if (err)
+		return err;
+
+	if (~ctx.cap_mask1_perm & mask) {
+		mlx5_ib_warn(dev, "trying to change bitmask 0x%X but change supported 0x%X\n",
+			     mask, ctx.cap_mask1_perm);
+		return -EINVAL;
+	}
+
+	ctx.cap_mask1 = value;
+	ctx.cap_mask1_perm = mask;
+	err = mlx5_core_modify_hca_vport_context(dev->mdev, 0,
+						 port_num, 0, &ctx);
+
+	return err;
+}
+
 static int mlx5_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 			       struct ib_port_modify *props)
 {
@@ -975,10 +1030,20 @@ static int mlx5_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 	struct ib_port_attr attr;
 	u32 tmp;
 	int err;
+	u32 change_mask;
+	u32 value;
+	bool is_ib = (mlx5_ib_port_link_layer(ibdev, port) ==
+		      IB_LINK_LAYER_INFINIBAND);
+
+	if (MLX5_CAP_GEN(dev->mdev, ib_virt) && is_ib) {
+		change_mask = props->clr_port_cap_mask | props->set_port_cap_mask;
+		value = ~props->clr_port_cap_mask | props->set_port_cap_mask;
+		return set_port_caps_atomic(dev, port, change_mask, value);
+	}
 
 	mutex_lock(&dev->cap_mask_mutex);
 
-	err = mlx5_ib_query_port(ibdev, port, &attr);
+	err = ib_query_port(ibdev, port, &attr);
 	if (err)
 		goto out;
 
@@ -992,6 +1057,86 @@ out:
 	return err;
 }
 
+static void print_lib_caps(struct mlx5_ib_dev *dev, u64 caps)
+{
+	mlx5_ib_dbg(dev, "MLX5_LIB_CAP_4K_UAR = %s\n",
+		    caps & MLX5_LIB_CAP_4K_UAR ? "y" : "n");
+}
+
+static int calc_total_bfregs(struct mlx5_ib_dev *dev, bool lib_uar_4k,
+			     struct mlx5_ib_alloc_ucontext_req_v2 *req,
+			     u32 *num_sys_pages)
+{
+	int uars_per_sys_page;
+	int bfregs_per_sys_page;
+	int ref_bfregs = req->total_num_bfregs;
+
+	if (req->total_num_bfregs == 0)
+		return -EINVAL;
+
+	BUILD_BUG_ON(MLX5_MAX_BFREGS % MLX5_NON_FP_BFREGS_IN_PAGE);
+	BUILD_BUG_ON(MLX5_MAX_BFREGS < MLX5_NON_FP_BFREGS_IN_PAGE);
+
+	if (req->total_num_bfregs > MLX5_MAX_BFREGS)
+		return -ENOMEM;
+
+	uars_per_sys_page = get_uars_per_sys_page(dev, lib_uar_4k);
+	bfregs_per_sys_page = uars_per_sys_page * MLX5_NON_FP_BFREGS_PER_UAR;
+	req->total_num_bfregs = ALIGN(req->total_num_bfregs, bfregs_per_sys_page);
+	*num_sys_pages = req->total_num_bfregs / bfregs_per_sys_page;
+
+	if (req->num_low_latency_bfregs > req->total_num_bfregs - 1)
+		return -EINVAL;
+
+	mlx5_ib_dbg(dev, "uar_4k: fw support %s, lib support %s, user requested %d bfregs, alloated %d, using %d sys pages\n",
+		    MLX5_CAP_GEN(dev->mdev, uar_4k) ? "yes" : "no",
+		    lib_uar_4k ? "yes" : "no", ref_bfregs,
+		    req->total_num_bfregs, *num_sys_pages);
+
+	return 0;
+}
+
+static int allocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *context)
+{
+	struct mlx5_bfreg_info *bfregi;
+	int err;
+	int i;
+
+	bfregi = &context->bfregi;
+	for (i = 0; i < bfregi->num_sys_pages; i++) {
+		err = mlx5_cmd_alloc_uar(dev->mdev, &bfregi->sys_pages[i]);
+		if (err)
+			goto error;
+
+		mlx5_ib_dbg(dev, "allocated uar %d\n", bfregi->sys_pages[i]);
+	}
+	return 0;
+
+error:
+	for (--i; i >= 0; i--)
+		if (mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]))
+			mlx5_ib_warn(dev, "failed to free uar %d\n", i);
+
+	return err;
+}
+
+static int deallocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *context)
+{
+	struct mlx5_bfreg_info *bfregi;
+	int err;
+	int i;
+
+	bfregi = &context->bfregi;
+	for (i = 0; i < bfregi->num_sys_pages; i++) {
+		err = mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]);
+		if (err) {
+			mlx5_ib_warn(dev, "failed to free uar %d\n", i);
+			return err;
+		}
+	}
+	return 0;
+}
+
 static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 						  struct ib_udata *udata)
 {
@@ -999,17 +1144,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_ib_alloc_ucontext_req_v2 req = {};
 	struct mlx5_ib_alloc_ucontext_resp resp = {};
 	struct mlx5_ib_ucontext *context;
-	struct mlx5_uuar_info *uuari;
-	struct mlx5_uar *uars;
-	int gross_uuars;
-	int num_uars;
+	struct mlx5_bfreg_info *bfregi;
 	int ver;
-	int uuarn;
 	int err;
-	int i;
 	size_t reqlen;
 	size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
 				     max_cqe_version);
+	bool lib_uar_4k;
 
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
@@ -1032,27 +1173,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (req.flags)
 		return ERR_PTR(-EINVAL);
 
-	if (req.total_num_uuars > MLX5_MAX_UUARS)
-		return ERR_PTR(-ENOMEM);
-
-	if (req.total_num_uuars == 0)
-		return ERR_PTR(-EINVAL);
-
 	if (req.comp_mask || req.reserved0 || req.reserved1 || req.reserved2)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	if (reqlen > sizeof(req) &&
-	    !ib_is_udata_cleared(udata, sizeof(req),
-				 reqlen - sizeof(req)))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	req.total_num_uuars = ALIGN(req.total_num_uuars,
-				    MLX5_NON_FP_BF_REGS_PER_PAGE);
-	if (req.num_low_latency_uuars > req.total_num_uuars - 1)
+	req.total_num_bfregs = ALIGN(req.total_num_bfregs,
+				    MLX5_NON_FP_BFREGS_PER_UAR);
+	if (req.num_low_latency_bfregs > req.total_num_bfregs - 1)
 		return ERR_PTR(-EINVAL);
 
-	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
-	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
 	resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
 	if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
 		resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
@@ -1065,6 +1193,10 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	resp.cqe_version = min_t(__u8,
 				 (__u8)MLX5_CAP_GEN(dev->mdev, cqe_version),
 				 req.max_cqe_version);
+	resp.log_uar_size = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+				MLX5_ADAPTER_PAGE_SHIFT : PAGE_SHIFT;
+	resp.num_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+					MLX5_CAP_GEN(dev->mdev, num_of_uars_per_page) : 1;
 	resp.response_length = min(offsetof(typeof(resp), response_length) +
 				   sizeof(resp.response_length), udata->outlen);
 
@@ -1072,58 +1204,58 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (!context)
 		return ERR_PTR(-ENOMEM);
 
-	uuari = &context->uuari;
-	mutex_init(&uuari->lock);
-	uars = kcalloc(num_uars, sizeof(*uars), GFP_KERNEL);
-	if (!uars) {
-		err = -ENOMEM;
+	lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR;
+	bfregi = &context->bfregi;
+
+	/* updates req->total_num_bfregs */
+	err = calc_total_bfregs(dev, lib_uar_4k, &req, &bfregi->num_sys_pages);
+	if (err)
 		goto out_ctx;
-	}
 
-	uuari->bitmap = kcalloc(BITS_TO_LONGS(gross_uuars),
-				sizeof(*uuari->bitmap),
+	mutex_init(&bfregi->lock);
+	bfregi->lib_uar_4k = lib_uar_4k;
+	bfregi->count = kcalloc(req.total_num_bfregs, sizeof(*bfregi->count),
 				GFP_KERNEL);
-	if (!uuari->bitmap) {
+	if (!bfregi->count) {
 		err = -ENOMEM;
-		goto out_uar_ctx;
-	}
-	/*
-	 * clear all fast path uuars
-	 */
-	for (i = 0; i < gross_uuars; i++) {
-		uuarn = i & 3;
-		if (uuarn == 2 || uuarn == 3)
-			set_bit(i, uuari->bitmap);
+		goto out_ctx;
 	}
 
-	uuari->count = kcalloc(gross_uuars, sizeof(*uuari->count), GFP_KERNEL);
-	if (!uuari->count) {
+	bfregi->sys_pages = kcalloc(bfregi->num_sys_pages,
+				    sizeof(*bfregi->sys_pages),
+				    GFP_KERNEL);
+	if (!bfregi->sys_pages) {
 		err = -ENOMEM;
-		goto out_bitmap;
+		goto out_count;
 	}
 
-	for (i = 0; i < num_uars; i++) {
-		err = mlx5_cmd_alloc_uar(dev->mdev, &uars[i].index);
-		if (err)
-			goto out_count;
-	}
+	err = allocate_uars(dev, context);
+	if (err)
+		goto out_sys_pages;
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range;
 #endif
 
+	context->upd_xlt_page = __get_free_page(GFP_KERNEL);
+	if (!context->upd_xlt_page) {
+		err = -ENOMEM;
+		goto out_uars;
+	}
+	mutex_init(&context->upd_xlt_page_mutex);
+
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) {
 		err = mlx5_core_alloc_transport_domain(dev->mdev,
 						       &context->tdn);
 		if (err)
-			goto out_uars;
+			goto out_page;
 	}
 
 	INIT_LIST_HEAD(&context->vma_private_list);
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
 
-	resp.tot_uuars = req.total_num_uuars;
+	resp.tot_bfregs = req.total_num_bfregs;
 	resp.num_ports = MLX5_CAP_GEN(dev->mdev, num_ports);
 
 	if (field_avail(typeof(resp), cqe_version, udata->outlen))
@@ -1135,32 +1267,46 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.cmds_supp_uhw);
 	}
 
+	if (field_avail(typeof(resp), eth_min_inline, udata->outlen)) {
+		if (mlx5_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET) {
+			mlx5_query_min_inline(dev->mdev, &resp.eth_min_inline);
+			resp.eth_min_inline++;
+		}
+		resp.response_length += sizeof(resp.eth_min_inline);
+	}
+
 	/*
 	 * We don't want to expose information from the PCI bar that is located
 	 * after 4096 bytes, so if the arch only supports larger pages, let's
 	 * pretend we don't support reading the HCA's core clock. This is also
 	 * forced by mmap function.
 	 */
-	if (PAGE_SIZE <= 4096 &&
-	    field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
-		resp.comp_mask |=
-			MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
-		resp.hca_core_clock_offset =
-			offsetof(struct mlx5_init_seg, internal_timer_h) %
-			PAGE_SIZE;
+	if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
+		if (PAGE_SIZE <= 4096) {
+			resp.comp_mask |=
+				MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
+			resp.hca_core_clock_offset =
+				offsetof(struct mlx5_init_seg, internal_timer_h) % PAGE_SIZE;
+		}
 		resp.response_length += sizeof(resp.hca_core_clock_offset) +
 					sizeof(resp.reserved2);
 	}
 
+	if (field_avail(typeof(resp), log_uar_size, udata->outlen))
+		resp.response_length += sizeof(resp.log_uar_size);
+
+	if (field_avail(typeof(resp), num_uars_per_page, udata->outlen))
+		resp.response_length += sizeof(resp.num_uars_per_page);
+
 	err = ib_copy_to_udata(udata, &resp, resp.response_length);
 	if (err)
 		goto out_td;
 
-	uuari->ver = ver;
-	uuari->num_low_latency_uuars = req.num_low_latency_uuars;
-	uuari->uars = uars;
-	uuari->num_uars = num_uars;
+	bfregi->ver = ver;
+	bfregi->num_low_latency_bfregs = req.num_low_latency_bfregs;
 	context->cqe_version = resp.cqe_version;
+	context->lib_caps = req.lib_caps;
+	print_lib_caps(dev, context->lib_caps);
 
 	return &context->ibucontext;
 
@@ -1168,20 +1314,21 @@ out_td:
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
 		mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
 
+out_page:
+	free_page(context->upd_xlt_page);
+
 out_uars:
-	for (i--; i >= 0; i--)
-		mlx5_cmd_free_uar(dev->mdev, uars[i].index);
-out_count:
-	kfree(uuari->count);
+	deallocate_uars(dev, context);
 
-out_bitmap:
-	kfree(uuari->bitmap);
+out_sys_pages:
+	kfree(bfregi->sys_pages);
 
-out_uar_ctx:
-	kfree(uars);
+out_count:
+	kfree(bfregi->count);
 
 out_ctx:
 	kfree(context);
+
 	return ERR_PTR(err);
 }
 
@@ -1189,28 +1336,31 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
 {
 	struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
 	struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);
-	struct mlx5_uuar_info *uuari = &context->uuari;
-	int i;
+	struct mlx5_bfreg_info *bfregi;
 
+	bfregi = &context->bfregi;
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
 		mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
 
-	for (i = 0; i < uuari->num_uars; i++) {
-		if (mlx5_cmd_free_uar(dev->mdev, uuari->uars[i].index))
-			mlx5_ib_warn(dev, "failed to free UAR 0x%x\n", uuari->uars[i].index);
-	}
-
-	kfree(uuari->count);
-	kfree(uuari->bitmap);
-	kfree(uuari->uars);
+	free_page(context->upd_xlt_page);
+	deallocate_uars(dev, context);
+	kfree(bfregi->sys_pages);
+	kfree(bfregi->count);
 	kfree(context);
 
 	return 0;
 }
 
-static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev, int index)
+static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,
+				 struct mlx5_bfreg_info *bfregi,
+				 int idx)
 {
-	return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) + index;
+	int fw_uars_per_page;
+
+	fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ? MLX5_UARS_IN_PAGE : 1;
+
+	return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) +
+			bfregi->sys_pages[idx] / fw_uars_per_page;
 }
 
 static int get_command(unsigned long offset)
@@ -1365,11 +1515,23 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 		    struct vm_area_struct *vma,
 		    struct mlx5_ib_ucontext *context)
 {
-	struct mlx5_uuar_info *uuari = &context->uuari;
+	struct mlx5_bfreg_info *bfregi = &context->bfregi;
 	int err;
 	unsigned long idx;
 	phys_addr_t pfn, pa;
 	pgprot_t prot;
+	int uars_per_page;
+
+	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+		return -EINVAL;
+
+	uars_per_page = get_uars_per_sys_page(dev, bfregi->lib_uar_4k);
+	idx = get_index(vma->vm_pgoff);
+	if (idx % uars_per_page ||
+	    idx * uars_per_page >= bfregi->num_sys_pages) {
+		mlx5_ib_warn(dev, "invalid uar index %lu\n", idx);
+		return -EINVAL;
+	}
 
 	switch (cmd) {
 	case MLX5_IB_MMAP_WC_PAGE:
@@ -1392,14 +1554,7 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 		return -EINVAL;
 	}
 
-	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
-		return -EINVAL;
-
-	idx = get_index(vma->vm_pgoff);
-	if (idx >= uuari->num_uars)
-		return -EINVAL;
-
-	pfn = uar_index2pfn(dev, uuari->uars[idx].index);
+	pfn = uar_index2pfn(dev, bfregi, idx);
 	mlx5_ib_dbg(dev, "uar idx 0x%lx, pfn %pa\n", idx, &pfn);
 
 	vma->vm_page_prot = prot;
@@ -1570,6 +1725,7 @@ static void set_tos(void *outer_c, void *outer_v, u8 mask, u8 val)
 #define LAST_IPV6_FIELD traffic_class
 #define LAST_TCP_UDP_FIELD src_port
 #define LAST_TUNNEL_FIELD tunnel_id
+#define LAST_FLOW_TAG_FIELD tag_id
 
 /* Field is the last supported field */
 #define FIELDS_NOT_SUPPORTED(filter, field)\
@@ -1580,7 +1736,7 @@ static void set_tos(void *outer_c, void *outer_v, u8 mask, u8 val)
 		   sizeof(filter.field))
 
 static int parse_flow_attr(u32 *match_c, u32 *match_v,
-			   const union ib_flow_spec *ib_spec)
+			   const union ib_flow_spec *ib_spec, u32 *tag_id)
 {
 	void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c,
 					   misc_parameters);
@@ -1604,7 +1760,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	switch (ib_spec->type & ~IB_FLOW_SPEC_INNER) {
 	case IB_FLOW_SPEC_ETH:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->eth.mask, LAST_ETH_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 					     dmac_47_16),
@@ -1622,9 +1778,9 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 
 		if (ib_spec->eth.mask.vlan_tag) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 vlan_tag, 1);
+				 cvlan_tag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 vlan_tag, 1);
+				 cvlan_tag, 1);
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 				 first_vid, ntohs(ib_spec->eth.mask.vlan_tag));
@@ -1652,7 +1808,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 		break;
 	case IB_FLOW_SPEC_IPV4:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->ipv4.mask, LAST_IPV4_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 ethertype, 0xffff);
@@ -1684,7 +1840,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 		break;
 	case IB_FLOW_SPEC_IPV6:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->ipv6.mask, LAST_IPV6_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 ethertype, 0xffff);
@@ -1725,7 +1881,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	case IB_FLOW_SPEC_TCP:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
 					 LAST_TCP_UDP_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
 			 0xff);
@@ -1745,7 +1901,7 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	case IB_FLOW_SPEC_UDP:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
 					 LAST_TCP_UDP_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
 			 0xff);
@@ -1765,13 +1921,22 @@ static int parse_flow_attr(u32 *match_c, u32 *match_v,
 	case IB_FLOW_SPEC_VXLAN_TUNNEL:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->tunnel.mask,
 					 LAST_TUNNEL_FIELD))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		MLX5_SET(fte_match_set_misc, misc_params_c, vxlan_vni,
 			 ntohl(ib_spec->tunnel.mask.tunnel_id));
 		MLX5_SET(fte_match_set_misc, misc_params_v, vxlan_vni,
 			 ntohl(ib_spec->tunnel.val.tunnel_id));
 		break;
+	case IB_FLOW_SPEC_ACTION_TAG:
+		if (FIELDS_NOT_SUPPORTED(ib_spec->flow_tag,
+					 LAST_FLOW_TAG_FIELD))
+			return -EOPNOTSUPP;
+		if (ib_spec->flow_tag.tag_id >= BIT(24))
+			return -EINVAL;
+
+		*tag_id = ib_spec->flow_tag.tag_id;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1955,6 +2120,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	struct mlx5_flow_spec *spec;
 	const void *ib_flow = (const void *)flow_attr + sizeof(*flow_attr);
 	unsigned int spec_index;
+	u32 flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 	int err = 0;
 
 	if (!is_valid_attr(flow_attr))
@@ -1971,7 +2137,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 
 	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
 		err = parse_flow_attr(spec->match_criteria,
-				      spec->match_value, ib_flow);
+				      spec->match_value, ib_flow, &flow_tag);
 		if (err < 0)
 			goto free;
 
@@ -1981,7 +2147,16 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
 	flow_act.action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
 		MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
-	flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+
+	if (flow_tag != MLX5_FS_DEFAULT_FLOW_TAG &&
+	    (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
+	     flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
+		mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n",
+			     flow_tag, flow_attr->type);
+		err = -EINVAL;
+		goto free;
+	}
+	flow_act.flow_tag = flow_tag;
 	handler->rule = mlx5_add_flow_rules(ft, spec,
 					    &flow_act,
 					    dst, 1);
@@ -2451,6 +2626,35 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 		ibdev->ib_active = false;
 }
 
+static int set_has_smi_cap(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_hca_vport_context vport_ctx;
+	int err;
+	int port;
+
+	for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++) {
+		dev->mdev->port_caps[port - 1].has_smi = false;
+		if (MLX5_CAP_GEN(dev->mdev, port_type) ==
+		    MLX5_CAP_PORT_TYPE_IB) {
+			if (MLX5_CAP_GEN(dev->mdev, ib_virt)) {
+				err = mlx5_query_hca_vport_context(dev->mdev, 0,
+								   port, 0,
+								   &vport_ctx);
+				if (err) {
+					mlx5_ib_err(dev, "query_hca_vport_context for port=%d failed %d\n",
+						    port, err);
+					return err;
+				}
+				dev->mdev->port_caps[port - 1].has_smi =
+					vport_ctx.has_smi;
+			} else {
+				dev->mdev->port_caps[port - 1].has_smi = true;
+			}
+		}
+	}
+	return 0;
+}
+
 static void get_ext_port_caps(struct mlx5_ib_dev *dev)
 {
 	int port;
@@ -2475,6 +2679,10 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	if (!dprops)
 		goto out;
 
+	err = set_has_smi_cap(dev);
+	if (err)
+		goto out;
+
 	err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
 	if (err) {
 		mlx5_ib_warn(dev, "query_device failed %d\n", err);
@@ -2482,6 +2690,7 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	}
 
 	for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++) {
+		memset(pprops, 0, sizeof(*pprops));
 		err = mlx5_ib_query_port(&dev->ib_dev, port, pprops);
 		if (err) {
 			mlx5_ib_warn(dev, "query_port %d failed %d\n",
@@ -2776,11 +2985,13 @@ static u32 get_core_cap_flags(struct ib_device *ibdev)
 	if (ll == IB_LINK_LAYER_INFINIBAND)
 		return RDMA_CORE_PORT_IBA_IB;
 
+	ret = RDMA_CORE_PORT_RAW_PACKET;
+
 	if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV4_CAP))
-		return 0;
+		return ret;
 
 	if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV6_CAP))
-		return 0;
+		return ret;
 
 	if (roce_version_cap & MLX5_ROCE_VERSION_1_CAP)
 		ret |= RDMA_CORE_PORT_IBA_ROCE;
@@ -2799,7 +3010,9 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
 	enum rdma_link_layer ll = mlx5_ib_port_link_layer(ibdev, port_num);
 	int err;
 
-	err = mlx5_ib_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = get_core_cap_flags(ibdev);
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
@@ -2920,13 +3133,102 @@ static void mlx5_disable_eth(struct mlx5_ib_dev *dev)
 		mlx5_nic_vport_disable_roce(dev->mdev);
 }
 
+struct mlx5_ib_q_counter {
+	const char *name;
+	size_t offset;
+};
+
+#define INIT_Q_COUNTER(_name)		\
+	{ .name = #_name, .offset = MLX5_BYTE_OFF(query_q_counter_out, _name)}
+
+static const struct mlx5_ib_q_counter basic_q_cnts[] = {
+	INIT_Q_COUNTER(rx_write_requests),
+	INIT_Q_COUNTER(rx_read_requests),
+	INIT_Q_COUNTER(rx_atomic_requests),
+	INIT_Q_COUNTER(out_of_buffer),
+};
+
+static const struct mlx5_ib_q_counter out_of_seq_q_cnts[] = {
+	INIT_Q_COUNTER(out_of_sequence),
+};
+
+static const struct mlx5_ib_q_counter retrans_q_cnts[] = {
+	INIT_Q_COUNTER(duplicate_request),
+	INIT_Q_COUNTER(rnr_nak_retry_err),
+	INIT_Q_COUNTER(packet_seq_err),
+	INIT_Q_COUNTER(implied_nak_seq_err),
+	INIT_Q_COUNTER(local_ack_timeout_err),
+};
+
 static void mlx5_ib_dealloc_q_counters(struct mlx5_ib_dev *dev)
 {
 	unsigned int i;
 
-	for (i = 0; i < dev->num_ports; i++)
+	for (i = 0; i < dev->num_ports; i++) {
 		mlx5_core_dealloc_q_counter(dev->mdev,
-					    dev->port[i].q_cnt_id);
+					    dev->port[i].q_cnts.set_id);
+		kfree(dev->port[i].q_cnts.names);
+		kfree(dev->port[i].q_cnts.offsets);
+	}
+}
+
+static int __mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev,
+				      const char ***names,
+				      size_t **offsets,
+				      u32 *num)
+{
+	u32 num_counters;
+
+	num_counters = ARRAY_SIZE(basic_q_cnts);
+
+	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt))
+		num_counters += ARRAY_SIZE(out_of_seq_q_cnts);
+
+	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters))
+		num_counters += ARRAY_SIZE(retrans_q_cnts);
+
+	*names = kcalloc(num_counters, sizeof(**names), GFP_KERNEL);
+	if (!*names)
+		return -ENOMEM;
+
+	*offsets = kcalloc(num_counters, sizeof(**offsets), GFP_KERNEL);
+	if (!*offsets)
+		goto err_names;
+
+	*num = num_counters;
+
+	return 0;
+
+err_names:
+	kfree(*names);
+	return -ENOMEM;
+}
+
+static void mlx5_ib_fill_q_counters(struct mlx5_ib_dev *dev,
+				    const char **names,
+				    size_t *offsets)
+{
+	int i;
+	int j = 0;
+
+	for (i = 0; i < ARRAY_SIZE(basic_q_cnts); i++, j++) {
+		names[j] = basic_q_cnts[i].name;
+		offsets[j] = basic_q_cnts[i].offset;
+	}
+
+	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt)) {
+		for (i = 0; i < ARRAY_SIZE(out_of_seq_q_cnts); i++, j++) {
+			names[j] = out_of_seq_q_cnts[i].name;
+			offsets[j] = out_of_seq_q_cnts[i].offset;
+		}
+	}
+
+	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) {
+		for (i = 0; i < ARRAY_SIZE(retrans_q_cnts); i++, j++) {
+			names[j] = retrans_q_cnts[i].name;
+			offsets[j] = retrans_q_cnts[i].offset;
+		}
+	}
 }
 
 static int mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev)
@@ -2935,14 +3237,26 @@ static int mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev)
 	int ret;
 
 	for (i = 0; i < dev->num_ports; i++) {
+		struct mlx5_ib_port *port = &dev->port[i];
+
 		ret = mlx5_core_alloc_q_counter(dev->mdev,
-						&dev->port[i].q_cnt_id);
+						&port->q_cnts.set_id);
 		if (ret) {
 			mlx5_ib_warn(dev,
 				     "couldn't allocate queue counter for port %d, err %d\n",
 				     i + 1, ret);
 			goto dealloc_counters;
 		}
+
+		ret = __mlx5_ib_alloc_q_counters(dev,
+						 &port->q_cnts.names,
+						 &port->q_cnts.offsets,
+						 &port->q_cnts.num_counters);
+		if (ret)
+			goto dealloc_counters;
+
+		mlx5_ib_fill_q_counters(dev, port->q_cnts.names,
+					port->q_cnts.offsets);
 	}
 
 	return 0;
@@ -2950,62 +3264,39 @@ static int mlx5_ib_alloc_q_counters(struct mlx5_ib_dev *dev)
 dealloc_counters:
 	while (--i >= 0)
 		mlx5_core_dealloc_q_counter(dev->mdev,
-					    dev->port[i].q_cnt_id);
+					    dev->port[i].q_cnts.set_id);
 
 	return ret;
 }
 
-static const char * const names[] = {
-	"rx_write_requests",
-	"rx_read_requests",
-	"rx_atomic_requests",
-	"out_of_buffer",
-	"out_of_sequence",
-	"duplicate_request",
-	"rnr_nak_retry_err",
-	"packet_seq_err",
-	"implied_nak_seq_err",
-	"local_ack_timeout_err",
-};
-
-static const size_t stats_offsets[] = {
-	MLX5_BYTE_OFF(query_q_counter_out, rx_write_requests),
-	MLX5_BYTE_OFF(query_q_counter_out, rx_read_requests),
-	MLX5_BYTE_OFF(query_q_counter_out, rx_atomic_requests),
-	MLX5_BYTE_OFF(query_q_counter_out, out_of_buffer),
-	MLX5_BYTE_OFF(query_q_counter_out, out_of_sequence),
-	MLX5_BYTE_OFF(query_q_counter_out, duplicate_request),
-	MLX5_BYTE_OFF(query_q_counter_out, rnr_nak_retry_err),
-	MLX5_BYTE_OFF(query_q_counter_out, packet_seq_err),
-	MLX5_BYTE_OFF(query_q_counter_out, implied_nak_seq_err),
-	MLX5_BYTE_OFF(query_q_counter_out, local_ack_timeout_err),
-};
-
 static struct rdma_hw_stats *mlx5_ib_alloc_hw_stats(struct ib_device *ibdev,
 						    u8 port_num)
 {
-	BUILD_BUG_ON(ARRAY_SIZE(names) != ARRAY_SIZE(stats_offsets));
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_ib_port *port = &dev->port[port_num - 1];
 
 	/* We support only per port stats */
 	if (port_num == 0)
 		return NULL;
 
-	return rdma_alloc_hw_stats_struct(names, ARRAY_SIZE(names),
+	return rdma_alloc_hw_stats_struct(port->q_cnts.names,
+					  port->q_cnts.num_counters,
 					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
 }
 
 static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 				struct rdma_hw_stats *stats,
-				u8 port, int index)
+				u8 port_num, int index)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_ib_port *port = &dev->port[port_num - 1];
 	int outlen = MLX5_ST_SZ_BYTES(query_q_counter_out);
 	void *out;
 	__be32 val;
 	int ret;
 	int i;
 
-	if (!port || !stats)
+	if (!stats)
 		return -ENOSYS;
 
 	out = mlx5_vzalloc(outlen);
@@ -3013,18 +3304,19 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 		return -ENOMEM;
 
 	ret = mlx5_core_query_q_counter(dev->mdev,
-					dev->port[port - 1].q_cnt_id, 0,
+					port->q_cnts.set_id, 0,
 					out, outlen);
 	if (ret)
 		goto free;
 
-	for (i = 0; i < ARRAY_SIZE(names); i++) {
-		val = *(__be32 *)(out + stats_offsets[i]);
+	for (i = 0; i < port->q_cnts.num_counters; i++) {
+		val = *(__be32 *)(out + port->q_cnts.offsets[i]);
 		stats->value[i] = (u64)be32_to_cpu(val);
 	}
+
 free:
 	kvfree(out);
-	return ARRAY_SIZE(names);
+	return port->q_cnts.num_counters;
 }
 
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
@@ -3060,8 +3352,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (mlx5_use_mad_ifc(dev))
 		get_ext_port_caps(dev);
 
-	MLX5_INIT_DOORBELL_LOCK(&dev->uar_lock);
-
 	if (!mlx5_lag_is_active(mdev))
 		name = "mlx5_%d";
 	else
@@ -3075,7 +3365,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.phys_port_cnt     = dev->num_ports;
 	dev->ib_dev.num_comp_vectors    =
 		dev->mdev->priv.eq_table.num_comp_vectors;
-	dev->ib_dev.dma_device	= &mdev->pdev->dev;
+	dev->ib_dev.dev.parent		= &mdev->pdev->dev;
 
 	dev->ib_dev.uverbs_abi_ver	= MLX5_IB_UVERBS_ABI_VERSION;
 	dev->ib_dev.uverbs_cmd_mask	=
@@ -3178,8 +3468,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 			(1ull << IB_USER_VERBS_CMD_DEALLOC_MW);
 	}
 
-	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt) &&
-	    MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) {
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
 		dev->ib_dev.get_hw_stats	= mlx5_ib_get_hw_stats;
 		dev->ib_dev.alloc_hw_stats	= mlx5_ib_alloc_hw_stats;
 	}
@@ -3233,13 +3522,27 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (err)
 		goto err_rsrc;
 
-	err = mlx5_ib_alloc_q_counters(dev);
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) {
+		err = mlx5_ib_alloc_q_counters(dev);
+		if (err)
+			goto err_odp;
+	}
+
+	dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev);
+	if (!dev->mdev->priv.uar)
+		goto err_q_cnt;
+
+	err = mlx5_alloc_bfreg(dev->mdev, &dev->bfreg, false, false);
+	if (err)
+		goto err_uar_page;
+
+	err = mlx5_alloc_bfreg(dev->mdev, &dev->fp_bfreg, false, true);
 	if (err)
-		goto err_odp;
+		goto err_bfreg;
 
 	err = ib_register_device(&dev->ib_dev, NULL);
 	if (err)
-		goto err_q_cnt;
+		goto err_fp_bfreg;
 
 	err = create_umr_res(dev);
 	if (err)
@@ -3262,8 +3565,18 @@ err_umrc:
 err_dev:
 	ib_unregister_device(&dev->ib_dev);
 
+err_fp_bfreg:
+	mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
+
+err_bfreg:
+	mlx5_free_bfreg(dev->mdev, &dev->bfreg);
+
+err_uar_page:
+	mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar);
+
 err_q_cnt:
-	mlx5_ib_dealloc_q_counters(dev);
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
+		mlx5_ib_dealloc_q_counters(dev);
 
 err_odp:
 	mlx5_ib_odp_remove_one(dev);
@@ -3293,7 +3606,11 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 
 	mlx5_remove_netdev_notifier(dev);
 	ib_unregister_device(&dev->ib_dev);
-	mlx5_ib_dealloc_q_counters(dev);
+	mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
+	mlx5_free_bfreg(dev->mdev, &dev->bfreg);
+	mlx5_put_uars_page(dev->mdev, mdev->priv.uar);
+	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
+		mlx5_ib_dealloc_q_counters(dev);
 	destroy_umrc_res(dev);
 	mlx5_ib_odp_remove_one(dev);
 	destroy_dev_resources(&dev->devr);
@@ -3307,6 +3624,9 @@ static struct mlx5_interface mlx5_ib_interface = {
 	.add            = mlx5_ib_add,
 	.remove         = mlx5_ib_remove,
 	.event          = mlx5_ib_event,
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	.pfault		= mlx5_ib_pfault,
+#endif
 	.protocol	= MLX5_INTERFACE_PROTOCOL_IB,
 };
 
@@ -3314,28 +3634,16 @@ static int __init mlx5_ib_init(void)
 {
 	int err;
 
-	if (deprecated_prof_sel != 2)
-		pr_warn("prof_sel is deprecated for mlx5_ib, set it for mlx5_core\n");
-
-	err = mlx5_ib_odp_init();
-	if (err)
-		return err;
+	mlx5_ib_odp_init();
 
 	err = mlx5_register_interface(&mlx5_ib_interface);
-	if (err)
-		goto clean_odp;
-
-	return err;
 
-clean_odp:
-	mlx5_ib_odp_cleanup();
 	return err;
 }
 
 static void __exit mlx5_ib_cleanup(void)
 {
 	mlx5_unregister_interface(&mlx5_ib_interface);
-	mlx5_ib_odp_cleanup();
 }
 
 module_init(mlx5_ib_init);
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 6851357c16f4..778d8a18925f 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -159,7 +159,7 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	unsigned long umem_page_shift = ilog2(umem->page_size);
 	int shift = page_shift - umem_page_shift;
 	int mask = (1 << shift) - 1;
-	int i, k;
+	int i, k, idx;
 	u64 cur = 0;
 	u64 base;
 	int len;
@@ -185,18 +185,36 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
 		len = sg_dma_len(sg) >> umem_page_shift;
 		base = sg_dma_address(sg);
-		for (k = 0; k < len; k++) {
+
+		/* Skip elements below offset */
+		if (i + len < offset << shift) {
+			i += len;
+			continue;
+		}
+
+		/* Skip pages below offset */
+		if (i < offset << shift) {
+			k = (offset << shift) - i;
+			i = offset << shift;
+		} else {
+			k = 0;
+		}
+
+		for (; k < len; k++) {
 			if (!(i & mask)) {
 				cur = base + (k << umem_page_shift);
 				cur |= access_flags;
+				idx = (i >> shift) - offset;
 
-				pas[i >> shift] = cpu_to_be64(cur);
+				pas[idx] = cpu_to_be64(cur);
 				mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
-					    i >> shift, be64_to_cpu(pas[i >> shift]));
-			}  else
-				mlx5_ib_dbg(dev, "=====> 0x%llx\n",
-					    base + (k << umem_page_shift));
+					    i >> shift, be64_to_cpu(pas[idx]));
+			}
 			i++;
+
+			/* Stop after num_pages reached */
+			if (i >> shift >= offset + num_pages)
+				return;
 		}
 	}
 }
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 6c6057eb60ea..3cd064b5f0bf 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -90,7 +90,6 @@ enum mlx5_ib_latency_class {
 	MLX5_IB_LATENCY_CLASS_LOW,
 	MLX5_IB_LATENCY_CLASS_MEDIUM,
 	MLX5_IB_LATENCY_CLASS_HIGH,
-	MLX5_IB_LATENCY_CLASS_FAST_PATH
 };
 
 enum mlx5_ib_mad_ifc_flags {
@@ -100,7 +99,7 @@ enum mlx5_ib_mad_ifc_flags {
 };
 
 enum {
-	MLX5_CROSS_CHANNEL_UUAR         = 0,
+	MLX5_CROSS_CHANNEL_BFREG         = 0,
 };
 
 enum {
@@ -120,11 +119,16 @@ struct mlx5_ib_ucontext {
 	/* protect doorbell record alloc/free
 	 */
 	struct mutex		db_page_mutex;
-	struct mlx5_uuar_info	uuari;
+	struct mlx5_bfreg_info	bfregi;
 	u8			cqe_version;
 	/* Transport Domain number */
 	u32			tdn;
 	struct list_head	vma_private_list;
+
+	unsigned long		upd_xlt_page;
+	/* protect ODP/KSM */
+	struct mutex		upd_xlt_page_mutex;
+	u64			lib_caps;
 };
 
 static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibucontext)
@@ -174,13 +178,12 @@ struct mlx5_ib_flow_db {
  * enum ib_send_flags and enum ib_qp_type for low-level driver
  */
 
-#define MLX5_IB_SEND_UMR_UNREG	IB_SEND_RESERVED_START
-#define MLX5_IB_SEND_UMR_FAIL_IF_FREE (IB_SEND_RESERVED_START << 1)
-#define MLX5_IB_SEND_UMR_UPDATE_MTT (IB_SEND_RESERVED_START << 2)
-
-#define MLX5_IB_SEND_UMR_UPDATE_TRANSLATION	(IB_SEND_RESERVED_START << 3)
-#define MLX5_IB_SEND_UMR_UPDATE_PD		(IB_SEND_RESERVED_START << 4)
-#define MLX5_IB_SEND_UMR_UPDATE_ACCESS		IB_SEND_RESERVED_END
+#define MLX5_IB_SEND_UMR_ENABLE_MR	       (IB_SEND_RESERVED_START << 0)
+#define MLX5_IB_SEND_UMR_DISABLE_MR	       (IB_SEND_RESERVED_START << 1)
+#define MLX5_IB_SEND_UMR_FAIL_IF_FREE	       (IB_SEND_RESERVED_START << 2)
+#define MLX5_IB_SEND_UMR_UPDATE_XLT	       (IB_SEND_RESERVED_START << 3)
+#define MLX5_IB_SEND_UMR_UPDATE_TRANSLATION    (IB_SEND_RESERVED_START << 4)
+#define MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS       IB_SEND_RESERVED_END
 
 #define MLX5_IB_QPT_REG_UMR	IB_QPT_RESERVED1
 /*
@@ -190,6 +193,17 @@ struct mlx5_ib_flow_db {
 #define MLX5_IB_QPT_HW_GSI	IB_QPT_RESERVED2
 #define MLX5_IB_WR_UMR		IB_WR_RESERVED1
 
+#define MLX5_IB_UMR_OCTOWORD	       16
+#define MLX5_IB_UMR_XLT_ALIGNMENT      64
+
+#define MLX5_IB_UPD_XLT_ZAP	      BIT(0)
+#define MLX5_IB_UPD_XLT_ENABLE	      BIT(1)
+#define MLX5_IB_UPD_XLT_ATOMIC	      BIT(2)
+#define MLX5_IB_UPD_XLT_ADDR	      BIT(3)
+#define MLX5_IB_UPD_XLT_PD	      BIT(4)
+#define MLX5_IB_UPD_XLT_ACCESS	      BIT(5)
+#define MLX5_IB_UPD_XLT_INDIRECT      BIT(6)
+
 /* Private QP creation flags to be passed in ib_qp_init_attr.create_flags.
  *
  * These flags are intended for internal use by the mlx5_ib driver, and they
@@ -207,6 +221,10 @@ struct wr_list {
 	u16	next;
 };
 
+enum mlx5_ib_rq_flags {
+	MLX5_IB_RQ_CVLAN_STRIPPING	= 1 << 0,
+};
+
 struct mlx5_ib_wq {
 	u64		       *wrid;
 	u32		       *wr_data;
@@ -264,29 +282,6 @@ struct mlx5_ib_rwq_ind_table {
 	u32			rqtn;
 };
 
-/*
- * Connect-IB can trigger up to four concurrent pagefaults
- * per-QP.
- */
-enum mlx5_ib_pagefault_context {
-	MLX5_IB_PAGEFAULT_RESPONDER_READ,
-	MLX5_IB_PAGEFAULT_REQUESTOR_READ,
-	MLX5_IB_PAGEFAULT_RESPONDER_WRITE,
-	MLX5_IB_PAGEFAULT_REQUESTOR_WRITE,
-	MLX5_IB_PAGEFAULT_CONTEXTS
-};
-
-static inline enum mlx5_ib_pagefault_context
-	mlx5_ib_get_pagefault_context(struct mlx5_pagefault *pagefault)
-{
-	return pagefault->flags & (MLX5_PFAULT_REQUESTOR | MLX5_PFAULT_WRITE);
-}
-
-struct mlx5_ib_pfault {
-	struct work_struct	work;
-	struct mlx5_pagefault	mpfault;
-};
-
 struct mlx5_ib_ubuffer {
 	struct ib_umem	       *umem;
 	int			buf_size;
@@ -318,6 +313,7 @@ struct mlx5_ib_rq {
 	struct mlx5_db		*doorbell;
 	u32			tirn;
 	u8			state;
+	u32			flags;
 };
 
 struct mlx5_ib_sq {
@@ -334,6 +330,12 @@ struct mlx5_ib_raw_packet_qp {
 	struct mlx5_ib_rq rq;
 };
 
+struct mlx5_bf {
+	int			buf_size;
+	unsigned long		offset;
+	struct mlx5_sq_bfreg   *bfreg;
+};
+
 struct mlx5_ib_qp {
 	struct ib_qp		ibqp;
 	union {
@@ -359,33 +361,19 @@ struct mlx5_ib_qp {
 	int			wq_sig;
 	int			scat_cqe;
 	int			max_inline_data;
-	struct mlx5_bf	       *bf;
+	struct mlx5_bf	        bf;
 	int			has_rq;
 
 	/* only for user space QPs. For kernel
 	 * we have it from the bf object
 	 */
-	int			uuarn;
+	int			bfregn;
 
 	int			create_type;
 
 	/* Store signature errors */
 	bool			signature_en;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	/*
-	 * A flag that is true for QP's that are in a state that doesn't
-	 * allow page faults, and shouldn't schedule any more faults.
-	 */
-	int                     disable_page_faults;
-	/*
-	 * The disable_page_faults_lock protects a QP's disable_page_faults
-	 * field, allowing for a thread to atomically check whether the QP
-	 * allows page faults, and if so schedule a page fault.
-	 */
-	spinlock_t              disable_page_faults_lock;
-	struct mlx5_ib_pfault	pagefaults[MLX5_IB_PAGEFAULT_CONTEXTS];
-#endif
 	struct list_head	qps_list;
 	struct list_head	cq_recv_list;
 	struct list_head	cq_send_list;
@@ -410,17 +398,16 @@ enum mlx5_ib_qp_flags {
 	MLX5_IB_QP_SQPN_QP1			= 1 << 6,
 	MLX5_IB_QP_CAP_SCATTER_FCS		= 1 << 7,
 	MLX5_IB_QP_RSS				= 1 << 8,
+	MLX5_IB_QP_CVLAN_STRIPPING		= 1 << 9,
 };
 
 struct mlx5_umr_wr {
 	struct ib_send_wr		wr;
-	union {
-		u64			virt_addr;
-		u64			offset;
-	} target;
+	u64				virt_addr;
+	u64				offset;
 	struct ib_pd		       *pd;
 	unsigned int			page_shift;
-	unsigned int			npages;
+	unsigned int			xlt_size;
 	u64				length;
 	int				access_flags;
 	u32				mkey;
@@ -517,6 +504,10 @@ struct mlx5_ib_mr {
 	int			live;
 	void			*descs_alloc;
 	int			access_flags; /* Needed for rereg MR */
+
+	struct mlx5_ib_mr      *parent;
+	atomic_t		num_leaf_free;
+	wait_queue_head_t       q_leaf_free;
 };
 
 struct mlx5_ib_mw {
@@ -555,6 +546,10 @@ struct mlx5_cache_ent {
 	struct dentry	       *dir;
 	char                    name[4];
 	u32                     order;
+	u32			xlt;
+	u32			access_mode;
+	u32			page;
+
 	u32			size;
 	u32                     cur;
 	u32                     miss;
@@ -569,6 +564,7 @@ struct mlx5_cache_ent {
 	struct work_struct	work;
 	struct delayed_work	dwork;
 	int			pending;
+	struct completion	compl;
 };
 
 struct mlx5_mr_cache {
@@ -599,8 +595,15 @@ struct mlx5_ib_resources {
 	struct mutex	mutex;
 };
 
+struct mlx5_ib_q_counters {
+	const char **names;
+	size_t *offsets;
+	u32 num_counters;
+	u16 set_id;
+};
+
 struct mlx5_ib_port {
-	u16 q_cnt_id;
+	struct mlx5_ib_q_counters q_cnts;
 };
 
 struct mlx5_roce {
@@ -617,7 +620,6 @@ struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	struct mlx5_core_dev		*mdev;
 	struct mlx5_roce		roce;
-	MLX5_DECLARE_DOORBELL_LOCK(uar_lock);
 	int				num_ports;
 	/* serialize update of capability mask
 	 */
@@ -634,11 +636,13 @@ struct mlx5_ib_dev {
 	int				fill_delay;
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	struct ib_odp_caps	odp_caps;
+	u64			odp_max_size;
 	/*
 	 * Sleepable RCU that prevents destruction of MRs while they are still
 	 * being used by a page fault handler.
 	 */
 	struct srcu_struct      mr_srcu;
+	u32			null_mkey;
 #endif
 	struct mlx5_ib_flow_db	flow_db;
 	/* protect resources needed as part of reset flow */
@@ -646,6 +650,8 @@ struct mlx5_ib_dev {
 	struct list_head	qp_list;
 	/* Array with num_ports elements */
 	struct mlx5_ib_port	*port;
+	struct mlx5_sq_bfreg     bfreg;
+	struct mlx5_sq_bfreg     fp_bfreg;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
@@ -787,8 +793,11 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
 			       struct ib_udata *udata);
 int mlx5_ib_dealloc_mw(struct ib_mw *mw);
-int mlx5_ib_update_mtt(struct mlx5_ib_mr *mr, u64 start_page_index,
-		       int npages, int zap);
+int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
+		       int page_shift, int flags);
+struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
+					     int access_flags);
+void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *mr);
 int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 			  u64 length, u64 virt_addr, int access_flags,
 			  struct ib_pd *pd, struct ib_udata *udata);
@@ -842,7 +851,9 @@ void mlx5_ib_copy_pas(u64 *old, u64 *new, int step, int num);
 int mlx5_ib_get_cqe_size(struct mlx5_ib_dev *dev, struct ib_cq *ibcq);
 int mlx5_mr_cache_init(struct mlx5_ib_dev *dev);
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev);
-int mlx5_mr_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift);
+
+struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev, int entry);
+void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 			    struct ib_mr_status *mr_status);
 struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
@@ -857,33 +868,32 @@ struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
 int mlx5_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-extern struct workqueue_struct *mlx5_ib_page_fault_wq;
-
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev);
-void mlx5_ib_mr_pfault_handler(struct mlx5_ib_qp *qp,
-			       struct mlx5_ib_pfault *pfault);
-void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp);
+void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
+		    struct mlx5_pagefault *pfault);
 int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev);
 void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *ibdev);
 int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
-void mlx5_ib_qp_disable_pagefaults(struct mlx5_ib_qp *qp);
-void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp);
 void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 			      unsigned long end);
+void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent);
+void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
+			   size_t nentries, struct mlx5_ib_mr *mr, int flags);
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 static inline void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 {
 	return;
 }
 
-static inline void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp)		{}
 static inline int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev) { return 0; }
-static inline void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *ibdev)	{}
+static inline void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *ibdev)	    {}
 static inline int mlx5_ib_odp_init(void) { return 0; }
-static inline void mlx5_ib_odp_cleanup(void)				{}
-static inline void mlx5_ib_qp_disable_pagefaults(struct mlx5_ib_qp *qp) {}
-static inline void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp)  {}
+static inline void mlx5_ib_odp_cleanup(void)				    {}
+static inline void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent) {}
+static inline void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
+					 size_t nentries, struct mlx5_ib_mr *mr,
+					 int flags) {}
 
 #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
@@ -898,6 +908,8 @@ int mlx5_ib_set_vf_guid(struct ib_device *device, int vf, u8 port,
 
 __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
 			       int index);
+int mlx5_get_roce_gid_type(struct mlx5_ib_dev *dev, u8 port_num,
+			   int index, enum ib_gid_type *gid_type);
 
 /* GSI QP helper functions */
 struct ib_qp *mlx5_ib_gsi_create_qp(struct ib_pd *pd,
@@ -1001,4 +1013,17 @@ static inline int get_srq_user_index(struct mlx5_ib_ucontext *ucontext,
 
 	return verify_assign_uidx(cqe_version, ucmd->uidx, user_index);
 }
+
+static inline int get_uars_per_sys_page(struct mlx5_ib_dev *dev, bool lib_support)
+{
+	return lib_support && MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+				MLX5_UARS_IN_PAGE : 1;
+}
+
+static inline int get_num_uars(struct mlx5_ib_dev *dev,
+			       struct mlx5_bfreg_info *bfregi)
+{
+	return get_uars_per_sys_page(dev, bfregi->lib_uar_4k) * bfregi->num_sys_pages;
+}
+
 #endif /* MLX5_IB_H */
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 8f608debe141..b8f9382a8b7d 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -46,14 +46,10 @@ enum {
 };
 
 #define MLX5_UMR_ALIGN 2048
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-static __be64 mlx5_ib_update_mtt_emergency_buffer[
-		MLX5_UMR_MTT_MIN_CHUNK_SIZE/sizeof(__be64)]
-	__aligned(MLX5_UMR_ALIGN);
-static DEFINE_MUTEX(mlx5_ib_update_mtt_emergency_buffer_mutex);
-#endif
 
 static int clean_mr(struct mlx5_ib_mr *mr);
+static int use_umr(struct mlx5_ib_dev *dev, int order);
+static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
 
 static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
@@ -134,6 +130,7 @@ static void reg_mr_callback(int status, void *context)
 		return;
 	}
 
+	mr->mmkey.type = MLX5_MKEY_MR;
 	spin_lock_irqsave(&dev->mdev->priv.mkey_lock, flags);
 	key = dev->mdev->priv.mkey_key++;
 	spin_unlock_irqrestore(&dev->mdev->priv.mkey_lock, flags);
@@ -153,6 +150,9 @@ static void reg_mr_callback(int status, void *context)
 	if (err)
 		pr_err("Error inserting to mkey tree. 0x%x\n", -err);
 	write_unlock_irqrestore(&table->lock, flags);
+
+	if (!completion_done(&ent->compl))
+		complete(&ent->compl);
 }
 
 static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
@@ -161,7 +161,6 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 	struct mlx5_cache_ent *ent = &cache->ent[c];
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	struct mlx5_ib_mr *mr;
-	int npages = 1 << ent->order;
 	void *mkc;
 	u32 *in;
 	int err = 0;
@@ -189,11 +188,11 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 
 		MLX5_SET(mkc, mkc, free, 1);
 		MLX5_SET(mkc, mkc, umr_en, 1);
-		MLX5_SET(mkc, mkc, access_mode, MLX5_MKC_ACCESS_MODE_MTT);
+		MLX5_SET(mkc, mkc, access_mode, ent->access_mode);
 
 		MLX5_SET(mkc, mkc, qpn, 0xffffff);
-		MLX5_SET(mkc, mkc, translations_octword_size, (npages + 1) / 2);
-		MLX5_SET(mkc, mkc, log_page_size, 12);
+		MLX5_SET(mkc, mkc, translations_octword_size, ent->xlt);
+		MLX5_SET(mkc, mkc, log_page_size, ent->page);
 
 		spin_lock_irq(&ent->lock);
 		ent->pending++;
@@ -451,6 +450,42 @@ static void cache_work_func(struct work_struct *work)
 	__cache_work_func(ent);
 }
 
+struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev, int entry)
+{
+	struct mlx5_mr_cache *cache = &dev->cache;
+	struct mlx5_cache_ent *ent;
+	struct mlx5_ib_mr *mr;
+	int err;
+
+	if (entry < 0 || entry >= MAX_MR_CACHE_ENTRIES) {
+		mlx5_ib_err(dev, "cache entry %d is out of range\n", entry);
+		return NULL;
+	}
+
+	ent = &cache->ent[entry];
+	while (1) {
+		spin_lock_irq(&ent->lock);
+		if (list_empty(&ent->head)) {
+			spin_unlock_irq(&ent->lock);
+
+			err = add_keys(dev, entry, 1);
+			if (err && err != -EAGAIN)
+				return ERR_PTR(err);
+
+			wait_for_completion(&ent->compl);
+		} else {
+			mr = list_first_entry(&ent->head, struct mlx5_ib_mr,
+					      list);
+			list_del(&mr->list);
+			ent->cur--;
+			spin_unlock_irq(&ent->lock);
+			if (ent->cur < ent->limit)
+				queue_work(cache->wq, &ent->work);
+			return mr;
+		}
+	}
+}
+
 static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
 {
 	struct mlx5_mr_cache *cache = &dev->cache;
@@ -460,12 +495,12 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
 	int i;
 
 	c = order2idx(dev, order);
-	if (c < 0 || c >= MAX_MR_CACHE_ENTRIES) {
+	if (c < 0 || c > MAX_UMR_CACHE_ENTRY) {
 		mlx5_ib_warn(dev, "order %d, cache index %d\n", order, c);
 		return NULL;
 	}
 
-	for (i = c; i < MAX_MR_CACHE_ENTRIES; i++) {
+	for (i = c; i < MAX_UMR_CACHE_ENTRY; i++) {
 		ent = &cache->ent[i];
 
 		mlx5_ib_dbg(dev, "order %d, cache index %d\n", ent->order, i);
@@ -492,7 +527,7 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
 	return mr;
 }
 
-static void free_cached_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
+void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
 	struct mlx5_mr_cache *cache = &dev->cache;
 	struct mlx5_cache_ent *ent;
@@ -504,6 +539,10 @@ static void free_cached_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		mlx5_ib_warn(dev, "order %d, cache index %d\n", mr->order, c);
 		return;
 	}
+
+	if (unreg_umr(dev, mr))
+		return;
+
 	ent = &cache->ent[c];
 	spin_lock_irq(&ent->lock);
 	list_add_tail(&mr->list, &ent->head);
@@ -606,7 +645,6 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_mr_cache *cache = &dev->cache;
 	struct mlx5_cache_ent *ent;
-	int limit;
 	int err;
 	int i;
 
@@ -619,25 +657,35 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 
 	setup_timer(&dev->delay_timer, delay_time_func, (unsigned long)dev);
 	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
-		INIT_LIST_HEAD(&cache->ent[i].head);
-		spin_lock_init(&cache->ent[i].lock);
-
 		ent = &cache->ent[i];
 		INIT_LIST_HEAD(&ent->head);
 		spin_lock_init(&ent->lock);
 		ent->order = i + 2;
 		ent->dev = dev;
+		ent->limit = 0;
 
-		if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) &&
-		    (mlx5_core_is_pf(dev->mdev)))
-			limit = dev->mdev->profile->mr_cache[i].limit;
-		else
-			limit = 0;
-
+		init_completion(&ent->compl);
 		INIT_WORK(&ent->work, cache_work_func);
 		INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
-		ent->limit = limit;
 		queue_work(cache->wq, &ent->work);
+
+		if (i > MAX_UMR_CACHE_ENTRY) {
+			mlx5_odp_init_mr_cache_entry(ent);
+			continue;
+		}
+
+		if (!use_umr(dev, ent->order))
+			continue;
+
+		ent->page = PAGE_SHIFT;
+		ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) /
+			   MLX5_IB_UMR_OCTOWORD;
+		ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
+		if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) &&
+		    mlx5_core_is_pf(dev->mdev))
+			ent->limit = dev->mdev->profile->mr_cache[i].limit;
+		else
+			ent->limit = 0;
 	}
 
 	err = mlx5_mr_cache_debugfs_init(dev);
@@ -732,6 +780,7 @@ struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc)
 		goto err_in;
 
 	kfree(in);
+	mr->mmkey.type = MLX5_MKEY_MR;
 	mr->ibmr.lkey = mr->mmkey.key;
 	mr->ibmr.rkey = mr->mmkey.key;
 	mr->umem = NULL;
@@ -757,94 +806,13 @@ static int get_octo_len(u64 addr, u64 len, int page_size)
 	return (npages + 1) / 2;
 }
 
-static int use_umr(int order)
+static int use_umr(struct mlx5_ib_dev *dev, int order)
 {
+	if (MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
+		return order <= MAX_UMR_CACHE_ENTRY + 2;
 	return order <= MLX5_MAX_UMR_SHIFT;
 }
 
-static int dma_map_mr_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
-			  int npages, int page_shift, int *size,
-			  __be64 **mr_pas, dma_addr_t *dma)
-{
-	__be64 *pas;
-	struct device *ddev = dev->ib_dev.dma_device;
-
-	/*
-	 * UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes.
-	 * To avoid copying garbage after the pas array, we allocate
-	 * a little more.
-	 */
-	*size = ALIGN(sizeof(u64) * npages, MLX5_UMR_MTT_ALIGNMENT);
-	*mr_pas = kmalloc(*size + MLX5_UMR_ALIGN - 1, GFP_KERNEL);
-	if (!(*mr_pas))
-		return -ENOMEM;
-
-	pas = PTR_ALIGN(*mr_pas, MLX5_UMR_ALIGN);
-	mlx5_ib_populate_pas(dev, umem, page_shift, pas, MLX5_IB_MTT_PRESENT);
-	/* Clear padding after the actual pages. */
-	memset(pas + npages, 0, *size - npages * sizeof(u64));
-
-	*dma = dma_map_single(ddev, pas, *size, DMA_TO_DEVICE);
-	if (dma_mapping_error(ddev, *dma)) {
-		kfree(*mr_pas);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static void prep_umr_wqe_common(struct ib_pd *pd, struct ib_send_wr *wr,
-				struct ib_sge *sg, u64 dma, int n, u32 key,
-				int page_shift)
-{
-	struct mlx5_ib_dev *dev = to_mdev(pd->device);
-	struct mlx5_umr_wr *umrwr = umr_wr(wr);
-
-	sg->addr = dma;
-	sg->length = ALIGN(sizeof(u64) * n, 64);
-	sg->lkey = dev->umrc.pd->local_dma_lkey;
-
-	wr->next = NULL;
-	wr->sg_list = sg;
-	if (n)
-		wr->num_sge = 1;
-	else
-		wr->num_sge = 0;
-
-	wr->opcode = MLX5_IB_WR_UMR;
-
-	umrwr->npages = n;
-	umrwr->page_shift = page_shift;
-	umrwr->mkey = key;
-}
-
-static void prep_umr_reg_wqe(struct ib_pd *pd, struct ib_send_wr *wr,
-			     struct ib_sge *sg, u64 dma, int n, u32 key,
-			     int page_shift, u64 virt_addr, u64 len,
-			     int access_flags)
-{
-	struct mlx5_umr_wr *umrwr = umr_wr(wr);
-
-	prep_umr_wqe_common(pd, wr, sg, dma, n, key, page_shift);
-
-	wr->send_flags = 0;
-
-	umrwr->target.virt_addr = virt_addr;
-	umrwr->length = len;
-	umrwr->access_flags = access_flags;
-	umrwr->pd = pd;
-}
-
-static void prep_umr_unreg_wqe(struct mlx5_ib_dev *dev,
-			       struct ib_send_wr *wr, u32 key)
-{
-	struct mlx5_umr_wr *umrwr = umr_wr(wr);
-
-	wr->send_flags = MLX5_IB_SEND_UMR_UNREG | MLX5_IB_SEND_UMR_FAIL_IF_FREE;
-	wr->opcode = MLX5_IB_WR_UMR;
-	umrwr->mkey = key;
-}
-
 static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length,
 		       int access_flags, struct ib_umem **umem,
 		       int *npages, int *page_shift, int *ncont,
@@ -891,21 +859,39 @@ static inline void mlx5_ib_init_umr_context(struct mlx5_ib_umr_context *context)
 	init_completion(&context->done);
 }
 
+static int mlx5_ib_post_send_wait(struct mlx5_ib_dev *dev,
+				  struct mlx5_umr_wr *umrwr)
+{
+	struct umr_common *umrc = &dev->umrc;
+	struct ib_send_wr *bad;
+	int err;
+	struct mlx5_ib_umr_context umr_context;
+
+	mlx5_ib_init_umr_context(&umr_context);
+	umrwr->wr.wr_cqe = &umr_context.cqe;
+
+	down(&umrc->sem);
+	err = ib_post_send(umrc->qp, &umrwr->wr, &bad);
+	if (err) {
+		mlx5_ib_warn(dev, "UMR post send failed, err %d\n", err);
+	} else {
+		wait_for_completion(&umr_context.done);
+		if (umr_context.status != IB_WC_SUCCESS) {
+			mlx5_ib_warn(dev, "reg umr failed (%u)\n",
+				     umr_context.status);
+			err = -EFAULT;
+		}
+	}
+	up(&umrc->sem);
+	return err;
+}
+
 static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 				  u64 virt_addr, u64 len, int npages,
 				  int page_shift, int order, int access_flags)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
-	struct device *ddev = dev->ib_dev.dma_device;
-	struct umr_common *umrc = &dev->umrc;
-	struct mlx5_ib_umr_context umr_context;
-	struct mlx5_umr_wr umrwr = {};
-	struct ib_send_wr *bad;
 	struct mlx5_ib_mr *mr;
-	struct ib_sge sg;
-	int size;
-	__be64 *mr_pas;
-	dma_addr_t dma;
 	int err = 0;
 	int i;
 
@@ -924,173 +910,180 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	if (!mr)
 		return ERR_PTR(-EAGAIN);
 
-	err = dma_map_mr_pas(dev, umem, npages, page_shift, &size, &mr_pas,
-			     &dma);
-	if (err)
-		goto free_mr;
-
-	mlx5_ib_init_umr_context(&umr_context);
-
-	umrwr.wr.wr_cqe = &umr_context.cqe;
-	prep_umr_reg_wqe(pd, &umrwr.wr, &sg, dma, npages, mr->mmkey.key,
-			 page_shift, virt_addr, len, access_flags);
-
-	down(&umrc->sem);
-	err = ib_post_send(umrc->qp, &umrwr.wr, &bad);
-	if (err) {
-		mlx5_ib_warn(dev, "post send failed, err %d\n", err);
-		goto unmap_dma;
-	} else {
-		wait_for_completion(&umr_context.done);
-		if (umr_context.status != IB_WC_SUCCESS) {
-			mlx5_ib_warn(dev, "reg umr failed\n");
-			err = -EFAULT;
-		}
-	}
-
+	mr->ibmr.pd = pd;
+	mr->umem = umem;
+	mr->access_flags = access_flags;
+	mr->desc_size = sizeof(struct mlx5_mtt);
 	mr->mmkey.iova = virt_addr;
 	mr->mmkey.size = len;
 	mr->mmkey.pd = to_mpd(pd)->pdn;
 
-	mr->live = 1;
-
-unmap_dma:
-	up(&umrc->sem);
-	dma_unmap_single(ddev, dma, size, DMA_TO_DEVICE);
+	err = mlx5_ib_update_xlt(mr, 0, npages, page_shift,
+				 MLX5_IB_UPD_XLT_ENABLE);
 
-	kfree(mr_pas);
-
-free_mr:
 	if (err) {
-		free_cached_mr(dev, mr);
+		mlx5_mr_cache_free(dev, mr);
 		return ERR_PTR(err);
 	}
 
+	mr->live = 1;
+
 	return mr;
 }
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-int mlx5_ib_update_mtt(struct mlx5_ib_mr *mr, u64 start_page_index, int npages,
-		       int zap)
+static inline int populate_xlt(struct mlx5_ib_mr *mr, int idx, int npages,
+			       void *xlt, int page_shift, size_t size,
+			       int flags)
 {
 	struct mlx5_ib_dev *dev = mr->dev;
-	struct device *ddev = dev->ib_dev.dma_device;
-	struct umr_common *umrc = &dev->umrc;
-	struct mlx5_ib_umr_context umr_context;
 	struct ib_umem *umem = mr->umem;
+	if (flags & MLX5_IB_UPD_XLT_INDIRECT) {
+		mlx5_odp_populate_klm(xlt, idx, npages, mr, flags);
+		return npages;
+	}
+
+	npages = min_t(size_t, npages, ib_umem_num_pages(umem) - idx);
+
+	if (!(flags & MLX5_IB_UPD_XLT_ZAP)) {
+		__mlx5_ib_populate_pas(dev, umem, page_shift,
+				       idx, npages, xlt,
+				       MLX5_IB_MTT_PRESENT);
+		/* Clear padding after the pages
+		 * brought from the umem.
+		 */
+		memset(xlt + (npages * sizeof(struct mlx5_mtt)), 0,
+		       size - npages * sizeof(struct mlx5_mtt));
+	}
+
+	return npages;
+}
+
+#define MLX5_MAX_UMR_CHUNK ((1 << (MLX5_MAX_UMR_SHIFT + 4)) - \
+			    MLX5_UMR_MTT_ALIGNMENT)
+#define MLX5_SPARE_UMR_CHUNK 0x10000
+
+int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
+		       int page_shift, int flags)
+{
+	struct mlx5_ib_dev *dev = mr->dev;
+	struct device *ddev = dev->ib_dev.dev.parent;
+	struct mlx5_ib_ucontext *uctx = NULL;
 	int size;
-	__be64 *pas;
+	void *xlt;
 	dma_addr_t dma;
-	struct ib_send_wr *bad;
 	struct mlx5_umr_wr wr;
 	struct ib_sge sg;
 	int err = 0;
-	const int page_index_alignment = MLX5_UMR_MTT_ALIGNMENT / sizeof(u64);
-	const int page_index_mask = page_index_alignment - 1;
+	int desc_size = (flags & MLX5_IB_UPD_XLT_INDIRECT)
+			       ? sizeof(struct mlx5_klm)
+			       : sizeof(struct mlx5_mtt);
+	const int page_align = MLX5_UMR_MTT_ALIGNMENT / desc_size;
+	const int page_mask = page_align - 1;
 	size_t pages_mapped = 0;
 	size_t pages_to_map = 0;
 	size_t pages_iter = 0;
-	int use_emergency_buf = 0;
+	gfp_t gfp;
 
 	/* UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes,
-	 * so we need to align the offset and length accordingly */
-	if (start_page_index & page_index_mask) {
-		npages += start_page_index & page_index_mask;
-		start_page_index &= ~page_index_mask;
+	 * so we need to align the offset and length accordingly
+	 */
+	if (idx & page_mask) {
+		npages += idx & page_mask;
+		idx &= ~page_mask;
 	}
 
-	pages_to_map = ALIGN(npages, page_index_alignment);
+	gfp = flags & MLX5_IB_UPD_XLT_ATOMIC ? GFP_ATOMIC : GFP_KERNEL;
+	gfp |= __GFP_ZERO | __GFP_NOWARN;
 
-	if (start_page_index + pages_to_map > MLX5_MAX_UMR_PAGES)
-		return -EINVAL;
+	pages_to_map = ALIGN(npages, page_align);
+	size = desc_size * pages_to_map;
+	size = min_t(int, size, MLX5_MAX_UMR_CHUNK);
+
+	xlt = (void *)__get_free_pages(gfp, get_order(size));
+	if (!xlt && size > MLX5_SPARE_UMR_CHUNK) {
+		mlx5_ib_dbg(dev, "Failed to allocate %d bytes of order %d. fallback to spare UMR allocation od %d bytes\n",
+			    size, get_order(size), MLX5_SPARE_UMR_CHUNK);
 
-	size = sizeof(u64) * pages_to_map;
-	size = min_t(int, PAGE_SIZE, size);
-	/* We allocate with GFP_ATOMIC to avoid recursion into page-reclaim
-	 * code, when we are called from an invalidation. The pas buffer must
-	 * be 2k-aligned for Connect-IB. */
-	pas = (__be64 *)get_zeroed_page(GFP_ATOMIC);
-	if (!pas) {
-		mlx5_ib_warn(dev, "unable to allocate memory during MTT update, falling back to slower chunked mechanism.\n");
-		pas = mlx5_ib_update_mtt_emergency_buffer;
-		size = MLX5_UMR_MTT_MIN_CHUNK_SIZE;
-		use_emergency_buf = 1;
-		mutex_lock(&mlx5_ib_update_mtt_emergency_buffer_mutex);
-		memset(pas, 0, size);
+		size = MLX5_SPARE_UMR_CHUNK;
+		xlt = (void *)__get_free_pages(gfp, get_order(size));
 	}
-	pages_iter = size / sizeof(u64);
-	dma = dma_map_single(ddev, pas, size, DMA_TO_DEVICE);
+
+	if (!xlt) {
+		uctx = to_mucontext(mr->ibmr.uobject->context);
+		mlx5_ib_warn(dev, "Using XLT emergency buffer\n");
+		size = PAGE_SIZE;
+		xlt = (void *)uctx->upd_xlt_page;
+		mutex_lock(&uctx->upd_xlt_page_mutex);
+		memset(xlt, 0, size);
+	}
+	pages_iter = size / desc_size;
+	dma = dma_map_single(ddev, xlt, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(ddev, dma)) {
-		mlx5_ib_err(dev, "unable to map DMA during MTT update.\n");
+		mlx5_ib_err(dev, "unable to map DMA during XLT update.\n");
 		err = -ENOMEM;
-		goto free_pas;
+		goto free_xlt;
 	}
 
+	sg.addr = dma;
+	sg.lkey = dev->umrc.pd->local_dma_lkey;
+
+	memset(&wr, 0, sizeof(wr));
+	wr.wr.send_flags = MLX5_IB_SEND_UMR_UPDATE_XLT;
+	if (!(flags & MLX5_IB_UPD_XLT_ENABLE))
+		wr.wr.send_flags |= MLX5_IB_SEND_UMR_FAIL_IF_FREE;
+	wr.wr.sg_list = &sg;
+	wr.wr.num_sge = 1;
+	wr.wr.opcode = MLX5_IB_WR_UMR;
+
+	wr.pd = mr->ibmr.pd;
+	wr.mkey = mr->mmkey.key;
+	wr.length = mr->mmkey.size;
+	wr.virt_addr = mr->mmkey.iova;
+	wr.access_flags = mr->access_flags;
+	wr.page_shift = page_shift;
+
 	for (pages_mapped = 0;
 	     pages_mapped < pages_to_map && !err;
-	     pages_mapped += pages_iter, start_page_index += pages_iter) {
+	     pages_mapped += pages_iter, idx += pages_iter) {
 		dma_sync_single_for_cpu(ddev, dma, size, DMA_TO_DEVICE);
-
-		npages = min_t(size_t,
-			       pages_iter,
-			       ib_umem_num_pages(umem) - start_page_index);
-
-		if (!zap) {
-			__mlx5_ib_populate_pas(dev, umem, PAGE_SHIFT,
-					       start_page_index, npages, pas,
-					       MLX5_IB_MTT_PRESENT);
-			/* Clear padding after the pages brought from the
-			 * umem. */
-			memset(pas + npages, 0, size - npages * sizeof(u64));
-		}
+		npages = populate_xlt(mr, idx, pages_iter, xlt,
+				      page_shift, size, flags);
 
 		dma_sync_single_for_device(ddev, dma, size, DMA_TO_DEVICE);
 
-		mlx5_ib_init_umr_context(&umr_context);
-
-		memset(&wr, 0, sizeof(wr));
-		wr.wr.wr_cqe = &umr_context.cqe;
-
-		sg.addr = dma;
-		sg.length = ALIGN(npages * sizeof(u64),
-				MLX5_UMR_MTT_ALIGNMENT);
-		sg.lkey = dev->umrc.pd->local_dma_lkey;
+		sg.length = ALIGN(npages * desc_size,
+				  MLX5_UMR_MTT_ALIGNMENT);
+
+		if (pages_mapped + pages_iter >= pages_to_map) {
+			if (flags & MLX5_IB_UPD_XLT_ENABLE)
+				wr.wr.send_flags |=
+					MLX5_IB_SEND_UMR_ENABLE_MR |
+					MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS |
+					MLX5_IB_SEND_UMR_UPDATE_TRANSLATION;
+			if (flags & MLX5_IB_UPD_XLT_PD ||
+			    flags & MLX5_IB_UPD_XLT_ACCESS)
+				wr.wr.send_flags |=
+					MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS;
+			if (flags & MLX5_IB_UPD_XLT_ADDR)
+				wr.wr.send_flags |=
+					MLX5_IB_SEND_UMR_UPDATE_TRANSLATION;
+		}
 
-		wr.wr.send_flags = MLX5_IB_SEND_UMR_FAIL_IF_FREE |
-				MLX5_IB_SEND_UMR_UPDATE_MTT;
-		wr.wr.sg_list = &sg;
-		wr.wr.num_sge = 1;
-		wr.wr.opcode = MLX5_IB_WR_UMR;
-		wr.npages = sg.length / sizeof(u64);
-		wr.page_shift = PAGE_SHIFT;
-		wr.mkey = mr->mmkey.key;
-		wr.target.offset = start_page_index;
+		wr.offset = idx * desc_size;
+		wr.xlt_size = sg.length;
 
-		down(&umrc->sem);
-		err = ib_post_send(umrc->qp, &wr.wr, &bad);
-		if (err) {
-			mlx5_ib_err(dev, "UMR post send failed, err %d\n", err);
-		} else {
-			wait_for_completion(&umr_context.done);
-			if (umr_context.status != IB_WC_SUCCESS) {
-				mlx5_ib_err(dev, "UMR completion failed, code %d\n",
-					    umr_context.status);
-				err = -EFAULT;
-			}
-		}
-		up(&umrc->sem);
+		err = mlx5_ib_post_send_wait(dev, &wr);
 	}
 	dma_unmap_single(ddev, dma, size, DMA_TO_DEVICE);
 
-free_pas:
-	if (!use_emergency_buf)
-		free_page((unsigned long)pas);
+free_xlt:
+	if (uctx)
+		mutex_unlock(&uctx->upd_xlt_page_mutex);
 	else
-		mutex_unlock(&mlx5_ib_update_mtt_emergency_buffer_mutex);
+		free_pages((unsigned long)xlt, get_order(size));
 
 	return err;
 }
-#endif
 
 /*
  * If ibmr is NULL it will be allocated by reg_create.
@@ -1122,8 +1115,9 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 		goto err_1;
 	}
 	pas = (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
-	mlx5_ib_populate_pas(dev, umem, page_shift, pas,
-			     pg_cap ? MLX5_IB_MTT_PRESENT : 0);
+	if (!(access_flags & IB_ACCESS_ON_DEMAND))
+		mlx5_ib_populate_pas(dev, umem, page_shift, pas,
+				     pg_cap ? MLX5_IB_MTT_PRESENT : 0);
 
 	/* The pg_access bit allows setting the access flags
 	 * in the page list submitted with the command. */
@@ -1153,6 +1147,8 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 		mlx5_ib_warn(dev, "create mkey failed\n");
 		goto err_2;
 	}
+	mr->mmkey.type = MLX5_MKEY_MR;
+	mr->desc_size = sizeof(struct mlx5_mtt);
 	mr->umem = umem;
 	mr->dev = dev;
 	mr->live = 1;
@@ -1198,20 +1194,33 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",
 		    start, virt_addr, length, access_flags);
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (!start && length == U64_MAX) {
+		if (!(access_flags & IB_ACCESS_ON_DEMAND) ||
+		    !(dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
+			return ERR_PTR(-EINVAL);
+
+		mr = mlx5_ib_alloc_implicit_mr(to_mpd(pd), access_flags);
+		return &mr->ibmr;
+	}
+#endif
+
 	err = mr_umem_get(pd, start, length, access_flags, &umem, &npages,
 			   &page_shift, &ncont, &order);
 
         if (err < 0)
 		return ERR_PTR(err);
 
-	if (use_umr(order)) {
+	if (use_umr(dev, order)) {
 		mr = reg_umr(pd, umem, virt_addr, length, ncont, page_shift,
 			     order, access_flags);
 		if (PTR_ERR(mr) == -EAGAIN) {
 			mlx5_ib_dbg(dev, "cache empty for order %d", order);
 			mr = NULL;
 		}
-	} else if (access_flags & IB_ACCESS_ON_DEMAND) {
+	} else if (access_flags & IB_ACCESS_ON_DEMAND &&
+		   !MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) {
 		err = -EINVAL;
 		pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB");
 		goto error;
@@ -1248,106 +1257,39 @@ error:
 static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
-	struct umr_common *umrc = &dev->umrc;
-	struct mlx5_ib_umr_context umr_context;
 	struct mlx5_umr_wr umrwr = {};
-	struct ib_send_wr *bad;
-	int err;
 
 	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		return 0;
 
-	mlx5_ib_init_umr_context(&umr_context);
+	umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR |
+			      MLX5_IB_SEND_UMR_FAIL_IF_FREE;
+	umrwr.wr.opcode = MLX5_IB_WR_UMR;
+	umrwr.mkey = mr->mmkey.key;
 
-	umrwr.wr.wr_cqe = &umr_context.cqe;
-	prep_umr_unreg_wqe(dev, &umrwr.wr, mr->mmkey.key);
-
-	down(&umrc->sem);
-	err = ib_post_send(umrc->qp, &umrwr.wr, &bad);
-	if (err) {
-		up(&umrc->sem);
-		mlx5_ib_dbg(dev, "err %d\n", err);
-		goto error;
-	} else {
-		wait_for_completion(&umr_context.done);
-		up(&umrc->sem);
-	}
-	if (umr_context.status != IB_WC_SUCCESS) {
-		mlx5_ib_warn(dev, "unreg umr failed\n");
-		err = -EFAULT;
-		goto error;
-	}
-	return 0;
-
-error:
-	return err;
+	return mlx5_ib_post_send_wait(dev, &umrwr);
 }
 
-static int rereg_umr(struct ib_pd *pd, struct mlx5_ib_mr *mr, u64 virt_addr,
-		     u64 length, int npages, int page_shift, int order,
+static int rereg_umr(struct ib_pd *pd, struct mlx5_ib_mr *mr,
 		     int access_flags, int flags)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
-	struct device *ddev = dev->ib_dev.dma_device;
-	struct mlx5_ib_umr_context umr_context;
-	struct ib_send_wr *bad;
 	struct mlx5_umr_wr umrwr = {};
-	struct ib_sge sg;
-	struct umr_common *umrc = &dev->umrc;
-	dma_addr_t dma = 0;
-	__be64 *mr_pas = NULL;
-	int size;
 	int err;
 
-	mlx5_ib_init_umr_context(&umr_context);
-
-	umrwr.wr.wr_cqe = &umr_context.cqe;
 	umrwr.wr.send_flags = MLX5_IB_SEND_UMR_FAIL_IF_FREE;
 
-	if (flags & IB_MR_REREG_TRANS) {
-		err = dma_map_mr_pas(dev, mr->umem, npages, page_shift, &size,
-				     &mr_pas, &dma);
-		if (err)
-			return err;
-
-		umrwr.target.virt_addr = virt_addr;
-		umrwr.length = length;
-		umrwr.wr.send_flags |= MLX5_IB_SEND_UMR_UPDATE_TRANSLATION;
-	}
-
-	prep_umr_wqe_common(pd, &umrwr.wr, &sg, dma, npages, mr->mmkey.key,
-			    page_shift);
+	umrwr.wr.opcode = MLX5_IB_WR_UMR;
+	umrwr.mkey = mr->mmkey.key;
 
-	if (flags & IB_MR_REREG_PD) {
+	if (flags & IB_MR_REREG_PD || flags & IB_MR_REREG_ACCESS) {
 		umrwr.pd = pd;
-		umrwr.wr.send_flags |= MLX5_IB_SEND_UMR_UPDATE_PD;
-	}
-
-	if (flags & IB_MR_REREG_ACCESS) {
 		umrwr.access_flags = access_flags;
-		umrwr.wr.send_flags |= MLX5_IB_SEND_UMR_UPDATE_ACCESS;
+		umrwr.wr.send_flags |= MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS;
 	}
 
-	/* post send request to UMR QP */
-	down(&umrc->sem);
-	err = ib_post_send(umrc->qp, &umrwr.wr, &bad);
-
-	if (err) {
-		mlx5_ib_warn(dev, "post send failed, err %d\n", err);
-	} else {
-		wait_for_completion(&umr_context.done);
-		if (umr_context.status != IB_WC_SUCCESS) {
-			mlx5_ib_warn(dev, "reg umr failed (%u)\n",
-				     umr_context.status);
-			err = -EFAULT;
-		}
-	}
+	err = mlx5_ib_post_send_wait(dev, &umrwr);
 
-	up(&umrc->sem);
-	if (flags & IB_MR_REREG_TRANS) {
-		dma_unmap_single(ddev, dma, size, DMA_TO_DEVICE);
-		kfree(mr_pas);
-	}
 	return err;
 }
 
@@ -1364,6 +1306,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 	u64 addr = (flags & IB_MR_REREG_TRANS) ? virt_addr : mr->umem->address;
 	u64 len = (flags & IB_MR_REREG_TRANS) ? length : mr->umem->length;
 	int page_shift = 0;
+	int upd_flags = 0;
 	int npages = 0;
 	int ncont = 0;
 	int order = 0;
@@ -1372,6 +1315,8 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 	mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",
 		    start, virt_addr, length, access_flags);
 
+	atomic_sub(mr->npages, &dev->mdev->priv.reg_pages);
+
 	if (flags != IB_MR_REREG_PD) {
 		/*
 		 * Replace umem. This needs to be done whether or not UMR is
@@ -1382,7 +1327,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		err = mr_umem_get(pd, addr, len, access_flags, &mr->umem,
 				  &npages, &page_shift, &ncont, &order);
 		if (err < 0) {
-			mr->umem = NULL;
+			clean_mr(mr);
 			return err;
 		}
 	}
@@ -1414,32 +1359,37 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		/*
 		 * Send a UMR WQE
 		 */
-		err = rereg_umr(pd, mr, addr, len, npages, page_shift,
-				order, access_flags, flags);
+		mr->ibmr.pd = pd;
+		mr->access_flags = access_flags;
+		mr->mmkey.iova = addr;
+		mr->mmkey.size = len;
+		mr->mmkey.pd = to_mpd(pd)->pdn;
+
+		if (flags & IB_MR_REREG_TRANS) {
+			upd_flags = MLX5_IB_UPD_XLT_ADDR;
+			if (flags & IB_MR_REREG_PD)
+				upd_flags |= MLX5_IB_UPD_XLT_PD;
+			if (flags & IB_MR_REREG_ACCESS)
+				upd_flags |= MLX5_IB_UPD_XLT_ACCESS;
+			err = mlx5_ib_update_xlt(mr, 0, npages, page_shift,
+						 upd_flags);
+		} else {
+			err = rereg_umr(pd, mr, access_flags, flags);
+		}
+
 		if (err) {
 			mlx5_ib_warn(dev, "Failed to rereg UMR\n");
+			ib_umem_release(mr->umem);
+			clean_mr(mr);
 			return err;
 		}
 	}
 
-	if (flags & IB_MR_REREG_PD) {
-		ib_mr->pd = pd;
-		mr->mmkey.pd = to_mpd(pd)->pdn;
-	}
+	set_mr_fileds(dev, mr, npages, len, access_flags);
 
-	if (flags & IB_MR_REREG_ACCESS)
-		mr->access_flags = access_flags;
-
-	if (flags & IB_MR_REREG_TRANS) {
-		atomic_sub(mr->npages, &dev->mdev->priv.reg_pages);
-		set_mr_fileds(dev, mr, npages, len, access_flags);
-		mr->mmkey.iova = addr;
-		mr->mmkey.size = len;
-	}
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	update_odp_mr(mr);
 #endif
-
 	return 0;
 }
 
@@ -1461,9 +1411,9 @@ mlx5_alloc_priv_descs(struct ib_device *device,
 
 	mr->descs = PTR_ALIGN(mr->descs_alloc, MLX5_UMR_ALIGN);
 
-	mr->desc_map = dma_map_single(device->dma_device, mr->descs,
+	mr->desc_map = dma_map_single(device->dev.parent, mr->descs,
 				      size, DMA_TO_DEVICE);
-	if (dma_mapping_error(device->dma_device, mr->desc_map)) {
+	if (dma_mapping_error(device->dev.parent, mr->desc_map)) {
 		ret = -ENOMEM;
 		goto err;
 	}
@@ -1482,7 +1432,7 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 		struct ib_device *device = mr->ibmr.device;
 		int size = mr->max_descs * mr->desc_size;
 
-		dma_unmap_single(device->dma_device, mr->desc_map,
+		dma_unmap_single(device->dev.parent, mr->desc_map,
 				 size, DMA_TO_DEVICE);
 		kfree(mr->descs_alloc);
 		mr->descs = NULL;
@@ -1518,12 +1468,7 @@ static int clean_mr(struct mlx5_ib_mr *mr)
 			return err;
 		}
 	} else {
-		err = unreg_umr(dev, mr);
-		if (err) {
-			mlx5_ib_warn(dev, "failed unregister\n");
-			return err;
-		}
-		free_cached_mr(dev, mr);
+		mlx5_mr_cache_free(dev, mr);
 	}
 
 	if (!umred)
@@ -1546,8 +1491,11 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 		/* Wait for all running page-fault handlers to finish. */
 		synchronize_srcu(&dev->mr_srcu);
 		/* Destroy all page mappings */
-		mlx5_ib_invalidate_range(umem, ib_umem_start(umem),
-					 ib_umem_end(umem));
+		if (umem->odp_data->page_list)
+			mlx5_ib_invalidate_range(umem, ib_umem_start(umem),
+						 ib_umem_end(umem));
+		else
+			mlx5_ib_free_implicit_mr(mr);
 		/*
 		 * We kill the umem before the MR for ODP,
 		 * so that there will not be any invalidations in
@@ -1603,11 +1551,11 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 		mr->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
 		MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT);
 		err = mlx5_alloc_priv_descs(pd->device, mr,
-					    ndescs, sizeof(u64));
+					    ndescs, sizeof(struct mlx5_mtt));
 		if (err)
 			goto err_free_in;
 
-		mr->desc_size = sizeof(u64);
+		mr->desc_size = sizeof(struct mlx5_mtt);
 		mr->max_descs = ndescs;
 	} else if (mr_type == IB_MR_TYPE_SG_GAPS) {
 		mr->access_mode = MLX5_MKC_ACCESS_MODE_KLMS;
@@ -1656,6 +1604,7 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 	if (err)
 		goto err_destroy_psv;
 
+	mr->mmkey.type = MLX5_MKEY_MR;
 	mr->ibmr.lkey = mr->mmkey.key;
 	mr->ibmr.rkey = mr->mmkey.key;
 	mr->umem = NULL;
@@ -1736,6 +1685,7 @@ struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
 	if (err)
 		goto free;
 
+	mw->mmkey.type = MLX5_MKEY_MW;
 	mw->ibmw.rkey = mw->mmkey.key;
 
 	resp.response_length = min(offsetof(typeof(resp), response_length) +
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index cacb631a7b0a..d7b12f0750e2 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -34,6 +34,7 @@
 #include <rdma/ib_umem_odp.h>
 
 #include "mlx5_ib.h"
+#include "cmd.h"
 
 #define MAX_PREFETCH_LEN (4*1024*1024U)
 
@@ -41,13 +42,146 @@
  * a pagefault. */
 #define MMU_NOTIFIER_TIMEOUT 1000
 
-struct workqueue_struct *mlx5_ib_page_fault_wq;
+#define MLX5_IMR_MTT_BITS (30 - PAGE_SHIFT)
+#define MLX5_IMR_MTT_SHIFT (MLX5_IMR_MTT_BITS + PAGE_SHIFT)
+#define MLX5_IMR_MTT_ENTRIES BIT_ULL(MLX5_IMR_MTT_BITS)
+#define MLX5_IMR_MTT_SIZE BIT_ULL(MLX5_IMR_MTT_SHIFT)
+#define MLX5_IMR_MTT_MASK (~(MLX5_IMR_MTT_SIZE - 1))
+
+#define MLX5_KSM_PAGE_SHIFT MLX5_IMR_MTT_SHIFT
+
+static u64 mlx5_imr_ksm_entries;
+
+static int check_parent(struct ib_umem_odp *odp,
+			       struct mlx5_ib_mr *parent)
+{
+	struct mlx5_ib_mr *mr = odp->private;
+
+	return mr && mr->parent == parent;
+}
+
+static struct ib_umem_odp *odp_next(struct ib_umem_odp *odp)
+{
+	struct mlx5_ib_mr *mr = odp->private, *parent = mr->parent;
+	struct ib_ucontext *ctx = odp->umem->context;
+	struct rb_node *rb;
+
+	down_read(&ctx->umem_rwsem);
+	while (1) {
+		rb = rb_next(&odp->interval_tree.rb);
+		if (!rb)
+			goto not_found;
+		odp = rb_entry(rb, struct ib_umem_odp, interval_tree.rb);
+		if (check_parent(odp, parent))
+			goto end;
+	}
+not_found:
+	odp = NULL;
+end:
+	up_read(&ctx->umem_rwsem);
+	return odp;
+}
+
+static struct ib_umem_odp *odp_lookup(struct ib_ucontext *ctx,
+				      u64 start, u64 length,
+				      struct mlx5_ib_mr *parent)
+{
+	struct ib_umem_odp *odp;
+	struct rb_node *rb;
+
+	down_read(&ctx->umem_rwsem);
+	odp = rbt_ib_umem_lookup(&ctx->umem_tree, start, length);
+	if (!odp)
+		goto end;
+
+	while (1) {
+		if (check_parent(odp, parent))
+			goto end;
+		rb = rb_next(&odp->interval_tree.rb);
+		if (!rb)
+			goto not_found;
+		odp = rb_entry(rb, struct ib_umem_odp, interval_tree.rb);
+		if (ib_umem_start(odp->umem) > start + length)
+			goto not_found;
+	}
+not_found:
+	odp = NULL;
+end:
+	up_read(&ctx->umem_rwsem);
+	return odp;
+}
+
+void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
+			   size_t nentries, struct mlx5_ib_mr *mr, int flags)
+{
+	struct ib_pd *pd = mr->ibmr.pd;
+	struct ib_ucontext *ctx = pd->uobject->context;
+	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct ib_umem_odp *odp;
+	unsigned long va;
+	int i;
+
+	if (flags & MLX5_IB_UPD_XLT_ZAP) {
+		for (i = 0; i < nentries; i++, pklm++) {
+			pklm->bcount = cpu_to_be32(MLX5_IMR_MTT_SIZE);
+			pklm->key = cpu_to_be32(dev->null_mkey);
+			pklm->va = 0;
+		}
+		return;
+	}
+
+	odp = odp_lookup(ctx, offset * MLX5_IMR_MTT_SIZE,
+			     nentries * MLX5_IMR_MTT_SIZE, mr);
+
+	for (i = 0; i < nentries; i++, pklm++) {
+		pklm->bcount = cpu_to_be32(MLX5_IMR_MTT_SIZE);
+		va = (offset + i) * MLX5_IMR_MTT_SIZE;
+		if (odp && odp->umem->address == va) {
+			struct mlx5_ib_mr *mtt = odp->private;
+
+			pklm->key = cpu_to_be32(mtt->ibmr.lkey);
+			odp = odp_next(odp);
+		} else {
+			pklm->key = cpu_to_be32(dev->null_mkey);
+		}
+		mlx5_ib_dbg(dev, "[%d] va %lx key %x\n",
+			    i, va, be32_to_cpu(pklm->key));
+	}
+}
+
+static void mr_leaf_free_action(struct work_struct *work)
+{
+	struct ib_umem_odp *odp = container_of(work, struct ib_umem_odp, work);
+	int idx = ib_umem_start(odp->umem) >> MLX5_IMR_MTT_SHIFT;
+	struct mlx5_ib_mr *mr = odp->private, *imr = mr->parent;
+
+	mr->parent = NULL;
+	synchronize_srcu(&mr->dev->mr_srcu);
+
+	if (!READ_ONCE(odp->dying)) {
+		mr->parent = imr;
+		if (atomic_dec_and_test(&imr->num_leaf_free))
+			wake_up(&imr->q_leaf_free);
+		return;
+	}
+
+	ib_umem_release(odp->umem);
+	if (imr->live)
+		mlx5_ib_update_xlt(imr, idx, 1, 0,
+				   MLX5_IB_UPD_XLT_INDIRECT |
+				   MLX5_IB_UPD_XLT_ATOMIC);
+	mlx5_mr_cache_free(mr->dev, mr);
+
+	if (atomic_dec_and_test(&imr->num_leaf_free))
+		wake_up(&imr->q_leaf_free);
+}
 
 void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 			      unsigned long end)
 {
 	struct mlx5_ib_mr *mr;
-	const u64 umr_block_mask = (MLX5_UMR_MTT_ALIGNMENT / sizeof(u64)) - 1;
+	const u64 umr_block_mask = (MLX5_UMR_MTT_ALIGNMENT /
+				    sizeof(struct mlx5_mtt)) - 1;
 	u64 idx = 0, blk_start_idx = 0;
 	int in_block = 0;
 	u64 addr;
@@ -90,16 +224,21 @@ void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 			u64 umr_offset = idx & umr_block_mask;
 
 			if (in_block && umr_offset == 0) {
-				mlx5_ib_update_mtt(mr, blk_start_idx,
-						   idx - blk_start_idx, 1);
+				mlx5_ib_update_xlt(mr, blk_start_idx,
+						   idx - blk_start_idx,
+						   PAGE_SHIFT,
+						   MLX5_IB_UPD_XLT_ZAP |
+						   MLX5_IB_UPD_XLT_ATOMIC);
 				in_block = 0;
 			}
 		}
 	}
 	if (in_block)
-		mlx5_ib_update_mtt(mr, blk_start_idx, idx - blk_start_idx + 1,
-				   1);
-
+		mlx5_ib_update_xlt(mr, blk_start_idx,
+				   idx - blk_start_idx + 1,
+				   PAGE_SHIFT,
+				   MLX5_IB_UPD_XLT_ZAP |
+				   MLX5_IB_UPD_XLT_ATOMIC);
 	/*
 	 * We are now sure that the device will not access the
 	 * memory. We can safely unmap it, and mark it as dirty if
@@ -107,6 +246,13 @@ void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 	 */
 
 	ib_umem_odp_unmap_dma_pages(umem, start, end);
+
+	if (unlikely(!umem->npages && mr->parent &&
+		     !umem->odp_data->dying)) {
+		WRITE_ONCE(umem->odp_data->dying, 1);
+		atomic_inc(&mr->parent->num_leaf_free);
+		schedule_work(&umem->odp_data->work);
+	}
 }
 
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
@@ -120,6 +266,11 @@ void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 
 	caps->general_caps = IB_ODP_SUPPORT;
 
+	if (MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
+		dev->odp_max_size = U64_MAX;
+	else
+		dev->odp_max_size = BIT_ULL(MLX5_MAX_UMR_SHIFT + PAGE_SHIFT);
+
 	if (MLX5_CAP_ODP(dev->mdev, ud_odp_caps.send))
 		caps->per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SEND;
 
@@ -135,6 +286,14 @@ void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.read))
 		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_READ;
 
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.atomic))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_ATOMIC;
+
+	if (MLX5_CAP_GEN(dev->mdev, fixed_buffer_size) &&
+	    MLX5_CAP_GEN(dev->mdev, null_mkey) &&
+	    MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
+		caps->general_caps |= IB_ODP_SUPPORT_IMPLICIT;
+
 	return;
 }
 
@@ -143,151 +302,386 @@ static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev,
 {
 	u32 base_key = mlx5_base_mkey(key);
 	struct mlx5_core_mkey *mmkey = __mlx5_mr_lookup(dev->mdev, base_key);
-	struct mlx5_ib_mr *mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
+	struct mlx5_ib_mr *mr;
+
+	if (!mmkey || mmkey->key != key || mmkey->type != MLX5_MKEY_MR)
+		return NULL;
 
-	if (!mmkey || mmkey->key != key || !mr->live)
+	mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
+
+	if (!mr->live)
 		return NULL;
 
 	return container_of(mmkey, struct mlx5_ib_mr, mmkey);
 }
 
-static void mlx5_ib_page_fault_resume(struct mlx5_ib_qp *qp,
-				      struct mlx5_ib_pfault *pfault,
+static void mlx5_ib_page_fault_resume(struct mlx5_ib_dev *dev,
+				      struct mlx5_pagefault *pfault,
 				      int error)
 {
-	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
-	u32 qpn = qp->trans_qp.base.mqp.qpn;
+	int wq_num = pfault->event_subtype == MLX5_PFAULT_SUBTYPE_WQE ?
+		     pfault->wqe.wq_num : pfault->token;
 	int ret = mlx5_core_page_fault_resume(dev->mdev,
-					      qpn,
-					      pfault->mpfault.flags,
+					      pfault->token,
+					      wq_num,
+					      pfault->type,
 					      error);
 	if (ret)
-		pr_err("Failed to resolve the page fault on QP 0x%x\n", qpn);
+		mlx5_ib_err(dev, "Failed to resolve the page fault on WQ 0x%x\n",
+			    wq_num);
+}
+
+static struct mlx5_ib_mr *implicit_mr_alloc(struct ib_pd *pd,
+					    struct ib_umem *umem,
+					    bool ksm, int access_flags)
+{
+	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct mlx5_ib_mr *mr;
+	int err;
+
+	mr = mlx5_mr_cache_alloc(dev, ksm ? MLX5_IMR_KSM_CACHE_ENTRY :
+					    MLX5_IMR_MTT_CACHE_ENTRY);
+
+	if (IS_ERR(mr))
+		return mr;
+
+	mr->ibmr.pd = pd;
+
+	mr->dev = dev;
+	mr->access_flags = access_flags;
+	mr->mmkey.iova = 0;
+	mr->umem = umem;
+
+	if (ksm) {
+		err = mlx5_ib_update_xlt(mr, 0,
+					 mlx5_imr_ksm_entries,
+					 MLX5_KSM_PAGE_SHIFT,
+					 MLX5_IB_UPD_XLT_INDIRECT |
+					 MLX5_IB_UPD_XLT_ZAP |
+					 MLX5_IB_UPD_XLT_ENABLE);
+
+	} else {
+		err = mlx5_ib_update_xlt(mr, 0,
+					 MLX5_IMR_MTT_ENTRIES,
+					 PAGE_SHIFT,
+					 MLX5_IB_UPD_XLT_ZAP |
+					 MLX5_IB_UPD_XLT_ENABLE |
+					 MLX5_IB_UPD_XLT_ATOMIC);
+	}
+
+	if (err)
+		goto fail;
+
+	mr->ibmr.lkey = mr->mmkey.key;
+	mr->ibmr.rkey = mr->mmkey.key;
+
+	mr->live = 1;
+
+	mlx5_ib_dbg(dev, "key %x dev %p mr %p\n",
+		    mr->mmkey.key, dev->mdev, mr);
+
+	return mr;
+
+fail:
+	mlx5_ib_err(dev, "Failed to register MKEY %d\n", err);
+	mlx5_mr_cache_free(dev, mr);
+
+	return ERR_PTR(err);
+}
+
+static struct ib_umem_odp *implicit_mr_get_data(struct mlx5_ib_mr *mr,
+						u64 io_virt, size_t bcnt)
+{
+	struct ib_ucontext *ctx = mr->ibmr.pd->uobject->context;
+	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.pd->device);
+	struct ib_umem_odp *odp, *result = NULL;
+	u64 addr = io_virt & MLX5_IMR_MTT_MASK;
+	int nentries = 0, start_idx = 0, ret;
+	struct mlx5_ib_mr *mtt;
+	struct ib_umem *umem;
+
+	mutex_lock(&mr->umem->odp_data->umem_mutex);
+	odp = odp_lookup(ctx, addr, 1, mr);
+
+	mlx5_ib_dbg(dev, "io_virt:%llx bcnt:%zx addr:%llx odp:%p\n",
+		    io_virt, bcnt, addr, odp);
+
+next_mr:
+	if (likely(odp)) {
+		if (nentries)
+			nentries++;
+	} else {
+		umem = ib_alloc_odp_umem(ctx, addr, MLX5_IMR_MTT_SIZE);
+		if (IS_ERR(umem)) {
+			mutex_unlock(&mr->umem->odp_data->umem_mutex);
+			return ERR_CAST(umem);
+		}
+
+		mtt = implicit_mr_alloc(mr->ibmr.pd, umem, 0, mr->access_flags);
+		if (IS_ERR(mtt)) {
+			mutex_unlock(&mr->umem->odp_data->umem_mutex);
+			ib_umem_release(umem);
+			return ERR_CAST(mtt);
+		}
+
+		odp = umem->odp_data;
+		odp->private = mtt;
+		mtt->umem = umem;
+		mtt->mmkey.iova = addr;
+		mtt->parent = mr;
+		INIT_WORK(&odp->work, mr_leaf_free_action);
+
+		if (!nentries)
+			start_idx = addr >> MLX5_IMR_MTT_SHIFT;
+		nentries++;
+	}
+
+	odp->dying = 0;
+
+	/* Return first odp if region not covered by single one */
+	if (likely(!result))
+		result = odp;
+
+	addr += MLX5_IMR_MTT_SIZE;
+	if (unlikely(addr < io_virt + bcnt)) {
+		odp = odp_next(odp);
+		if (odp && odp->umem->address != addr)
+			odp = NULL;
+		goto next_mr;
+	}
+
+	if (unlikely(nentries)) {
+		ret = mlx5_ib_update_xlt(mr, start_idx, nentries, 0,
+					 MLX5_IB_UPD_XLT_INDIRECT |
+					 MLX5_IB_UPD_XLT_ATOMIC);
+		if (ret) {
+			mlx5_ib_err(dev, "Failed to update PAS\n");
+			result = ERR_PTR(ret);
+		}
+	}
+
+	mutex_unlock(&mr->umem->odp_data->umem_mutex);
+	return result;
+}
+
+struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
+					     int access_flags)
+{
+	struct ib_ucontext *ctx = pd->ibpd.uobject->context;
+	struct mlx5_ib_mr *imr;
+	struct ib_umem *umem;
+
+	umem = ib_umem_get(ctx, 0, 0, IB_ACCESS_ON_DEMAND, 0);
+	if (IS_ERR(umem))
+		return ERR_CAST(umem);
+
+	imr = implicit_mr_alloc(&pd->ibpd, umem, 1, access_flags);
+	if (IS_ERR(imr)) {
+		ib_umem_release(umem);
+		return ERR_CAST(imr);
+	}
+
+	imr->umem = umem;
+	init_waitqueue_head(&imr->q_leaf_free);
+	atomic_set(&imr->num_leaf_free, 0);
+
+	return imr;
+}
+
+static int mr_leaf_free(struct ib_umem *umem, u64 start,
+			u64 end, void *cookie)
+{
+	struct mlx5_ib_mr *mr = umem->odp_data->private, *imr = cookie;
+
+	if (mr->parent != imr)
+		return 0;
+
+	ib_umem_odp_unmap_dma_pages(umem,
+				    ib_umem_start(umem),
+				    ib_umem_end(umem));
+
+	if (umem->odp_data->dying)
+		return 0;
+
+	WRITE_ONCE(umem->odp_data->dying, 1);
+	atomic_inc(&imr->num_leaf_free);
+	schedule_work(&umem->odp_data->work);
+
+	return 0;
+}
+
+void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
+{
+	struct ib_ucontext *ctx = imr->ibmr.pd->uobject->context;
+
+	down_read(&ctx->umem_rwsem);
+	rbt_ib_umem_for_each_in_range(&ctx->umem_tree, 0, ULLONG_MAX,
+				      mr_leaf_free, imr);
+	up_read(&ctx->umem_rwsem);
+
+	wait_event(imr->q_leaf_free, !atomic_read(&imr->num_leaf_free));
 }
 
 /*
- * Handle a single data segment in a page-fault WQE.
+ * Handle a single data segment in a page-fault WQE or RDMA region.
  *
- * Returns number of pages retrieved on success. The caller will continue to
+ * Returns number of pages retrieved on success. The caller may continue to
  * the next data segment.
  * Can return the following error codes:
  * -EAGAIN to designate a temporary error. The caller will abort handling the
  *  page fault and resolve it.
  * -EFAULT when there's an error mapping the requested pages. The caller will
- *  abort the page fault handling and possibly move the QP to an error state.
- * On other errors the QP should also be closed with an error.
+ *  abort the page fault handling.
  */
-static int pagefault_single_data_segment(struct mlx5_ib_qp *qp,
-					 struct mlx5_ib_pfault *pfault,
+static int pagefault_single_data_segment(struct mlx5_ib_dev *dev,
 					 u32 key, u64 io_virt, size_t bcnt,
+					 u32 *bytes_committed,
 					 u32 *bytes_mapped)
 {
-	struct mlx5_ib_dev *mib_dev = to_mdev(qp->ibqp.pd->device);
 	int srcu_key;
-	unsigned int current_seq;
+	unsigned int current_seq = 0;
 	u64 start_idx;
 	int npages = 0, ret = 0;
 	struct mlx5_ib_mr *mr;
 	u64 access_mask = ODP_READ_ALLOWED_BIT;
+	struct ib_umem_odp *odp;
+	int implicit = 0;
+	size_t size;
 
-	srcu_key = srcu_read_lock(&mib_dev->mr_srcu);
-	mr = mlx5_ib_odp_find_mr_lkey(mib_dev, key);
+	srcu_key = srcu_read_lock(&dev->mr_srcu);
+	mr = mlx5_ib_odp_find_mr_lkey(dev, key);
 	/*
 	 * If we didn't find the MR, it means the MR was closed while we were
 	 * handling the ODP event. In this case we return -EFAULT so that the
 	 * QP will be closed.
 	 */
 	if (!mr || !mr->ibmr.pd) {
-		pr_err("Failed to find relevant mr for lkey=0x%06x, probably the MR was destroyed\n",
-		       key);
+		mlx5_ib_dbg(dev, "Failed to find relevant mr for lkey=0x%06x, probably the MR was destroyed\n",
+			    key);
 		ret = -EFAULT;
 		goto srcu_unlock;
 	}
 	if (!mr->umem->odp_data) {
-		pr_debug("skipping non ODP MR (lkey=0x%06x) in page fault handler.\n",
-			 key);
+		mlx5_ib_dbg(dev, "skipping non ODP MR (lkey=0x%06x) in page fault handler.\n",
+			    key);
 		if (bytes_mapped)
 			*bytes_mapped +=
-				(bcnt - pfault->mpfault.bytes_committed);
+				(bcnt - *bytes_committed);
 		goto srcu_unlock;
 	}
-	if (mr->ibmr.pd != qp->ibqp.pd) {
-		pr_err("Page-fault with different PDs for QP and MR.\n");
-		ret = -EFAULT;
-		goto srcu_unlock;
+
+	/*
+	 * Avoid branches - this code will perform correctly
+	 * in all iterations (in iteration 2 and above,
+	 * bytes_committed == 0).
+	 */
+	io_virt += *bytes_committed;
+	bcnt -= *bytes_committed;
+
+	if (!mr->umem->odp_data->page_list) {
+		odp = implicit_mr_get_data(mr, io_virt, bcnt);
+
+		if (IS_ERR(odp)) {
+			ret = PTR_ERR(odp);
+			goto srcu_unlock;
+		}
+		mr = odp->private;
+		implicit = 1;
+
+	} else {
+		odp = mr->umem->odp_data;
 	}
 
-	current_seq = ACCESS_ONCE(mr->umem->odp_data->notifiers_seq);
+next_mr:
+	current_seq = READ_ONCE(odp->notifiers_seq);
 	/*
 	 * Ensure the sequence number is valid for some time before we call
 	 * gup.
 	 */
 	smp_rmb();
 
-	/*
-	 * Avoid branches - this code will perform correctly
-	 * in all iterations (in iteration 2 and above,
-	 * bytes_committed == 0).
-	 */
-	io_virt += pfault->mpfault.bytes_committed;
-	bcnt -= pfault->mpfault.bytes_committed;
-
+	size = min_t(size_t, bcnt, ib_umem_end(odp->umem) - io_virt);
 	start_idx = (io_virt - (mr->mmkey.iova & PAGE_MASK)) >> PAGE_SHIFT;
 
 	if (mr->umem->writable)
 		access_mask |= ODP_WRITE_ALLOWED_BIT;
-	npages = ib_umem_odp_map_dma_pages(mr->umem, io_virt, bcnt,
-					   access_mask, current_seq);
-	if (npages < 0) {
-		ret = npages;
+
+	ret = ib_umem_odp_map_dma_pages(mr->umem, io_virt, size,
+					access_mask, current_seq);
+
+	if (ret < 0)
 		goto srcu_unlock;
-	}
 
-	if (npages > 0) {
-		mutex_lock(&mr->umem->odp_data->umem_mutex);
+	if (ret > 0) {
+		int np = ret;
+
+		mutex_lock(&odp->umem_mutex);
 		if (!ib_umem_mmu_notifier_retry(mr->umem, current_seq)) {
 			/*
 			 * No need to check whether the MTTs really belong to
 			 * this MR, since ib_umem_odp_map_dma_pages already
 			 * checks this.
 			 */
-			ret = mlx5_ib_update_mtt(mr, start_idx, npages, 0);
+			ret = mlx5_ib_update_xlt(mr, start_idx, np,
+						 PAGE_SHIFT,
+						 MLX5_IB_UPD_XLT_ATOMIC);
 		} else {
 			ret = -EAGAIN;
 		}
-		mutex_unlock(&mr->umem->odp_data->umem_mutex);
+		mutex_unlock(&odp->umem_mutex);
 		if (ret < 0) {
 			if (ret != -EAGAIN)
-				pr_err("Failed to update mkey page tables\n");
+				mlx5_ib_err(dev, "Failed to update mkey page tables\n");
 			goto srcu_unlock;
 		}
 
 		if (bytes_mapped) {
-			u32 new_mappings = npages * PAGE_SIZE -
+			u32 new_mappings = np * PAGE_SIZE -
 				(io_virt - round_down(io_virt, PAGE_SIZE));
-			*bytes_mapped += min_t(u32, new_mappings, bcnt);
+			*bytes_mapped += min_t(u32, new_mappings, size);
 		}
+
+		npages += np;
+	}
+
+	bcnt -= size;
+	if (unlikely(bcnt)) {
+		struct ib_umem_odp *next;
+
+		io_virt += size;
+		next = odp_next(odp);
+		if (unlikely(!next || next->umem->address != io_virt)) {
+			mlx5_ib_dbg(dev, "next implicit leaf removed at 0x%llx. got %p\n",
+				    io_virt, next);
+			ret = -EAGAIN;
+			goto srcu_unlock_no_wait;
+		}
+		odp = next;
+		mr = odp->private;
+		goto next_mr;
 	}
 
 srcu_unlock:
 	if (ret == -EAGAIN) {
-		if (!mr->umem->odp_data->dying) {
-			struct ib_umem_odp *odp_data = mr->umem->odp_data;
+		if (implicit || !odp->dying) {
 			unsigned long timeout =
 				msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT);
 
 			if (!wait_for_completion_timeout(
-					&odp_data->notifier_completion,
+					&odp->notifier_completion,
 					timeout)) {
-				pr_warn("timeout waiting for mmu notifier completion\n");
+				mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d\n",
+					     current_seq, odp->notifiers_seq);
 			}
 		} else {
 			/* The MR is being killed, kill the QP as well. */
 			ret = -EFAULT;
 		}
 	}
-	srcu_read_unlock(&mib_dev->mr_srcu, srcu_key);
-	pfault->mpfault.bytes_committed = 0;
+
+srcu_unlock_no_wait:
+	srcu_read_unlock(&dev->mr_srcu, srcu_key);
+	*bytes_committed = 0;
 	return ret ? ret : npages;
 }
 
@@ -309,8 +703,9 @@ srcu_unlock:
  * Returns the number of pages loaded if positive, zero for an empty WQE, or a
  * negative error code.
  */
-static int pagefault_data_segments(struct mlx5_ib_qp *qp,
-				   struct mlx5_ib_pfault *pfault, void *wqe,
+static int pagefault_data_segments(struct mlx5_ib_dev *dev,
+				   struct mlx5_pagefault *pfault,
+				   struct mlx5_ib_qp *qp, void *wqe,
 				   void *wqe_end, u32 *bytes_mapped,
 				   u32 *total_wqe_bytes, int receive_queue)
 {
@@ -354,22 +749,23 @@ static int pagefault_data_segments(struct mlx5_ib_qp *qp,
 
 		if (!inline_segment && total_wqe_bytes) {
 			*total_wqe_bytes += bcnt - min_t(size_t, bcnt,
-					pfault->mpfault.bytes_committed);
+					pfault->bytes_committed);
 		}
 
 		/* A zero length data segment designates a length of 2GB. */
 		if (bcnt == 0)
 			bcnt = 1U << 31;
 
-		if (inline_segment || bcnt <= pfault->mpfault.bytes_committed) {
-			pfault->mpfault.bytes_committed -=
+		if (inline_segment || bcnt <= pfault->bytes_committed) {
+			pfault->bytes_committed -=
 				min_t(size_t, bcnt,
-				      pfault->mpfault.bytes_committed);
+				      pfault->bytes_committed);
 			continue;
 		}
 
-		ret = pagefault_single_data_segment(qp, pfault, key, io_virt,
-						    bcnt, bytes_mapped);
+		ret = pagefault_single_data_segment(dev, key, io_virt, bcnt,
+						    &pfault->bytes_committed,
+						    bytes_mapped);
 		if (ret < 0)
 			break;
 		npages += ret;
@@ -378,17 +774,29 @@ static int pagefault_data_segments(struct mlx5_ib_qp *qp,
 	return ret < 0 ? ret : npages;
 }
 
+static const u32 mlx5_ib_odp_opcode_cap[] = {
+	[MLX5_OPCODE_SEND]	       = IB_ODP_SUPPORT_SEND,
+	[MLX5_OPCODE_SEND_IMM]	       = IB_ODP_SUPPORT_SEND,
+	[MLX5_OPCODE_SEND_INVAL]       = IB_ODP_SUPPORT_SEND,
+	[MLX5_OPCODE_RDMA_WRITE]       = IB_ODP_SUPPORT_WRITE,
+	[MLX5_OPCODE_RDMA_WRITE_IMM]   = IB_ODP_SUPPORT_WRITE,
+	[MLX5_OPCODE_RDMA_READ]	       = IB_ODP_SUPPORT_READ,
+	[MLX5_OPCODE_ATOMIC_CS]	       = IB_ODP_SUPPORT_ATOMIC,
+	[MLX5_OPCODE_ATOMIC_FA]	       = IB_ODP_SUPPORT_ATOMIC,
+};
+
 /*
  * Parse initiator WQE. Advances the wqe pointer to point at the
  * scatter-gather list, and set wqe_end to the end of the WQE.
  */
 static int mlx5_ib_mr_initiator_pfault_handler(
-	struct mlx5_ib_qp *qp, struct mlx5_ib_pfault *pfault,
-	void **wqe, void **wqe_end, int wqe_length)
+	struct mlx5_ib_dev *dev, struct mlx5_pagefault *pfault,
+	struct mlx5_ib_qp *qp, void **wqe, void **wqe_end, int wqe_length)
 {
-	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
 	struct mlx5_wqe_ctrl_seg *ctrl = *wqe;
-	u16 wqe_index = pfault->mpfault.wqe.wqe_index;
+	u16 wqe_index = pfault->wqe.wqe_index;
+	u32 transport_caps;
+	struct mlx5_base_av *av;
 	unsigned ds, opcode;
 #if defined(DEBUG)
 	u32 ctrl_wqe_index, ctrl_qpn;
@@ -434,53 +842,49 @@ static int mlx5_ib_mr_initiator_pfault_handler(
 
 	opcode = be32_to_cpu(ctrl->opmod_idx_opcode) &
 		 MLX5_WQE_CTRL_OPCODE_MASK;
+
 	switch (qp->ibqp.qp_type) {
 	case IB_QPT_RC:
-		switch (opcode) {
-		case MLX5_OPCODE_SEND:
-		case MLX5_OPCODE_SEND_IMM:
-		case MLX5_OPCODE_SEND_INVAL:
-			if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
-			      IB_ODP_SUPPORT_SEND))
-				goto invalid_transport_or_opcode;
-			break;
-		case MLX5_OPCODE_RDMA_WRITE:
-		case MLX5_OPCODE_RDMA_WRITE_IMM:
-			if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
-			      IB_ODP_SUPPORT_WRITE))
-				goto invalid_transport_or_opcode;
-			*wqe += sizeof(struct mlx5_wqe_raddr_seg);
-			break;
-		case MLX5_OPCODE_RDMA_READ:
-			if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
-			      IB_ODP_SUPPORT_READ))
-				goto invalid_transport_or_opcode;
-			*wqe += sizeof(struct mlx5_wqe_raddr_seg);
-			break;
-		default:
-			goto invalid_transport_or_opcode;
-		}
+		transport_caps = dev->odp_caps.per_transport_caps.rc_odp_caps;
 		break;
 	case IB_QPT_UD:
-		switch (opcode) {
-		case MLX5_OPCODE_SEND:
-		case MLX5_OPCODE_SEND_IMM:
-			if (!(dev->odp_caps.per_transport_caps.ud_odp_caps &
-			      IB_ODP_SUPPORT_SEND))
-				goto invalid_transport_or_opcode;
-			*wqe += sizeof(struct mlx5_wqe_datagram_seg);
-			break;
-		default:
-			goto invalid_transport_or_opcode;
-		}
+		transport_caps = dev->odp_caps.per_transport_caps.ud_odp_caps;
 		break;
 	default:
-invalid_transport_or_opcode:
-		mlx5_ib_err(dev, "ODP fault on QP of an unsupported opcode or transport. transport: 0x%x opcode: 0x%x.\n",
-			    qp->ibqp.qp_type, opcode);
+		mlx5_ib_err(dev, "ODP fault on QP of an unsupported transport 0x%x\n",
+			    qp->ibqp.qp_type);
+		return -EFAULT;
+	}
+
+	if (unlikely(opcode >= sizeof(mlx5_ib_odp_opcode_cap) /
+	    sizeof(mlx5_ib_odp_opcode_cap[0]) ||
+	    !(transport_caps & mlx5_ib_odp_opcode_cap[opcode]))) {
+		mlx5_ib_err(dev, "ODP fault on QP of an unsupported opcode 0x%x\n",
+			    opcode);
 		return -EFAULT;
 	}
 
+	if (qp->ibqp.qp_type != IB_QPT_RC) {
+		av = *wqe;
+		if (av->dqp_dct & be32_to_cpu(MLX5_WQE_AV_EXT))
+			*wqe += sizeof(struct mlx5_av);
+		else
+			*wqe += sizeof(struct mlx5_base_av);
+	}
+
+	switch (opcode) {
+	case MLX5_OPCODE_RDMA_WRITE:
+	case MLX5_OPCODE_RDMA_WRITE_IMM:
+	case MLX5_OPCODE_RDMA_READ:
+		*wqe += sizeof(struct mlx5_wqe_raddr_seg);
+		break;
+	case MLX5_OPCODE_ATOMIC_CS:
+	case MLX5_OPCODE_ATOMIC_FA:
+		*wqe += sizeof(struct mlx5_wqe_raddr_seg);
+		*wqe += sizeof(struct mlx5_wqe_atomic_seg);
+		break;
+	}
+
 	return 0;
 }
 
@@ -489,10 +893,9 @@ invalid_transport_or_opcode:
  * scatter-gather list, and set wqe_end to the end of the WQE.
  */
 static int mlx5_ib_mr_responder_pfault_handler(
-	struct mlx5_ib_qp *qp, struct mlx5_ib_pfault *pfault,
-	void **wqe, void **wqe_end, int wqe_length)
+	struct mlx5_ib_dev *dev, struct mlx5_pagefault *pfault,
+	struct mlx5_ib_qp *qp, void **wqe, void **wqe_end, int wqe_length)
 {
-	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
 	struct mlx5_ib_wq *wq = &qp->rq;
 	int wqe_size = 1 << wq->wqe_shift;
 
@@ -529,70 +932,83 @@ invalid_transport_or_opcode:
 	return 0;
 }
 
-static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_qp *qp,
-					  struct mlx5_ib_pfault *pfault)
+static struct mlx5_ib_qp *mlx5_ib_odp_find_qp(struct mlx5_ib_dev *dev,
+					      u32 wq_num)
+{
+	struct mlx5_core_qp *mqp = __mlx5_qp_lookup(dev->mdev, wq_num);
+
+	if (!mqp) {
+		mlx5_ib_err(dev, "QPN 0x%6x not found\n", wq_num);
+		return NULL;
+	}
+
+	return to_mibqp(mqp);
+}
+
+static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
+					  struct mlx5_pagefault *pfault)
 {
-	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
 	int ret;
 	void *wqe, *wqe_end;
 	u32 bytes_mapped, total_wqe_bytes;
 	char *buffer = NULL;
-	int resume_with_error = 0;
-	u16 wqe_index = pfault->mpfault.wqe.wqe_index;
-	int requestor = pfault->mpfault.flags & MLX5_PFAULT_REQUESTOR;
-	u32 qpn = qp->trans_qp.base.mqp.qpn;
+	int resume_with_error = 1;
+	u16 wqe_index = pfault->wqe.wqe_index;
+	int requestor = pfault->type & MLX5_PFAULT_REQUESTOR;
+	struct mlx5_ib_qp *qp;
 
 	buffer = (char *)__get_free_page(GFP_KERNEL);
 	if (!buffer) {
 		mlx5_ib_err(dev, "Error allocating memory for IO page fault handling.\n");
-		resume_with_error = 1;
 		goto resolve_page_fault;
 	}
 
+	qp = mlx5_ib_odp_find_qp(dev, pfault->wqe.wq_num);
+	if (!qp)
+		goto resolve_page_fault;
+
 	ret = mlx5_ib_read_user_wqe(qp, requestor, wqe_index, buffer,
 				    PAGE_SIZE, &qp->trans_qp.base);
 	if (ret < 0) {
-		mlx5_ib_err(dev, "Failed reading a WQE following page fault, error=%x, wqe_index=%x, qpn=%x\n",
-			    -ret, wqe_index, qpn);
-		resume_with_error = 1;
+		mlx5_ib_err(dev, "Failed reading a WQE following page fault, error=%d, wqe_index=%x, qpn=%x\n",
+			    ret, wqe_index, pfault->token);
 		goto resolve_page_fault;
 	}
 
 	wqe = buffer;
 	if (requestor)
-		ret = mlx5_ib_mr_initiator_pfault_handler(qp, pfault, &wqe,
+		ret = mlx5_ib_mr_initiator_pfault_handler(dev, pfault, qp, &wqe,
 							  &wqe_end, ret);
 	else
-		ret = mlx5_ib_mr_responder_pfault_handler(qp, pfault, &wqe,
+		ret = mlx5_ib_mr_responder_pfault_handler(dev, pfault, qp, &wqe,
 							  &wqe_end, ret);
-	if (ret < 0) {
-		resume_with_error = 1;
+	if (ret < 0)
 		goto resolve_page_fault;
-	}
 
 	if (wqe >= wqe_end) {
 		mlx5_ib_err(dev, "ODP fault on invalid WQE.\n");
-		resume_with_error = 1;
 		goto resolve_page_fault;
 	}
 
-	ret = pagefault_data_segments(qp, pfault, wqe, wqe_end, &bytes_mapped,
-				      &total_wqe_bytes, !requestor);
+	ret = pagefault_data_segments(dev, pfault, qp, wqe, wqe_end,
+				      &bytes_mapped, &total_wqe_bytes,
+				      !requestor);
 	if (ret == -EAGAIN) {
+		resume_with_error = 0;
 		goto resolve_page_fault;
 	} else if (ret < 0 || total_wqe_bytes > bytes_mapped) {
-		mlx5_ib_err(dev, "Error getting user pages for page fault. Error: 0x%x\n",
-			    -ret);
-		resume_with_error = 1;
+		if (ret != -ENOENT)
+			mlx5_ib_err(dev, "PAGE FAULT error: %d. QP 0x%x. type: 0x%x\n",
+				    ret, pfault->wqe.wq_num, pfault->type);
 		goto resolve_page_fault;
 	}
 
+	resume_with_error = 0;
 resolve_page_fault:
-	mlx5_ib_page_fault_resume(qp, pfault, resume_with_error);
-	mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x resume_with_error=%d, flags: 0x%x\n",
-		    qpn, resume_with_error,
-		    pfault->mpfault.flags);
-
+	mlx5_ib_page_fault_resume(dev, pfault, resume_with_error);
+	mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x resume_with_error=%d, type: 0x%x\n",
+		    pfault->wqe.wq_num, resume_with_error,
+		    pfault->type);
 	free_page((unsigned long)buffer);
 }
 
@@ -602,15 +1018,14 @@ static int pages_in_range(u64 address, u32 length)
 		(address & PAGE_MASK)) >> PAGE_SHIFT;
 }
 
-static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_qp *qp,
-					   struct mlx5_ib_pfault *pfault)
+static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev,
+					   struct mlx5_pagefault *pfault)
 {
-	struct mlx5_pagefault *mpfault = &pfault->mpfault;
 	u64 address;
 	u32 length;
-	u32 prefetch_len = mpfault->bytes_committed;
+	u32 prefetch_len = pfault->bytes_committed;
 	int prefetch_activated = 0;
-	u32 rkey = mpfault->rdma.r_key;
+	u32 rkey = pfault->rdma.r_key;
 	int ret;
 
 	/* The RDMA responder handler handles the page fault in two parts.
@@ -619,38 +1034,40 @@ static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_qp *qp,
 	 * prefetches more pages. The second operation cannot use the pfault
 	 * context and therefore uses the dummy_pfault context allocated on
 	 * the stack */
-	struct mlx5_ib_pfault dummy_pfault = {};
-
-	dummy_pfault.mpfault.bytes_committed = 0;
-
-	mpfault->rdma.rdma_va += mpfault->bytes_committed;
-	mpfault->rdma.rdma_op_len -= min(mpfault->bytes_committed,
-					 mpfault->rdma.rdma_op_len);
-	mpfault->bytes_committed = 0;
+	pfault->rdma.rdma_va += pfault->bytes_committed;
+	pfault->rdma.rdma_op_len -= min(pfault->bytes_committed,
+					 pfault->rdma.rdma_op_len);
+	pfault->bytes_committed = 0;
 
-	address = mpfault->rdma.rdma_va;
-	length  = mpfault->rdma.rdma_op_len;
+	address = pfault->rdma.rdma_va;
+	length  = pfault->rdma.rdma_op_len;
 
 	/* For some operations, the hardware cannot tell the exact message
 	 * length, and in those cases it reports zero. Use prefetch
 	 * logic. */
 	if (length == 0) {
 		prefetch_activated = 1;
-		length = mpfault->rdma.packet_size;
+		length = pfault->rdma.packet_size;
 		prefetch_len = min(MAX_PREFETCH_LEN, prefetch_len);
 	}
 
-	ret = pagefault_single_data_segment(qp, pfault, rkey, address, length,
-					    NULL);
+	ret = pagefault_single_data_segment(dev, rkey, address, length,
+					    &pfault->bytes_committed, NULL);
 	if (ret == -EAGAIN) {
 		/* We're racing with an invalidation, don't prefetch */
 		prefetch_activated = 0;
 	} else if (ret < 0 || pages_in_range(address, length) > ret) {
-		mlx5_ib_page_fault_resume(qp, pfault, 1);
+		mlx5_ib_page_fault_resume(dev, pfault, 1);
+		if (ret != -ENOENT)
+			mlx5_ib_warn(dev, "PAGE FAULT error %d. QP 0x%x, type: 0x%x\n",
+				     ret, pfault->token, pfault->type);
 		return;
 	}
 
-	mlx5_ib_page_fault_resume(qp, pfault, 0);
+	mlx5_ib_page_fault_resume(dev, pfault, 0);
+	mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x, type: 0x%x, prefetch_activated: %d\n",
+		    pfault->token, pfault->type,
+		    prefetch_activated);
 
 	/* At this point, there might be a new pagefault already arriving in
 	 * the eq, switch to the dummy pagefault for the rest of the
@@ -658,139 +1075,93 @@ static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_qp *qp,
 	 * work-queue is being fenced. */
 
 	if (prefetch_activated) {
-		ret = pagefault_single_data_segment(qp, &dummy_pfault, rkey,
-						    address,
+		u32 bytes_committed = 0;
+
+		ret = pagefault_single_data_segment(dev, rkey, address,
 						    prefetch_len,
-						    NULL);
-		if (ret < 0) {
-			pr_warn("Prefetch failed (ret = %d, prefetch_activated = %d) for QPN %d, address: 0x%.16llx, length = 0x%.16x\n",
-				ret, prefetch_activated,
-				qp->ibqp.qp_num, address, prefetch_len);
+						    &bytes_committed, NULL);
+		if (ret < 0 && ret != -EAGAIN) {
+			mlx5_ib_warn(dev, "Prefetch failed. ret: %d, QP 0x%x, address: 0x%.16llx, length = 0x%.16x\n",
+				     ret, pfault->token, address, prefetch_len);
 		}
 	}
 }
 
-void mlx5_ib_mr_pfault_handler(struct mlx5_ib_qp *qp,
-			       struct mlx5_ib_pfault *pfault)
+void mlx5_ib_pfault(struct mlx5_core_dev *mdev, void *context,
+		    struct mlx5_pagefault *pfault)
 {
-	u8 event_subtype = pfault->mpfault.event_subtype;
+	struct mlx5_ib_dev *dev = context;
+	u8 event_subtype = pfault->event_subtype;
 
 	switch (event_subtype) {
 	case MLX5_PFAULT_SUBTYPE_WQE:
-		mlx5_ib_mr_wqe_pfault_handler(qp, pfault);
+		mlx5_ib_mr_wqe_pfault_handler(dev, pfault);
 		break;
 	case MLX5_PFAULT_SUBTYPE_RDMA:
-		mlx5_ib_mr_rdma_pfault_handler(qp, pfault);
+		mlx5_ib_mr_rdma_pfault_handler(dev, pfault);
 		break;
 	default:
-		pr_warn("Invalid page fault event subtype: 0x%x\n",
-			event_subtype);
-		mlx5_ib_page_fault_resume(qp, pfault, 1);
-		break;
+		mlx5_ib_err(dev, "Invalid page fault event subtype: 0x%x\n",
+			    event_subtype);
+		mlx5_ib_page_fault_resume(dev, pfault, 1);
 	}
 }
 
-static void mlx5_ib_qp_pfault_action(struct work_struct *work)
+void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent)
 {
-	struct mlx5_ib_pfault *pfault = container_of(work,
-						     struct mlx5_ib_pfault,
-						     work);
-	enum mlx5_ib_pagefault_context context =
-		mlx5_ib_get_pagefault_context(&pfault->mpfault);
-	struct mlx5_ib_qp *qp = container_of(pfault, struct mlx5_ib_qp,
-					     pagefaults[context]);
-	mlx5_ib_mr_pfault_handler(qp, pfault);
-}
-
-void mlx5_ib_qp_disable_pagefaults(struct mlx5_ib_qp *qp)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&qp->disable_page_faults_lock, flags);
-	qp->disable_page_faults = 1;
-	spin_unlock_irqrestore(&qp->disable_page_faults_lock, flags);
-
-	/*
-	 * Note that at this point, we are guarenteed that no more
-	 * work queue elements will be posted to the work queue with
-	 * the QP we are closing.
-	 */
-	flush_workqueue(mlx5_ib_page_fault_wq);
-}
-
-void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&qp->disable_page_faults_lock, flags);
-	qp->disable_page_faults = 0;
-	spin_unlock_irqrestore(&qp->disable_page_faults_lock, flags);
-}
-
-static void mlx5_ib_pfault_handler(struct mlx5_core_qp *qp,
-				   struct mlx5_pagefault *pfault)
-{
-	/*
-	 * Note that we will only get one fault event per QP per context
-	 * (responder/initiator, read/write), until we resolve the page fault
-	 * with the mlx5_ib_page_fault_resume command. Since this function is
-	 * called from within the work element, there is no risk of missing
-	 * events.
-	 */
-	struct mlx5_ib_qp *mibqp = to_mibqp(qp);
-	enum mlx5_ib_pagefault_context context =
-		mlx5_ib_get_pagefault_context(pfault);
-	struct mlx5_ib_pfault *qp_pfault = &mibqp->pagefaults[context];
-
-	qp_pfault->mpfault = *pfault;
-
-	/* No need to stop interrupts here since we are in an interrupt */
-	spin_lock(&mibqp->disable_page_faults_lock);
-	if (!mibqp->disable_page_faults)
-		queue_work(mlx5_ib_page_fault_wq, &qp_pfault->work);
-	spin_unlock(&mibqp->disable_page_faults_lock);
-}
-
-void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp)
-{
-	int i;
-
-	qp->disable_page_faults = 1;
-	spin_lock_init(&qp->disable_page_faults_lock);
+	if (!(ent->dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
+		return;
 
-	qp->trans_qp.base.mqp.pfault_handler = mlx5_ib_pfault_handler;
+	switch (ent->order - 2) {
+	case MLX5_IMR_MTT_CACHE_ENTRY:
+		ent->page = PAGE_SHIFT;
+		ent->xlt = MLX5_IMR_MTT_ENTRIES *
+			   sizeof(struct mlx5_mtt) /
+			   MLX5_IB_UMR_OCTOWORD;
+		ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
+		ent->limit = 0;
+		break;
 
-	for (i = 0; i < MLX5_IB_PAGEFAULT_CONTEXTS; ++i)
-		INIT_WORK(&qp->pagefaults[i].work, mlx5_ib_qp_pfault_action);
+	case MLX5_IMR_KSM_CACHE_ENTRY:
+		ent->page = MLX5_KSM_PAGE_SHIFT;
+		ent->xlt = mlx5_imr_ksm_entries *
+			   sizeof(struct mlx5_klm) /
+			   MLX5_IB_UMR_OCTOWORD;
+		ent->access_mode = MLX5_MKC_ACCESS_MODE_KSM;
+		ent->limit = 0;
+		break;
+	}
 }
 
-int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev)
+int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
 {
 	int ret;
 
-	ret = init_srcu_struct(&ibdev->mr_srcu);
+	ret = init_srcu_struct(&dev->mr_srcu);
 	if (ret)
 		return ret;
 
+	if (dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT) {
+		ret = mlx5_cmd_null_mkey(dev->mdev, &dev->null_mkey);
+		if (ret) {
+			mlx5_ib_err(dev, "Error getting null_mkey %d\n", ret);
+			return ret;
+		}
+	}
+
 	return 0;
 }
 
-void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *ibdev)
+void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *dev)
 {
-	cleanup_srcu_struct(&ibdev->mr_srcu);
+	cleanup_srcu_struct(&dev->mr_srcu);
 }
 
-int __init mlx5_ib_odp_init(void)
+int mlx5_ib_odp_init(void)
 {
-	mlx5_ib_page_fault_wq = alloc_ordered_workqueue("mlx5_ib_page_faults",
-							WQ_MEM_RECLAIM);
-	if (!mlx5_ib_page_fault_wq)
-		return -ENOMEM;
+	mlx5_imr_ksm_entries = BIT_ULL(get_order(TASK_SIZE) -
+				       MLX5_IMR_MTT_BITS);
 
 	return 0;
 }
 
-void mlx5_ib_odp_cleanup(void)
-{
-	destroy_workqueue(mlx5_ib_page_fault_wq);
-}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index a1b3125f0a6e..ad8a2638e339 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -475,60 +475,53 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
 	return 1;
 }
 
-static int first_med_uuar(void)
+static int first_med_bfreg(void)
 {
 	return 1;
 }
 
-static int next_uuar(int n)
-{
-	n++;
-
-	while (((n % 4) & 2))
-		n++;
+enum {
+	/* this is the first blue flame register in the array of bfregs assigned
+	 * to a processes. Since we do not use it for blue flame but rather
+	 * regular 64 bit doorbells, we do not need a lock for maintaiing
+	 * "odd/even" order
+	 */
+	NUM_NON_BLUE_FLAME_BFREGS = 1,
+};
 
-	return n;
+static int max_bfregs(struct mlx5_ib_dev *dev, struct mlx5_bfreg_info *bfregi)
+{
+	return get_num_uars(dev, bfregi) * MLX5_NON_FP_BFREGS_PER_UAR;
 }
 
-static int num_med_uuar(struct mlx5_uuar_info *uuari)
+static int num_med_bfreg(struct mlx5_ib_dev *dev,
+			 struct mlx5_bfreg_info *bfregi)
 {
 	int n;
 
-	n = uuari->num_uars * MLX5_NON_FP_BF_REGS_PER_PAGE -
-		uuari->num_low_latency_uuars - 1;
+	n = max_bfregs(dev, bfregi) - bfregi->num_low_latency_bfregs -
+	    NUM_NON_BLUE_FLAME_BFREGS;
 
 	return n >= 0 ? n : 0;
 }
 
-static int max_uuari(struct mlx5_uuar_info *uuari)
-{
-	return uuari->num_uars * 4;
-}
-
-static int first_hi_uuar(struct mlx5_uuar_info *uuari)
+static int first_hi_bfreg(struct mlx5_ib_dev *dev,
+			  struct mlx5_bfreg_info *bfregi)
 {
 	int med;
-	int i;
-	int t;
-
-	med = num_med_uuar(uuari);
-	for (t = 0, i = first_med_uuar();; i = next_uuar(i)) {
-		t++;
-		if (t == med)
-			return next_uuar(i);
-	}
 
-	return 0;
+	med = num_med_bfreg(dev, bfregi);
+	return ++med;
 }
 
-static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
+static int alloc_high_class_bfreg(struct mlx5_ib_dev *dev,
+				  struct mlx5_bfreg_info *bfregi)
 {
 	int i;
 
-	for (i = first_hi_uuar(uuari); i < max_uuari(uuari); i = next_uuar(i)) {
-		if (!test_bit(i, uuari->bitmap)) {
-			set_bit(i, uuari->bitmap);
-			uuari->count[i]++;
+	for (i = first_hi_bfreg(dev, bfregi); i < max_bfregs(dev, bfregi); i++) {
+		if (!bfregi->count[i]) {
+			bfregi->count[i]++;
 			return i;
 		}
 	}
@@ -536,87 +529,61 @@ static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
 	return -ENOMEM;
 }
 
-static int alloc_med_class_uuar(struct mlx5_uuar_info *uuari)
+static int alloc_med_class_bfreg(struct mlx5_ib_dev *dev,
+				 struct mlx5_bfreg_info *bfregi)
 {
-	int minidx = first_med_uuar();
+	int minidx = first_med_bfreg();
 	int i;
 
-	for (i = first_med_uuar(); i < first_hi_uuar(uuari); i = next_uuar(i)) {
-		if (uuari->count[i] < uuari->count[minidx])
+	for (i = first_med_bfreg(); i < first_hi_bfreg(dev, bfregi); i++) {
+		if (bfregi->count[i] < bfregi->count[minidx])
 			minidx = i;
+		if (!bfregi->count[minidx])
+			break;
 	}
 
-	uuari->count[minidx]++;
+	bfregi->count[minidx]++;
 	return minidx;
 }
 
-static int alloc_uuar(struct mlx5_uuar_info *uuari,
-		      enum mlx5_ib_latency_class lat)
+static int alloc_bfreg(struct mlx5_ib_dev *dev,
+		       struct mlx5_bfreg_info *bfregi,
+		       enum mlx5_ib_latency_class lat)
 {
-	int uuarn = -EINVAL;
+	int bfregn = -EINVAL;
 
-	mutex_lock(&uuari->lock);
+	mutex_lock(&bfregi->lock);
 	switch (lat) {
 	case MLX5_IB_LATENCY_CLASS_LOW:
-		uuarn = 0;
-		uuari->count[uuarn]++;
+		BUILD_BUG_ON(NUM_NON_BLUE_FLAME_BFREGS != 1);
+		bfregn = 0;
+		bfregi->count[bfregn]++;
 		break;
 
 	case MLX5_IB_LATENCY_CLASS_MEDIUM:
-		if (uuari->ver < 2)
-			uuarn = -ENOMEM;
+		if (bfregi->ver < 2)
+			bfregn = -ENOMEM;
 		else
-			uuarn = alloc_med_class_uuar(uuari);
+			bfregn = alloc_med_class_bfreg(dev, bfregi);
 		break;
 
 	case MLX5_IB_LATENCY_CLASS_HIGH:
-		if (uuari->ver < 2)
-			uuarn = -ENOMEM;
+		if (bfregi->ver < 2)
+			bfregn = -ENOMEM;
 		else
-			uuarn = alloc_high_class_uuar(uuari);
-		break;
-
-	case MLX5_IB_LATENCY_CLASS_FAST_PATH:
-		uuarn = 2;
+			bfregn = alloc_high_class_bfreg(dev, bfregi);
 		break;
 	}
-	mutex_unlock(&uuari->lock);
+	mutex_unlock(&bfregi->lock);
 
-	return uuarn;
+	return bfregn;
 }
 
-static void free_med_class_uuar(struct mlx5_uuar_info *uuari, int uuarn)
+static void free_bfreg(struct mlx5_ib_dev *dev, struct mlx5_bfreg_info *bfregi, int bfregn)
 {
-	clear_bit(uuarn, uuari->bitmap);
-	--uuari->count[uuarn];
-}
-
-static void free_high_class_uuar(struct mlx5_uuar_info *uuari, int uuarn)
-{
-	clear_bit(uuarn, uuari->bitmap);
-	--uuari->count[uuarn];
-}
-
-static void free_uuar(struct mlx5_uuar_info *uuari, int uuarn)
-{
-	int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE;
-	int high_uuar = nuuars - uuari->num_low_latency_uuars;
-
-	mutex_lock(&uuari->lock);
-	if (uuarn == 0) {
-		--uuari->count[uuarn];
-		goto out;
-	}
-
-	if (uuarn < high_uuar) {
-		free_med_class_uuar(uuari, uuarn);
-		goto out;
-	}
-
-	free_high_class_uuar(uuari, uuarn);
-
-out:
-	mutex_unlock(&uuari->lock);
+	mutex_lock(&bfregi->lock);
+	bfregi->count[bfregn]--;
+	mutex_unlock(&bfregi->lock);
 }
 
 static enum mlx5_qp_state to_mlx5_state(enum ib_qp_state state)
@@ -657,9 +624,20 @@ static void mlx5_ib_lock_cqs(struct mlx5_ib_cq *send_cq,
 static void mlx5_ib_unlock_cqs(struct mlx5_ib_cq *send_cq,
 			       struct mlx5_ib_cq *recv_cq);
 
-static int uuarn_to_uar_index(struct mlx5_uuar_info *uuari, int uuarn)
+static int bfregn_to_uar_index(struct mlx5_ib_dev *dev,
+			       struct mlx5_bfreg_info *bfregi, int bfregn)
 {
-	return uuari->uars[uuarn / MLX5_BF_REGS_PER_PAGE].index;
+	int bfregs_per_sys_page;
+	int index_of_sys_page;
+	int offset;
+
+	bfregs_per_sys_page = get_uars_per_sys_page(dev, bfregi->lib_uar_4k) *
+				MLX5_NON_FP_BFREGS_PER_UAR;
+	index_of_sys_page = bfregn / bfregs_per_sys_page;
+
+	offset = bfregn % bfregs_per_sys_page / MLX5_NON_FP_BFREGS_PER_UAR;
+
+	return bfregi->sys_pages[index_of_sys_page] + offset;
 }
 
 static int mlx5_ib_umem_get(struct mlx5_ib_dev *dev,
@@ -762,6 +740,13 @@ err_umem:
 	return err;
 }
 
+static int adjust_bfregn(struct mlx5_ib_dev *dev,
+			 struct mlx5_bfreg_info *bfregi, int bfregn)
+{
+	return bfregn / MLX5_NON_FP_BFREGS_PER_UAR * MLX5_BFREGS_PER_UAR +
+				bfregn % MLX5_NON_FP_BFREGS_PER_UAR;
+}
+
 static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			  struct mlx5_ib_qp *qp, struct ib_udata *udata,
 			  struct ib_qp_init_attr *attr,
@@ -776,7 +761,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	int uar_index;
 	int npages;
 	u32 offset = 0;
-	int uuarn;
+	int bfregn;
 	int ncont = 0;
 	__be64 *pas;
 	void *qpc;
@@ -794,27 +779,27 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	 */
 	if (qp->flags & MLX5_IB_QP_CROSS_CHANNEL)
 		/* In CROSS_CHANNEL CQ and QP must use the same UAR */
-		uuarn = MLX5_CROSS_CHANNEL_UUAR;
+		bfregn = MLX5_CROSS_CHANNEL_BFREG;
 	else {
-		uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_HIGH);
-		if (uuarn < 0) {
-			mlx5_ib_dbg(dev, "failed to allocate low latency UUAR\n");
+		bfregn = alloc_bfreg(dev, &context->bfregi, MLX5_IB_LATENCY_CLASS_HIGH);
+		if (bfregn < 0) {
+			mlx5_ib_dbg(dev, "failed to allocate low latency BFREG\n");
 			mlx5_ib_dbg(dev, "reverting to medium latency\n");
-			uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_MEDIUM);
-			if (uuarn < 0) {
-				mlx5_ib_dbg(dev, "failed to allocate medium latency UUAR\n");
+			bfregn = alloc_bfreg(dev, &context->bfregi, MLX5_IB_LATENCY_CLASS_MEDIUM);
+			if (bfregn < 0) {
+				mlx5_ib_dbg(dev, "failed to allocate medium latency BFREG\n");
 				mlx5_ib_dbg(dev, "reverting to high latency\n");
-				uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
-				if (uuarn < 0) {
-					mlx5_ib_warn(dev, "uuar allocation failed\n");
-					return uuarn;
+				bfregn = alloc_bfreg(dev, &context->bfregi, MLX5_IB_LATENCY_CLASS_LOW);
+				if (bfregn < 0) {
+					mlx5_ib_warn(dev, "bfreg allocation failed\n");
+					return bfregn;
 				}
 			}
 		}
 	}
 
-	uar_index = uuarn_to_uar_index(&context->uuari, uuarn);
-	mlx5_ib_dbg(dev, "uuarn 0x%x, uar_index 0x%x\n", uuarn, uar_index);
+	uar_index = bfregn_to_uar_index(dev, &context->bfregi, bfregn);
+	mlx5_ib_dbg(dev, "bfregn 0x%x, uar_index 0x%x\n", bfregn, uar_index);
 
 	qp->rq.offset = 0;
 	qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB);
@@ -822,7 +807,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 
 	err = set_user_buf_size(dev, qp, &ucmd, base, attr);
 	if (err)
-		goto err_uuar;
+		goto err_bfreg;
 
 	if (ucmd.buf_addr && ubuffer->buf_size) {
 		ubuffer->buf_addr = ucmd.buf_addr;
@@ -831,7 +816,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 				       &ubuffer->umem, &npages, &page_shift,
 				       &ncont, &offset);
 		if (err)
-			goto err_uuar;
+			goto err_bfreg;
 	} else {
 		ubuffer->umem = NULL;
 	}
@@ -854,8 +839,8 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	MLX5_SET(qpc, qpc, page_offset, offset);
 
 	MLX5_SET(qpc, qpc, uar_page, uar_index);
-	resp->uuar_index = uuarn;
-	qp->uuarn = uuarn;
+	resp->bfreg_index = adjust_bfregn(dev, &context->bfregi, bfregn);
+	qp->bfregn = bfregn;
 
 	err = mlx5_ib_db_map_user(context, ucmd.db_addr, &qp->db);
 	if (err) {
@@ -882,13 +867,13 @@ err_umem:
 	if (ubuffer->umem)
 		ib_umem_release(ubuffer->umem);
 
-err_uuar:
-	free_uuar(&context->uuari, uuarn);
+err_bfreg:
+	free_bfreg(dev, &context->bfregi, bfregn);
 	return err;
 }
 
-static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp,
-			    struct mlx5_ib_qp_base *base)
+static void destroy_qp_user(struct mlx5_ib_dev *dev, struct ib_pd *pd,
+			    struct mlx5_ib_qp *qp, struct mlx5_ib_qp_base *base)
 {
 	struct mlx5_ib_ucontext *context;
 
@@ -896,7 +881,7 @@ static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp,
 	mlx5_ib_db_unmap_user(context, &qp->db);
 	if (base->ubuffer.umem)
 		ib_umem_release(base->ubuffer.umem);
-	free_uuar(&context->uuari, qp->uuarn);
+	free_bfreg(dev, &context->bfregi, qp->bfregn);
 }
 
 static int create_kernel_qp(struct mlx5_ib_dev *dev,
@@ -905,14 +890,10 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 			    u32 **in, int *inlen,
 			    struct mlx5_ib_qp_base *base)
 {
-	enum mlx5_ib_latency_class lc = MLX5_IB_LATENCY_CLASS_LOW;
-	struct mlx5_uuar_info *uuari;
 	int uar_index;
 	void *qpc;
-	int uuarn;
 	int err;
 
-	uuari = &dev->mdev->priv.uuari;
 	if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN |
 					IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK |
 					IB_QP_CREATE_IPOIB_UD_LSO |
@@ -920,21 +901,20 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 		return -EINVAL;
 
 	if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
-		lc = MLX5_IB_LATENCY_CLASS_FAST_PATH;
-
-	uuarn = alloc_uuar(uuari, lc);
-	if (uuarn < 0) {
-		mlx5_ib_dbg(dev, "\n");
-		return -ENOMEM;
-	}
+		qp->bf.bfreg = &dev->fp_bfreg;
+	else
+		qp->bf.bfreg = &dev->bfreg;
 
-	qp->bf = &uuari->bfs[uuarn];
-	uar_index = qp->bf->uar->index;
+	/* We need to divide by two since each register is comprised of
+	 * two buffers of identical size, namely odd and even
+	 */
+	qp->bf.buf_size = (1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size)) / 2;
+	uar_index = qp->bf.bfreg->index;
 
 	err = calc_sq_size(dev, init_attr, qp);
 	if (err < 0) {
 		mlx5_ib_dbg(dev, "err %d\n", err);
-		goto err_uuar;
+		return err;
 	}
 
 	qp->rq.offset = 0;
@@ -944,7 +924,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	err = mlx5_buf_alloc(dev->mdev, base->ubuffer.buf_size, &qp->buf);
 	if (err) {
 		mlx5_ib_dbg(dev, "err %d\n", err);
-		goto err_uuar;
+		return err;
 	}
 
 	qp->sq.qend = mlx5_get_send_wqe(qp, qp->sq.wqe_cnt);
@@ -994,34 +974,30 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	return 0;
 
 err_wrid:
-	mlx5_db_free(dev->mdev, &qp->db);
 	kfree(qp->sq.wqe_head);
 	kfree(qp->sq.w_list);
 	kfree(qp->sq.wrid);
 	kfree(qp->sq.wr_data);
 	kfree(qp->rq.wrid);
+	mlx5_db_free(dev->mdev, &qp->db);
 
 err_free:
 	kvfree(*in);
 
 err_buf:
 	mlx5_buf_free(dev->mdev, &qp->buf);
-
-err_uuar:
-	free_uuar(&dev->mdev->priv.uuari, uuarn);
 	return err;
 }
 
 static void destroy_qp_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 {
-	mlx5_db_free(dev->mdev, &qp->db);
 	kfree(qp->sq.wqe_head);
 	kfree(qp->sq.w_list);
 	kfree(qp->sq.wrid);
 	kfree(qp->sq.wr_data);
 	kfree(qp->rq.wrid);
+	mlx5_db_free(dev->mdev, &qp->db);
 	mlx5_buf_free(dev->mdev, &qp->buf);
-	free_uuar(&dev->mdev->priv.uuari, qp->bf->uuarn);
 }
 
 static u32 get_rx_type(struct mlx5_ib_qp *qp, struct ib_qp_init_attr *attr)
@@ -1168,7 +1144,8 @@ static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 		return -ENOMEM;
 
 	rqc = MLX5_ADDR_OF(create_rq_in, in, ctx);
-	MLX5_SET(rqc, rqc, vsd, 1);
+	if (!(rq->flags & MLX5_IB_RQ_CVLAN_STRIPPING))
+		MLX5_SET(rqc, rqc, vsd, 1);
 	MLX5_SET(rqc, rqc, mem_rq_type, MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE);
 	MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST);
 	MLX5_SET(rqc, rqc, flush_in_error_en, 1);
@@ -1265,6 +1242,8 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (qp->rq.wqe_cnt) {
 		rq->base.container_mibqp = qp;
 
+		if (qp->flags & MLX5_IB_QP_CVLAN_STRIPPING)
+			rq->flags |= MLX5_IB_RQ_CVLAN_STRIPPING;
 		err = create_raw_packet_qp_rq(dev, rq, in);
 		if (err)
 			goto err_destroy_sq;
@@ -1353,7 +1332,7 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (init_attr->create_flags || init_attr->send_cq)
 		return -EINVAL;
 
-	min_resp_len = offsetof(typeof(resp), uuar_index) + sizeof(resp.uuar_index);
+	min_resp_len = offsetof(typeof(resp), bfreg_index) + sizeof(resp.bfreg_index);
 	if (udata->outlen < min_resp_len)
 		return -EINVAL;
 
@@ -1526,9 +1505,6 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	       &qp->raw_packet_qp.rq.base :
 	       &qp->trans_qp.base;
 
-	if (init_attr->qp_type != IB_QPT_RAW_PACKET)
-		mlx5_ib_odp_create_qp(qp);
-
 	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
@@ -1589,6 +1565,14 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
 		qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE;
 
+	if (init_attr->create_flags & IB_QP_CREATE_CVLAN_STRIPPING) {
+		if (!(MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
+		      MLX5_CAP_ETH(dev->mdev, vlan_cap)) ||
+		    (init_attr->qp_type != IB_QPT_RAW_PACKET))
+			return -EOPNOTSUPP;
+		qp->flags |= MLX5_IB_QP_CVLAN_STRIPPING;
+	}
+
 	if (pd && pd->uobject) {
 		if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
 			mlx5_ib_dbg(dev, "copy failed\n");
@@ -1795,7 +1779,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 
 err_create:
 	if (qp->create_type == MLX5_QP_USER)
-		destroy_qp_user(pd, qp, base);
+		destroy_qp_user(dev, pd, qp, base);
 	else if (qp->create_type == MLX5_QP_KERNEL)
 		destroy_qp_kernel(dev, qp);
 
@@ -1923,7 +1907,6 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 
 	if (qp->state != IB_QPS_RESET) {
 		if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET) {
-			mlx5_ib_qp_disable_pagefaults(qp);
 			err = mlx5_core_qp_modify(dev->mdev,
 						  MLX5_CMD_OP_2RST_QP, 0,
 						  NULL, &base->mqp);
@@ -1974,7 +1957,7 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 	if (qp->create_type == MLX5_QP_KERNEL)
 		destroy_qp_kernel(dev, qp);
 	else if (qp->create_type == MLX5_QP_USER)
-		destroy_qp_user(&get_pd(qp)->ibpd, qp, base);
+		destroy_qp_user(dev, &get_pd(qp)->ibpd, qp, base);
 }
 
 static const char *ib_qp_type_str(enum ib_qp_type type)
@@ -2229,6 +2212,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 {
 	enum rdma_link_layer ll = rdma_port_get_link_layer(&dev->ib_dev, port);
 	int err;
+	enum ib_gid_type gid_type;
 
 	if (attr_mask & IB_QP_PKEY_INDEX)
 		path->pkey_index = cpu_to_be16(alt ? attr->alt_pkey_index :
@@ -2247,10 +2231,16 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (ll == IB_LINK_LAYER_ETHERNET) {
 		if (!(ah->ah_flags & IB_AH_GRH))
 			return -EINVAL;
+		err = mlx5_get_roce_gid_type(dev, port, ah->grh.sgid_index,
+					     &gid_type);
+		if (err)
+			return err;
 		memcpy(path->rmac, ah->dmac, sizeof(ah->dmac));
 		path->udp_sport = mlx5_get_roce_udp_sport(dev, port,
 							  ah->grh.sgid_index);
 		path->dci_cfi_prio_sl = (ah->sl & 0x7) << 4;
+		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+			path->ecn_dscp = (ah->grh.traffic_class >> 2) & 0x3f;
 	} else {
 		path->fl_free_ar = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
 		path->fl_free_ar |=
@@ -2453,7 +2443,7 @@ static int modify_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 	if (raw_qp_param->set_mask & MLX5_RAW_QP_MOD_SET_RQ_Q_CTR_ID) {
 		if (MLX5_CAP_GEN(dev->mdev, modify_rq_counter_set_id)) {
 			MLX5_SET64(modify_rq_in, in, modify_bitmask,
-				   MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_MODIFY_RQ_COUNTER_SET_ID);
+				   MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_RQ_COUNTER_SET_ID);
 			MLX5_SET(rqc, rqc, counter_set_id, raw_qp_param->rq_q_ctr_id);
 		} else
 			pr_info_once("%s: RAW PACKET QP counters are not supported on current FW\n",
@@ -2808,7 +2798,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 			       qp->port) - 1;
 		mibport = &dev->port[port_num];
 		context->qp_counter_set_usr_page |=
-			cpu_to_be32((u32)(mibport->q_cnt_id) << 24);
+			cpu_to_be32((u32)(mibport->q_cnts.set_id) << 24);
 	}
 
 	if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
@@ -2823,16 +2813,6 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (mlx5_st < 0)
 		goto out;
 
-	/* If moving to a reset or error state, we must disable page faults on
-	 * this QP and flush all current page faults. Otherwise a stale page
-	 * fault may attempt to work on this QP after it is reset and moved
-	 * again to RTS, and may cause the driver and the device to get out of
-	 * sync. */
-	if (cur_state != IB_QPS_RESET && cur_state != IB_QPS_ERR &&
-	    (new_state == IB_QPS_RESET || new_state == IB_QPS_ERR) &&
-	    (qp->ibqp.qp_type != IB_QPT_RAW_PACKET))
-		mlx5_ib_qp_disable_pagefaults(qp);
-
 	if (mlx5_cur >= MLX5_QP_NUM_STATE || mlx5_new >= MLX5_QP_NUM_STATE ||
 	    !optab[mlx5_cur][mlx5_new])
 		goto out;
@@ -2846,7 +2826,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 
 		raw_qp_param.operation = op;
 		if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
-			raw_qp_param.rq_q_ctr_id = mibport->q_cnt_id;
+			raw_qp_param.rq_q_ctr_id = mibport->q_cnts.set_id;
 			raw_qp_param.set_mask |= MLX5_RAW_QP_MOD_SET_RQ_Q_CTR_ID;
 		}
 
@@ -2864,10 +2844,6 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (err)
 		goto out;
 
-	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT &&
-	    (qp->ibqp.qp_type != IB_QPT_RAW_PACKET))
-		mlx5_ib_qp_enable_pagefaults(qp);
-
 	qp->state = new_state;
 
 	if (attr_mask & IB_QP_ACCESS_FLAGS)
@@ -3029,20 +3005,20 @@ static void *set_eth_seg(struct mlx5_wqe_eth_seg *eseg,
 
 	if (wr->opcode == IB_WR_LSO) {
 		struct ib_ud_wr *ud_wr = container_of(wr, struct ib_ud_wr, wr);
-		int size_of_inl_hdr_start = sizeof(eseg->inline_hdr_start);
+		int size_of_inl_hdr_start = sizeof(eseg->inline_hdr.start);
 		u64 left, leftlen, copysz;
 		void *pdata = ud_wr->header;
 
 		left = ud_wr->hlen;
 		eseg->mss = cpu_to_be16(ud_wr->mss);
-		eseg->inline_hdr_sz = cpu_to_be16(left);
+		eseg->inline_hdr.sz = cpu_to_be16(left);
 
 		/*
 		 * check if there is space till the end of queue, if yes,
 		 * copy all in one shot, otherwise copy till the end of queue,
 		 * rollback and than the copy the left
 		 */
-		leftlen = qend - (void *)eseg->inline_hdr_start;
+		leftlen = qend - (void *)eseg->inline_hdr.start;
 		copysz = min_t(u64, leftlen, left);
 
 		memcpy(seg - size_of_inl_hdr_start, pdata, copysz);
@@ -3080,9 +3056,10 @@ static void set_data_ptr_seg(struct mlx5_wqe_data_seg *dseg, struct ib_sge *sg)
 	dseg->addr       = cpu_to_be64(sg->addr);
 }
 
-static __be16 get_klm_octo(int npages)
+static u64 get_xlt_octo(u64 bytes)
 {
-	return cpu_to_be16(ALIGN(npages, 8) / 2);
+	return ALIGN(bytes, MLX5_IB_UMR_XLT_ALIGNMENT) /
+	       MLX5_IB_UMR_OCTOWORD;
 }
 
 static __be64 frwr_mkey_mask(void)
@@ -3127,18 +3104,14 @@ static __be64 sig_mkey_mask(void)
 }
 
 static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
-				struct mlx5_ib_mr *mr)
+			    struct mlx5_ib_mr *mr)
 {
-	int ndescs = mr->ndescs;
+	int size = mr->ndescs * mr->desc_size;
 
 	memset(umr, 0, sizeof(*umr));
 
-	if (mr->access_mode == MLX5_MKC_ACCESS_MODE_KLMS)
-		/* KLMs take twice the size of MTTs */
-		ndescs *= 2;
-
 	umr->flags = MLX5_UMR_CHECK_NOT_FREE;
-	umr->klm_octowords = get_klm_octo(ndescs);
+	umr->xlt_octowords = cpu_to_be16(get_xlt_octo(size));
 	umr->mkey_mask = frwr_mkey_mask();
 }
 
@@ -3149,37 +3122,17 @@ static void set_linv_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr)
 	umr->flags = MLX5_UMR_INLINE;
 }
 
-static __be64 get_umr_reg_mr_mask(int atomic)
+static __be64 get_umr_enable_mr_mask(void)
 {
 	u64 result;
 
-	result = MLX5_MKEY_MASK_LEN		|
-		 MLX5_MKEY_MASK_PAGE_SIZE	|
-		 MLX5_MKEY_MASK_START_ADDR	|
-		 MLX5_MKEY_MASK_PD		|
-		 MLX5_MKEY_MASK_LR		|
-		 MLX5_MKEY_MASK_LW		|
-		 MLX5_MKEY_MASK_KEY		|
-		 MLX5_MKEY_MASK_RR		|
-		 MLX5_MKEY_MASK_RW		|
+	result = MLX5_MKEY_MASK_KEY |
 		 MLX5_MKEY_MASK_FREE;
 
-	if (atomic)
-		result |= MLX5_MKEY_MASK_A;
-
-	return cpu_to_be64(result);
-}
-
-static __be64 get_umr_unreg_mr_mask(void)
-{
-	u64 result;
-
-	result = MLX5_MKEY_MASK_FREE;
-
 	return cpu_to_be64(result);
 }
 
-static __be64 get_umr_update_mtt_mask(void)
+static __be64 get_umr_disable_mr_mask(void)
 {
 	u64 result;
 
@@ -3194,23 +3147,22 @@ static __be64 get_umr_update_translation_mask(void)
 
 	result = MLX5_MKEY_MASK_LEN |
 		 MLX5_MKEY_MASK_PAGE_SIZE |
-		 MLX5_MKEY_MASK_START_ADDR |
-		 MLX5_MKEY_MASK_KEY |
-		 MLX5_MKEY_MASK_FREE;
+		 MLX5_MKEY_MASK_START_ADDR;
 
 	return cpu_to_be64(result);
 }
 
-static __be64 get_umr_update_access_mask(void)
+static __be64 get_umr_update_access_mask(int atomic)
 {
 	u64 result;
 
-	result = MLX5_MKEY_MASK_LW |
+	result = MLX5_MKEY_MASK_LR |
+		 MLX5_MKEY_MASK_LW |
 		 MLX5_MKEY_MASK_RR |
-		 MLX5_MKEY_MASK_RW |
-		 MLX5_MKEY_MASK_A |
-		 MLX5_MKEY_MASK_KEY |
-		 MLX5_MKEY_MASK_FREE;
+		 MLX5_MKEY_MASK_RW;
+
+	if (atomic)
+		result |= MLX5_MKEY_MASK_A;
 
 	return cpu_to_be64(result);
 }
@@ -3219,9 +3171,7 @@ static __be64 get_umr_update_pd_mask(void)
 {
 	u64 result;
 
-	result = MLX5_MKEY_MASK_PD |
-		 MLX5_MKEY_MASK_KEY |
-		 MLX5_MKEY_MASK_FREE;
+	result = MLX5_MKEY_MASK_PD;
 
 	return cpu_to_be64(result);
 }
@@ -3238,24 +3188,24 @@ static void set_reg_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 	else
 		umr->flags = MLX5_UMR_CHECK_NOT_FREE; /* fail if not free */
 
-	if (!(wr->send_flags & MLX5_IB_SEND_UMR_UNREG)) {
-		umr->klm_octowords = get_klm_octo(umrwr->npages);
-		if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_MTT) {
-			umr->mkey_mask = get_umr_update_mtt_mask();
-			umr->bsf_octowords = get_klm_octo(umrwr->target.offset);
-			umr->flags |= MLX5_UMR_TRANSLATION_OFFSET_EN;
-		}
-		if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_TRANSLATION)
-			umr->mkey_mask |= get_umr_update_translation_mask();
-		if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_ACCESS)
-			umr->mkey_mask |= get_umr_update_access_mask();
-		if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_PD)
-			umr->mkey_mask |= get_umr_update_pd_mask();
-		if (!umr->mkey_mask)
-			umr->mkey_mask = get_umr_reg_mr_mask(atomic);
-	} else {
-		umr->mkey_mask = get_umr_unreg_mr_mask();
+	umr->xlt_octowords = cpu_to_be16(get_xlt_octo(umrwr->xlt_size));
+	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_XLT) {
+		u64 offset = get_xlt_octo(umrwr->offset);
+
+		umr->xlt_offset = cpu_to_be16(offset & 0xffff);
+		umr->xlt_offset_47_16 = cpu_to_be32(offset >> 16);
+		umr->flags |= MLX5_UMR_TRANSLATION_OFFSET_EN;
+	}
+	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_TRANSLATION)
+		umr->mkey_mask |= get_umr_update_translation_mask();
+	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS) {
+		umr->mkey_mask |= get_umr_update_access_mask(atomic);
+		umr->mkey_mask |= get_umr_update_pd_mask();
 	}
+	if (wr->send_flags & MLX5_IB_SEND_UMR_ENABLE_MR)
+		umr->mkey_mask |= get_umr_enable_mr_mask();
+	if (wr->send_flags & MLX5_IB_SEND_UMR_DISABLE_MR)
+		umr->mkey_mask |= get_umr_disable_mr_mask();
 
 	if (!wr->num_sge)
 		umr->flags |= MLX5_UMR_INLINE;
@@ -3303,17 +3253,17 @@ static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *w
 	struct mlx5_umr_wr *umrwr = umr_wr(wr);
 
 	memset(seg, 0, sizeof(*seg));
-	if (wr->send_flags & MLX5_IB_SEND_UMR_UNREG) {
+	if (wr->send_flags & MLX5_IB_SEND_UMR_DISABLE_MR)
 		seg->status = MLX5_MKEY_STATUS_FREE;
-		return;
-	}
 
 	seg->flags = convert_access(umrwr->access_flags);
-	if (!(wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_MTT)) {
-		if (umrwr->pd)
-			seg->flags_pd = cpu_to_be32(to_mpd(umrwr->pd)->pdn);
-		seg->start_addr = cpu_to_be64(umrwr->target.virt_addr);
-	}
+	if (umrwr->pd)
+		seg->flags_pd = cpu_to_be32(to_mpd(umrwr->pd)->pdn);
+	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_TRANSLATION &&
+	    !umrwr->length)
+		seg->flags_pd |= cpu_to_be32(MLX5_MKEY_LEN64);
+
+	seg->start_addr = cpu_to_be64(umrwr->virt_addr);
 	seg->len = cpu_to_be64(umrwr->length);
 	seg->log2_page_size = umrwr->page_shift;
 	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff00 |
@@ -3611,7 +3561,7 @@ static int set_sig_data_segment(struct ib_sig_handover_wr *wr,
 }
 
 static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
-				 struct ib_sig_handover_wr *wr, u32 nelements,
+				 struct ib_sig_handover_wr *wr, u32 size,
 				 u32 length, u32 pdn)
 {
 	struct ib_mr *sig_mr = wr->sig_mr;
@@ -3626,17 +3576,17 @@ static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
 	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL | sigerr << 26 |
 				    MLX5_MKEY_BSF_EN | pdn);
 	seg->len = cpu_to_be64(length);
-	seg->xlt_oct_size = cpu_to_be32(be16_to_cpu(get_klm_octo(nelements)));
+	seg->xlt_oct_size = cpu_to_be32(get_xlt_octo(size));
 	seg->bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
 }
 
 static void set_sig_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
-				u32 nelements)
+				u32 size)
 {
 	memset(umr, 0, sizeof(*umr));
 
 	umr->flags = MLX5_FLAGS_INLINE | MLX5_FLAGS_CHECK_FREE;
-	umr->klm_octowords = get_klm_octo(nelements);
+	umr->xlt_octowords = cpu_to_be16(get_xlt_octo(size));
 	umr->bsf_octowords = cpu_to_be16(MLX5_MKEY_BSF_OCTO_SIZE);
 	umr->mkey_mask = sig_mkey_mask();
 }
@@ -3648,7 +3598,7 @@ static int set_sig_umr_wr(struct ib_send_wr *send_wr, struct mlx5_ib_qp *qp,
 	struct ib_sig_handover_wr *wr = sig_handover_wr(send_wr);
 	struct mlx5_ib_mr *sig_mr = to_mmr(wr->sig_mr);
 	u32 pdn = get_pd(qp)->pdn;
-	u32 klm_oct_size;
+	u32 xlt_size;
 	int region_len, ret;
 
 	if (unlikely(wr->wr.num_sge != 1) ||
@@ -3670,15 +3620,15 @@ static int set_sig_umr_wr(struct ib_send_wr *send_wr, struct mlx5_ib_qp *qp,
 	 * then we use strided block format (3 octowords),
 	 * else we use single KLM (1 octoword)
 	 **/
-	klm_oct_size = wr->prot ? 3 : 1;
+	xlt_size = wr->prot ? 0x30 : sizeof(struct mlx5_klm);
 
-	set_sig_umr_segment(*seg, klm_oct_size);
+	set_sig_umr_segment(*seg, xlt_size);
 	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
 	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
 	if (unlikely((*seg == qp->sq.qend)))
 		*seg = mlx5_get_send_wqe(qp, 0);
 
-	set_sig_mkey_segment(*seg, wr, klm_oct_size, region_len, pdn);
+	set_sig_mkey_segment(*seg, wr, xlt_size, region_len, pdn);
 	*seg += sizeof(struct mlx5_mkey_seg);
 	*size += sizeof(struct mlx5_mkey_seg) / 16;
 	if (unlikely((*seg == qp->sq.qend)))
@@ -3708,8 +3658,9 @@ static int set_psv_wr(struct ib_sig_domain *domain,
 		psv_seg->ref_tag = cpu_to_be32(domain->sig.dif.ref_tag);
 		break;
 	default:
-		pr_err("Bad signature type given.\n");
-		return 1;
+		pr_err("Bad signature type (%d) is given.\n",
+		       domain->sig_type);
+		return -EINVAL;
 	}
 
 	*seg += sizeof(*psv_seg);
@@ -3784,24 +3735,6 @@ static void dump_wqe(struct mlx5_ib_qp *qp, int idx, int size_16)
 	}
 }
 
-static void mlx5_bf_copy(u64 __iomem *dst, u64 *src,
-			 unsigned bytecnt, struct mlx5_ib_qp *qp)
-{
-	while (bytecnt > 0) {
-		__iowrite64_copy(dst++, src++, 8);
-		__iowrite64_copy(dst++, src++, 8);
-		__iowrite64_copy(dst++, src++, 8);
-		__iowrite64_copy(dst++, src++, 8);
-		__iowrite64_copy(dst++, src++, 8);
-		__iowrite64_copy(dst++, src++, 8);
-		__iowrite64_copy(dst++, src++, 8);
-		__iowrite64_copy(dst++, src++, 8);
-		bytecnt -= 64;
-		if (unlikely(src == qp->sq.qend))
-			src = mlx5_get_send_wqe(qp, 0);
-	}
-}
-
 static u8 get_fence(u8 fence, struct ib_send_wr *wr)
 {
 	if (unlikely(wr->opcode == IB_WR_LOCAL_INV &&
@@ -3897,7 +3830,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		return mlx5_ib_gsi_post_send(ibqp, wr, bad_wr);
 
 	qp = to_mqp(ibqp);
-	bf = qp->bf;
+	bf = &qp->bf;
 	qend = qp->sq.qend;
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
@@ -4067,6 +4000,12 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			break;
 
 		case IB_QPT_SMI:
+			if (unlikely(!mdev->port_caps[qp->port - 1].has_smi)) {
+				mlx5_ib_warn(dev, "Send SMP MADs is not allowed\n");
+				err = -EPERM;
+				*bad_wr = wr;
+				goto out;
+			}
 		case MLX5_IB_QPT_HW_GSI:
 			set_datagram_seg(seg, wr);
 			seg += sizeof(struct mlx5_wqe_datagram_seg);
@@ -4170,28 +4109,13 @@ out:
 		 * we hit doorbell */
 		wmb();
 
-		if (bf->need_lock)
-			spin_lock(&bf->lock);
-		else
-			__acquire(&bf->lock);
-
-		/* TBD enable WC */
-		if (0 && nreq == 1 && bf->uuarn && inl && size > 1 && size <= bf->buf_size / 16) {
-			mlx5_bf_copy(bf->reg + bf->offset, (u64 *)ctrl, ALIGN(size * 16, 64), qp);
-			/* wc_wmb(); */
-		} else {
-			mlx5_write64((__be32 *)ctrl, bf->regreg + bf->offset,
-				     MLX5_GET_DOORBELL_LOCK(&bf->lock32));
-			/* Make sure doorbells don't leak out of SQ spinlock
-			 * and reach the HCA out of order.
-			 */
-			mmiowb();
-		}
+		/* currently we support only regular doorbells */
+		mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset, NULL);
+		/* Make sure doorbells don't leak out of SQ spinlock
+		 * and reach the HCA out of order.
+		 */
+		mmiowb();
 		bf->offset ^= bf->buf_size;
-		if (bf->need_lock)
-			spin_unlock(&bf->lock);
-		else
-			__release(&bf->lock);
 	}
 
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
@@ -4559,14 +4483,6 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 		return mlx5_ib_gsi_query_qp(ibqp, qp_attr, qp_attr_mask,
 					    qp_init_attr);
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	/*
-	 * Wait for any outstanding page faults, in case the user frees memory
-	 * based upon this query's result.
-	 */
-	flush_workqueue(mlx5_ib_page_fault_wq);
-#endif
-
 	mutex_lock(&qp->mutex);
 
 	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) {
@@ -4691,6 +4607,7 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 		      struct ib_wq_init_attr *init_attr)
 {
 	struct mlx5_ib_dev *dev;
+	int has_net_offloads;
 	__be64 *rq_pas0;
 	void *in;
 	void *rqc;
@@ -4722,9 +4639,28 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 	MLX5_SET(wq, wq, log_wq_pg_sz, rwq->log_page_size);
 	MLX5_SET(wq, wq, wq_signature, rwq->wq_sig);
 	MLX5_SET64(wq, wq, dbr_addr, rwq->db.dma);
+	has_net_offloads = MLX5_CAP_GEN(dev->mdev, eth_net_offloads);
+	if (init_attr->create_flags & IB_WQ_FLAGS_CVLAN_STRIPPING) {
+		if (!(has_net_offloads && MLX5_CAP_ETH(dev->mdev, vlan_cap))) {
+			mlx5_ib_dbg(dev, "VLAN offloads are not supported\n");
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+	} else {
+		MLX5_SET(rqc, rqc, vsd, 1);
+	}
+	if (init_attr->create_flags & IB_WQ_FLAGS_SCATTER_FCS) {
+		if (!(has_net_offloads && MLX5_CAP_ETH(dev->mdev, scatter_fcs))) {
+			mlx5_ib_dbg(dev, "Scatter FCS is not supported\n");
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+		MLX5_SET(rqc, rqc, scatter_fcs, 1);
+	}
 	rq_pas0 = (__be64 *)MLX5_ADDR_OF(wq, wq, pas);
 	mlx5_ib_populate_pas(dev, rwq->umem, rwq->page_shift, rq_pas0, 0);
 	err = mlx5_core_create_rq_tracked(dev->mdev, in, inlen, &rwq->core_qp);
+out:
 	kvfree(in);
 	return err;
 }
@@ -5008,10 +4944,37 @@ int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 	MLX5_SET(modify_rq_in, in, rq_state, curr_wq_state);
 	MLX5_SET(rqc, rqc, state, wq_state);
 
+	if (wq_attr_mask & IB_WQ_FLAGS) {
+		if (wq_attr->flags_mask & IB_WQ_FLAGS_CVLAN_STRIPPING) {
+			if (!(MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
+			      MLX5_CAP_ETH(dev->mdev, vlan_cap))) {
+				mlx5_ib_dbg(dev, "VLAN offloads are not "
+					    "supported\n");
+				err = -EOPNOTSUPP;
+				goto out;
+			}
+			MLX5_SET64(modify_rq_in, in, modify_bitmask,
+				   MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_VSD);
+			MLX5_SET(rqc, rqc, vsd,
+				 (wq_attr->flags & IB_WQ_FLAGS_CVLAN_STRIPPING) ? 0 : 1);
+		}
+	}
+
+	if (curr_wq_state == IB_WQS_RESET && wq_state == IB_WQS_RDY) {
+		if (MLX5_CAP_GEN(dev->mdev, modify_rq_counter_set_id)) {
+			MLX5_SET64(modify_rq_in, in, modify_bitmask,
+				   MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_RQ_COUNTER_SET_ID);
+			MLX5_SET(rqc, rqc, counter_set_id, dev->port->q_cnts.set_id);
+		} else
+			pr_info_once("%s: Receive WQ counters are not supported on current FW\n",
+				     dev->ib_dev.name);
+	}
+
 	err = mlx5_core_modify_rq(dev->mdev, rwq->core_qp.qpn, in, inlen);
-	kvfree(in);
 	if (!err)
 		rwq->ibwq.state = (wq_state == MLX5_RQC_STATE_ERR) ? IB_WQS_ERR : wq_state;
 
+out:
+	kvfree(in);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 6f4397ee1ed6..7cb145f9a6db 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -165,8 +165,6 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 	int err;
 	int i;
 	struct mlx5_wqe_srq_next_seg *next;
-	int page_shift;
-	int npages;
 
 	err = mlx5_db_alloc(dev->mdev, &srq->db);
 	if (err) {
@@ -179,7 +177,6 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 		err = -ENOMEM;
 		goto err_db;
 	}
-	page_shift = srq->buf.page_shift;
 
 	srq->head    = 0;
 	srq->tail    = srq->msrq.max - 1;
@@ -191,10 +188,8 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 			cpu_to_be16((i + 1) & (srq->msrq.max - 1));
 	}
 
-	npages = DIV_ROUND_UP(srq->buf.npages, 1 << (page_shift - PAGE_SHIFT));
-	mlx5_ib_dbg(dev, "buf_size %d, page_shift %d, npages %d, calc npages %d\n",
-		    buf_size, page_shift, srq->buf.npages, npages);
-	in->pas = mlx5_vzalloc(sizeof(*in->pas) * npages);
+	mlx5_ib_dbg(dev, "srq->buf.page_shift = %d\n", srq->buf.page_shift);
+	in->pas = mlx5_vzalloc(sizeof(*in->pas) * srq->buf.npages);
 	if (!in->pas) {
 		err = -ENOMEM;
 		goto err_buf;
@@ -208,7 +203,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 	}
 	srq->wq_sig = !!srq_signature;
 
-	in->log_page_size = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
+	in->log_page_size = srq->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 	if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1 &&
 	    in->type == IB_SRQT_XRC)
 		in->user_index = MLX5_IB_DEFAULT_UIDX;
diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c
index ded76c101dde..c309e5c96383 100644
--- a/drivers/infiniband/hw/mthca/mthca_main.c
+++ b/drivers/infiniband/hw/mthca/mthca_main.c
@@ -851,20 +851,18 @@ err_uar_table_free:
 
 static int mthca_enable_msi_x(struct mthca_dev *mdev)
 {
-	struct msix_entry entries[3];
 	int err;
 
-	entries[0].entry = 0;
-	entries[1].entry = 1;
-	entries[2].entry = 2;
-
-	err = pci_enable_msix_exact(mdev->pdev, entries, ARRAY_SIZE(entries));
-	if (err)
+	err = pci_alloc_irq_vectors(mdev->pdev, 3, 3, PCI_IRQ_MSIX);
+	if (err < 0)
 		return err;
 
-	mdev->eq_table.eq[MTHCA_EQ_COMP ].msi_x_vector = entries[0].vector;
-	mdev->eq_table.eq[MTHCA_EQ_ASYNC].msi_x_vector = entries[1].vector;
-	mdev->eq_table.eq[MTHCA_EQ_CMD  ].msi_x_vector = entries[2].vector;
+	mdev->eq_table.eq[MTHCA_EQ_COMP ].msi_x_vector =
+			pci_irq_vector(mdev->pdev, 0);
+	mdev->eq_table.eq[MTHCA_EQ_ASYNC].msi_x_vector =
+			pci_irq_vector(mdev->pdev, 1);
+	mdev->eq_table.eq[MTHCA_EQ_CMD  ].msi_x_vector =
+			pci_irq_vector(mdev->pdev, 2);
 
 	return 0;
 }
@@ -1018,7 +1016,7 @@ static int __mthca_init_one(struct pci_dev *pdev, int hca_type)
 	err = mthca_setup_hca(mdev);
 	if (err == -EBUSY && (mdev->mthca_flags & MTHCA_FLAG_MSI_X)) {
 		if (mdev->mthca_flags & MTHCA_FLAG_MSI_X)
-			pci_disable_msix(pdev);
+			pci_free_irq_vectors(pdev);
 		mdev->mthca_flags &= ~MTHCA_FLAG_MSI_X;
 
 		err = mthca_setup_hca(mdev);
@@ -1062,7 +1060,7 @@ err_cleanup:
 
 err_close:
 	if (mdev->mthca_flags & MTHCA_FLAG_MSI_X)
-		pci_disable_msix(pdev);
+		pci_free_irq_vectors(pdev);
 
 	mthca_close_hca(mdev);
 
@@ -1113,7 +1111,7 @@ static void __mthca_remove_one(struct pci_dev *pdev)
 		mthca_cmd_cleanup(mdev);
 
 		if (mdev->mthca_flags & MTHCA_FLAG_MSI_X)
-			pci_disable_msix(pdev);
+			pci_free_irq_vectors(pdev);
 
 		ib_dealloc_device(&mdev->ib_dev);
 		pci_release_regions(pdev);
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index d31708742ba5..22d0e6ee5af6 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -146,7 +146,7 @@ static int mthca_query_port(struct ib_device *ibdev,
 	if (!in_mad || !out_mad)
 		goto out;
 
-	memset(props, 0, sizeof *props);
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	init_query_mad(in_mad);
 	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
@@ -212,7 +212,7 @@ static int mthca_modify_port(struct ib_device *ibdev,
 	if (mutex_lock_interruptible(&to_mdev(ibdev)->cap_mask_mutex))
 		return -ERESTARTSYS;
 
-	err = mthca_query_port(ibdev, port, &attr);
+	err = ib_query_port(ibdev, port, &attr);
 	if (err)
 		goto out;
 
@@ -1166,13 +1166,14 @@ static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
-	err = mthca_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
 	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 
 	return 0;
@@ -1223,7 +1224,7 @@ int mthca_register_device(struct mthca_dev *dev)
 	dev->ib_dev.node_type            = RDMA_NODE_IB_CA;
 	dev->ib_dev.phys_port_cnt        = dev->limits.num_ports;
 	dev->ib_dev.num_comp_vectors     = 1;
-	dev->ib_dev.dma_device           = &dev->pdev->dev;
+	dev->ib_dev.dev.parent           = &dev->pdev->dev;
 	dev->ib_dev.query_device         = mthca_query_device;
 	dev->ib_dev.query_port           = mthca_query_port;
 	dev->ib_dev.modify_device        = mthca_modify_device;
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 8e703479e7ce..fb983df7c157 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -135,17 +135,17 @@ static void record_ird_ord(struct nes_cm_node *, u16, u16);
 /* instance of function pointers for client API */
 /* set address of this instance to cm_core->cm_ops at cm_core alloc */
 static const struct nes_cm_ops nes_cm_api = {
-	mini_cm_accelerated,
-	mini_cm_listen,
-	mini_cm_del_listen,
-	mini_cm_connect,
-	mini_cm_close,
-	mini_cm_accept,
-	mini_cm_reject,
-	mini_cm_recv_pkt,
-	mini_cm_dealloc_core,
-	mini_cm_get,
-	mini_cm_set
+	.accelerated = mini_cm_accelerated,
+	.listen = mini_cm_listen,
+	.stop_listener = mini_cm_del_listen,
+	.connect = mini_cm_connect,
+	.close = mini_cm_close,
+	.accept = mini_cm_accept,
+	.reject = mini_cm_reject,
+	.recv_pkt = mini_cm_recv_pkt,
+	.destroy_cm_core = mini_cm_dealloc_core,
+	.get = mini_cm_get,
+	.set = mini_cm_set
 };
 
 static struct nes_cm_core *g_cm_core;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 5a31f3c6a421..ccf0a4cffe9c 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -475,7 +475,7 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr
 	struct nes_vnic *nesvnic = to_nesvnic(ibdev);
 	struct net_device *netdev = nesvnic->netdev;
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->max_mtu = IB_MTU_4096;
 	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
@@ -3660,13 +3660,14 @@ static int nes_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
 	err = nes_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
 
 	return 0;
 }
@@ -3730,7 +3731,6 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev)
 
 	nesibdev->ibdev.phys_port_cnt = 1;
 	nesibdev->ibdev.num_comp_vectors = 1;
-	nesibdev->ibdev.dma_device = &nesdev->pcidev->dev;
 	nesibdev->ibdev.dev.parent = &nesdev->pcidev->dev;
 	nesibdev->ibdev.query_device = nes_query_device;
 	nesibdev->ibdev.query_port = nes_query_port;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 14d33b0f3950..cd66e1e45dd7 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -59,7 +59,7 @@ static u16 ocrdma_hdr_type_to_proto_num(int devid, u8 hdr_type)
 {
 	switch (hdr_type) {
 	case OCRDMA_L3_TYPE_IB_GRH:
-		return (u16)0x8915;
+		return (u16)ETH_P_IBOE;
 	case OCRDMA_L3_TYPE_IPV4:
 		return (u16)0x0800;
 	case OCRDMA_L3_TYPE_IPV6:
@@ -94,7 +94,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 	proto_num = ocrdma_hdr_type_to_proto_num(dev->id, ah->hdr_type);
 	if (!proto_num)
 		return -EINVAL;
-	nxthdr = (proto_num == 0x8915) ? 0x1b : 0x11;
+	nxthdr = (proto_num == ETH_P_IBOE) ? 0x1b : 0x11;
 	/* VLAN */
 	if (!vlan_tag || (vlan_tag > 0xFFF))
 		vlan_tag = dev->pvid;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 9a305201545e..aa6967197620 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -44,6 +44,7 @@
 #include <linux/interrupt.h>
 #include <linux/log2.h>
 #include <linux/dma-mapping.h>
+#include <linux/if_ether.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_user_verbs.h>
@@ -2984,7 +2985,7 @@ static int ocrdma_parse_dcbxcfg_rsp(struct ocrdma_dev *dev, int ptype,
 				OCRDMA_APP_PARAM_APP_PROTO_MASK;
 
 		if (
-			valid && proto == OCRDMA_APP_PROTO_ROCE &&
+			valid && proto == ETH_P_IBOE &&
 			proto_sel == OCRDMA_PROTO_SELECT_L2) {
 			for (slindx = 0; slindx <
 				OCRDMA_MAX_SERVICE_LEVEL_INDEX; slindx++) {
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 896071502739..57c9a2ad0260 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -93,15 +93,16 @@ static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
 	int err;
 
 	dev = get_ocrdma_dev(ibdev);
-	err = ocrdma_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+	if (ocrdma_is_udp_encap_supported(dev))
+		immutable->core_cap_flags |= RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
-	if (ocrdma_is_udp_encap_supported(dev))
-		immutable->core_cap_flags |= RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
 	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 
 	return 0;
@@ -198,7 +199,7 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
 	dev->ibdev.alloc_ucontext = ocrdma_alloc_ucontext;
 	dev->ibdev.dealloc_ucontext = ocrdma_dealloc_ucontext;
 	dev->ibdev.mmap = ocrdma_mmap;
-	dev->ibdev.dma_device = &dev->nic_info.pdev->dev;
+	dev->ibdev.dev.parent = &dev->nic_info.pdev->dev;
 
 	dev->ibdev.process_mad = ocrdma_process_mad;
 	dev->ibdev.get_port_immutable = ocrdma_port_immutable;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
index 37df4481bb8f..6ef89c226ad8 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
@@ -1901,7 +1901,6 @@ struct ocrdma_eth_vlan {
 	u8 smac[6];
 	__be16 eth_type;
 	__be16 vlan_tag;
-#define OCRDMA_ROCE_ETH_TYPE 0x8915
 	__be16 roce_eth_type;
 } __packed;
 
@@ -2179,10 +2178,6 @@ enum OCRDMA_DCBX_PARAM_TYPE {
 	OCRDMA_PARAMETER_TYPE_PEER	= 0x02
 };
 
-enum OCRDMA_DCBX_APP_PROTO {
-	OCRDMA_APP_PROTO_ROCE	= 0x8915
-};
-
 enum OCRDMA_DCBX_PROTO {
 	OCRDMA_PROTO_SELECT_L2	= 0x00,
 	OCRDMA_PROTO_SELECT_L4	= 0x01
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 6af44f8db3d5..bc9fb144e57b 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -210,6 +210,7 @@ int ocrdma_query_port(struct ib_device *ibdev,
 	struct ocrdma_dev *dev;
 	struct net_device *netdev;
 
+	/* props being zeroed by the caller, avoid zeroing it here */
 	dev = get_ocrdma_dev(ibdev);
 	if (port > 1) {
 		pr_err("%s(%d) invalid_port=0x%x\n", __func__,
@@ -1170,8 +1171,7 @@ int ocrdma_destroy_cq(struct ib_cq *ibcq)
 
 	dev->cq_tbl[cq->id] = NULL;
 	indx = ocrdma_get_eq_table_index(dev, cq->eqn);
-	if (indx == -EINVAL)
-		BUG();
+	BUG_ON(indx == -EINVAL);
 
 	eq = &dev->eq_tbl[indx];
 	irq = ocrdma_get_irq(dev, eq);
@@ -1741,8 +1741,7 @@ static void ocrdma_discard_cqes(struct ocrdma_qp *qp, struct ocrdma_cq *cq)
 				wqe_idx = (le32_to_cpu(cqe->rq.buftag_qpn) >>
 					OCRDMA_CQE_BUFTAG_SHIFT) &
 					qp->srq->rq.max_wqe_idx;
-				if (wqe_idx < 1)
-					BUG();
+				BUG_ON(wqe_idx < 1);
 				spin_lock_irqsave(&qp->srq->q_lock, flags);
 				ocrdma_hwq_inc_tail(&qp->srq->rq);
 				ocrdma_srq_toggle_bit(qp->srq, wqe_idx - 1);
@@ -2388,15 +2387,13 @@ static int ocrdma_srq_get_idx(struct ocrdma_srq *srq)
 		if (srq->idx_bit_fields[row]) {
 			indx = ffs(srq->idx_bit_fields[row]);
 			indx = (row * 32) + (indx - 1);
-			if (indx >= srq->rq.max_cnt)
-				BUG();
+			BUG_ON(indx >= srq->rq.max_cnt);
 			ocrdma_srq_toggle_bit(srq, indx);
 			break;
 		}
 	}
 
-	if (row == srq->bit_fields_len)
-		BUG();
+	BUG_ON(row == srq->bit_fields_len);
 	return indx + 1; /* Use from index 1 */
 }
 
@@ -2754,8 +2751,7 @@ static void ocrdma_update_free_srq_cqe(struct ib_wc *ibwc,
 	srq = get_ocrdma_srq(qp->ibqp.srq);
 	wqe_idx = (le32_to_cpu(cqe->rq.buftag_qpn) >>
 		OCRDMA_CQE_BUFTAG_SHIFT) & srq->rq.max_wqe_idx;
-	if (wqe_idx < 1)
-		BUG();
+	BUG_ON(wqe_idx < 1);
 
 	ibwc->wr_id = srq->rqe_wr_id_tbl[wqe_idx];
 	spin_lock_irqsave(&srq->q_lock, flags);
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 3ac8aa5ef37d..b9b47e5cc8b3 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -170,7 +170,7 @@ static int qedr_register_device(struct qedr_dev *dev)
 	dev->ibdev.get_port_immutable = qedr_port_immutable;
 	dev->ibdev.get_netdev = qedr_get_netdev;
 
-	dev->ibdev.dma_device = &dev->pdev->dev;
+	dev->ibdev.dev.parent = &dev->pdev->dev;
 
 	dev->ibdev.get_link_layer = qedr_link_layer;
 	dev->ibdev.get_dev_fw_str = qedr_get_dev_fw_str;
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index a9a8d8745d2e..699632893dd9 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -287,7 +287,7 @@ static inline int qedr_gsi_build_header(struct qedr_dev *dev,
 	has_udp = (sgid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP);
 	if (!has_udp) {
 		/* RoCE v1 */
-		ether_type = ETH_P_ROCE;
+		ether_type = ETH_P_IBOE;
 		*roce_mode = ROCE_V1;
 	} else if (ipv6_addr_v4mapped((struct in6_addr *)&sgid)) {
 		/* RoCE v2 IPv4 */
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.h b/drivers/infiniband/hw/qedr/qedr_cm.h
index 9ba6e15cd93f..78efb1b056d1 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.h
+++ b/drivers/infiniband/hw/qedr/qedr_cm.h
@@ -37,7 +37,6 @@
 
 #define QEDR_GSI_MAX_RECV_SGE	(1)	/* LL2 FW limitation */
 
-#define ETH_P_ROCE		(0x8915)
 #define QEDR_ROCE_V2_UDP_SPORT	(0000)
 
 static inline u32 qedr_get_ipv4_from_gid(u8 *gid)
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index c7d6c9a783bd..6b3bb32803bd 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -238,8 +238,8 @@ int qedr_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *attr)
 	}
 
 	rdma_port = dev->ops->rdma_query_port(dev->rdma_ctx);
-	memset(attr, 0, sizeof(*attr));
 
+	/* *attr being zeroed by the caller, avoid zeroing it here */
 	if (rdma_port->port_state == QED_RDMA_PORT_UP) {
 		attr->state = IB_PORT_ACTIVE;
 		attr->phys_state = 5;
@@ -771,8 +771,10 @@ static inline int qedr_init_user_queue(struct ib_ucontext *ib_ctx,
 		goto err0;
 
 	q->pbl_tbl = qedr_alloc_pbl_tbl(dev, &q->pbl_info, GFP_KERNEL);
-	if (IS_ERR_OR_NULL(q->pbl_tbl))
+	if (IS_ERR(q->pbl_tbl)) {
+		rc = PTR_ERR(q->pbl_tbl);
 		goto err0;
+	}
 
 	qedr_populate_pbls(dev, q->umem, q->pbl_tbl, &q->pbl_info);
 
@@ -1086,30 +1088,6 @@ static inline int get_gid_info_from_table(struct ib_qp *ibqp,
 	return 0;
 }
 
-static void qedr_cleanup_user_sq(struct qedr_dev *dev, struct qedr_qp *qp)
-{
-	qedr_free_pbl(dev, &qp->usq.pbl_info, qp->usq.pbl_tbl);
-	ib_umem_release(qp->usq.umem);
-}
-
-static void qedr_cleanup_user_rq(struct qedr_dev *dev, struct qedr_qp *qp)
-{
-	qedr_free_pbl(dev, &qp->urq.pbl_info, qp->urq.pbl_tbl);
-	ib_umem_release(qp->urq.umem);
-}
-
-static void qedr_cleanup_kernel_sq(struct qedr_dev *dev, struct qedr_qp *qp)
-{
-	dev->ops->common->chain_free(dev->cdev, &qp->sq.pbl);
-	kfree(qp->wqe_wr_id);
-}
-
-static void qedr_cleanup_kernel_rq(struct qedr_dev *dev, struct qedr_qp *qp)
-{
-	dev->ops->common->chain_free(dev->cdev, &qp->rq.pbl);
-	kfree(qp->rqe_wr_id);
-}
-
 static int qedr_check_qp_attrs(struct ib_pd *ibpd, struct qedr_dev *dev,
 			       struct ib_qp_init_attr *attrs)
 {
@@ -1198,15 +1176,13 @@ static int qedr_copy_qp_uresp(struct qedr_dev *dev,
 	return rc;
 }
 
-static void qedr_set_qp_init_params(struct qedr_dev *dev,
-				    struct qedr_qp *qp,
-				    struct qedr_pd *pd,
-				    struct ib_qp_init_attr *attrs)
+static void qedr_set_common_qp_params(struct qedr_dev *dev,
+				      struct qedr_qp *qp,
+				      struct qedr_pd *pd,
+				      struct ib_qp_init_attr *attrs)
 {
-	qp->pd = pd;
-
 	spin_lock_init(&qp->q_lock);
-
+	qp->pd = pd;
 	qp->qp_type = attrs->qp_type;
 	qp->max_inline_data = attrs->cap.max_inline_data;
 	qp->sq.max_sges = attrs->cap.max_send_sge;
@@ -1215,103 +1191,161 @@ static void qedr_set_qp_init_params(struct qedr_dev *dev,
 	qp->sq_cq = get_qedr_cq(attrs->send_cq);
 	qp->rq_cq = get_qedr_cq(attrs->recv_cq);
 	qp->dev = dev;
+	qp->rq.max_sges = attrs->cap.max_recv_sge;
 
 	DP_DEBUG(dev, QEDR_MSG_QP,
+		 "RQ params:\trq_max_sges = %d, rq_cq_id = %d\n",
+		 qp->rq.max_sges, qp->rq_cq->icid);
+	DP_DEBUG(dev, QEDR_MSG_QP,
 		 "QP params:\tpd = %d, qp_type = %d, max_inline_data = %d, state = %d, signaled = %d, use_srq=%d\n",
 		 pd->pd_id, qp->qp_type, qp->max_inline_data,
 		 qp->state, qp->signaled, (attrs->srq) ? 1 : 0);
 	DP_DEBUG(dev, QEDR_MSG_QP,
 		 "SQ params:\tsq_max_sges = %d, sq_cq_id = %d\n",
 		 qp->sq.max_sges, qp->sq_cq->icid);
-	qp->rq.max_sges = attrs->cap.max_recv_sge;
-	DP_DEBUG(dev, QEDR_MSG_QP,
-		 "RQ params:\trq_max_sges = %d, rq_cq_id = %d\n",
-		 qp->rq.max_sges, qp->rq_cq->icid);
 }
 
-static inline void
-qedr_init_qp_user_params(struct qed_rdma_create_qp_in_params *params,
-			 struct qedr_create_qp_ureq *ureq)
-{
-	/* QP handle to be written in CQE */
-	params->qp_handle_lo = ureq->qp_handle_lo;
-	params->qp_handle_hi = ureq->qp_handle_hi;
-}
-
-static inline void
-qedr_init_qp_kernel_doorbell_sq(struct qedr_dev *dev, struct qedr_qp *qp)
+static void qedr_set_roce_db_info(struct qedr_dev *dev, struct qedr_qp *qp)
 {
 	qp->sq.db = dev->db_addr +
 		    DB_ADDR_SHIFT(DQ_PWM_OFFSET_XCM_RDMA_SQ_PROD);
 	qp->sq.db_data.data.icid = qp->icid + 1;
+	qp->rq.db = dev->db_addr +
+		    DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_ROCE_RQ_PROD);
+	qp->rq.db_data.data.icid = qp->icid;
 }
 
 static inline void
-qedr_init_qp_kernel_doorbell_rq(struct qedr_dev *dev, struct qedr_qp *qp)
+qedr_init_common_qp_in_params(struct qedr_dev *dev,
+			      struct qedr_pd *pd,
+			      struct qedr_qp *qp,
+			      struct ib_qp_init_attr *attrs,
+			      bool fmr_and_reserved_lkey,
+			      struct qed_rdma_create_qp_in_params *params)
 {
-	qp->rq.db = dev->db_addr +
-		    DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_ROCE_RQ_PROD);
-	qp->rq.db_data.data.icid = qp->icid;
+	/* QP handle to be written in an async event */
+	params->qp_handle_async_lo = lower_32_bits((uintptr_t) qp);
+	params->qp_handle_async_hi = upper_32_bits((uintptr_t) qp);
+
+	params->signal_all = (attrs->sq_sig_type == IB_SIGNAL_ALL_WR);
+	params->fmr_and_reserved_lkey = fmr_and_reserved_lkey;
+	params->pd = pd->pd_id;
+	params->dpi = pd->uctx ? pd->uctx->dpi : dev->dpi;
+	params->sq_cq_id = get_qedr_cq(attrs->send_cq)->icid;
+	params->stats_queue = 0;
+	params->rq_cq_id = get_qedr_cq(attrs->recv_cq)->icid;
+	params->srq_id = 0;
+	params->use_srq = false;
 }
 
-static inline int
-qedr_init_qp_kernel_params_rq(struct qedr_dev *dev,
-			      struct qedr_qp *qp, struct ib_qp_init_attr *attrs)
+static inline void qedr_qp_user_print(struct qedr_dev *dev, struct qedr_qp *qp)
 {
-	/* Allocate driver internal RQ array */
-	qp->rqe_wr_id = kcalloc(qp->rq.max_wr, sizeof(*qp->rqe_wr_id),
-				GFP_KERNEL);
-	if (!qp->rqe_wr_id)
-		return -ENOMEM;
+	DP_DEBUG(dev, QEDR_MSG_QP, "create qp: successfully created user QP. "
+		 "qp=%p. "
+		 "sq_addr=0x%llx, "
+		 "sq_len=%zd, "
+		 "rq_addr=0x%llx, "
+		 "rq_len=%zd"
+		 "\n",
+		 qp,
+		 qp->usq.buf_addr,
+		 qp->usq.buf_len, qp->urq.buf_addr, qp->urq.buf_len);
+}
 
-	DP_DEBUG(dev, QEDR_MSG_QP, "RQ max_wr set to %d.\n", qp->rq.max_wr);
+static void qedr_cleanup_user(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+	if (qp->usq.umem)
+		ib_umem_release(qp->usq.umem);
+	qp->usq.umem = NULL;
 
-	return 0;
+	if (qp->urq.umem)
+		ib_umem_release(qp->urq.umem);
+	qp->urq.umem = NULL;
 }
 
-static inline int
-qedr_init_qp_kernel_params_sq(struct qedr_dev *dev,
-			      struct qedr_qp *qp,
-			      struct ib_qp_init_attr *attrs,
-			      struct qed_rdma_create_qp_in_params *params)
+static int qedr_create_user_qp(struct qedr_dev *dev,
+			       struct qedr_qp *qp,
+			       struct ib_pd *ibpd,
+			       struct ib_udata *udata,
+			       struct ib_qp_init_attr *attrs)
 {
-	u32 temp_max_wr;
+	struct qed_rdma_create_qp_in_params in_params;
+	struct qed_rdma_create_qp_out_params out_params;
+	struct qedr_pd *pd = get_qedr_pd(ibpd);
+	struct ib_ucontext *ib_ctx = NULL;
+	struct qedr_ucontext *ctx = NULL;
+	struct qedr_create_qp_ureq ureq;
+	int rc = -EINVAL;
 
-	/* Allocate driver internal SQ array */
-	temp_max_wr = attrs->cap.max_send_wr * dev->wq_multiplier;
-	temp_max_wr = min_t(u32, temp_max_wr, dev->attr.max_sqe);
+	ib_ctx = ibpd->uobject->context;
+	ctx = get_qedr_ucontext(ib_ctx);
 
-	/* temp_max_wr < attr->max_sqe < u16 so the casting is safe */
-	qp->sq.max_wr = (u16)temp_max_wr;
-	qp->wqe_wr_id = kcalloc(qp->sq.max_wr, sizeof(*qp->wqe_wr_id),
-				GFP_KERNEL);
-	if (!qp->wqe_wr_id)
-		return -ENOMEM;
+	memset(&ureq, 0, sizeof(ureq));
+	rc = ib_copy_from_udata(&ureq, udata, sizeof(ureq));
+	if (rc) {
+		DP_ERR(dev, "Problem copying data from user space\n");
+		return rc;
+	}
 
-	DP_DEBUG(dev, QEDR_MSG_QP, "SQ max_wr set to %d.\n", qp->sq.max_wr);
+	/* SQ - read access only (0), dma sync not required (0) */
+	rc = qedr_init_user_queue(ib_ctx, dev, &qp->usq, ureq.sq_addr,
+				  ureq.sq_len, 0, 0);
+	if (rc)
+		return rc;
 
-	/* QP handle to be written in CQE */
-	params->qp_handle_lo = lower_32_bits((uintptr_t)qp);
-	params->qp_handle_hi = upper_32_bits((uintptr_t)qp);
+	/* RQ - read access only (0), dma sync not required (0) */
+	rc = qedr_init_user_queue(ib_ctx, dev, &qp->urq, ureq.rq_addr,
+				  ureq.rq_len, 0, 0);
+
+	if (rc)
+		return rc;
+
+	memset(&in_params, 0, sizeof(in_params));
+	qedr_init_common_qp_in_params(dev, pd, qp, attrs, false, &in_params);
+	in_params.qp_handle_lo = ureq.qp_handle_lo;
+	in_params.qp_handle_hi = ureq.qp_handle_hi;
+	in_params.sq_num_pages = qp->usq.pbl_info.num_pbes;
+	in_params.sq_pbl_ptr = qp->usq.pbl_tbl->pa;
+	in_params.rq_num_pages = qp->urq.pbl_info.num_pbes;
+	in_params.rq_pbl_ptr = qp->urq.pbl_tbl->pa;
+
+	qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
+					      &in_params, &out_params);
+
+	if (!qp->qed_qp) {
+		rc = -ENOMEM;
+		goto err1;
+	}
+
+	qp->qp_id = out_params.qp_id;
+	qp->icid = out_params.icid;
+
+	rc = qedr_copy_qp_uresp(dev, qp, udata);
+	if (rc)
+		goto err;
+
+	qedr_qp_user_print(dev, qp);
 
 	return 0;
+err:
+	rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp);
+	if (rc)
+		DP_ERR(dev, "create qp: fatal fault. rc=%d", rc);
+
+err1:
+	qedr_cleanup_user(dev, qp);
+	return rc;
 }
 
-static inline int qedr_init_qp_kernel_sq(struct qedr_dev *dev,
-					 struct qedr_qp *qp,
-					 struct ib_qp_init_attr *attrs)
+static int
+qedr_roce_create_kernel_qp(struct qedr_dev *dev,
+			   struct qedr_qp *qp,
+			   struct qed_rdma_create_qp_in_params *in_params,
+			   u32 n_sq_elems, u32 n_rq_elems)
 {
-	u32 n_sq_elems, n_sq_entries;
+	struct qed_rdma_create_qp_out_params out_params;
 	int rc;
 
-	/* A single work request may take up to QEDR_MAX_SQ_WQE_SIZE elements in
-	 * the ring. The ring should allow at least a single WR, even if the
-	 * user requested none, due to allocation issues.
-	 */
-	n_sq_entries = attrs->cap.max_send_wr;
-	n_sq_entries = min_t(u32, n_sq_entries, dev->attr.max_sqe);
-	n_sq_entries = max_t(u32, n_sq_entries, 1);
-	n_sq_elems = n_sq_entries * QEDR_MAX_SQE_ELEMENTS_PER_SQE;
 	rc = dev->ops->common->chain_alloc(dev->cdev,
 					   QED_CHAIN_USE_TO_PRODUCE,
 					   QED_CHAIN_MODE_PBL,
@@ -1319,31 +1353,13 @@ static inline int qedr_init_qp_kernel_sq(struct qedr_dev *dev,
 					   n_sq_elems,
 					   QEDR_SQE_ELEMENT_SIZE,
 					   &qp->sq.pbl);
-	if (rc) {
-		DP_ERR(dev, "failed to allocate QP %p SQ\n", qp);
-		return rc;
-	}
 
-	DP_DEBUG(dev, QEDR_MSG_SQ,
-		 "SQ Pbl base addr = %llx max_send_wr=%d max_wr=%d capacity=%d, rc=%d\n",
-		 qed_chain_get_pbl_phys(&qp->sq.pbl), attrs->cap.max_send_wr,
-		 n_sq_entries, qed_chain_get_capacity(&qp->sq.pbl), rc);
-	return 0;
-}
+	if (rc)
+		return rc;
 
-static inline int qedr_init_qp_kernel_rq(struct qedr_dev *dev,
-					 struct qedr_qp *qp,
-					 struct ib_qp_init_attr *attrs)
-{
-	u32 n_rq_elems, n_rq_entries;
-	int rc;
+	in_params->sq_num_pages = qed_chain_get_page_cnt(&qp->sq.pbl);
+	in_params->sq_pbl_ptr = qed_chain_get_pbl_phys(&qp->sq.pbl);
 
-	/* A single work request may take up to QEDR_MAX_RQ_WQE_SIZE elements in
-	 * the ring. There ring should allow at least a single WR, even if the
-	 * user requested none, due to allocation issues.
-	 */
-	n_rq_entries = max_t(u32, attrs->cap.max_recv_wr, 1);
-	n_rq_elems = n_rq_entries * QEDR_MAX_RQE_ELEMENTS_PER_RQE;
 	rc = dev->ops->common->chain_alloc(dev->cdev,
 					   QED_CHAIN_USE_TO_CONSUME_PRODUCE,
 					   QED_CHAIN_MODE_PBL,
@@ -1351,136 +1367,102 @@ static inline int qedr_init_qp_kernel_rq(struct qedr_dev *dev,
 					   n_rq_elems,
 					   QEDR_RQE_ELEMENT_SIZE,
 					   &qp->rq.pbl);
+	if (rc)
+		return rc;
 
-	if (rc) {
-		DP_ERR(dev, "failed to allocate memory for QP %p RQ\n", qp);
-		return -ENOMEM;
-	}
-
-	DP_DEBUG(dev, QEDR_MSG_RQ,
-		 "RQ Pbl base addr = %llx max_recv_wr=%d max_wr=%d capacity=%d, rc=%d\n",
-		 qed_chain_get_pbl_phys(&qp->rq.pbl), attrs->cap.max_recv_wr,
-		 n_rq_entries, qed_chain_get_capacity(&qp->rq.pbl), rc);
+	in_params->rq_num_pages = qed_chain_get_page_cnt(&qp->rq.pbl);
+	in_params->rq_pbl_ptr = qed_chain_get_pbl_phys(&qp->rq.pbl);
 
-	/* n_rq_entries < u16 so the casting is safe */
-	qp->rq.max_wr = (u16)n_rq_entries;
+	qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
+					      in_params, &out_params);
 
-	return 0;
-}
+	if (!qp->qed_qp)
+		return -EINVAL;
 
-static inline void
-qedr_init_qp_in_params_sq(struct qedr_dev *dev,
-			  struct qedr_pd *pd,
-			  struct qedr_qp *qp,
-			  struct ib_qp_init_attr *attrs,
-			  struct ib_udata *udata,
-			  struct qed_rdma_create_qp_in_params *params)
-{
-	/* QP handle to be written in an async event */
-	params->qp_handle_async_lo = lower_32_bits((uintptr_t)qp);
-	params->qp_handle_async_hi = upper_32_bits((uintptr_t)qp);
+	qp->qp_id = out_params.qp_id;
+	qp->icid = out_params.icid;
 
-	params->signal_all = (attrs->sq_sig_type == IB_SIGNAL_ALL_WR);
-	params->fmr_and_reserved_lkey = !udata;
-	params->pd = pd->pd_id;
-	params->dpi = pd->uctx ? pd->uctx->dpi : dev->dpi;
-	params->sq_cq_id = get_qedr_cq(attrs->send_cq)->icid;
-	params->max_sq_sges = 0;
-	params->stats_queue = 0;
+	qedr_set_roce_db_info(dev, qp);
 
-	if (udata) {
-		params->sq_num_pages = qp->usq.pbl_info.num_pbes;
-		params->sq_pbl_ptr = qp->usq.pbl_tbl->pa;
-	} else {
-		params->sq_num_pages = qed_chain_get_page_cnt(&qp->sq.pbl);
-		params->sq_pbl_ptr = qed_chain_get_pbl_phys(&qp->sq.pbl);
-	}
+	return 0;
 }
 
-static inline void
-qedr_init_qp_in_params_rq(struct qedr_qp *qp,
-			  struct ib_qp_init_attr *attrs,
-			  struct ib_udata *udata,
-			  struct qed_rdma_create_qp_in_params *params)
+static void qedr_cleanup_kernel(struct qedr_dev *dev, struct qedr_qp *qp)
 {
-	params->rq_cq_id = get_qedr_cq(attrs->recv_cq)->icid;
-	params->srq_id = 0;
-	params->use_srq = false;
+	dev->ops->common->chain_free(dev->cdev, &qp->sq.pbl);
+	kfree(qp->wqe_wr_id);
 
-	if (udata) {
-		params->rq_num_pages = qp->urq.pbl_info.num_pbes;
-		params->rq_pbl_ptr = qp->urq.pbl_tbl->pa;
-	} else {
-		params->rq_num_pages = qed_chain_get_page_cnt(&qp->rq.pbl);
-		params->rq_pbl_ptr = qed_chain_get_pbl_phys(&qp->rq.pbl);
-	}
+	dev->ops->common->chain_free(dev->cdev, &qp->rq.pbl);
+	kfree(qp->rqe_wr_id);
 }
 
-static inline void qedr_qp_user_print(struct qedr_dev *dev, struct qedr_qp *qp)
+static int qedr_create_kernel_qp(struct qedr_dev *dev,
+				 struct qedr_qp *qp,
+				 struct ib_pd *ibpd,
+				 struct ib_qp_init_attr *attrs)
 {
-	DP_DEBUG(dev, QEDR_MSG_QP,
-		 "create qp: successfully created user QP. qp=%p, sq_addr=0x%llx, sq_len=%zd, rq_addr=0x%llx, rq_len=%zd\n",
-		 qp, qp->usq.buf_addr, qp->usq.buf_len, qp->urq.buf_addr,
-		 qp->urq.buf_len);
-}
+	struct qed_rdma_create_qp_in_params in_params;
+	struct qedr_pd *pd = get_qedr_pd(ibpd);
+	int rc = -EINVAL;
+	u32 n_rq_elems;
+	u32 n_sq_elems;
+	u32 n_sq_entries;
 
-static inline int qedr_init_user_qp(struct ib_ucontext *ib_ctx,
-				    struct qedr_dev *dev,
-				    struct qedr_qp *qp,
-				    struct qedr_create_qp_ureq *ureq)
-{
-	int rc;
+	memset(&in_params, 0, sizeof(in_params));
 
-	/* SQ - read access only (0), dma sync not required (0) */
-	rc = qedr_init_user_queue(ib_ctx, dev, &qp->usq, ureq->sq_addr,
-				  ureq->sq_len, 0, 0);
-	if (rc)
-		return rc;
+	/* A single work request may take up to QEDR_MAX_SQ_WQE_SIZE elements in
+	 * the ring. The ring should allow at least a single WR, even if the
+	 * user requested none, due to allocation issues.
+	 * We should add an extra WR since the prod and cons indices of
+	 * wqe_wr_id are managed in such a way that the WQ is considered full
+	 * when (prod+1)%max_wr==cons. We currently don't do that because we
+	 * double the number of entries due an iSER issue that pushes far more
+	 * WRs than indicated. If we decline its ib_post_send() then we get
+	 * error prints in the dmesg we'd like to avoid.
+	 */
+	qp->sq.max_wr = min_t(u32, attrs->cap.max_send_wr * dev->wq_multiplier,
+			      dev->attr.max_sqe);
 
-	/* RQ - read access only (0), dma sync not required (0) */
-	rc = qedr_init_user_queue(ib_ctx, dev, &qp->urq, ureq->rq_addr,
-				  ureq->rq_len, 0, 0);
+	qp->wqe_wr_id = kzalloc(qp->sq.max_wr * sizeof(*qp->wqe_wr_id),
+				GFP_KERNEL);
+	if (!qp->wqe_wr_id) {
+		DP_ERR(dev, "create qp: failed SQ shadow memory allocation\n");
+		return -ENOMEM;
+	}
 
-	if (rc)
-		qedr_cleanup_user_sq(dev, qp);
-	return rc;
-}
+	/* QP handle to be written in CQE */
+	in_params.qp_handle_lo = lower_32_bits((uintptr_t) qp);
+	in_params.qp_handle_hi = upper_32_bits((uintptr_t) qp);
 
-static inline int
-qedr_init_kernel_qp(struct qedr_dev *dev,
-		    struct qedr_qp *qp,
-		    struct ib_qp_init_attr *attrs,
-		    struct qed_rdma_create_qp_in_params *params)
-{
-	int rc;
+	/* A single work request may take up to QEDR_MAX_RQ_WQE_SIZE elements in
+	 * the ring. There ring should allow at least a single WR, even if the
+	 * user requested none, due to allocation issues.
+	 */
+	qp->rq.max_wr = (u16) max_t(u32, attrs->cap.max_recv_wr, 1);
 
-	rc = qedr_init_qp_kernel_sq(dev, qp, attrs);
-	if (rc) {
-		DP_ERR(dev, "failed to init kernel QP %p SQ\n", qp);
-		return rc;
+	/* Allocate driver internal RQ array */
+	qp->rqe_wr_id = kzalloc(qp->rq.max_wr * sizeof(*qp->rqe_wr_id),
+				GFP_KERNEL);
+	if (!qp->rqe_wr_id) {
+		DP_ERR(dev,
+		       "create qp: failed RQ shadow memory allocation\n");
+		kfree(qp->wqe_wr_id);
+		return -ENOMEM;
 	}
 
-	rc = qedr_init_qp_kernel_params_sq(dev, qp, attrs, params);
-	if (rc) {
-		dev->ops->common->chain_free(dev->cdev, &qp->sq.pbl);
-		DP_ERR(dev, "failed to init kernel QP %p SQ params\n", qp);
-		return rc;
-	}
+	qedr_init_common_qp_in_params(dev, pd, qp, attrs, true, &in_params);
 
-	rc = qedr_init_qp_kernel_rq(dev, qp, attrs);
-	if (rc) {
-		qedr_cleanup_kernel_sq(dev, qp);
-		DP_ERR(dev, "failed to init kernel QP %p RQ\n", qp);
-		return rc;
-	}
+	n_sq_entries = attrs->cap.max_send_wr;
+	n_sq_entries = min_t(u32, n_sq_entries, dev->attr.max_sqe);
+	n_sq_entries = max_t(u32, n_sq_entries, 1);
+	n_sq_elems = n_sq_entries * QEDR_MAX_SQE_ELEMENTS_PER_SQE;
 
-	rc = qedr_init_qp_kernel_params_rq(dev, qp, attrs);
-	if (rc) {
-		DP_ERR(dev, "failed to init kernel QP %p RQ params\n", qp);
-		qedr_cleanup_kernel_sq(dev, qp);
-		dev->ops->common->chain_free(dev->cdev, &qp->rq.pbl);
-		return rc;
-	}
+	n_rq_elems = qp->rq.max_wr * QEDR_MAX_RQE_ELEMENTS_PER_RQE;
+
+	rc = qedr_roce_create_kernel_qp(dev, qp, &in_params,
+					n_sq_elems, n_rq_elems);
+	if (rc)
+		qedr_cleanup_kernel(dev, qp);
 
 	return rc;
 }
@@ -1490,12 +1472,7 @@ struct ib_qp *qedr_create_qp(struct ib_pd *ibpd,
 			     struct ib_udata *udata)
 {
 	struct qedr_dev *dev = get_qedr_dev(ibpd->device);
-	struct qed_rdma_create_qp_out_params out_params;
-	struct qed_rdma_create_qp_in_params in_params;
 	struct qedr_pd *pd = get_qedr_pd(ibpd);
-	struct ib_ucontext *ib_ctx = NULL;
-	struct qedr_ucontext *ctx = NULL;
-	struct qedr_create_qp_ureq ureq;
 	struct qedr_qp *qp;
 	struct ib_qp *ibqp;
 	int rc = 0;
@@ -1510,101 +1487,42 @@ struct ib_qp *qedr_create_qp(struct ib_pd *ibpd,
 	if (attrs->srq)
 		return ERR_PTR(-EINVAL);
 
-	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
-	if (!qp)
-		return ERR_PTR(-ENOMEM);
-
 	DP_DEBUG(dev, QEDR_MSG_QP,
-		 "create qp: sq_cq=%p, sq_icid=%d, rq_cq=%p, rq_icid=%d\n",
+		 "create qp: called from %s, event_handler=%p, eepd=%p sq_cq=%p, sq_icid=%d, rq_cq=%p, rq_icid=%d\n",
+		 udata ? "user library" : "kernel", attrs->event_handler, pd,
 		 get_qedr_cq(attrs->send_cq),
 		 get_qedr_cq(attrs->send_cq)->icid,
 		 get_qedr_cq(attrs->recv_cq),
 		 get_qedr_cq(attrs->recv_cq)->icid);
 
-	qedr_set_qp_init_params(dev, qp, pd, attrs);
+	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+	if (!qp) {
+		DP_ERR(dev, "create qp: failed allocating memory\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	qedr_set_common_qp_params(dev, qp, pd, attrs);
 
 	if (attrs->qp_type == IB_QPT_GSI) {
-		if (udata) {
-			DP_ERR(dev,
-			       "create qp: unexpected udata when creating GSI QP\n");
-			goto err0;
-		}
 		ibqp = qedr_create_gsi_qp(dev, attrs, qp);
 		if (IS_ERR(ibqp))
 			kfree(qp);
 		return ibqp;
 	}
 
-	memset(&in_params, 0, sizeof(in_params));
-
-	if (udata) {
-		if (!(udata && ibpd->uobject && ibpd->uobject->context))
-			goto err0;
-
-		ib_ctx = ibpd->uobject->context;
-		ctx = get_qedr_ucontext(ib_ctx);
-
-		memset(&ureq, 0, sizeof(ureq));
-		if (ib_copy_from_udata(&ureq, udata, sizeof(ureq))) {
-			DP_ERR(dev,
-			       "create qp: problem copying data from user space\n");
-			goto err0;
-		}
-
-		rc = qedr_init_user_qp(ib_ctx, dev, qp, &ureq);
-		if (rc)
-			goto err0;
-
-		qedr_init_qp_user_params(&in_params, &ureq);
-	} else {
-		rc = qedr_init_kernel_qp(dev, qp, attrs, &in_params);
-		if (rc)
-			goto err0;
-	}
-
-	qedr_init_qp_in_params_sq(dev, pd, qp, attrs, udata, &in_params);
-	qedr_init_qp_in_params_rq(qp, attrs, udata, &in_params);
-
-	qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
-					      &in_params, &out_params);
+	if (udata)
+		rc = qedr_create_user_qp(dev, qp, ibpd, udata, attrs);
+	else
+		rc = qedr_create_kernel_qp(dev, qp, ibpd, attrs);
 
-	if (!qp->qed_qp)
-		goto err1;
+	if (rc)
+		goto err;
 
-	qp->qp_id = out_params.qp_id;
-	qp->icid = out_params.icid;
 	qp->ibqp.qp_num = qp->qp_id;
 
-	if (udata) {
-		rc = qedr_copy_qp_uresp(dev, qp, udata);
-		if (rc)
-			goto err2;
-
-		qedr_qp_user_print(dev, qp);
-	} else {
-		qedr_init_qp_kernel_doorbell_sq(dev, qp);
-		qedr_init_qp_kernel_doorbell_rq(dev, qp);
-	}
-
-	DP_DEBUG(dev, QEDR_MSG_QP, "created %s space QP %p\n",
-		 udata ? "user" : "kernel", qp);
-
 	return &qp->ibqp;
 
-err2:
-	rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp);
-	if (rc)
-		DP_ERR(dev, "create qp: fatal fault. rc=%d", rc);
-err1:
-	if (udata) {
-		qedr_cleanup_user_sq(dev, qp);
-		qedr_cleanup_user_rq(dev, qp);
-	} else {
-		qedr_cleanup_kernel_sq(dev, qp);
-		qedr_cleanup_kernel_rq(dev, qp);
-	}
-
-err0:
+err:
 	kfree(qp);
 
 	return ERR_PTR(-EFAULT);
@@ -2085,6 +2003,24 @@ err:
 	return rc;
 }
 
+int qedr_free_qp_resources(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+	int rc = 0;
+
+	if (qp->qp_type != IB_QPT_GSI) {
+		rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp);
+		if (rc)
+			return rc;
+	}
+
+	if (qp->ibqp.uobject && qp->ibqp.uobject->context)
+		qedr_cleanup_user(dev, qp);
+	else
+		qedr_cleanup_kernel(dev, qp);
+
+	return 0;
+}
+
 int qedr_destroy_qp(struct ib_qp *ibqp)
 {
 	struct qedr_qp *qp = get_qedr_qp(ibqp);
@@ -2107,21 +2043,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp)
 		qedr_modify_qp(ibqp, &attr, attr_mask, NULL);
 	}
 
-	if (qp->qp_type != IB_QPT_GSI) {
-		rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp);
-		if (rc)
-			return rc;
-	} else {
+	if (qp->qp_type == IB_QPT_GSI)
 		qedr_destroy_gsi_qp(dev);
-	}
 
-	if (ibqp->uobject && ibqp->uobject->context) {
-		qedr_cleanup_user_sq(dev, qp);
-		qedr_cleanup_user_rq(dev, qp);
-	} else {
-		qedr_cleanup_kernel_sq(dev, qp);
-		qedr_cleanup_kernel_rq(dev, qp);
-	}
+	qedr_free_qp_resources(dev, qp);
 
 	kfree(qp);
 
@@ -2182,8 +2107,8 @@ static int init_mr_info(struct qedr_dev *dev, struct mr_info *info,
 		goto done;
 
 	info->pbl_table = qedr_alloc_pbl_tbl(dev, &info->pbl_info, GFP_KERNEL);
-	if (!info->pbl_table) {
-		rc = -ENOMEM;
+	if (IS_ERR(info->pbl_table)) {
+		rc = PTR_ERR(info->pbl_table);
 		goto done;
 	}
 
@@ -2194,7 +2119,7 @@ static int init_mr_info(struct qedr_dev *dev, struct mr_info *info,
 	 * list and allocating another one
 	 */
 	tmp = qedr_alloc_pbl_tbl(dev, &info->pbl_info, GFP_KERNEL);
-	if (!tmp) {
+	if (IS_ERR(tmp)) {
 		DP_DEBUG(dev, QEDR_MSG_MR, "Extra PBL is not allocated\n");
 		goto done;
 	}
@@ -3569,14 +3494,15 @@ int qedr_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
-	err = qedr_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE |
+				    RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE |
-				    RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
 	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 
 	return 0;
diff --git a/drivers/infiniband/hw/qib/qib_common.h b/drivers/infiniband/hw/qib/qib_common.h
index 1d6e63eb1146..a4a1f56ce824 100644
--- a/drivers/infiniband/hw/qib/qib_common.h
+++ b/drivers/infiniband/hw/qib/qib_common.h
@@ -742,11 +742,7 @@ struct qib_tid_session_member {
 #define SIZE_OF_CRC 1
 
 #define QIB_DEFAULT_P_KEY 0xFFFF
-#define QIB_AETH_CREDIT_SHIFT 24
-#define QIB_AETH_CREDIT_MASK 0x1F
-#define QIB_AETH_CREDIT_INVAL 0x1F
 #define QIB_PSN_MASK 0xFFFFFF
-#define QIB_MSN_MASK 0xFFFFFF
 #define QIB_EAGER_TID_ID QLOGIC_IB_I_TID_MASK
 #define QIB_MULTICAST_QPN 0xFFFFFF
 
diff --git a/drivers/infiniband/hw/qib/qib_dma.c b/drivers/infiniband/hw/qib/qib_dma.c
deleted file mode 100644
index 59fe092b4b0f..000000000000
--- a/drivers/infiniband/hw/qib/qib_dma.c
+++ /dev/null
@@ -1,169 +0,0 @@
-/*
- * Copyright (c) 2006, 2009, 2010 QLogic, Corporation. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-#include <linux/types.h>
-#include <linux/scatterlist.h>
-
-#include "qib_verbs.h"
-
-#define BAD_DMA_ADDRESS ((u64) 0)
-
-/*
- * The following functions implement driver specific replacements
- * for the ib_dma_*() functions.
- *
- * These functions return kernel virtual addresses instead of
- * device bus addresses since the driver uses the CPU to copy
- * data instead of using hardware DMA.
- */
-
-static int qib_mapping_error(struct ib_device *dev, u64 dma_addr)
-{
-	return dma_addr == BAD_DMA_ADDRESS;
-}
-
-static u64 qib_dma_map_single(struct ib_device *dev, void *cpu_addr,
-			      size_t size, enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-	return (u64) cpu_addr;
-}
-
-static void qib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size,
-				 enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-}
-
-static u64 qib_dma_map_page(struct ib_device *dev, struct page *page,
-			    unsigned long offset, size_t size,
-			    enum dma_data_direction direction)
-{
-	u64 addr;
-
-	BUG_ON(!valid_dma_direction(direction));
-
-	if (offset + size > PAGE_SIZE) {
-		addr = BAD_DMA_ADDRESS;
-		goto done;
-	}
-
-	addr = (u64) page_address(page);
-	if (addr)
-		addr += offset;
-	/* TODO: handle highmem pages */
-
-done:
-	return addr;
-}
-
-static void qib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size,
-			       enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-}
-
-static int qib_map_sg(struct ib_device *dev, struct scatterlist *sgl,
-		      int nents, enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	u64 addr;
-	int i;
-	int ret = nents;
-
-	BUG_ON(!valid_dma_direction(direction));
-
-	for_each_sg(sgl, sg, nents, i) {
-		addr = (u64) page_address(sg_page(sg));
-		/* TODO: handle highmem pages */
-		if (!addr) {
-			ret = 0;
-			break;
-		}
-		sg->dma_address = addr + sg->offset;
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-	}
-	return ret;
-}
-
-static void qib_unmap_sg(struct ib_device *dev,
-			 struct scatterlist *sg, int nents,
-			 enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-}
-
-static void qib_sync_single_for_cpu(struct ib_device *dev, u64 addr,
-				    size_t size, enum dma_data_direction dir)
-{
-}
-
-static void qib_sync_single_for_device(struct ib_device *dev, u64 addr,
-				       size_t size,
-				       enum dma_data_direction dir)
-{
-}
-
-static void *qib_dma_alloc_coherent(struct ib_device *dev, size_t size,
-				    u64 *dma_handle, gfp_t flag)
-{
-	struct page *p;
-	void *addr = NULL;
-
-	p = alloc_pages(flag, get_order(size));
-	if (p)
-		addr = page_address(p);
-	if (dma_handle)
-		*dma_handle = (u64) addr;
-	return addr;
-}
-
-static void qib_dma_free_coherent(struct ib_device *dev, size_t size,
-				  void *cpu_addr, u64 dma_handle)
-{
-	free_pages((unsigned long) cpu_addr, get_order(size));
-}
-
-struct ib_dma_mapping_ops qib_dma_mapping_ops = {
-	.mapping_error = qib_mapping_error,
-	.map_single = qib_dma_map_single,
-	.unmap_single = qib_dma_unmap_single,
-	.map_page = qib_dma_map_page,
-	.unmap_page = qib_dma_unmap_page,
-	.map_sg = qib_map_sg,
-	.unmap_sg = qib_unmap_sg,
-	.sync_single_for_cpu = qib_sync_single_for_cpu,
-	.sync_single_for_device = qib_sync_single_for_device,
-	.alloc_coherent = qib_dma_alloc_coherent,
-	.free_coherent = qib_dma_free_coherent
-};
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 2d1eacf1dfed..9396c1807cc3 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -893,7 +893,7 @@ bail:
 /*
  * qib_file_vma_fault - handle a VMA page fault.
  */
-static int qib_file_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int qib_file_vma_fault(struct vm_fault *vmf)
 {
 	struct page *page;
 
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index 92399d3ffd15..06de1cbcf67d 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -707,7 +707,7 @@ static void qib_6120_clear_freeze(struct qib_devdata *dd)
 	/* disable error interrupts, to avoid confusion */
 	qib_write_kreg(dd, kr_errmask, 0ULL);
 
-	/* also disable interrupts; errormask is sometimes overwriten */
+	/* also disable interrupts; errormask is sometimes overwritten */
 	qib_6120_set_intr_state(dd, 0);
 
 	qib_cancel_sends(dd->pport);
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index e55e31a69195..55a18384c22d 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -1259,7 +1259,7 @@ static void qib_7220_clear_freeze(struct qib_devdata *dd)
 	/* disable error interrupts, to avoid confusion */
 	qib_write_kreg(dd, kr_errmask, 0ULL);
 
-	/* also disable interrupts; errormask is sometimes overwriten */
+	/* also disable interrupts; errormask is sometimes overwritten */
 	qib_7220_set_intr_state(dd, 0);
 
 	qib_cancel_sends(dd->pport);
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index c4a3616062f1..12c4208fd701 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -2053,7 +2053,7 @@ static void qib_7322_clear_freeze(struct qib_devdata *dd)
 			qib_write_kreg_port(dd->pport + pidx, krp_errmask,
 					    0ULL);
 
-	/* also disable interrupts; errormask is sometimes overwriten */
+	/* also disable interrupts; errormask is sometimes overwritten */
 	qib_7322_set_intr_state(dd, 0);
 
 	/* clear the freeze, and be sure chip saw it */
@@ -2893,7 +2893,6 @@ static void qib_setup_7322_cleanup(struct qib_devdata *dd)
 			dd->cspec->gpio_mask &= ~mask;
 			qib_write_kreg(dd, kr_gpio_mask, dd->cspec->gpio_mask);
 			spin_unlock_irqrestore(&dd->cspec->gpio_lock, flags);
-			qib_qsfp_deinit(&dd->pport[i].cpspec->qsfp_data);
 		}
 	}
 }
diff --git a/drivers/infiniband/hw/qib/qib_keys.c b/drivers/infiniband/hw/qib/qib_keys.c
index 2c3c93572c17..8fdf79f8d4e4 100644
--- a/drivers/infiniband/hw/qib/qib_keys.c
+++ b/drivers/infiniband/hw/qib/qib_keys.c
@@ -158,10 +158,7 @@ int qib_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
 	unsigned n, m;
 	size_t off;
 
-	/*
-	 * We use RKEY == zero for kernel virtual addresses
-	 * (see qib_get_dma_mr and qib_dma.c).
-	 */
+	/* We use RKEY == zero for kernel virtual addresses */
 	rcu_read_lock();
 	if (rkey == 0) {
 		struct rvt_pd *pd = ibpd_to_rvtpd(qp->ibqp.pd);
diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c
index 6abe1c621aa4..c379b8342a09 100644
--- a/drivers/infiniband/hw/qib/qib_pcie.c
+++ b/drivers/infiniband/hw/qib/qib_pcie.c
@@ -682,13 +682,6 @@ qib_pci_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_CAN_RECOVER;
 }
 
-static pci_ers_result_t
-qib_pci_link_reset(struct pci_dev *pdev)
-{
-	qib_devinfo(pdev, "QIB link_reset function called, ignored\n");
-	return PCI_ERS_RESULT_CAN_RECOVER;
-}
-
 static void
 qib_pci_resume(struct pci_dev *pdev)
 {
@@ -707,7 +700,6 @@ qib_pci_resume(struct pci_dev *pdev)
 const struct pci_error_handlers qib_pci_err_handler = {
 	.error_detected = qib_pci_error_detected,
 	.mmio_enabled = qib_pci_mmio_enabled,
-	.link_reset = qib_pci_link_reset,
 	.slot_reset = qib_pci_slot_reset,
 	.resume = qib_pci_resume,
 };
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 99d31efe4c2f..2ac0c0f79e74 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -61,43 +61,6 @@ static inline unsigned find_next_offset(struct rvt_qpn_table *qpt,
 	return off;
 }
 
-/*
- * Convert the AETH credit code into the number of credits.
- */
-static u32 credit_table[31] = {
-	0,                      /* 0 */
-	1,                      /* 1 */
-	2,                      /* 2 */
-	3,                      /* 3 */
-	4,                      /* 4 */
-	6,                      /* 5 */
-	8,                      /* 6 */
-	12,                     /* 7 */
-	16,                     /* 8 */
-	24,                     /* 9 */
-	32,                     /* A */
-	48,                     /* B */
-	64,                     /* C */
-	96,                     /* D */
-	128,                    /* E */
-	192,                    /* F */
-	256,                    /* 10 */
-	384,                    /* 11 */
-	512,                    /* 12 */
-	768,                    /* 13 */
-	1024,                   /* 14 */
-	1536,                   /* 15 */
-	2048,                   /* 16 */
-	3072,                   /* 17 */
-	4096,                   /* 18 */
-	6144,                   /* 19 */
-	8192,                   /* 1A */
-	12288,                  /* 1B */
-	16384,                  /* 1C */
-	24576,                  /* 1D */
-	32768                   /* 1E */
-};
-
 const struct rvt_operation_params qib_post_parms[RVT_OPERATION_MAX] = {
 [IB_WR_RDMA_WRITE] = {
 	.length = sizeof(struct ib_rdma_wr),
@@ -354,66 +317,6 @@ u32 qib_mtu_from_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, u32 pmtu)
 	return ib_mtu_enum_to_int(pmtu);
 }
 
-/**
- * qib_compute_aeth - compute the AETH (syndrome + MSN)
- * @qp: the queue pair to compute the AETH for
- *
- * Returns the AETH.
- */
-__be32 qib_compute_aeth(struct rvt_qp *qp)
-{
-	u32 aeth = qp->r_msn & QIB_MSN_MASK;
-
-	if (qp->ibqp.srq) {
-		/*
-		 * Shared receive queues don't generate credits.
-		 * Set the credit field to the invalid value.
-		 */
-		aeth |= QIB_AETH_CREDIT_INVAL << QIB_AETH_CREDIT_SHIFT;
-	} else {
-		u32 min, max, x;
-		u32 credits;
-		struct rvt_rwq *wq = qp->r_rq.wq;
-		u32 head;
-		u32 tail;
-
-		/* sanity check pointers before trusting them */
-		head = wq->head;
-		if (head >= qp->r_rq.size)
-			head = 0;
-		tail = wq->tail;
-		if (tail >= qp->r_rq.size)
-			tail = 0;
-		/*
-		 * Compute the number of credits available (RWQEs).
-		 * XXX Not holding the r_rq.lock here so there is a small
-		 * chance that the pair of reads are not atomic.
-		 */
-		credits = head - tail;
-		if ((int)credits < 0)
-			credits += qp->r_rq.size;
-		/*
-		 * Binary search the credit table to find the code to
-		 * use.
-		 */
-		min = 0;
-		max = 31;
-		for (;;) {
-			x = (min + max) / 2;
-			if (credit_table[x] == credits)
-				break;
-			if (credit_table[x] > credits)
-				max = x;
-			else if (min == x)
-				break;
-			else
-				min = x;
-		}
-		aeth |= x << QIB_AETH_CREDIT_SHIFT;
-	}
-	return cpu_to_be32(aeth);
-}
-
 void *qib_qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp, gfp_t gfp)
 {
 	struct qib_qp_priv *priv;
@@ -448,7 +351,6 @@ void qib_stop_send_queue(struct rvt_qp *qp)
 	struct qib_qp_priv *priv = qp->priv;
 
 	cancel_work_sync(&priv->s_work);
-	del_timer_sync(&qp->s_timer);
 }
 
 void qib_quiesce_qp(struct rvt_qp *qp)
@@ -474,43 +376,6 @@ void qib_flush_qp_waiters(struct rvt_qp *qp)
 }
 
 /**
- * qib_get_credit - flush the send work queue of a QP
- * @qp: the qp who's send work queue to flush
- * @aeth: the Acknowledge Extended Transport Header
- *
- * The QP s_lock should be held.
- */
-void qib_get_credit(struct rvt_qp *qp, u32 aeth)
-{
-	u32 credit = (aeth >> QIB_AETH_CREDIT_SHIFT) & QIB_AETH_CREDIT_MASK;
-
-	/*
-	 * If the credit is invalid, we can send
-	 * as many packets as we like.  Otherwise, we have to
-	 * honor the credit field.
-	 */
-	if (credit == QIB_AETH_CREDIT_INVAL) {
-		if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT)) {
-			qp->s_flags |= RVT_S_UNLIMITED_CREDIT;
-			if (qp->s_flags & RVT_S_WAIT_SSN_CREDIT) {
-				qp->s_flags &= ~RVT_S_WAIT_SSN_CREDIT;
-				qib_schedule_send(qp);
-			}
-		}
-	} else if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT)) {
-		/* Compute new LSN (i.e., MSN + credit) */
-		credit = (aeth + credit_table[credit]) & QIB_MSN_MASK;
-		if (qib_cmp24(credit, qp->s_lsn) > 0) {
-			qp->s_lsn = credit;
-			if (qp->s_flags & RVT_S_WAIT_SSN_CREDIT) {
-				qp->s_flags &= ~RVT_S_WAIT_SSN_CREDIT;
-				qib_schedule_send(qp);
-			}
-		}
-	}
-}
-
-/**
  * qib_check_send_wqe - validate wr/wqe
  * @qp - The qp
  * @wqe - The built wqe
diff --git a/drivers/infiniband/hw/qib/qib_qsfp.c b/drivers/infiniband/hw/qib/qib_qsfp.c
index 4c7c3c84a741..295d40a83bb6 100644
--- a/drivers/infiniband/hw/qib/qib_qsfp.c
+++ b/drivers/infiniband/hw/qib/qib_qsfp.c
@@ -485,16 +485,6 @@ void qib_qsfp_init(struct qib_qsfp_data *qd,
 	dd->f_gpio_mod(dd, mask, mask, mask);
 }
 
-void qib_qsfp_deinit(struct qib_qsfp_data *qd)
-{
-	/*
-	 * There is nothing to do here for now.  our work is scheduled
-	 * with queue_work(), and flush_workqueue() from remove_one
-	 * will block until all work setup with queue_work()
-	 * completes.
-	 */
-}
-
 int qib_qsfp_dump(struct qib_pportdata *ppd, char *buf, int len)
 {
 	struct qib_qsfp_cache cd;
diff --git a/drivers/infiniband/hw/qib/qib_qsfp.h b/drivers/infiniband/hw/qib/qib_qsfp.h
index 91908f533a2b..ad8dbd6ac0cf 100644
--- a/drivers/infiniband/hw/qib/qib_qsfp.h
+++ b/drivers/infiniband/hw/qib/qib_qsfp.h
@@ -186,4 +186,3 @@ extern int qib_refresh_qsfp_cache(struct qib_pportdata *ppd,
 extern int qib_qsfp_mod_present(struct qib_pportdata *ppd);
 extern void qib_qsfp_init(struct qib_qsfp_data *qd,
 			  void (*fevent)(struct work_struct *));
-extern void qib_qsfp_deinit(struct qib_qsfp_data *qd);
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index 031433cb7206..12658e3fe154 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -38,7 +38,6 @@
 /* cut down ridiculously long IB macro names */
 #define OP(x) IB_OPCODE_RC_##x
 
-static void rc_timeout(unsigned long arg);
 
 static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe,
 		       u32 psn, u32 pmtu)
@@ -50,19 +49,10 @@ static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe,
 	ss->sg_list = wqe->sg_list + 1;
 	ss->num_sge = wqe->wr.num_sge;
 	ss->total_len = wqe->length;
-	qib_skip_sge(ss, len, 0);
+	rvt_skip_sge(ss, len, false);
 	return wqe->length - len;
 }
 
-static void start_timer(struct rvt_qp *qp)
-{
-	qp->s_flags |= RVT_S_TIMER;
-	qp->s_timer.function = rc_timeout;
-	/* 4.096 usec. * (1 << qp->timeout) */
-	qp->s_timer.expires = jiffies + qp->timeout_jiffies;
-	add_timer(&qp->s_timer);
-}
-
 /**
  * qib_make_rc_ack - construct a response packet (ACK, NAK, or RDMA read)
  * @dev: the device for this QP
@@ -144,7 +134,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp,
 				qp->s_ack_state = OP(RDMA_READ_RESPONSE_ONLY);
 				e->sent = 1;
 			}
-			ohdr->u.aeth = qib_compute_aeth(qp);
+			ohdr->u.aeth = rvt_compute_aeth(qp);
 			hwords++;
 			qp->s_ack_rdma_psn = e->psn;
 			bth2 = qp->s_ack_rdma_psn++ & QIB_PSN_MASK;
@@ -153,7 +143,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp,
 			qp->s_cur_sge = NULL;
 			len = 0;
 			qp->s_ack_state = OP(ATOMIC_ACKNOWLEDGE);
-			ohdr->u.at.aeth = qib_compute_aeth(qp);
+			ohdr->u.at.aeth = rvt_compute_aeth(qp);
 			ib_u64_put(e->atomic_data, &ohdr->u.at.atomic_ack_eth);
 			hwords += sizeof(ohdr->u.at) / sizeof(u32);
 			bth2 = e->psn & QIB_PSN_MASK;
@@ -174,7 +164,7 @@ static int qib_make_rc_ack(struct qib_ibdev *dev, struct rvt_qp *qp,
 		if (len > pmtu)
 			len = pmtu;
 		else {
-			ohdr->u.aeth = qib_compute_aeth(qp);
+			ohdr->u.aeth = rvt_compute_aeth(qp);
 			hwords++;
 			qp->s_ack_state = OP(RDMA_READ_RESPONSE_LAST);
 			e = &qp->s_ack_queue[qp->s_tail_ack_queue];
@@ -197,11 +187,11 @@ normal:
 		qp->s_cur_sge = NULL;
 		if (qp->s_nak_state)
 			ohdr->u.aeth =
-				cpu_to_be32((qp->r_msn & QIB_MSN_MASK) |
+				cpu_to_be32((qp->r_msn & IB_MSN_MASK) |
 					    (qp->s_nak_state <<
-					     QIB_AETH_CREDIT_SHIFT));
+					     IB_AETH_CREDIT_SHIFT));
 		else
-			ohdr->u.aeth = qib_compute_aeth(qp);
+			ohdr->u.aeth = rvt_compute_aeth(qp);
 		hwords++;
 		len = 0;
 		bth0 = OP(ACKNOWLEDGE) << 24;
@@ -257,7 +247,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 			goto bail;
 		/* We are in the error state, flush the work request. */
 		smp_read_barrier_depends(); /* see post_one_send() */
-		if (qp->s_last == ACCESS_ONCE(qp->s_head))
+		if (qp->s_last == READ_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (atomic_read(&priv->s_dma_busy)) {
@@ -303,7 +293,8 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 		newreq = 0;
 		if (qp->s_cur == qp->s_tail) {
 			/* Check if send work queue is empty. */
-			if (qp->s_tail == qp->s_head)
+			smp_read_barrier_depends(); /* see post_one_send() */
+			if (qp->s_tail == READ_ONCE(qp->s_head))
 				goto bail;
 			/*
 			 * If a fence is requested, wait for previous
@@ -330,7 +321,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 		case IB_WR_SEND_WITH_IMM:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    qib_cmp24(wqe->ssn, qp->s_lsn + 1) > 0) {
+			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
@@ -361,7 +352,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
-			    qib_cmp24(wqe->ssn, qp->s_lsn + 1) > 0) {
+			    rvt_cmp_msn(wqe->ssn, qp->s_lsn + 1) > 0) {
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
@@ -657,11 +648,11 @@ void qib_send_rc_ack(struct rvt_qp *qp)
 	if (qp->s_mig_state == IB_MIG_MIGRATED)
 		bth0 |= IB_BTH_MIG_REQ;
 	if (qp->r_nak_state)
-		ohdr->u.aeth = cpu_to_be32((qp->r_msn & QIB_MSN_MASK) |
+		ohdr->u.aeth = cpu_to_be32((qp->r_msn & IB_MSN_MASK) |
 					    (qp->r_nak_state <<
-					     QIB_AETH_CREDIT_SHIFT));
+					     IB_AETH_CREDIT_SHIFT));
 	else
-		ohdr->u.aeth = qib_compute_aeth(qp);
+		ohdr->u.aeth = rvt_compute_aeth(qp);
 	lrh0 |= ibp->sl_to_vl[qp->remote_ah_attr.sl] << 12 |
 		qp->remote_ah_attr.sl << 4;
 	hdr.lrh[0] = cpu_to_be16(lrh0);
@@ -836,7 +827,7 @@ done:
  * Back up requester to resend the last un-ACKed request.
  * The QP r_lock and s_lock should be held and interrupts disabled.
  */
-static void qib_restart_rc(struct rvt_qp *qp, u32 psn, int wait)
+void qib_restart_rc(struct rvt_qp *qp, u32 psn, int wait)
 {
 	struct rvt_swqe *wqe = rvt_get_swqe_ptr(qp, qp->s_acked);
 	struct qib_ibport *ibp;
@@ -869,46 +860,6 @@ static void qib_restart_rc(struct rvt_qp *qp, u32 psn, int wait)
 }
 
 /*
- * This is called from s_timer for missing responses.
- */
-static void rc_timeout(unsigned long arg)
-{
-	struct rvt_qp *qp = (struct rvt_qp *)arg;
-	struct qib_ibport *ibp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&qp->r_lock, flags);
-	spin_lock(&qp->s_lock);
-	if (qp->s_flags & RVT_S_TIMER) {
-		ibp = to_iport(qp->ibqp.device, qp->port_num);
-		ibp->rvp.n_rc_timeouts++;
-		qp->s_flags &= ~RVT_S_TIMER;
-		del_timer(&qp->s_timer);
-		qib_restart_rc(qp, qp->s_last_psn + 1, 1);
-		qib_schedule_send(qp);
-	}
-	spin_unlock(&qp->s_lock);
-	spin_unlock_irqrestore(&qp->r_lock, flags);
-}
-
-/*
- * This is called from s_timer for RNR timeouts.
- */
-void qib_rc_rnr_retry(unsigned long arg)
-{
-	struct rvt_qp *qp = (struct rvt_qp *)arg;
-	unsigned long flags;
-
-	spin_lock_irqsave(&qp->s_lock, flags);
-	if (qp->s_flags & RVT_S_WAIT_RNR) {
-		qp->s_flags &= ~RVT_S_WAIT_RNR;
-		del_timer(&qp->s_timer);
-		qib_schedule_send(qp);
-	}
-	spin_unlock_irqrestore(&qp->s_lock, flags);
-}
-
-/*
  * Set qp->s_sending_psn to the next PSN after the given one.
  * This would be psn+1 except when RDMA reads are present.
  */
@@ -944,7 +895,7 @@ void qib_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 	u32 opcode;
 	u32 psn;
 
-	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_OR_FLUSH_SEND))
+	if (!(ib_rvt_state_ops[qp->state] & RVT_SEND_OR_FLUSH_OR_RECV_OK))
 		return;
 
 	/* Find out where the BTH is */
@@ -971,7 +922,7 @@ void qib_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 	if ((psn & IB_BTH_REQ_ACK) && qp->s_acked != qp->s_tail &&
 	    !(qp->s_flags & (RVT_S_TIMER | RVT_S_WAIT_RNR | RVT_S_WAIT_PSN)) &&
 	    (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
-		start_timer(qp);
+		rvt_add_retry_timer(qp);
 
 	while (qp->s_last != qp->s_acked) {
 		u32 s_last;
@@ -1084,12 +1035,6 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 	u32 ack_psn;
 	int diff;
 
-	/* Remove QP from retry timer */
-	if (qp->s_flags & (RVT_S_TIMER | RVT_S_WAIT_RNR)) {
-		qp->s_flags &= ~(RVT_S_TIMER | RVT_S_WAIT_RNR);
-		del_timer(&qp->s_timer);
-	}
-
 	/*
 	 * Note that NAKs implicitly ACK outstanding SEND and RDMA write
 	 * requests and implicitly NAK RDMA read and atomic requests issued
@@ -1097,7 +1042,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 	 * request but will include an ACK'ed request(s).
 	 */
 	ack_psn = psn;
-	if (aeth >> 29)
+	if (aeth >> IB_AETH_NAK_SHIFT)
 		ack_psn--;
 	wqe = rvt_get_swqe_ptr(qp, qp->s_acked);
 	ibp = to_iport(qp->ibqp.device, qp->port_num);
@@ -1177,7 +1122,7 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			break;
 	}
 
-	switch (aeth >> 29) {
+	switch (aeth >> IB_AETH_NAK_SHIFT) {
 	case 0:         /* ACK */
 		this_cpu_inc(*ibp->rvp.rc_acks);
 		if (qp->s_acked != qp->s_tail) {
@@ -1185,27 +1130,30 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 			 * We are expecting more ACKs so
 			 * reset the retransmit timer.
 			 */
-			start_timer(qp);
+			rvt_mod_retry_timer(qp);
 			/*
 			 * We can stop resending the earlier packets and
 			 * continue with the next packet the receiver wants.
 			 */
 			if (qib_cmp24(qp->s_psn, psn) <= 0)
 				reset_psn(qp, psn + 1);
-		} else if (qib_cmp24(qp->s_psn, psn) <= 0) {
-			qp->s_state = OP(SEND_LAST);
-			qp->s_psn = psn + 1;
+		} else {
+			/* No more acks - kill all timers */
+			rvt_stop_rc_timers(qp);
+			if (qib_cmp24(qp->s_psn, psn) <= 0) {
+				qp->s_state = OP(SEND_LAST);
+				qp->s_psn = psn + 1;
+			}
 		}
 		if (qp->s_flags & RVT_S_WAIT_ACK) {
 			qp->s_flags &= ~RVT_S_WAIT_ACK;
 			qib_schedule_send(qp);
 		}
-		qib_get_credit(qp, aeth);
+		rvt_get_credit(qp, aeth);
 		qp->s_rnr_retry = qp->s_rnr_retry_cnt;
 		qp->s_retry = qp->s_retry_cnt;
 		update_last_psn(qp, psn);
-		ret = 1;
-		goto bail;
+		return 1;
 
 	case 1:         /* RNR NAK */
 		ibp->rvp.n_rnr_naks++;
@@ -1228,21 +1176,17 @@ static int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 		reset_psn(qp, psn);
 
 		qp->s_flags &= ~(RVT_S_WAIT_SSN_CREDIT | RVT_S_WAIT_ACK);
-		qp->s_flags |= RVT_S_WAIT_RNR;
-		qp->s_timer.function = qib_rc_rnr_retry;
-		qp->s_timer.expires = jiffies + usecs_to_jiffies(
-			ib_qib_rnr_table[(aeth >> QIB_AETH_CREDIT_SHIFT) &
-					   QIB_AETH_CREDIT_MASK]);
-		add_timer(&qp->s_timer);
-		goto bail;
+		rvt_stop_rc_timers(qp);
+		rvt_add_rnr_timer(qp, aeth);
+		return 0;
 
 	case 3:         /* NAK */
 		if (qp->s_acked == qp->s_tail)
 			goto bail;
 		/* The last valid PSN is the previous PSN. */
 		update_last_psn(qp, psn - 1);
-		switch ((aeth >> QIB_AETH_CREDIT_SHIFT) &
-			QIB_AETH_CREDIT_MASK) {
+		switch ((aeth >> IB_AETH_CREDIT_SHIFT) &
+			IB_AETH_CREDIT_MASK) {
 		case 0: /* PSN sequence error */
 			ibp->rvp.n_seq_naks++;
 			/*
@@ -1290,6 +1234,7 @@ reserved:
 	}
 
 bail:
+	rvt_stop_rc_timers(qp);
 	return ret;
 }
 
@@ -1303,10 +1248,7 @@ static void rdma_seq_err(struct rvt_qp *qp, struct qib_ibport *ibp, u32 psn,
 	struct rvt_swqe *wqe;
 
 	/* Remove QP from retry timer */
-	if (qp->s_flags & (RVT_S_TIMER | RVT_S_WAIT_RNR)) {
-		qp->s_flags &= ~(RVT_S_TIMER | RVT_S_WAIT_RNR);
-		del_timer(&qp->s_timer);
-	}
+	rvt_stop_rc_timers(qp);
 
 	wqe = rvt_get_swqe_ptr(qp, qp->s_acked);
 
@@ -1390,7 +1332,7 @@ static void qib_rc_rcv_resp(struct qib_ibport *ibp,
 
 	/* Ignore invalid responses. */
 	smp_read_barrier_depends(); /* see post_one_send */
-	if (qib_cmp24(psn, ACCESS_ONCE(qp->s_next_psn)) >= 0)
+	if (qib_cmp24(psn, READ_ONCE(qp->s_next_psn)) >= 0)
 		goto ack_done;
 
 	/* Ignore duplicate responses. */
@@ -1399,8 +1341,8 @@ static void qib_rc_rcv_resp(struct qib_ibport *ibp,
 		/* Update credits for "ghost" ACKs */
 		if (diff == 0 && opcode == OP(ACKNOWLEDGE)) {
 			aeth = be32_to_cpu(ohdr->u.aeth);
-			if ((aeth >> 29) == 0)
-				qib_get_credit(qp, aeth);
+			if ((aeth >> IB_AETH_NAK_SHIFT) == 0)
+				rvt_get_credit(qp, aeth);
 		}
 		goto ack_done;
 	}
@@ -1461,8 +1403,7 @@ read_middle:
 		 * We got a response so update the timeout.
 		 * 4.096 usec. * (1 << qp->timeout)
 		 */
-		qp->s_flags |= RVT_S_TIMER;
-		mod_timer(&qp->s_timer, jiffies + qp->timeout_jiffies);
+		rvt_mod_retry_timer(qp);
 		if (qp->s_flags & RVT_S_WAIT_ACK) {
 			qp->s_flags &= ~RVT_S_WAIT_ACK;
 			qib_schedule_send(qp);
@@ -1764,25 +1705,6 @@ send_ack:
 	return 0;
 }
 
-void qib_rc_error(struct rvt_qp *qp, enum ib_wc_status err)
-{
-	unsigned long flags;
-	int lastwqe;
-
-	spin_lock_irqsave(&qp->s_lock, flags);
-	lastwqe = rvt_error_qp(qp, err);
-	spin_unlock_irqrestore(&qp->s_lock, flags);
-
-	if (lastwqe) {
-		struct ib_event ev;
-
-		ev.device = qp->ibqp.device;
-		ev.element.qp = &qp->ibqp;
-		ev.event = IB_EVENT_QP_LAST_WQE_REACHED;
-		qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
-	}
-}
-
 static inline void qib_update_ack_queue(struct rvt_qp *qp, unsigned n)
 {
 	unsigned next;
@@ -1894,17 +1816,8 @@ void qib_rc_rcv(struct qib_ctxtdata *rcd, struct ib_header *hdr,
 		break;
 	}
 
-	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST)) {
-		qp->r_flags |= RVT_R_COMM_EST;
-		if (qp->ibqp.event_handler) {
-			struct ib_event ev;
-
-			ev.device = qp->ibqp.device;
-			ev.element.qp = &qp->ibqp;
-			ev.event = IB_EVENT_COMM_EST;
-			qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
-		}
-	}
+	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST))
+		rvt_comm_est(qp);
 
 	/* OK, process the packet. */
 	switch (opcode) {
@@ -2196,7 +2109,7 @@ rnr_nak:
 	return;
 
 nack_op_err:
-	qib_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 	qp->r_nak_state = IB_NAK_REMOTE_OPERATIONAL_ERROR;
 	qp->r_ack_psn = qp->r_psn;
 	/* Queue NAK for later */
@@ -2210,7 +2123,7 @@ nack_op_err:
 nack_inv_unlck:
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 nack_inv:
-	qib_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 	qp->r_nak_state = IB_NAK_INVALID_REQUEST;
 	qp->r_ack_psn = qp->r_psn;
 	/* Queue NAK for later */
@@ -2224,7 +2137,7 @@ nack_inv:
 nack_acc_unlck:
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 nack_acc:
-	qib_rc_error(qp, IB_WC_LOC_PROT_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_PROT_ERR);
 	qp->r_nak_state = IB_NAK_REMOTE_ACCESS_ERROR;
 	qp->r_ack_psn = qp->r_psn;
 send_ack:
diff --git a/drivers/infiniband/hw/qib/qib_ruc.c b/drivers/infiniband/hw/qib/qib_ruc.c
index e54a2feeeb10..17655cc3e6fe 100644
--- a/drivers/infiniband/hw/qib/qib_ruc.c
+++ b/drivers/infiniband/hw/qib/qib_ruc.c
@@ -38,44 +38,6 @@
 #include "qib_mad.h"
 
 /*
- * Convert the AETH RNR timeout code into the number of microseconds.
- */
-const u32 ib_qib_rnr_table[32] = {
-	655360,	/* 00: 655.36 */
-	10,	/* 01:    .01 */
-	20,	/* 02     .02 */
-	30,	/* 03:    .03 */
-	40,	/* 04:    .04 */
-	60,	/* 05:    .06 */
-	80,	/* 06:    .08 */
-	120,	/* 07:    .12 */
-	160,	/* 08:    .16 */
-	240,	/* 09:    .24 */
-	320,	/* 0A:    .32 */
-	480,	/* 0B:    .48 */
-	640,	/* 0C:    .64 */
-	960,	/* 0D:    .96 */
-	1280,	/* 0E:   1.28 */
-	1920,	/* 0F:   1.92 */
-	2560,	/* 10:   2.56 */
-	3840,	/* 11:   3.84 */
-	5120,	/* 12:   5.12 */
-	7680,	/* 13:   7.68 */
-	10240,	/* 14:  10.24 */
-	15360,	/* 15:  15.36 */
-	20480,	/* 16:  20.48 */
-	30720,	/* 17:  30.72 */
-	40960,	/* 18:  40.96 */
-	61440,	/* 19:  61.44 */
-	81920,	/* 1A:  81.92 */
-	122880,	/* 1B: 122.88 */
-	163840,	/* 1C: 163.84 */
-	245760,	/* 1D: 245.76 */
-	327680,	/* 1E: 327.68 */
-	491520	/* 1F: 491.52 */
-};
-
-/*
  * Validate a RWQE and fill in the SGE state.
  * Return 1 if OK.
  */
@@ -599,11 +561,8 @@ rnr_nak:
 	spin_lock_irqsave(&sqp->s_lock, flags);
 	if (!(ib_rvt_state_ops[sqp->state] & RVT_PROCESS_RECV_OK))
 		goto clr_busy;
-	sqp->s_flags |= RVT_S_WAIT_RNR;
-	sqp->s_timer.function = qib_rc_rnr_retry;
-	sqp->s_timer.expires = jiffies +
-		usecs_to_jiffies(ib_qib_rnr_table[qp->r_min_rnr_timer]);
-	add_timer(&sqp->s_timer);
+	rvt_add_rnr_timer(sqp, qp->r_min_rnr_timer <<
+				IB_AETH_CREDIT_SHIFT);
 	goto clr_busy;
 
 op_err:
@@ -621,7 +580,7 @@ acc_err:
 	wc.status = IB_WC_LOC_PROT_ERR;
 err:
 	/* responder goes to error state */
-	qib_rc_error(qp, wc.status);
+	rvt_rc_error(qp, wc.status);
 
 serr:
 	spin_lock_irqsave(&sqp->s_lock, flags);
diff --git a/drivers/infiniband/hw/qib/qib_uc.c b/drivers/infiniband/hw/qib/qib_uc.c
index 5b2d483451ad..b337b60fc40d 100644
--- a/drivers/infiniband/hw/qib/qib_uc.c
+++ b/drivers/infiniband/hw/qib/qib_uc.c
@@ -325,17 +325,8 @@ inv:
 		goto inv;
 	}
 
-	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST)) {
-		qp->r_flags |= RVT_R_COMM_EST;
-		if (qp->ibqp.event_handler) {
-			struct ib_event ev;
-
-			ev.device = qp->ibqp.device;
-			ev.element.qp = &qp->ibqp;
-			ev.event = IB_EVENT_COMM_EST;
-			qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
-		}
-	}
+	if (qp->state == IB_QPS_RTR && !(qp->r_flags & RVT_R_COMM_EST))
+		rvt_comm_est(qp);
 
 	/* OK, process the packet. */
 	switch (opcode) {
@@ -527,7 +518,7 @@ drop:
 	return;
 
 op_err:
-	qib_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+	rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 	return;
 
 }
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index f45cad1198b0..ddd4e7458750 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -152,7 +152,7 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 
 		ret = qib_get_rwqe(qp, 0);
 		if (ret < 0) {
-			qib_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			goto bail_unlock;
 		}
 		if (!ret) {
@@ -177,7 +177,7 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 			     sizeof(grh), 1);
 		wc.wc_flags |= IB_WC_GRH;
 	} else
-		qib_skip_sge(&qp->r_sge, sizeof(struct ib_grh), 1);
+		rvt_skip_sge(&qp->r_sge, sizeof(struct ib_grh), true);
 	ssge.sg_list = swqe->sg_list + 1;
 	ssge.sge = *swqe->sg_list;
 	ssge.num_sge = swqe->wr.num_sge;
@@ -548,7 +548,7 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 
 		ret = qib_get_rwqe(qp, 0);
 		if (ret < 0) {
-			qib_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
+			rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
 			return;
 		}
 		if (!ret) {
@@ -567,7 +567,7 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 			     sizeof(struct ib_grh), 1);
 		wc.wc_flags |= IB_WC_GRH;
 	} else
-		qib_skip_sge(&qp->r_sge, sizeof(struct ib_grh), 1);
+		rvt_skip_sge(&qp->r_sge, sizeof(struct ib_grh), true);
 	qib_copy_sge(&qp->r_sge, data, wc.byte_len - sizeof(struct ib_grh), 1);
 	rvt_put_ss(&qp->r_sge);
 	if (!test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags))
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 75f08624ac05..ce83ba9a12ef 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/device.h>
 
 #include "qib.h"
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 3e0677c51276..926f3c8eba69 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -144,8 +144,8 @@ qib_user_sdma_rb_search(struct rb_root *root, pid_t pid)
 	struct rb_node *node = root->rb_node;
 
 	while (node) {
-		sdma_rb_node = container_of(node,
-			struct qib_user_sdma_rb_node, node);
+		sdma_rb_node = rb_entry(node, struct qib_user_sdma_rb_node,
+					node);
 		if (pid < sdma_rb_node->pid)
 			node = node->rb_left;
 		else if (pid > sdma_rb_node->pid)
@@ -164,7 +164,7 @@ qib_user_sdma_rb_insert(struct rb_root *root, struct qib_user_sdma_rb_node *new)
 	struct qib_user_sdma_rb_node *got;
 
 	while (*node) {
-		got = container_of(*node, struct qib_user_sdma_rb_node, node);
+		got = rb_entry(*node, struct qib_user_sdma_rb_node, node);
 		parent = *node;
 		if (new->pid < got->pid)
 			node = &((*node)->rb_left);
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index 4b54c0ddd08a..83f8b5f24381 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -129,78 +129,16 @@ void qib_copy_sge(struct rvt_sge_state *ss, void *data, u32 length, int release)
 	struct rvt_sge *sge = &ss->sge;
 
 	while (length) {
-		u32 len = sge->length;
+		u32 len = rvt_get_sge_length(sge, length);
 
-		if (len > length)
-			len = length;
-		if (len > sge->sge_length)
-			len = sge->sge_length;
-		BUG_ON(len == 0);
+		WARN_ON_ONCE(len == 0);
 		memcpy(sge->vaddr, data, len);
-		sge->vaddr += len;
-		sge->length -= len;
-		sge->sge_length -= len;
-		if (sge->sge_length == 0) {
-			if (release)
-				rvt_put_mr(sge->mr);
-			if (--ss->num_sge)
-				*sge = *ss->sg_list++;
-		} else if (sge->length == 0 && sge->mr->lkey) {
-			if (++sge->n >= RVT_SEGSZ) {
-				if (++sge->m >= sge->mr->mapsz)
-					break;
-				sge->n = 0;
-			}
-			sge->vaddr =
-				sge->mr->map[sge->m]->segs[sge->n].vaddr;
-			sge->length =
-				sge->mr->map[sge->m]->segs[sge->n].length;
-		}
+		rvt_update_sge(ss, len, release);
 		data += len;
 		length -= len;
 	}
 }
 
-/**
- * qib_skip_sge - skip over SGE memory - XXX almost dup of prev func
- * @ss: the SGE state
- * @length: the number of bytes to skip
- */
-void qib_skip_sge(struct rvt_sge_state *ss, u32 length, int release)
-{
-	struct rvt_sge *sge = &ss->sge;
-
-	while (length) {
-		u32 len = sge->length;
-
-		if (len > length)
-			len = length;
-		if (len > sge->sge_length)
-			len = sge->sge_length;
-		BUG_ON(len == 0);
-		sge->vaddr += len;
-		sge->length -= len;
-		sge->sge_length -= len;
-		if (sge->sge_length == 0) {
-			if (release)
-				rvt_put_mr(sge->mr);
-			if (--ss->num_sge)
-				*sge = *ss->sg_list++;
-		} else if (sge->length == 0 && sge->mr->lkey) {
-			if (++sge->n >= RVT_SEGSZ) {
-				if (++sge->m >= sge->mr->mapsz)
-					break;
-				sge->n = 0;
-			}
-			sge->vaddr =
-				sge->mr->map[sge->m]->segs[sge->n].vaddr;
-			sge->length =
-				sge->mr->map[sge->m]->segs[sge->n].length;
-		}
-		length -= len;
-	}
-}
-
 /*
  * Count the number of DMA descriptors needed to send length bytes of data.
  * Don't modify the qib_sge_state to get the count.
@@ -468,27 +406,6 @@ static void mem_timer(unsigned long data)
 	}
 }
 
-static void update_sge(struct rvt_sge_state *ss, u32 length)
-{
-	struct rvt_sge *sge = &ss->sge;
-
-	sge->vaddr += length;
-	sge->length -= length;
-	sge->sge_length -= length;
-	if (sge->sge_length == 0) {
-		if (--ss->num_sge)
-			*sge = *ss->sg_list++;
-	} else if (sge->length == 0 && sge->mr->lkey) {
-		if (++sge->n >= RVT_SEGSZ) {
-			if (++sge->m >= sge->mr->mapsz)
-				return;
-			sge->n = 0;
-		}
-		sge->vaddr = sge->mr->map[sge->m]->segs[sge->n].vaddr;
-		sge->length = sge->mr->map[sge->m]->segs[sge->n].length;
-	}
-}
-
 #ifdef __LITTLE_ENDIAN
 static inline u32 get_upper_bits(u32 data, u32 shift)
 {
@@ -646,11 +563,11 @@ static void copy_io(u32 __iomem *piobuf, struct rvt_sge_state *ss,
 				data = clear_upper_bytes(v, extra, 0);
 			}
 		}
-		update_sge(ss, len);
+		rvt_update_sge(ss, len, false);
 		length -= len;
 	}
 	/* Update address before sending packet. */
-	update_sge(ss, length);
+	rvt_update_sge(ss, length, false);
 	if (flush_wc) {
 		/* must flush early everything before trigger word */
 		qib_flush_wc();
@@ -1069,7 +986,7 @@ static int qib_verbs_send_pio(struct rvt_qp *qp, struct ib_header *ibhdr,
 		u32 *addr = (u32 *) ss->sge.vaddr;
 
 		/* Update address before sending packet. */
-		update_sge(ss, len);
+		rvt_update_sge(ss, len, false);
 		if (flush_wc) {
 			qib_pio_copy(piobuf, addr, dwords - 1);
 			/* must flush early everything before trigger word */
@@ -1303,6 +1220,7 @@ static int qib_query_port(struct rvt_dev_info *rdi, u8 port_num,
 	enum ib_mtu mtu;
 	u16 lid = ppd->lid;
 
+	/* props being zeroed by the caller, avoid zeroing it here */
 	props->lid = lid ? lid : be16_to_cpu(IB_LID_PERMISSIVE);
 	props->lmc = ppd->lmc;
 	props->state = dd->f_iblink_state(ppd->lastibcstat);
@@ -1632,7 +1550,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	ibdev->owner = THIS_MODULE;
 	ibdev->node_guid = ppd->guid;
 	ibdev->phys_port_cnt = dd->num_pports;
-	ibdev->dma_device = &dd->pcidev->dev;
+	ibdev->dev.parent = &dd->pcidev->dev;
 	ibdev->modify_device = qib_modify_device;
 	ibdev->process_mad = qib_process_mad;
 
@@ -1659,6 +1577,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.stop_send_queue = qib_stop_send_queue;
 	dd->verbs_dev.rdi.driver_f.flush_qp_waiters = qib_flush_qp_waiters;
 	dd->verbs_dev.rdi.driver_f.notify_error_qp = qib_notify_error_qp;
+	dd->verbs_dev.rdi.driver_f.notify_restart_rc = qib_restart_rc;
 	dd->verbs_dev.rdi.driver_f.mtu_to_path_mtu = qib_mtu_to_path_mtu;
 	dd->verbs_dev.rdi.driver_f.mtu_from_qp = qib_mtu_from_qp;
 	dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = qib_get_pmtu_from_attr;
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index 94fd30fdedac..212e8ce71be8 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -270,8 +270,6 @@ int qib_snapshot_counters(struct qib_pportdata *ppd, u64 *swords,
 int qib_get_counters(struct qib_pportdata *ppd,
 		     struct qib_verbs_counters *cntrs);
 
-__be32 qib_compute_aeth(struct rvt_qp *qp);
-
 /*
  * Functions provided by qib driver for rdmavt to use
  */
@@ -281,7 +279,7 @@ void qib_qp_priv_free(struct rvt_dev_info *rdi, struct rvt_qp *qp);
 void qib_notify_qp_reset(struct rvt_qp *qp);
 int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 		  enum ib_qp_type type, u8 port, gfp_t gfp);
-
+void qib_restart_rc(struct rvt_qp *qp, u32 psn, int wait);
 #ifdef CONFIG_DEBUG_FS
 
 struct qib_qp_iter;
@@ -294,8 +292,6 @@ void qib_qp_iter_print(struct seq_file *s, struct qib_qp_iter *iter);
 
 #endif
 
-void qib_get_credit(struct rvt_qp *qp, u32 aeth);
-
 unsigned qib_pkt_delay(u32 plen, u8 snd_mult, u8 rcv_mult);
 
 void qib_verbs_sdma_desc_avail(struct qib_pportdata *ppd, unsigned avail);
@@ -308,8 +304,6 @@ int qib_verbs_send(struct rvt_qp *qp, struct ib_header *hdr,
 void qib_copy_sge(struct rvt_sge_state *ss, void *data, u32 length,
 		  int release);
 
-void qib_skip_sge(struct rvt_sge_state *ss, u32 length, int release);
-
 void qib_uc_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 		int has_grh, void *data, u32 tlen, struct rvt_qp *qp);
 
@@ -326,8 +320,6 @@ void qib_rc_rnr_retry(unsigned long arg);
 
 void qib_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr);
 
-void qib_rc_error(struct rvt_qp *qp, enum ib_wc_status err);
-
 int qib_post_ud_send(struct rvt_qp *qp, struct ib_send_wr *wr);
 
 void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
diff --git a/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h b/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h
index 596e0ed49a8e..bf7d197a9f42 100644
--- a/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h
+++ b/drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h
@@ -34,7 +34,6 @@
 #ifndef USNIC_CMN_PKT_HDR_H
 #define USNIC_CMN_PKT_HDR_H
 
-#define USNIC_ROCE_ETHERTYPE		(0x8915)
 #define USNIC_ROCE_GRH_VER              (8)
 #define USNIC_PROTO_VER                 (1)
 #define USNIC_ROCE_GRH_VER_SHIFT        (4)
diff --git a/drivers/infiniband/hw/usnic/usnic_fwd.h b/drivers/infiniband/hw/usnic/usnic_fwd.h
index 3a8add9ddf46..b2ac22be0731 100644
--- a/drivers/infiniband/hw/usnic/usnic_fwd.h
+++ b/drivers/infiniband/hw/usnic/usnic_fwd.h
@@ -36,6 +36,7 @@
 
 #include <linux/if.h>
 #include <linux/netdevice.h>
+#include <linux/if_ether.h>
 #include <linux/pci.h>
 #include <linux/in.h>
 
@@ -97,7 +98,7 @@ static inline void usnic_fwd_init_usnic_filter(struct filter *filter,
 						uint32_t usnic_id)
 {
 	filter->type = FILTER_USNIC_ID;
-	filter->u.usnic.ethtype = USNIC_ROCE_ETHERTYPE;
+	filter->u.usnic.ethtype = ETH_P_IBOE;
 	filter->u.usnic.flags = FILTER_FIELD_USNIC_ETHTYPE |
 				FILTER_FIELD_USNIC_ID |
 				FILTER_FIELD_USNIC_PROTO;
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index 0a89a955550b..c0c1e8b027b1 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -321,7 +321,9 @@ static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
-	err = usnic_ib_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_USNIC;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
@@ -380,7 +382,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	us_ibdev->ib_dev.node_type = RDMA_NODE_USNIC_UDP;
 	us_ibdev->ib_dev.phys_port_cnt = USNIC_IB_PORT_CNT;
 	us_ibdev->ib_dev.num_comp_vectors = USNIC_IB_NUM_COMP_VECTORS;
-	us_ibdev->ib_dev.dma_device = &dev->dev;
+	us_ibdev->ib_dev.dev.parent = &dev->dev;
 	us_ibdev->ib_dev.uverbs_abi_ver = USNIC_UVERBS_ABI_VERSION;
 	strlcpy(us_ibdev->ib_dev.name, "usnic_%d", IB_DEVICE_NAME_MAX);
 
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c
index 80ef3f8998c8..04443242e258 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c
@@ -80,7 +80,7 @@ usnic_ib_show_config(struct device *device, struct device_attribute *attr,
 	left = PAGE_SIZE;
 
 	mutex_lock(&us_ibdev->usdev_lock);
-	if (atomic_read(&us_ibdev->vf_cnt.refcount) > 0) {
+	if (kref_read(&us_ibdev->vf_cnt) > 0) {
 		char *busname;
 
 		/*
@@ -99,7 +99,7 @@ usnic_ib_show_config(struct device *device, struct device_attribute *attr,
 			PCI_FUNC(us_ibdev->pdev->devfn),
 			netdev_name(us_ibdev->netdev),
 			us_ibdev->ufdev->mac,
-			atomic_read(&us_ibdev->vf_cnt.refcount));
+			kref_read(&us_ibdev->vf_cnt));
 		UPDATE_PTR_LEFT(n, ptr, left);
 
 		for (res_type = USNIC_VNIC_RES_TYPE_EOL;
@@ -147,7 +147,7 @@ usnic_ib_show_max_vf(struct device *device, struct device_attribute *attr,
 	us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev);
 
 	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			atomic_read(&us_ibdev->vf_cnt.refcount));
+			kref_read(&us_ibdev->vf_cnt));
 }
 
 static ssize_t
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 74819a7951e2..3284730d3c09 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -291,11 +291,11 @@ int usnic_ib_query_device(struct ib_device *ibdev,
 	qp_per_vf = max(us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_WQ],
 			us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_RQ]);
 	props->max_qp = qp_per_vf *
-		atomic_read(&us_ibdev->vf_cnt.refcount);
+		kref_read(&us_ibdev->vf_cnt);
 	props->device_cap_flags = IB_DEVICE_PORT_ACTIVE_EVENT |
 		IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
 	props->max_cq = us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_CQ] *
-		atomic_read(&us_ibdev->vf_cnt.refcount);
+		kref_read(&us_ibdev->vf_cnt);
 	props->max_pd = USNIC_UIOM_MAX_PD_CNT;
 	props->max_mr = USNIC_UIOM_MAX_MR_CNT;
 	props->local_ca_ack_delay = 0;
@@ -330,7 +330,7 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 
 	mutex_lock(&us_ibdev->usdev_lock);
 	__ethtool_get_link_ksettings(us_ibdev->netdev, &cmd);
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->lid = 0;
 	props->lmc = 1;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 1ccee6ea5bc3..c49db7c33979 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -34,7 +34,8 @@
 
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/iommu.h>
 #include <linux/workqueue.h>
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 71e1d55d69d6..3cd96c1b9502 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -196,13 +196,7 @@ struct pvrdma_dev {
 	spinlock_t cmd_lock; /* Command lock. */
 	struct semaphore cmd_sema;
 	struct completion cmd_done;
-	struct {
-		enum pvrdma_intr_type type; /* Intr type */
-		struct msix_entry msix_entry[PVRDMA_MAX_INTERRUPTS];
-		irq_handler_t handler[PVRDMA_MAX_INTERRUPTS];
-		u8 enabled[PVRDMA_MAX_INTERRUPTS];
-		u8 size;
-	} intr;
+	unsigned int nr_vectors;
 
 	/* RDMA-related device information. */
 	union ib_gid *sgid_tbl;
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
index e429ca5b16aa..69bda611d313 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
@@ -373,7 +373,7 @@ retry:
 	wc->sl = cqe->sl;
 	wc->dlid_path_bits = cqe->dlid_path_bits;
 	wc->port_num = cqe->port_num;
-	wc->vendor_err = 0;
+	wc->vendor_err = cqe->vendor_err;
 
 	/* Update shared ring state */
 	pvrdma_idx_ring_inc(&cq->ring_state->rx.cons_head, cq->ibcq.cqe);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
index c06768635d65..e69d6f3cae32 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
@@ -149,12 +149,6 @@ enum pvrdma_intr_cause {
 	PVRDMA_INTR_CAUSE_CQ		= (1 << PVRDMA_INTR_VECTOR_CQ),
 };
 
-enum pvrdma_intr_type {
-	PVRDMA_INTR_TYPE_INTX,		/* Legacy. */
-	PVRDMA_INTR_TYPE_MSI,		/* MSI. */
-	PVRDMA_INTR_TYPE_MSIX,		/* MSI-X. */
-};
-
 enum pvrdma_gos_bits {
 	PVRDMA_GOS_BITS_UNK,		/* Unknown. */
 	PVRDMA_GOS_BITS_32,		/* 32-bit. */
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index bd8fbd3d2032..100bea5c42ff 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -132,13 +132,14 @@ static int pvrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
 	struct ib_port_attr attr;
 	int err;
 
-	err = pvrdma_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
 	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 	return 0;
 }
@@ -172,7 +173,7 @@ static int pvrdma_register_device(struct pvrdma_dev *dev)
 	dev->flags = 0;
 	dev->ib_dev.owner = THIS_MODULE;
 	dev->ib_dev.num_comp_vectors = 1;
-	dev->ib_dev.dma_device = &dev->pdev->dev;
+	dev->ib_dev.dev.parent = &dev->pdev->dev;
 	dev->ib_dev.uverbs_abi_ver = PVRDMA_UVERBS_ABI_VERSION;
 	dev->ib_dev.uverbs_cmd_mask =
 		(1ull << IB_USER_VERBS_CMD_GET_CONTEXT)		|
@@ -282,7 +283,7 @@ static irqreturn_t pvrdma_intr0_handler(int irq, void *dev_id)
 
 	dev_dbg(&dev->pdev->dev, "interrupt 0 (response) handler\n");
 
-	if (dev->intr.type != PVRDMA_INTR_TYPE_MSIX) {
+	if (!dev->pdev->msix_enabled) {
 		/* Legacy intr */
 		icr = pvrdma_read_reg(dev, PVRDMA_REG_ICR);
 		if (icr == 0)
@@ -489,31 +490,13 @@ static irqreturn_t pvrdma_intrx_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void pvrdma_disable_msi_all(struct pvrdma_dev *dev)
-{
-	if (dev->intr.type == PVRDMA_INTR_TYPE_MSIX)
-		pci_disable_msix(dev->pdev);
-	else if (dev->intr.type == PVRDMA_INTR_TYPE_MSI)
-		pci_disable_msi(dev->pdev);
-}
-
 static void pvrdma_free_irq(struct pvrdma_dev *dev)
 {
 	int i;
 
 	dev_dbg(&dev->pdev->dev, "freeing interrupts\n");
-
-	if (dev->intr.type == PVRDMA_INTR_TYPE_MSIX) {
-		for (i = 0; i < dev->intr.size; i++) {
-			if (dev->intr.enabled[i]) {
-				free_irq(dev->intr.msix_entry[i].vector, dev);
-				dev->intr.enabled[i] = 0;
-			}
-		}
-	} else if (dev->intr.type == PVRDMA_INTR_TYPE_INTX ||
-		   dev->intr.type == PVRDMA_INTR_TYPE_MSI) {
-		free_irq(dev->pdev->irq, dev);
-	}
+	for (i = 0; i < dev->nr_vectors; i++)
+		free_irq(pci_irq_vector(dev->pdev, i), dev);
 }
 
 static void pvrdma_enable_intrs(struct pvrdma_dev *dev)
@@ -528,126 +511,48 @@ static void pvrdma_disable_intrs(struct pvrdma_dev *dev)
 	pvrdma_write_reg(dev, PVRDMA_REG_IMR, ~0);
 }
 
-static int pvrdma_enable_msix(struct pci_dev *pdev, struct pvrdma_dev *dev)
-{
-	int i;
-	int ret;
-
-	for (i = 0; i < PVRDMA_MAX_INTERRUPTS; i++) {
-		dev->intr.msix_entry[i].entry = i;
-		dev->intr.msix_entry[i].vector = i;
-
-		switch (i) {
-		case 0:
-			/* CMD ring handler */
-			dev->intr.handler[i] = pvrdma_intr0_handler;
-			break;
-		case 1:
-			/* Async event ring handler */
-			dev->intr.handler[i] = pvrdma_intr1_handler;
-			break;
-		default:
-			/* Completion queue handler */
-			dev->intr.handler[i] = pvrdma_intrx_handler;
-			break;
-		}
-	}
-
-	ret = pci_enable_msix(pdev, dev->intr.msix_entry,
-			      PVRDMA_MAX_INTERRUPTS);
-	if (!ret) {
-		dev->intr.type = PVRDMA_INTR_TYPE_MSIX;
-		dev->intr.size = PVRDMA_MAX_INTERRUPTS;
-	} else if (ret > 0) {
-		ret = pci_enable_msix(pdev, dev->intr.msix_entry, ret);
-		if (!ret) {
-			dev->intr.type = PVRDMA_INTR_TYPE_MSIX;
-			dev->intr.size = ret;
-		} else {
-			dev->intr.size = 0;
-		}
-	}
-
-	dev_dbg(&pdev->dev, "using interrupt type %d, size %d\n",
-		dev->intr.type, dev->intr.size);
-
-	return ret;
-}
-
 static int pvrdma_alloc_intrs(struct pvrdma_dev *dev)
 {
-	int ret = 0;
-	int i;
+	struct pci_dev *pdev = dev->pdev;
+	int ret = 0, i;
 
-	if (pci_find_capability(dev->pdev, PCI_CAP_ID_MSIX) &&
-	    pvrdma_enable_msix(dev->pdev, dev)) {
-		/* Try MSI */
-		ret = pci_enable_msi(dev->pdev);
-		if (!ret) {
-			dev->intr.type = PVRDMA_INTR_TYPE_MSI;
-		} else {
-			/* Legacy INTR */
-			dev->intr.type = PVRDMA_INTR_TYPE_INTX;
-		}
+	ret = pci_alloc_irq_vectors(pdev, 1, PVRDMA_MAX_INTERRUPTS,
+			PCI_IRQ_MSIX);
+	if (ret < 0) {
+		ret = pci_alloc_irq_vectors(pdev, 1, 1,
+				PCI_IRQ_MSI | PCI_IRQ_LEGACY);
+		if (ret < 0)
+			return ret;
 	}
+	dev->nr_vectors = ret;
 
-	/* Request First IRQ */
-	switch (dev->intr.type) {
-	case PVRDMA_INTR_TYPE_INTX:
-	case PVRDMA_INTR_TYPE_MSI:
-		ret = request_irq(dev->pdev->irq, pvrdma_intr0_handler,
-				  IRQF_SHARED, DRV_NAME, dev);
-		if (ret) {
-			dev_err(&dev->pdev->dev,
-				"failed to request interrupt\n");
-			goto disable_msi;
-		}
-		break;
-	case PVRDMA_INTR_TYPE_MSIX:
-		ret = request_irq(dev->intr.msix_entry[0].vector,
-				  pvrdma_intr0_handler, 0, DRV_NAME, dev);
-		if (ret) {
-			dev_err(&dev->pdev->dev,
-				"failed to request interrupt 0\n");
-			goto disable_msi;
-		}
-		dev->intr.enabled[0] = 1;
-		break;
-	default:
-		/* Not reached */
-		break;
+	ret = request_irq(pci_irq_vector(dev->pdev, 0), pvrdma_intr0_handler,
+			pdev->msix_enabled ? 0 : IRQF_SHARED, DRV_NAME, dev);
+	if (ret) {
+		dev_err(&dev->pdev->dev,
+			"failed to request interrupt 0\n");
+		goto out_free_vectors;
 	}
 
-	/* For MSIX: request intr for each vector */
-	if (dev->intr.size > 1) {
-		ret = request_irq(dev->intr.msix_entry[1].vector,
-				  pvrdma_intr1_handler, 0, DRV_NAME, dev);
+	for (i = 1; i < dev->nr_vectors; i++) {
+		ret = request_irq(pci_irq_vector(dev->pdev, i),
+				i == 1 ? pvrdma_intr1_handler :
+					 pvrdma_intrx_handler,
+				0, DRV_NAME, dev);
 		if (ret) {
 			dev_err(&dev->pdev->dev,
-				"failed to request interrupt 1\n");
-			goto free_irq;
-		}
-		dev->intr.enabled[1] = 1;
-
-		for (i = 2; i < dev->intr.size; i++) {
-			ret = request_irq(dev->intr.msix_entry[i].vector,
-					  pvrdma_intrx_handler, 0,
-					  DRV_NAME, dev);
-			if (ret) {
-				dev_err(&dev->pdev->dev,
-					"failed to request interrupt %d\n", i);
-				goto free_irq;
-			}
-			dev->intr.enabled[i] = 1;
+				"failed to request interrupt %d\n", i);
+			goto free_irqs;
 		}
 	}
 
 	return 0;
 
-free_irq:
-	pvrdma_free_irq(dev);
-disable_msi:
-	pvrdma_disable_msi_all(dev);
+free_irqs:
+	while (--i >= 0)
+		free_irq(pci_irq_vector(dev->pdev, i), dev);
+out_free_vectors:
+	pci_free_irq_vectors(pdev);
 	return ret;
 }
 
@@ -1091,7 +996,7 @@ err_free_uar_table:
 	pvrdma_uar_table_cleanup(dev);
 err_free_intrs:
 	pvrdma_free_irq(dev);
-	pvrdma_disable_msi_all(dev);
+	pci_free_irq_vectors(pdev);
 err_free_cq_ring:
 	pvrdma_page_dir_cleanup(dev, &dev->cq_pdir);
 err_free_async_ring:
@@ -1141,7 +1046,7 @@ static void pvrdma_pci_remove(struct pci_dev *pdev)
 
 	pvrdma_disable_intrs(dev);
 	pvrdma_free_irq(dev);
-	pvrdma_disable_msi_all(dev);
+	pci_free_irq_vectors(pdev);
 
 	/* Deactivate pvrdma device */
 	pvrdma_write_reg(dev, PVRDMA_REG_CTL, PVRDMA_DEVICE_CTL_RESET);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index c8c01e558125..dbbfd35e7da7 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -151,7 +151,7 @@ static int pvrdma_set_rq_size(struct pvrdma_dev *dev,
 }
 
 static int pvrdma_set_sq_size(struct pvrdma_dev *dev, struct ib_qp_cap *req_cap,
-			      enum ib_qp_type type, struct pvrdma_qp *qp)
+			      struct pvrdma_qp *qp)
 {
 	if (req_cap->max_send_wr > dev->dsr->caps.max_qp_wr ||
 	    req_cap->max_send_sge > dev->dsr->caps.max_sge) {
@@ -276,8 +276,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 			qp->is_kernel = true;
 
 			ret = pvrdma_set_sq_size(to_vdev(pd->device),
-						 &init_attr->cap,
-						 init_attr->qp_type, qp);
+						 &init_attr->cap, qp);
 			if (ret)
 				goto err_qp;
 
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
index c2aa52638dcb..fec17c49103b 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
@@ -135,7 +135,7 @@ int pvrdma_query_port(struct ib_device *ibdev, u8 port,
 		return err;
 	}
 
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->state = pvrdma_port_state_to_ib(resp->attrs.state);
 	props->max_mtu = pvrdma_mtu_to_ib(resp->attrs.max_mtu);
@@ -275,7 +275,7 @@ int pvrdma_modify_port(struct ib_device *ibdev, u8 port, int mask,
 	}
 
 	mutex_lock(&vdev->port_mutex);
-	ret = pvrdma_query_port(ibdev, port, &attr);
+	ret = ib_query_port(ibdev, port, &attr);
 	if (ret)
 		goto out;
 
diff --git a/drivers/infiniband/sw/rdmavt/Kconfig b/drivers/infiniband/sw/rdmavt/Kconfig
index 1da8d01a6855..fdd001ce13d8 100644
--- a/drivers/infiniband/sw/rdmavt/Kconfig
+++ b/drivers/infiniband/sw/rdmavt/Kconfig
@@ -1,5 +1,6 @@
 config INFINIBAND_RDMAVT
 	tristate "RDMA verbs transport library"
 	depends on 64BIT
+	select DMA_VIRT_OPS
 	---help---
 	This is a common software verbs provider for RDMA networks.
diff --git a/drivers/infiniband/sw/rdmavt/Makefile b/drivers/infiniband/sw/rdmavt/Makefile
index ccaa7992ac97..78b276a90401 100644
--- a/drivers/infiniband/sw/rdmavt/Makefile
+++ b/drivers/infiniband/sw/rdmavt/Makefile
@@ -7,7 +7,7 @@
 #
 obj-$(CONFIG_INFINIBAND_RDMAVT) += rdmavt.o
 
-rdmavt-y := vt.o ah.o cq.o dma.o mad.o mcast.o mmap.o mr.o pd.o qp.o srq.o \
-	trace.o
+rdmavt-y := vt.o ah.o cq.o mad.o mcast.o mmap.o mr.o pd.o qp.o \
+	rc.o srq.o trace.o
 
 CFLAGS_trace.o = -I$(src)
diff --git a/drivers/infiniband/sw/rdmavt/dma.c b/drivers/infiniband/sw/rdmavt/dma.c
deleted file mode 100644
index f2cefb0d9180..000000000000
--- a/drivers/infiniband/sw/rdmavt/dma.c
+++ /dev/null
@@ -1,198 +0,0 @@
-/*
- * Copyright(c) 2016 Intel Corporation.
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *  - Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- *  - Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in
- *    the documentation and/or other materials provided with the
- *    distribution.
- *  - Neither the name of Intel Corporation nor the names of its
- *    contributors may be used to endorse or promote products derived
- *    from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER 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.
- *
- */
-#include <linux/types.h>
-#include <linux/scatterlist.h>
-#include <rdma/ib_verbs.h>
-
-#include "dma.h"
-
-#define BAD_DMA_ADDRESS ((u64)0)
-
-/*
- * The following functions implement driver specific replacements
- * for the ib_dma_*() functions.
- *
- * These functions return kernel virtual addresses instead of
- * device bus addresses since the driver uses the CPU to copy
- * data instead of using hardware DMA.
- */
-
-static int rvt_mapping_error(struct ib_device *dev, u64 dma_addr)
-{
-	return dma_addr == BAD_DMA_ADDRESS;
-}
-
-static u64 rvt_dma_map_single(struct ib_device *dev, void *cpu_addr,
-			      size_t size, enum dma_data_direction direction)
-{
-	if (WARN_ON(!valid_dma_direction(direction)))
-		return BAD_DMA_ADDRESS;
-
-	return (u64)cpu_addr;
-}
-
-static void rvt_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size,
-				 enum dma_data_direction direction)
-{
-	/* This is a stub, nothing to be done here */
-}
-
-static u64 rvt_dma_map_page(struct ib_device *dev, struct page *page,
-			    unsigned long offset, size_t size,
-			    enum dma_data_direction direction)
-{
-	u64 addr;
-
-	if (WARN_ON(!valid_dma_direction(direction)))
-		return BAD_DMA_ADDRESS;
-
-	addr = (u64)page_address(page);
-	if (addr)
-		addr += offset;
-
-	return addr;
-}
-
-static void rvt_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size,
-			       enum dma_data_direction direction)
-{
-	/* This is a stub, nothing to be done here */
-}
-
-static int rvt_map_sg(struct ib_device *dev, struct scatterlist *sgl,
-		      int nents, enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	u64 addr;
-	int i;
-	int ret = nents;
-
-	if (WARN_ON(!valid_dma_direction(direction)))
-		return 0;
-
-	for_each_sg(sgl, sg, nents, i) {
-		addr = (u64)page_address(sg_page(sg));
-		if (!addr) {
-			ret = 0;
-			break;
-		}
-		sg->dma_address = addr + sg->offset;
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-	}
-	return ret;
-}
-
-static void rvt_unmap_sg(struct ib_device *dev,
-			 struct scatterlist *sg, int nents,
-			 enum dma_data_direction direction)
-{
-	/* This is a stub, nothing to be done here */
-}
-
-static int rvt_map_sg_attrs(struct ib_device *dev, struct scatterlist *sgl,
-			    int nents, enum dma_data_direction direction,
-			    unsigned long attrs)
-{
-	return rvt_map_sg(dev, sgl, nents, direction);
-}
-
-static void rvt_unmap_sg_attrs(struct ib_device *dev,
-			       struct scatterlist *sg, int nents,
-			       enum dma_data_direction direction,
-			       unsigned long attrs)
-{
-	return rvt_unmap_sg(dev, sg, nents, direction);
-}
-
-static void rvt_sync_single_for_cpu(struct ib_device *dev, u64 addr,
-				    size_t size, enum dma_data_direction dir)
-{
-}
-
-static void rvt_sync_single_for_device(struct ib_device *dev, u64 addr,
-				       size_t size,
-				       enum dma_data_direction dir)
-{
-}
-
-static void *rvt_dma_alloc_coherent(struct ib_device *dev, size_t size,
-				    u64 *dma_handle, gfp_t flag)
-{
-	struct page *p;
-	void *addr = NULL;
-
-	p = alloc_pages(flag, get_order(size));
-	if (p)
-		addr = page_address(p);
-	if (dma_handle)
-		*dma_handle = (u64)addr;
-	return addr;
-}
-
-static void rvt_dma_free_coherent(struct ib_device *dev, size_t size,
-				  void *cpu_addr, u64 dma_handle)
-{
-	free_pages((unsigned long)cpu_addr, get_order(size));
-}
-
-struct ib_dma_mapping_ops rvt_default_dma_mapping_ops = {
-	.mapping_error = rvt_mapping_error,
-	.map_single = rvt_dma_map_single,
-	.unmap_single = rvt_dma_unmap_single,
-	.map_page = rvt_dma_map_page,
-	.unmap_page = rvt_dma_unmap_page,
-	.map_sg = rvt_map_sg,
-	.unmap_sg = rvt_unmap_sg,
-	.map_sg_attrs = rvt_map_sg_attrs,
-	.unmap_sg_attrs = rvt_unmap_sg_attrs,
-	.sync_single_for_cpu = rvt_sync_single_for_cpu,
-	.sync_single_for_device = rvt_sync_single_for_device,
-	.alloc_coherent = rvt_dma_alloc_coherent,
-	.free_coherent = rvt_dma_free_coherent
-};
diff --git a/drivers/infiniband/sw/rdmavt/dma.h b/drivers/infiniband/sw/rdmavt/dma.h
deleted file mode 100644
index 979f07e09195..000000000000
--- a/drivers/infiniband/sw/rdmavt/dma.h
+++ /dev/null
@@ -1,53 +0,0 @@
-#ifndef DEF_RDMAVTDMA_H
-#define DEF_RDMAVTDMA_H
-
-/*
- * Copyright(c) 2016 Intel Corporation.
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *  - Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- *  - Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in
- *    the documentation and/or other materials provided with the
- *    distribution.
- *  - Neither the name of Intel Corporation nor the names of its
- *    contributors may be used to endorse or promote products derived
- *    from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER 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.
- *
- */
-
-extern struct ib_dma_mapping_ops rvt_default_dma_mapping_ops;
-
-#endif          /* DEF_RDMAVTDMA_H */
diff --git a/drivers/infiniband/sw/rdmavt/mad.c b/drivers/infiniband/sw/rdmavt/mad.c
index f6e99778d7ca..bba241faca61 100644
--- a/drivers/infiniband/sw/rdmavt/mad.c
+++ b/drivers/infiniband/sw/rdmavt/mad.c
@@ -74,9 +74,9 @@ int rvt_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		    u16 *out_mad_pkey_index)
 {
 	/*
-	 * MAD processing is quite different between hfi1 and qib. Therfore this
-	 * is expected to be provided by the driver. Other drivers in the future
-	 * may chose to implement this but it should not be made into a
+	 * MAD processing is quite different between hfi1 and qib. Therefore
+	 * this is expected to be provided by the driver. Other drivers in the
+	 * future may choose to implement this but it should not be made into a
 	 * requirement.
 	 */
 	if (ibport_num_to_idx(ibdev, port_num) < 0)
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 52fd15276ee6..ae30b6838d79 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -120,10 +120,19 @@ static void rvt_deinit_mregion(struct rvt_mregion *mr)
 	mr->mapsz = 0;
 	while (i)
 		kfree(mr->map[--i]);
+	percpu_ref_exit(&mr->refcount);
+}
+
+static void __rvt_mregion_complete(struct percpu_ref *ref)
+{
+	struct rvt_mregion *mr = container_of(ref, struct rvt_mregion,
+					      refcount);
+
+	complete(&mr->comp);
 }
 
 static int rvt_init_mregion(struct rvt_mregion *mr, struct ib_pd *pd,
-			    int count)
+			    int count, unsigned int percpu_flags)
 {
 	int m, i = 0;
 	struct rvt_dev_info *dev = ib_to_rvt(pd->device);
@@ -133,19 +142,23 @@ static int rvt_init_mregion(struct rvt_mregion *mr, struct ib_pd *pd,
 	for (; i < m; i++) {
 		mr->map[i] = kzalloc_node(sizeof(*mr->map[0]), GFP_KERNEL,
 					  dev->dparms.node);
-		if (!mr->map[i]) {
-			rvt_deinit_mregion(mr);
-			return -ENOMEM;
-		}
+		if (!mr->map[i])
+			goto bail;
 		mr->mapsz++;
 	}
 	init_completion(&mr->comp);
 	/* count returning the ptr to user */
-	atomic_set(&mr->refcount, 1);
+	if (percpu_ref_init(&mr->refcount, &__rvt_mregion_complete,
+			    percpu_flags, GFP_KERNEL))
+		goto bail;
+
 	atomic_set(&mr->lkey_invalid, 0);
 	mr->pd = pd;
 	mr->max_segs = count;
 	return 0;
+bail:
+	rvt_deinit_mregion(mr);
+	return -ENOMEM;
 }
 
 /**
@@ -180,8 +193,7 @@ static int rvt_alloc_lkey(struct rvt_mregion *mr, int dma_region)
 		if (!tmr) {
 			rcu_assign_pointer(dev->dma_mr, mr);
 			mr->lkey_published = 1;
-		} else {
-			rvt_put_mr(mr);
+			rvt_get_mr(mr);
 		}
 		goto success;
 	}
@@ -239,11 +251,14 @@ static void rvt_free_lkey(struct rvt_mregion *mr)
 	int freed = 0;
 
 	spin_lock_irqsave(&rkt->lock, flags);
-	if (!mr->lkey_published)
-		goto out;
-	if (lkey == 0) {
-		RCU_INIT_POINTER(dev->dma_mr, NULL);
+	if (!lkey) {
+		if (mr->lkey_published) {
+			RCU_INIT_POINTER(dev->dma_mr, NULL);
+			rvt_put_mr(mr);
+		}
 	} else {
+		if (!mr->lkey_published)
+			goto out;
 		r = lkey >> (32 - dev->dparms.lkey_table_size);
 		RCU_INIT_POINTER(rkt->table[r], NULL);
 	}
@@ -253,7 +268,7 @@ out:
 	spin_unlock_irqrestore(&rkt->lock, flags);
 	if (freed) {
 		synchronize_rcu();
-		rvt_put_mr(mr);
+		percpu_ref_kill(&mr->refcount);
 	}
 }
 
@@ -269,7 +284,7 @@ static struct rvt_mr *__rvt_alloc_mr(int count, struct ib_pd *pd)
 	if (!mr)
 		goto bail;
 
-	rval = rvt_init_mregion(&mr->mr, pd, count);
+	rval = rvt_init_mregion(&mr->mr, pd, count, 0);
 	if (rval)
 		goto bail;
 	/*
@@ -294,8 +309,8 @@ bail:
 
 static void __rvt_free_mr(struct rvt_mr *mr)
 {
-	rvt_deinit_mregion(&mr->mr);
 	rvt_free_lkey(&mr->mr);
+	rvt_deinit_mregion(&mr->mr);
 	kfree(mr);
 }
 
@@ -305,8 +320,8 @@ static void __rvt_free_mr(struct rvt_mr *mr)
  * @acc: access flags
  *
  * Return: the memory region on success, otherwise returns an errno.
- * Note that all DMA addresses should be created via the
- * struct ib_dma_mapping_ops functions (see dma.c).
+ * Note that all DMA addresses should be created via the functions in
+ * struct dma_virt_ops.
  */
 struct ib_mr *rvt_get_dma_mr(struct ib_pd *pd, int acc)
 {
@@ -323,7 +338,7 @@ struct ib_mr *rvt_get_dma_mr(struct ib_pd *pd, int acc)
 		goto bail;
 	}
 
-	rval = rvt_init_mregion(&mr->mr, pd, 0);
+	rval = rvt_init_mregion(&mr->mr, pd, 0, 0);
 	if (rval) {
 		ret = ERR_PTR(rval);
 		goto bail;
@@ -445,8 +460,8 @@ int rvt_dereg_mr(struct ib_mr *ibmr)
 	timeout = wait_for_completion_timeout(&mr->mr.comp, 5 * HZ);
 	if (!timeout) {
 		rvt_pr_err(rdi,
-			   "rvt_dereg_mr timeout mr %p pd %p refcount %u\n",
-			   mr, mr->mr.pd, atomic_read(&mr->mr.refcount));
+			   "rvt_dereg_mr timeout mr %p pd %p\n",
+			   mr, mr->mr.pd);
 		rvt_get_mr(&mr->mr);
 		ret = -EBUSY;
 		goto out;
@@ -623,7 +638,8 @@ struct ib_fmr *rvt_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
 	if (!fmr)
 		goto bail;
 
-	rval = rvt_init_mregion(&fmr->mr, pd, fmr_attr->max_pages);
+	rval = rvt_init_mregion(&fmr->mr, pd, fmr_attr->max_pages,
+				PERCPU_REF_INIT_ATOMIC);
 	if (rval)
 		goto bail;
 
@@ -674,11 +690,12 @@ int rvt_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
 	struct rvt_fmr *fmr = to_ifmr(ibfmr);
 	struct rvt_lkey_table *rkt;
 	unsigned long flags;
-	int m, n, i;
+	int m, n;
+	unsigned long i;
 	u32 ps;
 	struct rvt_dev_info *rdi = ib_to_rvt(ibfmr->device);
 
-	i = atomic_read(&fmr->mr.refcount);
+	i = atomic_long_read(&fmr->mr.refcount.count);
 	if (i > 2)
 		return -EBUSY;
 
@@ -782,7 +799,7 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 
 	/*
 	 * We use LKEY == zero for kernel virtual addresses
-	 * (see rvt_get_dma_mr and dma.c).
+	 * (see rvt_get_dma_mr() and dma_virt_ops).
 	 */
 	rcu_read_lock();
 	if (sge->lkey == 0) {
@@ -880,7 +897,7 @@ int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
 
 	/*
 	 * We use RKEY == zero for kernel virtual addresses
-	 * (see rvt_get_dma_mr and dma.c).
+	 * (see rvt_get_dma_mr() and dma_virt_ops).
 	 */
 	rcu_read_lock();
 	if (rkey == 0) {
diff --git a/drivers/infiniband/sw/rdmavt/pd.c b/drivers/infiniband/sw/rdmavt/pd.c
index d1292f324c67..8a89afff3363 100644
--- a/drivers/infiniband/sw/rdmavt/pd.c
+++ b/drivers/infiniband/sw/rdmavt/pd.c
@@ -90,7 +90,7 @@ struct ib_pd *rvt_alloc_pd(struct ib_device *ibdev,
 	spin_unlock(&dev->n_pds_lock);
 
 	/* ib_alloc_pd() will initialize pd->ibpd. */
-	pd->user = udata ? 1 : 0;
+	pd->user = !!udata;
 
 	ret = &pd->ibpd;
 
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 2a13ac660f2b..f5ad8d4bfb39 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -51,10 +51,51 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_hdrs.h>
 #include "qp.h"
 #include "vt.h"
 #include "trace.h"
 
+static void rvt_rc_timeout(unsigned long arg);
+
+/*
+ * Convert the AETH RNR timeout code into the number of microseconds.
+ */
+static const u32 ib_rvt_rnr_table[32] = {
+	655360, /* 00: 655.36 */
+	10,     /* 01:    .01 */
+	20,     /* 02     .02 */
+	30,     /* 03:    .03 */
+	40,     /* 04:    .04 */
+	60,     /* 05:    .06 */
+	80,     /* 06:    .08 */
+	120,    /* 07:    .12 */
+	160,    /* 08:    .16 */
+	240,    /* 09:    .24 */
+	320,    /* 0A:    .32 */
+	480,    /* 0B:    .48 */
+	640,    /* 0C:    .64 */
+	960,    /* 0D:    .96 */
+	1280,   /* 0E:   1.28 */
+	1920,   /* 0F:   1.92 */
+	2560,   /* 10:   2.56 */
+	3840,   /* 11:   3.84 */
+	5120,   /* 12:   5.12 */
+	7680,   /* 13:   7.68 */
+	10240,  /* 14:  10.24 */
+	15360,  /* 15:  15.36 */
+	20480,  /* 16:  20.48 */
+	30720,  /* 17:  30.72 */
+	40960,  /* 18:  40.96 */
+	61440,  /* 19:  61.44 */
+	81920,  /* 1A:  81.92 */
+	122880, /* 1B: 122.88 */
+	163840, /* 1C: 163.84 */
+	245760, /* 1D: 245.76 */
+	327680, /* 1E: 327.68 */
+	491520  /* 1F: 491.52 */
+};
+
 /*
  * Note that it is OK to post send work requests in the SQE and ERR
  * states; rvt_do_send() will process them and generate error
@@ -200,7 +241,8 @@ int rvt_driver_qp_init(struct rvt_dev_info *rdi)
 	if (!rdi->driver_f.free_all_qps ||
 	    !rdi->driver_f.qp_priv_alloc ||
 	    !rdi->driver_f.qp_priv_free ||
-	    !rdi->driver_f.notify_qp_reset)
+	    !rdi->driver_f.notify_qp_reset ||
+	    !rdi->driver_f.notify_restart_rc)
 		return -EINVAL;
 
 	/* allocate parent object */
@@ -587,6 +629,7 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 
 		/* Let drivers flush their waitlist */
 		rdi->driver_f.flush_qp_waiters(qp);
+		rvt_stop_rc_timers(qp);
 		qp->s_flags &= ~(RVT_S_TIMER | RVT_S_ANY_WAIT);
 		spin_unlock(&qp->s_lock);
 		spin_unlock(&qp->s_hlock);
@@ -594,7 +637,7 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 
 		/* Stop the send queue and the retry timer */
 		rdi->driver_f.stop_send_queue(qp);
-
+		rvt_del_timers_sync(qp);
 		/* Wait for things to stop */
 		rdi->driver_f.quiesce_qp(qp);
 
@@ -730,6 +773,11 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 			if (!qp->s_ack_queue)
 				goto bail_qp;
 		}
+		/* initialize timers needed for rc qp */
+		setup_timer(&qp->s_timer, rvt_rc_timeout, (unsigned long)qp);
+		hrtimer_init(&qp->s_rnr_timer, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_REL);
+		qp->s_rnr_timer.function = rvt_rc_rnr_retry;
 
 		/*
 		 * Driver needs to set up it's private QP structure and do any
@@ -1868,3 +1916,184 @@ int rvt_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 	}
 	return 0;
 }
+
+/**
+ * qp_comm_est - handle trap with QP established
+ * @qp: the QP
+ */
+void rvt_comm_est(struct rvt_qp *qp)
+{
+	qp->r_flags |= RVT_R_COMM_EST;
+	if (qp->ibqp.event_handler) {
+		struct ib_event ev;
+
+		ev.device = qp->ibqp.device;
+		ev.element.qp = &qp->ibqp;
+		ev.event = IB_EVENT_COMM_EST;
+		qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
+	}
+}
+EXPORT_SYMBOL(rvt_comm_est);
+
+void rvt_rc_error(struct rvt_qp *qp, enum ib_wc_status err)
+{
+	unsigned long flags;
+	int lastwqe;
+
+	spin_lock_irqsave(&qp->s_lock, flags);
+	lastwqe = rvt_error_qp(qp, err);
+	spin_unlock_irqrestore(&qp->s_lock, flags);
+
+	if (lastwqe) {
+		struct ib_event ev;
+
+		ev.device = qp->ibqp.device;
+		ev.element.qp = &qp->ibqp;
+		ev.event = IB_EVENT_QP_LAST_WQE_REACHED;
+		qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
+	}
+}
+EXPORT_SYMBOL(rvt_rc_error);
+
+/*
+ *  rvt_rnr_tbl_to_usec - return index into ib_rvt_rnr_table
+ *  @index - the index
+ *  return usec from an index into ib_rvt_rnr_table
+ */
+unsigned long rvt_rnr_tbl_to_usec(u32 index)
+{
+	return ib_rvt_rnr_table[(index & IB_AETH_CREDIT_MASK)];
+}
+EXPORT_SYMBOL(rvt_rnr_tbl_to_usec);
+
+static inline unsigned long rvt_aeth_to_usec(u32 aeth)
+{
+	return ib_rvt_rnr_table[(aeth >> IB_AETH_CREDIT_SHIFT) &
+				  IB_AETH_CREDIT_MASK];
+}
+
+/*
+ *  rvt_add_retry_timer - add/start a retry timer
+ *  @qp - the QP
+ *  add a retry timer on the QP
+ */
+void rvt_add_retry_timer(struct rvt_qp *qp)
+{
+	struct ib_qp *ibqp = &qp->ibqp;
+	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
+
+	lockdep_assert_held(&qp->s_lock);
+	qp->s_flags |= RVT_S_TIMER;
+       /* 4.096 usec. * (1 << qp->timeout) */
+	qp->s_timer.expires = jiffies + qp->timeout_jiffies +
+			     rdi->busy_jiffies;
+	add_timer(&qp->s_timer);
+}
+EXPORT_SYMBOL(rvt_add_retry_timer);
+
+/**
+ * rvt_add_rnr_timer - add/start an rnr timer
+ * @qp - the QP
+ * @aeth - aeth of RNR timeout, simulated aeth for loopback
+ * add an rnr timer on the QP
+ */
+void rvt_add_rnr_timer(struct rvt_qp *qp, u32 aeth)
+{
+	u32 to;
+
+	lockdep_assert_held(&qp->s_lock);
+	qp->s_flags |= RVT_S_WAIT_RNR;
+	to = rvt_aeth_to_usec(aeth);
+	hrtimer_start(&qp->s_rnr_timer,
+		      ns_to_ktime(1000 * to), HRTIMER_MODE_REL);
+}
+EXPORT_SYMBOL(rvt_add_rnr_timer);
+
+/**
+ * rvt_stop_rc_timers - stop all timers
+ * @qp - the QP
+ * stop any pending timers
+ */
+void rvt_stop_rc_timers(struct rvt_qp *qp)
+{
+	lockdep_assert_held(&qp->s_lock);
+	/* Remove QP from all timers */
+	if (qp->s_flags & (RVT_S_TIMER | RVT_S_WAIT_RNR)) {
+		qp->s_flags &= ~(RVT_S_TIMER | RVT_S_WAIT_RNR);
+		del_timer(&qp->s_timer);
+		hrtimer_try_to_cancel(&qp->s_rnr_timer);
+	}
+}
+EXPORT_SYMBOL(rvt_stop_rc_timers);
+
+/**
+ * rvt_stop_rnr_timer - stop an rnr timer
+ * @qp - the QP
+ *
+ * stop an rnr timer and return if the timer
+ * had been pending.
+ */
+static int rvt_stop_rnr_timer(struct rvt_qp *qp)
+{
+	int rval = 0;
+
+	lockdep_assert_held(&qp->s_lock);
+	/* Remove QP from rnr timer */
+	if (qp->s_flags & RVT_S_WAIT_RNR) {
+		qp->s_flags &= ~RVT_S_WAIT_RNR;
+		rval = hrtimer_try_to_cancel(&qp->s_rnr_timer);
+	}
+	return rval;
+}
+
+/**
+ * rvt_del_timers_sync - wait for any timeout routines to exit
+ * @qp - the QP
+ */
+void rvt_del_timers_sync(struct rvt_qp *qp)
+{
+	del_timer_sync(&qp->s_timer);
+	hrtimer_cancel(&qp->s_rnr_timer);
+}
+EXPORT_SYMBOL(rvt_del_timers_sync);
+
+/**
+ * This is called from s_timer for missing responses.
+ */
+static void rvt_rc_timeout(unsigned long arg)
+{
+	struct rvt_qp *qp = (struct rvt_qp *)arg;
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->r_lock, flags);
+	spin_lock(&qp->s_lock);
+	if (qp->s_flags & RVT_S_TIMER) {
+		qp->s_flags &= ~RVT_S_TIMER;
+		del_timer(&qp->s_timer);
+		if (rdi->driver_f.notify_restart_rc)
+			rdi->driver_f.notify_restart_rc(qp,
+							qp->s_last_psn + 1,
+							1);
+		rdi->driver_f.schedule_send(qp);
+	}
+	spin_unlock(&qp->s_lock);
+	spin_unlock_irqrestore(&qp->r_lock, flags);
+}
+
+/*
+ * This is called from s_timer for RNR timeouts.
+ */
+enum hrtimer_restart rvt_rc_rnr_retry(struct hrtimer *t)
+{
+	struct rvt_qp *qp = container_of(t, struct rvt_qp, s_rnr_timer);
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->s_lock, flags);
+	rvt_stop_rnr_timer(qp);
+	rdi->driver_f.schedule_send(qp);
+	spin_unlock_irqrestore(&qp->s_lock, flags);
+	return HRTIMER_NORESTART;
+}
+EXPORT_SYMBOL(rvt_rc_rnr_retry);
diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c
new file mode 100644
index 000000000000..6131cc558bdb
--- /dev/null
+++ b/drivers/infiniband/sw/rdmavt/rc.c
@@ -0,0 +1,189 @@
+/*
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  - Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  - Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER 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.
+ *
+ */
+
+#include <rdma/rdma_vt.h>
+#include <rdma/ib_hdrs.h>
+
+/*
+ * Convert the AETH credit code into the number of credits.
+ */
+static const u16 credit_table[31] = {
+	0,                      /* 0 */
+	1,                      /* 1 */
+	2,                      /* 2 */
+	3,                      /* 3 */
+	4,                      /* 4 */
+	6,                      /* 5 */
+	8,                      /* 6 */
+	12,                     /* 7 */
+	16,                     /* 8 */
+	24,                     /* 9 */
+	32,                     /* A */
+	48,                     /* B */
+	64,                     /* C */
+	96,                     /* D */
+	128,                    /* E */
+	192,                    /* F */
+	256,                    /* 10 */
+	384,                    /* 11 */
+	512,                    /* 12 */
+	768,                    /* 13 */
+	1024,                   /* 14 */
+	1536,                   /* 15 */
+	2048,                   /* 16 */
+	3072,                   /* 17 */
+	4096,                   /* 18 */
+	6144,                   /* 19 */
+	8192,                   /* 1A */
+	12288,                  /* 1B */
+	16384,                  /* 1C */
+	24576,                  /* 1D */
+	32768                   /* 1E */
+};
+
+/**
+ * rvt_compute_aeth - compute the AETH (syndrome + MSN)
+ * @qp: the queue pair to compute the AETH for
+ *
+ * Returns the AETH.
+ */
+__be32 rvt_compute_aeth(struct rvt_qp *qp)
+{
+	u32 aeth = qp->r_msn & IB_MSN_MASK;
+
+	if (qp->ibqp.srq) {
+		/*
+		 * Shared receive queues don't generate credits.
+		 * Set the credit field to the invalid value.
+		 */
+		aeth |= IB_AETH_CREDIT_INVAL << IB_AETH_CREDIT_SHIFT;
+	} else {
+		u32 min, max, x;
+		u32 credits;
+		struct rvt_rwq *wq = qp->r_rq.wq;
+		u32 head;
+		u32 tail;
+
+		/* sanity check pointers before trusting them */
+		head = wq->head;
+		if (head >= qp->r_rq.size)
+			head = 0;
+		tail = wq->tail;
+		if (tail >= qp->r_rq.size)
+			tail = 0;
+		/*
+		 * Compute the number of credits available (RWQEs).
+		 * There is a small chance that the pair of reads are
+		 * not atomic, which is OK, since the fuzziness is
+		 * resolved as further ACKs go out.
+		 */
+		credits = head - tail;
+		if ((int)credits < 0)
+			credits += qp->r_rq.size;
+		/*
+		 * Binary search the credit table to find the code to
+		 * use.
+		 */
+		min = 0;
+		max = 31;
+		for (;;) {
+			x = (min + max) / 2;
+			if (credit_table[x] == credits)
+				break;
+			if (credit_table[x] > credits) {
+				max = x;
+			} else {
+				if (min == x)
+					break;
+				min = x;
+			}
+		}
+		aeth |= x << IB_AETH_CREDIT_SHIFT;
+	}
+	return cpu_to_be32(aeth);
+}
+EXPORT_SYMBOL(rvt_compute_aeth);
+
+/**
+ * rvt_get_credit - flush the send work queue of a QP
+ * @qp: the qp who's send work queue to flush
+ * @aeth: the Acknowledge Extended Transport Header
+ *
+ * The QP s_lock should be held.
+ */
+void rvt_get_credit(struct rvt_qp *qp, u32 aeth)
+{
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+	u32 credit = (aeth >> IB_AETH_CREDIT_SHIFT) & IB_AETH_CREDIT_MASK;
+
+	lockdep_assert_held(&qp->s_lock);
+	/*
+	 * If the credit is invalid, we can send
+	 * as many packets as we like.  Otherwise, we have to
+	 * honor the credit field.
+	 */
+	if (credit == IB_AETH_CREDIT_INVAL) {
+		if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT)) {
+			qp->s_flags |= RVT_S_UNLIMITED_CREDIT;
+			if (qp->s_flags & RVT_S_WAIT_SSN_CREDIT) {
+				qp->s_flags &= ~RVT_S_WAIT_SSN_CREDIT;
+				rdi->driver_f.schedule_send(qp);
+			}
+		}
+	} else if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT)) {
+		/* Compute new LSN (i.e., MSN + credit) */
+		credit = (aeth + credit_table[credit]) & IB_MSN_MASK;
+		if (rvt_cmp_msn(credit, qp->s_lsn) > 0) {
+			qp->s_lsn = credit;
+			if (qp->s_flags & RVT_S_WAIT_SSN_CREDIT) {
+				qp->s_flags &= ~RVT_S_WAIT_SSN_CREDIT;
+				rdi->driver_f.schedule_send(qp);
+			}
+		}
+	}
+}
+EXPORT_SYMBOL(rvt_get_credit);
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index d430c2f7cec4..0d7c6bb551d9 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -47,6 +47,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/dma-mapping.h>
 #include "vt.h"
 #include "trace.h"
 
@@ -165,7 +166,7 @@ static int rvt_query_port(struct ib_device *ibdev, u8 port_num,
 		return -EINVAL;
 
 	rvp = rdi->ports[port_index];
-	memset(props, 0, sizeof(*props));
+	/* props being zeroed by the caller, avoid zeroing it here */
 	props->sm_lid = rvp->sm_lid;
 	props->sm_sl = rvp->sm_sl;
 	props->port_cap_flags = rvp->port_cap_flags;
@@ -326,13 +327,14 @@ static int rvt_get_port_immutable(struct ib_device *ibdev, u8 port_num,
 	if (port_index < 0)
 		return -EINVAL;
 
-	err = rvt_query_port(ibdev, port_num, &attr);
+	immutable->core_cap_flags = rdi->dparms.core_cap_flags;
+
+	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = rdi->dparms.core_cap_flags;
 	immutable->max_mad_size = rdi->dparms.max_mad_size;
 
 	return 0;
@@ -777,8 +779,7 @@ int rvt_register_device(struct rvt_dev_info *rdi)
 	}
 
 	/* DMA Operations */
-	rdi->ibdev.dma_ops =
-		rdi->ibdev.dma_ops ? : &rvt_default_dma_mapping_ops;
+	rdi->ibdev.dev.dma_ops = rdi->ibdev.dev.dma_ops ? : &dma_virt_ops;
 
 	/* Protection Domain */
 	spin_lock_init(&rdi->n_pds_lock);
diff --git a/drivers/infiniband/sw/rdmavt/vt.h b/drivers/infiniband/sw/rdmavt/vt.h
index 6b01eaa4461b..f363505312be 100644
--- a/drivers/infiniband/sw/rdmavt/vt.h
+++ b/drivers/infiniband/sw/rdmavt/vt.h
@@ -50,7 +50,6 @@
 
 #include <rdma/rdma_vt.h>
 #include <linux/pci.h>
-#include "dma.h"
 #include "pd.h"
 #include "qp.h"
 #include "ah.h"
diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig
index 1e4e628fe7b0..7d1ac27ed251 100644
--- a/drivers/infiniband/sw/rxe/Kconfig
+++ b/drivers/infiniband/sw/rxe/Kconfig
@@ -2,6 +2,7 @@ config RDMA_RXE
 	tristate "Software RDMA over Ethernet (RoCE) driver"
 	depends on INET && PCI && INFINIBAND
 	depends on NET_UDP_TUNNEL
+	select DMA_VIRT_OPS
 	---help---
 	This driver implements the InfiniBand RDMA transport over
 	the Linux network stack. It enables a system with a
diff --git a/drivers/infiniband/sw/rxe/Makefile b/drivers/infiniband/sw/rxe/Makefile
index 3b3fb9d1c470..ec35ff022a42 100644
--- a/drivers/infiniband/sw/rxe/Makefile
+++ b/drivers/infiniband/sw/rxe/Makefile
@@ -14,7 +14,6 @@ rdma_rxe-y := \
 	rxe_qp.o \
 	rxe_cq.o \
 	rxe_mr.o \
-	rxe_dma.o \
 	rxe_opcode.o \
 	rxe_mmap.o \
 	rxe_icrc.o \
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index ab6c3c25d7ff..b12dd9b5a89d 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -178,7 +178,7 @@ static int rxe_init_ports(struct rxe_dev *rxe)
 		return -ENOMEM;
 
 	port->pkey_tbl[0] = 0xffff;
-	port->port_guid = rxe->ifc_ops->port_guid(rxe);
+	port->port_guid = rxe_port_guid(rxe);
 
 	spin_lock_init(&port->port_lock);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index d369f24425f9..4cd55d5617f7 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -254,7 +254,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp,
 		}
 		break;
 	default:
-		WARN_ON(1);
+		WARN_ON_ONCE(1);
 	}
 
 	/* Check operation validity. */
@@ -412,13 +412,21 @@ static void make_send_cqe(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 	}
 }
 
+/*
+ * IBA Spec. Section 10.7.3.1 SIGNALED COMPLETIONS
+ * ---------8<---------8<-------------
+ * ...Note that if a completion error occurs, a Work Completion
+ * will always be generated, even if the signaling
+ * indicator requests an Unsignaled Completion.
+ * ---------8<---------8<-------------
+ */
 static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 {
 	struct rxe_cqe cqe;
 
 	if ((qp->sq_sig_type == IB_SIGNAL_ALL_WR) ||
 	    (wqe->wr.send_flags & IB_SEND_SIGNALED) ||
-	    (qp->req.state == QP_STATE_ERROR)) {
+	    wqe->status != IB_WC_SUCCESS) {
 		make_send_cqe(qp, wqe, &cqe);
 		advance_consumer(qp->sq.queue);
 		rxe_cq_post(qp->scq, &cqe, 0);
@@ -503,57 +511,40 @@ static inline enum comp_state complete_wqe(struct rxe_qp *qp,
 	return COMPST_GET_WQE;
 }
 
-int rxe_completer(void *arg)
+static void rxe_drain_resp_pkts(struct rxe_qp *qp, bool notify)
 {
-	struct rxe_qp *qp = (struct rxe_qp *)arg;
-	struct rxe_send_wqe *wqe = wqe;
-	struct sk_buff *skb = NULL;
-	struct rxe_pkt_info *pkt = NULL;
-	enum comp_state state;
-
-	rxe_add_ref(qp);
-
-	if (!qp->valid) {
-		while ((skb = skb_dequeue(&qp->resp_pkts))) {
-			rxe_drop_ref(qp);
-			kfree_skb(skb);
-		}
-		skb = NULL;
-		pkt = NULL;
-
-		while (queue_head(qp->sq.queue))
-			advance_consumer(qp->sq.queue);
+	struct sk_buff *skb;
+	struct rxe_send_wqe *wqe;
 
-		goto exit;
+	while ((skb = skb_dequeue(&qp->resp_pkts))) {
+		rxe_drop_ref(qp);
+		kfree_skb(skb);
 	}
 
-	if (qp->req.state == QP_STATE_ERROR) {
-		while ((skb = skb_dequeue(&qp->resp_pkts))) {
-			rxe_drop_ref(qp);
-			kfree_skb(skb);
-		}
-		skb = NULL;
-		pkt = NULL;
-
-		while ((wqe = queue_head(qp->sq.queue))) {
+	while ((wqe = queue_head(qp->sq.queue))) {
+		if (notify) {
 			wqe->status = IB_WC_WR_FLUSH_ERR;
 			do_complete(qp, wqe);
+		} else {
+			advance_consumer(qp->sq.queue);
 		}
-
-		goto exit;
 	}
+}
 
-	if (qp->req.state == QP_STATE_RESET) {
-		while ((skb = skb_dequeue(&qp->resp_pkts))) {
-			rxe_drop_ref(qp);
-			kfree_skb(skb);
-		}
-		skb = NULL;
-		pkt = NULL;
+int rxe_completer(void *arg)
+{
+	struct rxe_qp *qp = (struct rxe_qp *)arg;
+	struct rxe_send_wqe *wqe = wqe;
+	struct sk_buff *skb = NULL;
+	struct rxe_pkt_info *pkt = NULL;
+	enum comp_state state;
 
-		while (queue_head(qp->sq.queue))
-			advance_consumer(qp->sq.queue);
+	rxe_add_ref(qp);
 
+	if (!qp->valid || qp->req.state == QP_STATE_ERROR ||
+	    qp->req.state == QP_STATE_RESET) {
+		rxe_drain_resp_pkts(qp, qp->valid &&
+				    qp->req.state == QP_STATE_ERROR);
 		goto exit;
 	}
 
@@ -639,6 +630,7 @@ int rxe_completer(void *arg)
 			if (pkt) {
 				rxe_drop_ref(pkt->qp);
 				kfree_skb(skb);
+				skb = NULL;
 			}
 			goto done;
 
@@ -662,6 +654,7 @@ int rxe_completer(void *arg)
 			    qp->qp_timeout_jiffies)
 				mod_timer(&qp->retrans_timer,
 					  jiffies + qp->qp_timeout_jiffies);
+			WARN_ON_ONCE(skb);
 			goto exit;
 
 		case COMPST_ERROR_RETRY:
@@ -674,8 +667,10 @@ int rxe_completer(void *arg)
 			 */
 
 			/* there is nothing to retry in this case */
-			if (!wqe || (wqe->state == wqe_state_posted))
+			if (!wqe || (wqe->state == wqe_state_posted)) {
+				WARN_ON_ONCE(skb);
 				goto exit;
+			}
 
 			if (qp->comp.retry_cnt > 0) {
 				if (qp->comp.retry_cnt != 7)
@@ -697,8 +692,10 @@ int rxe_completer(void *arg)
 				if (pkt) {
 					rxe_drop_ref(pkt->qp);
 					kfree_skb(skb);
+					skb = NULL;
 				}
 
+				WARN_ON_ONCE(skb);
 				goto exit;
 
 			} else {
@@ -718,6 +715,9 @@ int rxe_completer(void *arg)
 				mod_timer(&qp->rnr_nak_timer,
 					  jiffies + rnrnak_jiffies(aeth_syn(pkt)
 						& ~AETH_TYPE_MASK));
+				rxe_drop_ref(pkt->qp);
+				kfree_skb(skb);
+				skb = NULL;
 				goto exit;
 			} else {
 				wqe->status = IB_WC_RNR_RETRY_EXC_ERR;
@@ -726,14 +726,17 @@ int rxe_completer(void *arg)
 			break;
 
 		case COMPST_ERROR:
+			WARN_ON_ONCE(wqe->status == IB_WC_SUCCESS);
 			do_complete(qp, wqe);
 			rxe_qp_error(qp);
 
 			if (pkt) {
 				rxe_drop_ref(pkt->qp);
 				kfree_skb(skb);
+				skb = NULL;
 			}
 
+			WARN_ON_ONCE(skb);
 			goto exit;
 		}
 	}
@@ -742,6 +745,7 @@ exit:
 	/* we come here if we are done with processing and want the task to
 	 * exit from the loop calling us
 	 */
+	WARN_ON_ONCE(skb);
 	rxe_drop_ref(qp);
 	return -EAGAIN;
 
@@ -749,6 +753,7 @@ done:
 	/* we come here if we have processed a packet we want the task to call
 	 * us again to see if there is anything else to do
 	 */
+	WARN_ON_ONCE(skb);
 	rxe_drop_ref(qp);
 	return 0;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index e5e6a5e7dee9..49fe42c23f4d 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -156,9 +156,9 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited)
 	return 0;
 }
 
-void rxe_cq_cleanup(void *arg)
+void rxe_cq_cleanup(struct rxe_pool_entry *arg)
 {
-	struct rxe_cq *cq = arg;
+	struct rxe_cq *cq = container_of(arg, typeof(*cq), pelem);
 
 	if (cq->queue)
 		rxe_queue_cleanup(cq->queue);
diff --git a/drivers/infiniband/sw/rxe/rxe_dma.c b/drivers/infiniband/sw/rxe/rxe_dma.c
deleted file mode 100644
index a0f8af5851ae..000000000000
--- a/drivers/infiniband/sw/rxe/rxe_dma.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
- * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *	- Redistributions of source code must retain the above
- *	  copyright notice, this list of conditions and the following
- *	  disclaimer.
- *
- *	- Redistributions in binary form must reproduce the above
- *	  copyright notice, this list of conditions and the following
- *	  disclaimer in the documentation and/or other materials
- *	  provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include "rxe.h"
-#include "rxe_loc.h"
-
-#define DMA_BAD_ADDER ((u64)0)
-
-static int rxe_mapping_error(struct ib_device *dev, u64 dma_addr)
-{
-	return dma_addr == DMA_BAD_ADDER;
-}
-
-static u64 rxe_dma_map_single(struct ib_device *dev,
-			      void *cpu_addr, size_t size,
-			      enum dma_data_direction direction)
-{
-	WARN_ON(!valid_dma_direction(direction));
-	return (uintptr_t)cpu_addr;
-}
-
-static void rxe_dma_unmap_single(struct ib_device *dev,
-				 u64 addr, size_t size,
-				 enum dma_data_direction direction)
-{
-	WARN_ON(!valid_dma_direction(direction));
-}
-
-static u64 rxe_dma_map_page(struct ib_device *dev,
-			    struct page *page,
-			    unsigned long offset,
-			    size_t size, enum dma_data_direction direction)
-{
-	u64 addr;
-
-	WARN_ON(!valid_dma_direction(direction));
-
-	if (offset + size > PAGE_SIZE) {
-		addr = DMA_BAD_ADDER;
-		goto done;
-	}
-
-	addr = (uintptr_t)page_address(page);
-	if (addr)
-		addr += offset;
-
-done:
-	return addr;
-}
-
-static void rxe_dma_unmap_page(struct ib_device *dev,
-			       u64 addr, size_t size,
-			       enum dma_data_direction direction)
-{
-	WARN_ON(!valid_dma_direction(direction));
-}
-
-static int rxe_map_sg(struct ib_device *dev, struct scatterlist *sgl,
-		      int nents, enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	u64 addr;
-	int i;
-	int ret = nents;
-
-	WARN_ON(!valid_dma_direction(direction));
-
-	for_each_sg(sgl, sg, nents, i) {
-		addr = (uintptr_t)page_address(sg_page(sg));
-		if (!addr) {
-			ret = 0;
-			break;
-		}
-		sg->dma_address = addr + sg->offset;
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-	}
-
-	return ret;
-}
-
-static void rxe_unmap_sg(struct ib_device *dev,
-			 struct scatterlist *sg, int nents,
-			 enum dma_data_direction direction)
-{
-	WARN_ON(!valid_dma_direction(direction));
-}
-
-static int rxe_map_sg_attrs(struct ib_device *dev, struct scatterlist *sgl,
-			    int nents, enum dma_data_direction direction,
-			    unsigned long attrs)
-{
-	return rxe_map_sg(dev, sgl, nents, direction);
-}
-
-static void rxe_unmap_sg_attrs(struct ib_device *dev,
-			       struct scatterlist *sg, int nents,
-			       enum dma_data_direction direction,
-			       unsigned long attrs)
-{
-	rxe_unmap_sg(dev, sg, nents, direction);
-}
-
-static void rxe_sync_single_for_cpu(struct ib_device *dev,
-				    u64 addr,
-				    size_t size, enum dma_data_direction dir)
-{
-}
-
-static void rxe_sync_single_for_device(struct ib_device *dev,
-				       u64 addr,
-				       size_t size, enum dma_data_direction dir)
-{
-}
-
-static void *rxe_dma_alloc_coherent(struct ib_device *dev, size_t size,
-				    u64 *dma_handle, gfp_t flag)
-{
-	struct page *p;
-	void *addr = NULL;
-
-	p = alloc_pages(flag, get_order(size));
-	if (p)
-		addr = page_address(p);
-
-	if (dma_handle)
-		*dma_handle = (uintptr_t)addr;
-
-	return addr;
-}
-
-static void rxe_dma_free_coherent(struct ib_device *dev, size_t size,
-				  void *cpu_addr, u64 dma_handle)
-{
-	free_pages((unsigned long)cpu_addr, get_order(size));
-}
-
-struct ib_dma_mapping_ops rxe_dma_mapping_ops = {
-	.mapping_error		= rxe_mapping_error,
-	.map_single		= rxe_dma_map_single,
-	.unmap_single		= rxe_dma_unmap_single,
-	.map_page		= rxe_dma_map_page,
-	.unmap_page		= rxe_dma_unmap_page,
-	.map_sg			= rxe_map_sg,
-	.unmap_sg		= rxe_unmap_sg,
-	.map_sg_attrs		= rxe_map_sg_attrs,
-	.unmap_sg_attrs		= rxe_unmap_sg_attrs,
-	.sync_single_for_cpu	= rxe_sync_single_for_cpu,
-	.sync_single_for_device	= rxe_sync_single_for_device,
-	.alloc_coherent		= rxe_dma_alloc_coherent,
-	.free_coherent		= rxe_dma_free_coherent
-};
diff --git a/drivers/infiniband/sw/rxe/rxe_hdr.h b/drivers/infiniband/sw/rxe/rxe_hdr.h
index d57b5e956ceb..6cb18406f5b8 100644
--- a/drivers/infiniband/sw/rxe/rxe_hdr.h
+++ b/drivers/infiniband/sw/rxe/rxe_hdr.h
@@ -53,8 +53,16 @@ struct rxe_pkt_info {
 };
 
 /* Macros should be used only for received skb */
-#define SKB_TO_PKT(skb) ((struct rxe_pkt_info *)(skb)->cb)
-#define PKT_TO_SKB(pkt) container_of((void *)(pkt), struct sk_buff, cb)
+static inline struct rxe_pkt_info *SKB_TO_PKT(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct rxe_pkt_info) > sizeof(skb->cb));
+	return (void *)skb->cb;
+}
+
+static inline struct sk_buff *PKT_TO_SKB(struct rxe_pkt_info *pkt)
+{
+	return container_of((void *)pkt, struct sk_buff, cb);
+}
 
 /*
  * IBA header types and methods
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index efe4c6a35442..183a9d379b41 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -64,7 +64,7 @@ int rxe_cq_resize_queue(struct rxe_cq *cq, int new_cqe, struct ib_udata *udata);
 
 int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited);
 
-void rxe_cq_cleanup(void *arg);
+void rxe_cq_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_mcast.c */
 int rxe_mcast_get_grp(struct rxe_dev *rxe, union ib_gid *mgid,
@@ -78,7 +78,7 @@ int rxe_mcast_drop_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
 
 void rxe_drop_all_mcast_groups(struct rxe_qp *qp);
 
-void rxe_mc_cleanup(void *arg);
+void rxe_mc_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_mmap.c */
 struct rxe_mmap_info {
@@ -137,10 +137,26 @@ int mem_check_range(struct rxe_mem *mem, u64 iova, size_t length);
 int rxe_mem_map_pages(struct rxe_dev *rxe, struct rxe_mem *mem,
 		      u64 *page, int num_pages, u64 iova);
 
-void rxe_mem_cleanup(void *arg);
+void rxe_mem_cleanup(struct rxe_pool_entry *arg);
 
 int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
 
+/* rxe_net.c */
+int rxe_loopback(struct sk_buff *skb);
+int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
+	     struct sk_buff *skb);
+__be64 rxe_port_guid(struct rxe_dev *rxe);
+struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
+				int paylen, struct rxe_pkt_info *pkt);
+int rxe_prepare(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
+		struct sk_buff *skb, u32 *crc);
+enum rdma_link_layer rxe_link_layer(struct rxe_dev *rxe, unsigned int port_num);
+const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num);
+struct device *rxe_dma_device(struct rxe_dev *rxe);
+__be64 rxe_node_guid(struct rxe_dev *rxe);
+int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid);
+int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid);
+
 /* rxe_qp.c */
 int rxe_qp_chk_init(struct rxe_dev *rxe, struct ib_qp_init_attr *init);
 
@@ -162,7 +178,7 @@ void rxe_qp_error(struct rxe_qp *qp);
 
 void rxe_qp_destroy(struct rxe_qp *qp);
 
-void rxe_qp_cleanup(void *arg);
+void rxe_qp_cleanup(struct rxe_pool_entry *arg);
 
 static inline int qp_num(struct rxe_qp *qp)
 {
@@ -221,10 +237,9 @@ int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq,
 		      struct ib_srq_attr *attr, enum ib_srq_attr_mask mask,
 		      struct ib_udata *udata);
 
-extern struct ib_dma_mapping_ops rxe_dma_mapping_ops;
-
 void rxe_release(struct kref *kref);
 
+void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify);
 int rxe_completer(void *arg);
 int rxe_requester(void *arg);
 int rxe_responder(void *arg);
@@ -256,9 +271,9 @@ static inline int rxe_xmit_packet(struct rxe_dev *rxe, struct rxe_qp *qp,
 
 	if (pkt->mask & RXE_LOOPBACK_MASK) {
 		memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt));
-		err = rxe->ifc_ops->loopback(skb);
+		err = rxe_loopback(skb);
 	} else {
-		err = rxe->ifc_ops->send(rxe, pkt, skb);
+		err = rxe_send(rxe, pkt, skb);
 	}
 
 	if (err) {
diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c
index fa95544ca7e0..522a7942c56c 100644
--- a/drivers/infiniband/sw/rxe/rxe_mcast.c
+++ b/drivers/infiniband/sw/rxe/rxe_mcast.c
@@ -61,7 +61,7 @@ int rxe_mcast_get_grp(struct rxe_dev *rxe, union ib_gid *mgid,
 
 	rxe_add_key(grp, mgid);
 
-	err = rxe->ifc_ops->mcast_add(rxe, mgid);
+	err = rxe_mcast_add(rxe, mgid);
 	if (err)
 		goto err2;
 
@@ -180,11 +180,11 @@ void rxe_drop_all_mcast_groups(struct rxe_qp *qp)
 	}
 }
 
-void rxe_mc_cleanup(void *arg)
+void rxe_mc_cleanup(struct rxe_pool_entry *arg)
 {
-	struct rxe_mc_grp *grp = arg;
+	struct rxe_mc_grp *grp = container_of(arg, typeof(*grp), pelem);
 	struct rxe_dev *rxe = grp->rxe;
 
 	rxe_drop_key(grp);
-	rxe->ifc_ops->mcast_delete(rxe, &grp->mgid);
+	rxe_mcast_delete(rxe, &grp->mgid);
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 86a6585b847d..37eea7441ca4 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -91,9 +91,9 @@ static void rxe_mem_init(int access, struct rxe_mem *mem)
 	mem->map_shift		= ilog2(RXE_BUF_PER_MAP);
 }
 
-void rxe_mem_cleanup(void *arg)
+void rxe_mem_cleanup(struct rxe_pool_entry *arg)
 {
-	struct rxe_mem *mem = arg;
+	struct rxe_mem *mem = container_of(arg, typeof(*mem), pelem);
 	int i;
 
 	if (mem->umem)
@@ -125,7 +125,7 @@ static int rxe_mem_alloc(struct rxe_dev *rxe, struct rxe_mem *mem, int num_buf)
 			goto err2;
 	}
 
-	WARN_ON(!is_power_of_2(RXE_BUF_PER_MAP));
+	BUILD_BUG_ON(!is_power_of_2(RXE_BUF_PER_MAP));
 
 	mem->map_shift	= ilog2(RXE_BUF_PER_MAP);
 	mem->map_mask	= RXE_BUF_PER_MAP - 1;
@@ -191,7 +191,7 @@ int rxe_mem_init_user(struct rxe_dev *rxe, struct rxe_pd *pd, u64 start,
 		goto err1;
 	}
 
-	WARN_ON(!is_power_of_2(umem->page_size));
+	WARN_ON_ONCE(!is_power_of_2(umem->page_size));
 
 	mem->page_shift		= ilog2(umem->page_size);
 	mem->page_mask		= umem->page_size - 1;
@@ -377,7 +377,7 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
 		return 0;
 	}
 
-	WARN_ON(!mem->map);
+	WARN_ON_ONCE(!mem->map);
 
 	err = mem_check_range(mem, iova, length);
 	if (err) {
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 4abdeb359fb4..d8610960630a 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -102,29 +102,29 @@ static __be64 rxe_mac_to_eui64(struct net_device *ndev)
 	return eui64;
 }
 
-static __be64 node_guid(struct rxe_dev *rxe)
+__be64 rxe_node_guid(struct rxe_dev *rxe)
 {
 	return rxe_mac_to_eui64(rxe->ndev);
 }
 
-static __be64 port_guid(struct rxe_dev *rxe)
+__be64 rxe_port_guid(struct rxe_dev *rxe)
 {
 	return rxe_mac_to_eui64(rxe->ndev);
 }
 
-static struct device *dma_device(struct rxe_dev *rxe)
+struct device *rxe_dma_device(struct rxe_dev *rxe)
 {
 	struct net_device *ndev;
 
 	ndev = rxe->ndev;
 
-	if (ndev->priv_flags & IFF_802_1Q_VLAN)
+	if (is_vlan_dev(ndev))
 		ndev = vlan_dev_real_dev(ndev);
 
 	return ndev->dev.parent;
 }
 
-static int mcast_add(struct rxe_dev *rxe, union ib_gid *mgid)
+int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid)
 {
 	int err;
 	unsigned char ll_addr[ETH_ALEN];
@@ -135,7 +135,7 @@ static int mcast_add(struct rxe_dev *rxe, union ib_gid *mgid)
 	return err;
 }
 
-static int mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid)
+int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid)
 {
 	int err;
 	unsigned char ll_addr[ETH_ALEN];
@@ -243,8 +243,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
 {
 	int err;
 	struct socket *sock;
-	struct udp_port_cfg udp_cfg = {0};
-	struct udp_tunnel_sock_cfg tnl_cfg = {0};
+	struct udp_port_cfg udp_cfg = { };
+	struct udp_tunnel_sock_cfg tnl_cfg = { };
 
 	if (ipv6) {
 		udp_cfg.family = AF_INET6;
@@ -397,8 +397,8 @@ static int prepare6(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
 	return 0;
 }
 
-static int prepare(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
-		   struct sk_buff *skb, u32 *crc)
+int rxe_prepare(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
+		struct sk_buff *skb, u32 *crc)
 {
 	int err = 0;
 	struct rxe_av *av = rxe_get_av(pkt);
@@ -424,8 +424,7 @@ static void rxe_skb_tx_dtor(struct sk_buff *skb)
 		rxe_run_task(&qp->req.task, 1);
 }
 
-static int send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
-		struct sk_buff *skb)
+int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb)
 {
 	struct sk_buff *nskb;
 	struct rxe_av *av;
@@ -461,7 +460,7 @@ static int send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
 	return 0;
 }
 
-static int loopback(struct sk_buff *skb)
+int rxe_loopback(struct sk_buff *skb)
 {
 	return rxe_rcv(skb);
 }
@@ -471,8 +470,8 @@ static inline int addr_same(struct rxe_dev *rxe, struct rxe_av *av)
 	return rxe->port.port_guid == av->grh.dgid.global.interface_id;
 }
 
-static struct sk_buff *init_packet(struct rxe_dev *rxe, struct rxe_av *av,
-				   int paylen, struct rxe_pkt_info *pkt)
+struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
+				int paylen, struct rxe_pkt_info *pkt)
 {
 	unsigned int hdr_len;
 	struct sk_buff *skb;
@@ -511,31 +510,16 @@ static struct sk_buff *init_packet(struct rxe_dev *rxe, struct rxe_av *av,
  * this is required by rxe_cfg to match rxe devices in
  * /sys/class/infiniband up with their underlying ethernet devices
  */
-static char *parent_name(struct rxe_dev *rxe, unsigned int port_num)
+const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num)
 {
 	return rxe->ndev->name;
 }
 
-static enum rdma_link_layer link_layer(struct rxe_dev *rxe,
-				       unsigned int port_num)
+enum rdma_link_layer rxe_link_layer(struct rxe_dev *rxe, unsigned int port_num)
 {
 	return IB_LINK_LAYER_ETHERNET;
 }
 
-static struct rxe_ifc_ops ifc_ops = {
-	.node_guid	= node_guid,
-	.port_guid	= port_guid,
-	.dma_device	= dma_device,
-	.mcast_add	= mcast_add,
-	.mcast_delete	= mcast_delete,
-	.prepare	= prepare,
-	.send		= send,
-	.loopback	= loopback,
-	.init_packet	= init_packet,
-	.parent_name	= parent_name,
-	.link_layer	= link_layer,
-};
-
 struct rxe_dev *rxe_net_add(struct net_device *ndev)
 {
 	int err;
@@ -545,7 +529,6 @@ struct rxe_dev *rxe_net_add(struct net_device *ndev)
 	if (!rxe)
 		return NULL;
 
-	rxe->ifc_ops = &ifc_ops;
 	rxe->ndev = ndev;
 
 	err = rxe_add(rxe, ndev->mtu);
@@ -658,7 +641,7 @@ struct notifier_block rxe_net_notifier = {
 	.notifier_call = rxe_notify,
 };
 
-int rxe_net_ipv4_init(void)
+static int rxe_net_ipv4_init(void)
 {
 	recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net,
 				htons(ROCE_V2_UDP_DPORT), false);
@@ -671,7 +654,7 @@ int rxe_net_ipv4_init(void)
 	return 0;
 }
 
-int rxe_net_ipv6_init(void)
+static int rxe_net_ipv6_init(void)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index d723947a8542..75d11ee635ec 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -102,7 +102,7 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
 	},
 };
 
-static inline char *pool_name(struct rxe_pool *pool)
+static inline const char *pool_name(struct rxe_pool *pool)
 {
 	return rxe_type_info[pool->type].name;
 }
@@ -112,13 +112,6 @@ static inline struct kmem_cache *pool_cache(struct rxe_pool *pool)
 	return rxe_type_info[pool->type].cache;
 }
 
-static inline enum rxe_elem_type rxe_type(void *arg)
-{
-	struct rxe_pool_entry *elem = arg;
-
-	return elem->pool->type;
-}
-
 int rxe_cache_init(void)
 {
 	int err;
@@ -273,6 +266,7 @@ static u32 alloc_index(struct rxe_pool *pool)
 	if (index >= range)
 		index = find_first_zero_bit(pool->table, range);
 
+	WARN_ON_ONCE(index >= range);
 	set_bit(index, pool->table);
 	pool->last = index;
 	return index + pool->min_index;
@@ -461,7 +455,7 @@ void *rxe_pool_get_index(struct rxe_pool *pool, u32 index)
 
 out:
 	spin_unlock_irqrestore(&pool->pool_lock, flags);
-	return node ? (void *)elem : NULL;
+	return node ? elem : NULL;
 }
 
 void *rxe_pool_get_key(struct rxe_pool *pool, void *key)
@@ -497,5 +491,5 @@ void *rxe_pool_get_key(struct rxe_pool *pool, void *key)
 
 out:
 	spin_unlock_irqrestore(&pool->pool_lock, flags);
-	return node ? ((void *)elem) : NULL;
+	return node ? elem : NULL;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.h b/drivers/infiniband/sw/rxe/rxe_pool.h
index 4d04830adcae..47df28e43acf 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.h
+++ b/drivers/infiniband/sw/rxe/rxe_pool.h
@@ -57,10 +57,12 @@ enum rxe_elem_type {
 	RXE_NUM_TYPES,		/* keep me last */
 };
 
+struct rxe_pool_entry;
+
 struct rxe_type_info {
-	char			*name;
+	const char		*name;
 	size_t			size;
-	void			(*cleanup)(void *obj);
+	void			(*cleanup)(struct rxe_pool_entry *obj);
 	enum rxe_pool_flags	flags;
 	u32			max_index;
 	u32			min_index;
@@ -91,7 +93,7 @@ struct rxe_pool {
 	spinlock_t              pool_lock; /* pool spinlock */
 	size_t			elem_size;
 	struct kref		ref_cnt;
-	void			(*cleanup)(void *obj);
+	void			(*cleanup)(struct rxe_pool_entry *obj);
 	enum rxe_pool_state	state;
 	enum rxe_pool_flags	flags;
 	enum rxe_elem_type	type;
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 44b2108253bd..f98a19e61a3d 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -273,13 +273,8 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
 	rxe_init_task(rxe, &qp->comp.task, qp,
 		      rxe_completer, "comp");
 
-	init_timer(&qp->rnr_nak_timer);
-	qp->rnr_nak_timer.function = rnr_nak_timer;
-	qp->rnr_nak_timer.data = (unsigned long)qp;
-
-	init_timer(&qp->retrans_timer);
-	qp->retrans_timer.function = retransmit_timer;
-	qp->retrans_timer.data = (unsigned long)qp;
+	setup_timer(&qp->rnr_nak_timer, rnr_nak_timer, (unsigned long)qp);
+	setup_timer(&qp->retrans_timer, retransmit_timer, (unsigned long)qp);
 	qp->qp_timeout_jiffies = 0; /* Can't be set for UD/UC in modify_qp */
 
 	return 0;
@@ -824,9 +819,9 @@ void rxe_qp_destroy(struct rxe_qp *qp)
 }
 
 /* called when the last reference to the qp is dropped */
-void rxe_qp_cleanup(void *arg)
+void rxe_qp_cleanup(struct rxe_pool_entry *arg)
 {
-	struct rxe_qp *qp = arg;
+	struct rxe_qp *qp = container_of(arg, typeof(*qp), pelem);
 
 	rxe_drop_all_mcast_groups(qp);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index 252b4d637d45..50886031096f 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -389,7 +389,7 @@ int rxe_rcv(struct sk_buff *skb)
 	calc_icrc = rxe_icrc_hdr(pkt, skb);
 	calc_icrc = crc32_le(calc_icrc, (u8 *)payload_addr(pkt),
 			     payload_size(pkt));
-	calc_icrc = cpu_to_be32(~calc_icrc);
+	calc_icrc = (__force u32)cpu_to_be32(~calc_icrc);
 	if (unlikely(calc_icrc != pack_icrc)) {
 		if (skb->protocol == htons(ETH_P_IPV6))
 			pr_warn_ratelimited("bad ICRC from %pI6c\n",
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 73d4a97603a1..dbfde0dc6ff7 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -361,19 +361,14 @@ static inline int check_init_depth(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	return -EAGAIN;
 }
 
-static inline int get_mtu(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
+static inline int get_mtu(struct rxe_qp *qp)
 {
 	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
-	struct rxe_port *port;
-	struct rxe_av *av;
 
 	if ((qp_type(qp) == IB_QPT_RC) || (qp_type(qp) == IB_QPT_UC))
 		return qp->mtu;
 
-	av = &wqe->av;
-	port = &rxe->port;
-
-	return port->mtu_cap;
+	return rxe->port.mtu_cap;
 }
 
 static struct sk_buff *init_req_packet(struct rxe_qp *qp,
@@ -409,7 +404,7 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 
 	/* init skb */
 	av = rxe_get_av(pkt);
-	skb = rxe->ifc_ops->init_packet(rxe, av, paylen, pkt);
+	skb = rxe_init_packet(rxe, av, paylen, pkt);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -480,7 +475,7 @@ static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 	u32 *p;
 	int err;
 
-	err = rxe->ifc_ops->prepare(rxe, pkt, skb, &crc);
+	err = rxe_prepare(rxe, pkt, skb, &crc);
 	if (err)
 		return err;
 
@@ -599,8 +594,13 @@ int rxe_requester(void *arg)
 	rxe_add_ref(qp);
 
 next_wqe:
-	if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
+	if (unlikely(!qp->valid))
+		goto exit;
+
+	if (unlikely(qp->req.state == QP_STATE_ERROR)) {
+		rxe_drain_req_pkts(qp, true);
 		goto exit;
+	}
 
 	if (unlikely(qp->req.state == QP_STATE_RESET)) {
 		qp->req.wqe_index = consumer_index(qp->sq.queue);
@@ -635,6 +635,7 @@ next_wqe:
 				goto exit;
 			}
 			rmr->state = RXE_MEM_STATE_FREE;
+			rxe_drop_ref(rmr);
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
 		} else if (wqe->wr.opcode == IB_WR_REG_MR) {
@@ -679,7 +680,7 @@ next_wqe:
 			goto exit;
 	}
 
-	mtu = get_mtu(qp, wqe);
+	mtu = get_mtu(qp);
 	payload = (mask & RXE_WRITE_OR_SEND) ? wqe->dma.resid : 0;
 	if (payload > mtu) {
 		if (qp_type(qp) == IB_QPT_UD) {
@@ -748,17 +749,8 @@ err:
 	kfree_skb(skb);
 	wqe->status = IB_WC_LOC_PROT_ERR;
 	wqe->state = wqe_state_error;
-
-	/*
-	 * IBA Spec. Section 10.7.3.1 SIGNALED COMPLETIONS
-	 * ---------8<---------8<-------------
-	 * ...Note that if a completion error occurs, a Work Completion
-	 * will always be generated, even if the signaling
-	 * indicator requests an Unsignaled Completion.
-	 * ---------8<---------8<-------------
-	 */
-	wqe->wr.send_flags |= IB_SEND_SIGNALED;
 	__rxe_do_task(&qp->comp.task);
+
 exit:
 	rxe_drop_ref(qp);
 	return -EAGAIN;
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 5bcf07328972..d404a8aba7af 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -307,7 +307,7 @@ static enum resp_states check_op_valid(struct rxe_qp *qp,
 		break;
 
 	default:
-		WARN_ON(1);
+		WARN_ON_ONCE(1);
 		break;
 	}
 
@@ -418,7 +418,7 @@ static enum resp_states check_length(struct rxe_qp *qp,
 static enum resp_states check_rkey(struct rxe_qp *qp,
 				   struct rxe_pkt_info *pkt)
 {
-	struct rxe_mem *mem;
+	struct rxe_mem *mem = NULL;
 	u64 va;
 	u32 rkey;
 	u32 resid;
@@ -459,50 +459,50 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	mem = lookup_mem(qp->pd, access, rkey, lookup_remote);
 	if (!mem) {
 		state = RESPST_ERR_RKEY_VIOLATION;
-		goto err1;
+		goto err;
 	}
 
 	if (unlikely(mem->state == RXE_MEM_STATE_FREE)) {
 		state = RESPST_ERR_RKEY_VIOLATION;
-		goto err1;
+		goto err;
 	}
 
 	if (mem_check_range(mem, va, resid)) {
 		state = RESPST_ERR_RKEY_VIOLATION;
-		goto err2;
+		goto err;
 	}
 
 	if (pkt->mask & RXE_WRITE_MASK)	 {
 		if (resid > mtu) {
 			if (pktlen != mtu || bth_pad(pkt)) {
 				state = RESPST_ERR_LENGTH;
-				goto err2;
+				goto err;
 			}
 
 			qp->resp.resid = mtu;
 		} else {
 			if (pktlen != resid) {
 				state = RESPST_ERR_LENGTH;
-				goto err2;
+				goto err;
 			}
 			if ((bth_pad(pkt) != (0x3 & (-resid)))) {
 				/* This case may not be exactly that
 				 * but nothing else fits.
 				 */
 				state = RESPST_ERR_LENGTH;
-				goto err2;
+				goto err;
 			}
 		}
 	}
 
-	WARN_ON(qp->resp.mr);
+	WARN_ON_ONCE(qp->resp.mr);
 
 	qp->resp.mr = mem;
 	return RESPST_EXECUTE;
 
-err2:
-	rxe_drop_ref(mem);
-err1:
+err:
+	if (mem)
+		rxe_drop_ref(mem);
 	return state;
 }
 
@@ -608,7 +608,7 @@ static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp,
 	pad = (-payload) & 0x3;
 	paylen = rxe_opcode[opcode].length + payload + pad + RXE_ICRC_SIZE;
 
-	skb = rxe->ifc_ops->init_packet(rxe, &qp->pri_av, paylen, ack);
+	skb = rxe_init_packet(rxe, &qp->pri_av, paylen, ack);
 	if (!skb)
 		return NULL;
 
@@ -637,7 +637,7 @@ static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp,
 	if (ack->mask & RXE_ATMACK_MASK)
 		atmack_set_orig(ack, qp->resp.atomic_orig);
 
-	err = rxe->ifc_ops->prepare(rxe, ack, skb, &crc);
+	err = rxe_prepare(rxe, ack, skb, &crc);
 	if (err) {
 		kfree_skb(skb);
 		return NULL;
@@ -808,9 +808,10 @@ static enum resp_states execute(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
 		err = process_atomic(qp, pkt);
 		if (err)
 			return err;
-	} else
+	} else {
 		/* Unreachable */
-		WARN_ON(1);
+		WARN_ON_ONCE(1);
+	}
 
 	/* We successfully processed this new request. */
 	qp->resp.msn++;
@@ -906,6 +907,7 @@ static enum resp_states do_complete(struct rxe_qp *qp,
 					return RESPST_ERROR;
 				}
 				rmr->state = RXE_MEM_STATE_FREE;
+				rxe_drop_ref(rmr);
 			}
 
 			wc->qp			= &qp->ibqp;
@@ -1206,6 +1208,19 @@ static enum resp_states do_class_d1e_error(struct rxe_qp *qp)
 	}
 }
 
+void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify)
+{
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&qp->req_pkts))) {
+		rxe_drop_ref(qp);
+		kfree_skb(skb);
+	}
+
+	while (!qp->srq && qp->rq.queue && queue_head(qp->rq.queue))
+		advance_consumer(qp->rq.queue);
+}
+
 int rxe_responder(void *arg)
 {
 	struct rxe_qp *qp = (struct rxe_qp *)arg;
@@ -1373,21 +1388,10 @@ int rxe_responder(void *arg)
 
 			goto exit;
 
-		case RESPST_RESET: {
-			struct sk_buff *skb;
-
-			while ((skb = skb_dequeue(&qp->req_pkts))) {
-				rxe_drop_ref(qp);
-				kfree_skb(skb);
-			}
-
-			while (!qp->srq && qp->rq.queue &&
-			       queue_head(qp->rq.queue))
-				advance_consumer(qp->rq.queue);
-
+		case RESPST_RESET:
+			rxe_drain_req_pkts(qp, false);
 			qp->resp.wqe = NULL;
 			goto exit;
-		}
 
 		case RESPST_ERROR:
 			qp->resp.goto_error = 0;
@@ -1396,7 +1400,7 @@ int rxe_responder(void *arg)
 			goto exit;
 
 		default:
-			WARN_ON(1);
+			WARN_ON_ONCE(1);
 		}
 	}
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index beb7021ff18a..5113e502f6f9 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -31,6 +31,7 @@
  * SOFTWARE.
  */
 
+#include <linux/dma-mapping.h>
 #include "rxe.h"
 #include "rxe_loc.h"
 #include "rxe_queue.h"
@@ -86,6 +87,7 @@ static int rxe_query_port(struct ib_device *dev,
 
 	port = &rxe->port;
 
+	/* *attr being zeroed by the caller, avoid zeroing it here */
 	*attr = port->attr;
 
 	mutex_lock(&rxe->usdev_lock);
@@ -168,7 +170,7 @@ static int rxe_query_pkey(struct ib_device *device,
 	struct rxe_port *port;
 
 	if (unlikely(port_num != 1)) {
-		dev_warn(device->dma_device, "invalid port_num = %d\n",
+		dev_warn(device->dev.parent, "invalid port_num = %d\n",
 			 port_num);
 		goto err1;
 	}
@@ -176,7 +178,7 @@ static int rxe_query_pkey(struct ib_device *device,
 	port = &rxe->port;
 
 	if (unlikely(index >= port->attr.pkey_tbl_len)) {
-		dev_warn(device->dma_device, "invalid index = %d\n",
+		dev_warn(device->dev.parent, "invalid index = %d\n",
 			 index);
 		goto err1;
 	}
@@ -234,7 +236,7 @@ static enum rdma_link_layer rxe_get_link_layer(struct ib_device *dev,
 {
 	struct rxe_dev *rxe = to_rdev(dev);
 
-	return rxe->ifc_ops->link_layer(rxe, port_num);
+	return rxe_link_layer(rxe, port_num);
 }
 
 static struct ib_ucontext *rxe_alloc_ucontext(struct ib_device *dev,
@@ -261,13 +263,14 @@ static int rxe_port_immutable(struct ib_device *dev, u8 port_num,
 	int err;
 	struct ib_port_attr attr;
 
-	err = rxe_query_port(dev, port_num, &attr);
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
+
+	err = ib_query_port(dev, port_num, &attr);
 	if (err)
 		return err;
 
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
-	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
 	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 
 	return 0;
@@ -1209,10 +1212,8 @@ static ssize_t rxe_show_parent(struct device *device,
 {
 	struct rxe_dev *rxe = container_of(device, struct rxe_dev,
 					   ib_dev.dev);
-	char *name;
 
-	name = rxe->ifc_ops->parent_name(rxe, 1);
-	return snprintf(buf, 16, "%s\n", name);
+	return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1));
 }
 
 static DEVICE_ATTR(parent, S_IRUGO, rxe_show_parent, NULL);
@@ -1234,10 +1235,10 @@ int rxe_register_device(struct rxe_dev *rxe)
 	dev->node_type = RDMA_NODE_IB_CA;
 	dev->phys_port_cnt = 1;
 	dev->num_comp_vectors = RXE_NUM_COMP_VECTORS;
-	dev->dma_device = rxe->ifc_ops->dma_device(rxe);
+	dev->dev.parent = rxe_dma_device(rxe);
 	dev->local_dma_lkey = 0;
-	dev->node_guid = rxe->ifc_ops->node_guid(rxe);
-	dev->dma_ops = &rxe_dma_mapping_ops;
+	dev->node_guid = rxe_node_guid(rxe);
+	dev->dev.dma_ops = &dma_virt_ops;
 
 	dev->uverbs_abi_ver = RXE_UVERBS_ABI_VERSION;
 	dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index cac1d52a08f0..e100c500ae85 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -372,26 +372,6 @@ struct rxe_port {
 	u32			qp_gsi_index;
 };
 
-/* callbacks from rdma_rxe to network interface layer */
-struct rxe_ifc_ops {
-	void (*release)(struct rxe_dev *rxe);
-	__be64 (*node_guid)(struct rxe_dev *rxe);
-	__be64 (*port_guid)(struct rxe_dev *rxe);
-	struct device *(*dma_device)(struct rxe_dev *rxe);
-	int (*mcast_add)(struct rxe_dev *rxe, union ib_gid *mgid);
-	int (*mcast_delete)(struct rxe_dev *rxe, union ib_gid *mgid);
-	int (*prepare)(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
-		       struct sk_buff *skb, u32 *crc);
-	int (*send)(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
-		    struct sk_buff *skb);
-	int (*loopback)(struct sk_buff *skb);
-	struct sk_buff *(*init_packet)(struct rxe_dev *rxe, struct rxe_av *av,
-				       int paylen, struct rxe_pkt_info *pkt);
-	char *(*parent_name)(struct rxe_dev *rxe, unsigned int port_num);
-	enum rdma_link_layer (*link_layer)(struct rxe_dev *rxe,
-					   unsigned int port_num);
-};
-
 struct rxe_dev {
 	struct ib_device	ib_dev;
 	struct ib_device_attr	attr;
@@ -400,8 +380,6 @@ struct rxe_dev {
 	struct kref		ref_cnt;
 	struct mutex	usdev_lock;
 
-	struct rxe_ifc_ops	*ifc_ops;
-
 	struct net_device	*ndev;
 
 	int			xmit_errors;
@@ -475,6 +453,6 @@ static inline struct rxe_mem *to_rmw(struct ib_mw *mw)
 int rxe_register_device(struct rxe_dev *rxe);
 int rxe_unregister_device(struct rxe_dev *rxe);
 
-void rxe_mc_cleanup(void *arg);
+void rxe_mc_cleanup(struct rxe_pool_entry *arg);
 
 #endif /* RXE_VERBS_H */
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index da12717a3eb7..bed233bf45c3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -500,9 +500,9 @@ void ipoib_pkey_event(struct work_struct *work);
 void ipoib_ib_dev_cleanup(struct net_device *dev);
 
 int ipoib_ib_dev_open(struct net_device *dev);
-int ipoib_ib_dev_up(struct net_device *dev);
-int ipoib_ib_dev_down(struct net_device *dev);
-int ipoib_ib_dev_stop(struct net_device *dev);
+void ipoib_ib_dev_up(struct net_device *dev);
+void ipoib_ib_dev_down(struct net_device *dev);
+void ipoib_ib_dev_stop(struct net_device *dev);
 void ipoib_pkey_dev_check_presence(struct net_device *dev);
 
 int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
@@ -513,7 +513,7 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work);
 void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
 
 void ipoib_mcast_restart_task(struct work_struct *work);
-int ipoib_mcast_start_thread(struct net_device *dev);
+void ipoib_mcast_start_thread(struct net_device *dev);
 int ipoib_mcast_stop_thread(struct net_device *dev);
 
 void ipoib_mcast_dev_down(struct net_device *dev);
@@ -593,7 +593,7 @@ void ipoib_pkey_open(struct ipoib_dev_priv *priv);
 void ipoib_drain_cq(struct net_device *dev);
 
 void ipoib_set_ethtool_ops(struct net_device *dev);
-int ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca);
+void ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca);
 
 #define IPOIB_FLAGS_RC		0x80
 #define IPOIB_FLAGS_UC		0x40
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 096c4f6fbd65..0cdf2b7f272f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/moduleparam.h>
+#include <linux/sched/signal.h>
 
 #include "ipoib.h"
 
@@ -363,7 +364,7 @@ static int ipoib_cm_nonsrq_init_rx(struct net_device *dev, struct ib_cm_id *cm_i
 	t = kmalloc(sizeof *t, GFP_KERNEL);
 	if (!t) {
 		ret = -ENOMEM;
-		goto err_free;
+		goto err_free_1;
 	}
 
 	ipoib_cm_init_rx_wr(dev, &t->wr, t->sge);
@@ -410,6 +411,8 @@ err_count:
 
 err_free:
 	kfree(t);
+
+err_free_1:
 	ipoib_cm_free_rx_ring(dev, rx->rx_ring);
 
 	return ret;
@@ -820,9 +823,12 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	    wc->status != IB_WC_WR_FLUSH_ERR) {
 		struct ipoib_neigh *neigh;
 
-		ipoib_dbg(priv, "failed cm send event "
-			   "(status=%d, wrid=%d vend_err %x)\n",
-			   wc->status, wr_id, wc->vendor_err);
+		if (wc->status != IB_WC_RNR_RETRY_EXC_ERR)
+			ipoib_warn(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
+				   wc->status, wr_id, wc->vendor_err);
+		else
+			ipoib_dbg(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
+				  wc->status, wr_id, wc->vendor_err);
 
 		spin_lock_irqsave(&priv->lock, flags);
 		neigh = tx->neigh;
@@ -1015,9 +1021,10 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even
 
 	while ((skb = __skb_dequeue(&skqueue))) {
 		skb->dev = p->dev;
-		if (dev_queue_xmit(skb))
-			ipoib_warn(priv, "dev_queue_xmit failed "
-				   "to requeue packet\n");
+		ret = dev_queue_xmit(skb);
+		if (ret)
+			ipoib_warn(priv, "%s:dev_queue_xmit failed to re-queue packet, ret:%d\n",
+				   __func__, ret);
 	}
 
 	ret = ib_send_cm_rtu(cm_id, NULL, 0);
@@ -1151,13 +1158,13 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
 	ret = ipoib_cm_modify_tx_init(p->dev, p->id,  p->qp);
 	if (ret) {
 		ipoib_warn(priv, "failed to modify tx qp to rtr: %d\n", ret);
-		goto err_modify;
+		goto err_modify_send;
 	}
 
 	ret = ipoib_cm_send_req(p->dev, p->id, p->qp, qpn, pathrec);
 	if (ret) {
 		ipoib_warn(priv, "failed to send cm req: %d\n", ret);
-		goto err_send_cm;
+		goto err_modify_send;
 	}
 
 	ipoib_dbg(priv, "Request connection 0x%x for gid %pI6 qpn 0x%x\n",
@@ -1165,8 +1172,7 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
 
 	return 0;
 
-err_send_cm:
-err_modify:
+err_modify_send:
 	ib_destroy_cm_id(p->id);
 err_id:
 	p->id = NULL;
@@ -1388,7 +1394,7 @@ static void ipoib_cm_tx_reap(struct work_struct *work)
 
 	while (!list_empty(&priv->cm.reap_list)) {
 		p = list_entry(priv->cm.reap_list.next, typeof(*p), list);
-		list_del(&p->list);
+		list_del_init(&p->list);
 		spin_unlock_irqrestore(&priv->lock, flags);
 		netif_tx_unlock_bh(dev);
 		ipoib_cm_tx_destroy(p);
@@ -1507,12 +1513,14 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 
 	ret = ipoib_set_mode(dev, buf);
 
-	rtnl_unlock();
-
-	if (!ret)
-		return count;
+	/* The assumption is that the function ipoib_set_mode returned
+	 * with the rtnl held by it, if not the value -EBUSY returned,
+	 * then no need to rtnl_unlock
+	 */
+	if (ret != -EBUSY)
+		rtnl_unlock();
 
-	return ret;
+	return (!ret || ret == -EBUSY) ? count : ret;
 }
 
 static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO, show_mode, set_mode);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
index 7b6d40ff1acf..bac455a1942d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
@@ -65,7 +65,7 @@ static void ipoib_get_drvinfo(struct net_device *netdev,
 	ib_get_device_fw_str(priv->ca, drvinfo->fw_version,
 			     sizeof(drvinfo->fw_version));
 
-	strlcpy(drvinfo->bus_info, dev_name(priv->ca->dma_device),
+	strlcpy(drvinfo->bus_info, dev_name(priv->ca->dev.parent),
 		sizeof(drvinfo->bus_info));
 
 	strlcpy(drvinfo->version, ipoib_driver_version,
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 5038f9d2d753..12c4f84a6639 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -755,7 +755,7 @@ void ipoib_pkey_dev_check_presence(struct net_device *dev)
 		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
 }
 
-int ipoib_ib_dev_up(struct net_device *dev)
+void ipoib_ib_dev_up(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -763,15 +763,15 @@ int ipoib_ib_dev_up(struct net_device *dev)
 
 	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
 		ipoib_dbg(priv, "PKEY is not assigned.\n");
-		return 0;
+		return;
 	}
 
 	set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
 
-	return ipoib_mcast_start_thread(dev);
+	ipoib_mcast_start_thread(dev);
 }
 
-int ipoib_ib_dev_down(struct net_device *dev)
+void ipoib_ib_dev_down(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -784,8 +784,6 @@ int ipoib_ib_dev_down(struct net_device *dev)
 	ipoib_mcast_dev_flush(dev);
 
 	ipoib_flush_paths(dev);
-
-	return 0;
 }
 
 static int recvs_pending(struct net_device *dev)
@@ -840,7 +838,7 @@ void ipoib_drain_cq(struct net_device *dev)
 	local_bh_enable();
 }
 
-int ipoib_ib_dev_stop(struct net_device *dev)
+void ipoib_ib_dev_stop(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_qp_attr qp_attr;
@@ -913,8 +911,6 @@ timeout:
 	ipoib_flush_ah(dev);
 
 	ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP);
-
-	return 0;
 }
 
 int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 3ce0765a05ab..d1d3fb7a6127 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -126,8 +126,7 @@ int ipoib_open(struct net_device *dev)
 		goto err_disable;
 	}
 
-	if (ipoib_ib_dev_up(dev))
-		goto err_stop;
+	ipoib_ib_dev_up(dev);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
 		struct ipoib_dev_priv *cpriv;
@@ -150,9 +149,6 @@ int ipoib_open(struct net_device *dev)
 
 	return 0;
 
-err_stop:
-	ipoib_ib_dev_stop(dev);
-
 err_disable:
 	clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
 
@@ -229,6 +225,10 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
 
 	priv->admin_mtu = new_mtu;
 
+	if (priv->mcast_mtu < priv->admin_mtu)
+		ipoib_dbg(priv, "MTU must be smaller than the underlying "
+				"link layer MTU - 4 (%u)\n", priv->mcast_mtu);
+
 	dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);
 
 	return 0;
@@ -470,6 +470,13 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
+	if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) &&
+	     !strcmp(buf, "connected\n")) ||
+	     (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) &&
+	     !strcmp(buf, "datagram\n"))) {
+		return 0;
+	}
+
 	/* flush paths if we switch modes so that connections are restarted */
 	if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) {
 		set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
@@ -481,8 +488,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
 
 		ipoib_flush_paths(dev);
-		rtnl_lock();
-		return 0;
+		return (!rtnl_trylock()) ? -EBUSY : 0;
 	}
 
 	if (!strcmp(buf, "datagram\n")) {
@@ -491,8 +497,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
 		rtnl_unlock();
 		ipoib_flush_paths(dev);
-		rtnl_lock();
-		return 0;
+		return (!rtnl_trylock()) ? -EBUSY : 0;
 	}
 
 	return -EINVAL;
@@ -716,6 +721,14 @@ int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv)
 	return ret;
 }
 
+static void push_pseudo_header(struct sk_buff *skb, const char *daddr)
+{
+	struct ipoib_pseudo_header *phdr;
+
+	phdr = (struct ipoib_pseudo_header *)skb_push(skb, sizeof(*phdr));
+	memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
+}
+
 void ipoib_flush_paths(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -834,10 +847,12 @@ static void path_rec_completion(int status,
 		ipoib_put_ah(old_ah);
 
 	while ((skb = __skb_dequeue(&skqueue))) {
+		int ret;
 		skb->dev = dev;
-		if (dev_queue_xmit(skb))
-			ipoib_warn(priv, "dev_queue_xmit failed "
-				   "to requeue packet\n");
+		ret = dev_queue_xmit(skb);
+		if (ret)
+			ipoib_warn(priv, "%s: dev_queue_xmit failed to re-queue packet, ret:%d\n",
+				   __func__, ret);
 	}
 }
 
@@ -940,8 +955,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 			}
 			if (skb_queue_len(&neigh->queue) <
 			    IPOIB_MAX_PATH_REC_QUEUE) {
-				/* put pseudoheader back on for next time */
-				skb_push(skb, IPOIB_PSEUDO_LEN);
+				push_pseudo_header(skb, neigh->daddr);
 				__skb_queue_tail(&neigh->queue, skb);
 			} else {
 				ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
@@ -959,10 +973,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 
 		if (!path->query && path_rec_start(dev, path))
 			goto err_path;
-		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+			push_pseudo_header(skb, neigh->daddr);
 			__skb_queue_tail(&neigh->queue, skb);
-		else
+		} else {
 			goto err_drop;
+		}
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
@@ -998,8 +1014,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 		}
 		if (path) {
 			if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
-				/* put pseudoheader back on for next time */
-				skb_push(skb, IPOIB_PSEUDO_LEN);
+				push_pseudo_header(skb, phdr->hwaddr);
 				__skb_queue_tail(&path->queue, skb);
 			} else {
 				++dev->stats.tx_dropped;
@@ -1031,8 +1046,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 		return;
 	} else if ((path->query || !path_rec_start(dev, path)) &&
 		   skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
-		/* put pseudoheader back on for next time */
-		skb_push(skb, IPOIB_PSEUDO_LEN);
+		push_pseudo_header(skb, phdr->hwaddr);
 		__skb_queue_tail(&path->queue, skb);
 	} else {
 		++dev->stats.tx_dropped;
@@ -1113,8 +1127,7 @@ send_using_neigh:
 	}
 
 	if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
-		/* put pseudoheader back on for next time */
-		skb_push(skb, sizeof(*phdr));
+		push_pseudo_header(skb, phdr->hwaddr);
 		spin_lock_irqsave(&priv->lock, flags);
 		__skb_queue_tail(&neigh->queue, skb);
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1146,7 +1159,6 @@ static int ipoib_hard_header(struct sk_buff *skb,
 			     unsigned short type,
 			     const void *daddr, const void *saddr, unsigned len)
 {
-	struct ipoib_pseudo_header *phdr;
 	struct ipoib_header *header;
 
 	header = (struct ipoib_header *) skb_push(skb, sizeof *header);
@@ -1159,8 +1171,7 @@ static int ipoib_hard_header(struct sk_buff *skb,
 	 * destination address into skb hard header so we can figure out where
 	 * to send the packet later.
 	 */
-	phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
-	memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
+	push_pseudo_header(skb, daddr);
 
 	return IPOIB_HARD_LEN;
 }
@@ -1286,7 +1297,7 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
 				/* remove from path/mc list */
-				list_del(&neigh->list);
+				list_del_init(&neigh->list);
 				call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
 			} else {
 				np = &neigh->hnext;
@@ -1450,7 +1461,7 @@ void ipoib_neigh_free(struct ipoib_neigh *neigh)
 					   rcu_dereference_protected(neigh->hnext,
 								     lockdep_is_held(&priv->lock)));
 			/* remove from parent list */
-			list_del(&neigh->list);
+			list_del_init(&neigh->list);
 			call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
 			return;
 		} else {
@@ -1535,7 +1546,7 @@ void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid)
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
 				/* remove from parent list */
-				list_del(&neigh->list);
+				list_del_init(&neigh->list);
 				call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
 			} else {
 				np = &neigh->hnext;
@@ -1577,7 +1588,7 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
 					   rcu_dereference_protected(neigh->hnext,
 								     lockdep_is_held(&priv->lock)));
 			/* remove from path/mc list */
-			list_del(&neigh->list);
+			list_del_init(&neigh->list);
 			call_rcu(&neigh->rcu, ipoib_neigh_reclaim);
 		}
 	}
@@ -1984,7 +1995,7 @@ int ipoib_add_pkey_attr(struct net_device *dev)
 	return device_create_file(&dev->dev, &dev_attr_pkey);
 }
 
-int ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca)
+void ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca)
 {
 	priv->hca_caps = hca->attrs.device_cap_flags;
 
@@ -1996,8 +2007,6 @@ int ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca)
 
 		priv->dev->features |= priv->dev->hw_features;
 	}
-
-	return 0;
 }
 
 static struct net_device *ipoib_add_port(const char *format,
@@ -2011,7 +2020,7 @@ static struct net_device *ipoib_add_port(const char *format,
 	if (!priv)
 		goto alloc_mem_failed;
 
-	SET_NETDEV_DEV(priv->dev, hca->dma_device);
+	SET_NETDEV_DEV(priv->dev, hca->dev.parent);
 	priv->dev->dev_id = port - 1;
 
 	result = ib_query_port(hca, port, &attr);
@@ -2037,9 +2046,7 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto device_init_failed;
 	}
 
-	result = ipoib_set_dev_features(priv, hca);
-	if (result)
-		goto device_init_failed;
+	ipoib_set_dev_features(priv, hca);
 
 	/*
 	 * Set the full membership bit, so that we join the right
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index fddff403d5d2..69e146cdc306 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -314,9 +314,11 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 		netif_tx_unlock_bh(dev);
 
 		skb->dev = dev;
-		if (dev_queue_xmit(skb))
-			ipoib_warn(priv, "dev_queue_xmit failed to requeue packet\n");
 
+		ret = dev_queue_xmit(skb);
+		if (ret)
+			ipoib_warn(priv, "%s:dev_queue_xmit failed to re-queue packet, ret:%d\n",
+				   __func__, ret);
 		netif_tx_lock_bh(dev);
 	}
 	netif_tx_unlock_bh(dev);
@@ -674,7 +676,7 @@ out:
 	spin_unlock_irq(&priv->lock);
 }
 
-int ipoib_mcast_start_thread(struct net_device *dev)
+void ipoib_mcast_start_thread(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	unsigned long flags;
@@ -684,8 +686,6 @@ int ipoib_mcast_start_thread(struct net_device *dev)
 	spin_lock_irqsave(&priv->lock, flags);
 	__ipoib_mcast_schedule_join_thread(priv, NULL, 0);
 	spin_unlock_irqrestore(&priv->lock, flags);
-
-	return 0;
 }
 
 int ipoib_mcast_stop_thread(struct net_device *dev)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index fd811115af49..3e10e3dac2e7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 
 #include <linux/init.h>
 #include <linux/seq_file.h>
@@ -61,9 +62,7 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 	priv->parent = ppriv->dev;
 	set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
 
-	result = ipoib_set_dev_features(priv, ppriv->ca);
-	if (result)
-		goto err;
+	ipoib_set_dev_features(priv, ppriv->ca);
 
 	priv->pkey = pkey;
 
@@ -168,11 +167,11 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 out:
 	up_write(&ppriv->vlan_rwsem);
 
+	rtnl_unlock();
+
 	if (result)
 		free_netdev(priv->dev);
 
-	rtnl_unlock();
-
 	return result;
 }
 
@@ -196,7 +195,6 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 	list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
 		if (priv->pkey == pkey &&
 		    priv->child_type == IPOIB_LEGACY_CHILD) {
-			unregister_netdevice(priv->dev);
 			list_del(&priv->list);
 			dev = priv->dev;
 			break;
@@ -204,6 +202,11 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 	}
 	up_write(&ppriv->vlan_rwsem);
 
+	if (dev) {
+		ipoib_dbg(ppriv, "delete child vlan %s\n", dev->name);
+		unregister_netdevice(dev);
+	}
+
 	rtnl_unlock();
 
 	if (dev) {
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index e71af717e71b..5a887efb4bdf 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -652,7 +652,7 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep,
 		}
 
 		if (iscsi_host_add(shost,
-				   ib_conn->device->ib_device->dma_device)) {
+				   ib_conn->device->ib_device->dev.parent)) {
 			mutex_unlock(&iser_conn->state_mutex);
 			goto free_host;
 		}
@@ -994,6 +994,7 @@ static struct scsi_host_template iscsi_iser_sht = {
 	.change_queue_depth	= scsi_change_queue_depth,
 	.sg_tablesize           = ISCSI_ISER_DEF_SG_TABLESIZE,
 	.cmd_per_lun            = ISER_DEF_CMD_PER_LUN,
+	.eh_timed_out		= iscsi_eh_cmd_timed_out,
 	.eh_abort_handler       = iscsi_eh_abort,
 	.eh_device_reset_handler= iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 6a9d1cb548ee..30b622f2ab73 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -597,7 +597,9 @@ static void iser_free_ib_conn_res(struct iser_conn *iser_conn,
 		  iser_conn, ib_conn->cma_id, ib_conn->qp);
 
 	if (ib_conn->qp != NULL) {
+		mutex_lock(&ig.connlist_mutex);
 		ib_conn->comp->active_qps--;
+		mutex_unlock(&ig.connlist_mutex);
 		rdma_destroy_qp(ib_conn->cma_id);
 		ib_conn->qp = NULL;
 	}
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 314e95516068..91cbe86b25c8 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -728,7 +728,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 		iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
 		break;
 	default:
-		isert_warn("conn %p teminating in state %d\n",
+		isert_warn("conn %p terminating in state %d\n",
 			   isert_conn, isert_conn->state);
 	}
 	mutex_unlock(&isert_conn->mutex);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 79bf48477ddb..cee46266f434 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -40,6 +40,7 @@
 #include <linux/parser.h>
 #include <linux/random.h>
 #include <linux/jiffies.h>
+#include <linux/lockdep.h>
 #include <rdma/ib_cache.h>
 
 #include <linux/atomic.h>
@@ -371,7 +372,6 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device,
 	struct srp_fr_desc *d;
 	struct ib_mr *mr;
 	int i, ret = -EINVAL;
-	enum ib_mr_type mr_type;
 
 	if (pool_size <= 0)
 		goto err;
@@ -385,13 +385,9 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device,
 	spin_lock_init(&pool->lock);
 	INIT_LIST_HEAD(&pool->free_list);
 
-	if (device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)
-		mr_type = IB_MR_TYPE_SG_GAPS;
-	else
-		mr_type = IB_MR_TYPE_MEM_REG;
-
 	for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) {
-		mr = ib_alloc_mr(pd, mr_type, max_page_list_len);
+		mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG,
+				 max_page_list_len);
 		if (IS_ERR(mr)) {
 			ret = PTR_ERR(mr);
 			if (ret == -ENOMEM)
@@ -470,9 +466,13 @@ static struct srp_fr_pool *srp_alloc_fr_pool(struct srp_target_port *target)
  * completion handler can access the queue pair while it is
  * being destroyed.
  */
-static void srp_destroy_qp(struct ib_qp *qp)
+static void srp_destroy_qp(struct srp_rdma_ch *ch, struct ib_qp *qp)
 {
-	ib_drain_rq(qp);
+	spin_lock_irq(&ch->lock);
+	ib_process_cq_direct(ch->send_cq, -1);
+	spin_unlock_irq(&ch->lock);
+
+	ib_drain_qp(qp);
 	ib_destroy_qp(qp);
 }
 
@@ -546,7 +546,7 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch)
 	}
 
 	if (ch->qp)
-		srp_destroy_qp(ch->qp);
+		srp_destroy_qp(ch, ch->qp);
 	if (ch->recv_cq)
 		ib_free_cq(ch->recv_cq);
 	if (ch->send_cq)
@@ -570,7 +570,7 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch)
 	return 0;
 
 err_qp:
-	srp_destroy_qp(qp);
+	srp_destroy_qp(ch, qp);
 
 err_send_cq:
 	ib_free_cq(send_cq);
@@ -613,7 +613,7 @@ static void srp_free_ch_ib(struct srp_target_port *target,
 			ib_destroy_fmr_pool(ch->fmr_pool);
 	}
 
-	srp_destroy_qp(ch->qp);
+	srp_destroy_qp(ch, ch->qp);
 	ib_free_cq(ch->send_cq);
 	ib_free_cq(ch->recv_cq);
 
@@ -1804,6 +1804,8 @@ static struct srp_iu *__srp_get_tx_iu(struct srp_rdma_ch *ch,
 	s32 rsv = (iu_type == SRP_IU_TSK_MGMT) ? 0 : SRP_TSK_MGMT_SQ_SIZE;
 	struct srp_iu *iu;
 
+	lockdep_assert_held(&ch->lock);
+
 	ib_process_cq_direct(ch->send_cq, -1);
 
 	if (list_empty(&ch->free_tx))
@@ -1824,6 +1826,11 @@ static struct srp_iu *__srp_get_tx_iu(struct srp_rdma_ch *ch,
 	return iu;
 }
 
+/*
+ * Note: if this function is called from inside ib_drain_sq() then it will
+ * be called without ch->lock being held. If ib_drain_sq() dequeues a WQE
+ * with status IB_WC_SUCCESS then that's a bug.
+ */
 static void srp_send_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct srp_iu *iu = container_of(wc->wr_cqe, struct srp_iu, cqe);
@@ -1834,6 +1841,8 @@ static void srp_send_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
+	lockdep_assert_held(&ch->lock);
+
 	list_add(&iu->list, &ch->free_tx);
 }
 
@@ -1889,17 +1898,24 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp)
 	if (unlikely(rsp->tag & SRP_TAG_TSK_MGMT)) {
 		spin_lock_irqsave(&ch->lock, flags);
 		ch->req_lim += be32_to_cpu(rsp->req_lim_delta);
+		if (rsp->tag == ch->tsk_mgmt_tag) {
+			ch->tsk_mgmt_status = -1;
+			if (be32_to_cpu(rsp->resp_data_len) >= 4)
+				ch->tsk_mgmt_status = rsp->data[3];
+			complete(&ch->tsk_mgmt_done);
+		} else {
+			shost_printk(KERN_ERR, target->scsi_host,
+				     "Received tsk mgmt response too late for tag %#llx\n",
+				     rsp->tag);
+		}
 		spin_unlock_irqrestore(&ch->lock, flags);
-
-		ch->tsk_mgmt_status = -1;
-		if (be32_to_cpu(rsp->resp_data_len) >= 4)
-			ch->tsk_mgmt_status = rsp->data[3];
-		complete(&ch->tsk_mgmt_done);
 	} else {
 		scmnd = scsi_host_find_tag(target->scsi_host, rsp->tag);
-		if (scmnd) {
+		if (scmnd && scmnd->host_scribble) {
 			req = (void *)scmnd->host_scribble;
 			scmnd = srp_claim_req(ch, req, NULL, scmnd);
+		} else {
+			scmnd = NULL;
 		}
 		if (!scmnd) {
 			shost_printk(KERN_ERR, target->scsi_host,
@@ -2531,19 +2547,18 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth)
 }
 
 static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
-			     u8 func)
+			     u8 func, u8 *status)
 {
 	struct srp_target_port *target = ch->target;
 	struct srp_rport *rport = target->rport;
 	struct ib_device *dev = target->srp_host->srp_dev->dev;
 	struct srp_iu *iu;
 	struct srp_tsk_mgmt *tsk_mgmt;
+	int res;
 
 	if (!ch->connected || target->qp_in_error)
 		return -1;
 
-	init_completion(&ch->tsk_mgmt_done);
-
 	/*
 	 * Lock the rport mutex to avoid that srp_create_ch_ib() is
 	 * invoked while a task management function is being sent.
@@ -2566,10 +2581,16 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
 
 	tsk_mgmt->opcode 	= SRP_TSK_MGMT;
 	int_to_scsilun(lun, &tsk_mgmt->lun);
-	tsk_mgmt->tag		= req_tag | SRP_TAG_TSK_MGMT;
 	tsk_mgmt->tsk_mgmt_func = func;
 	tsk_mgmt->task_tag	= req_tag;
 
+	spin_lock_irq(&ch->lock);
+	ch->tsk_mgmt_tag = (ch->tsk_mgmt_tag + 1) | SRP_TAG_TSK_MGMT;
+	tsk_mgmt->tag = ch->tsk_mgmt_tag;
+	spin_unlock_irq(&ch->lock);
+
+	init_completion(&ch->tsk_mgmt_done);
+
 	ib_dma_sync_single_for_device(dev, iu->dma, sizeof *tsk_mgmt,
 				      DMA_TO_DEVICE);
 	if (srp_post_send(ch, iu, sizeof(*tsk_mgmt))) {
@@ -2578,13 +2599,15 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
 
 		return -1;
 	}
+	res = wait_for_completion_timeout(&ch->tsk_mgmt_done,
+					msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS));
+	if (res > 0 && status)
+		*status = ch->tsk_mgmt_status;
 	mutex_unlock(&rport->mutex);
 
-	if (!wait_for_completion_timeout(&ch->tsk_mgmt_done,
-					 msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS)))
-		return -1;
+	WARN_ON_ONCE(res < 0);
 
-	return 0;
+	return res > 0 ? 0 : -1;
 }
 
 static int srp_abort(struct scsi_cmnd *scmnd)
@@ -2610,7 +2633,7 @@ static int srp_abort(struct scsi_cmnd *scmnd)
 	shost_printk(KERN_ERR, target->scsi_host,
 		     "Sending SRP abort for tag %#x\n", tag);
 	if (srp_send_tsk_mgmt(ch, tag, scmnd->device->lun,
-			      SRP_TSK_ABORT_TASK) == 0)
+			      SRP_TSK_ABORT_TASK, NULL) == 0)
 		ret = SUCCESS;
 	else if (target->rport->state == SRP_RPORT_LOST)
 		ret = FAST_IO_FAIL;
@@ -2628,14 +2651,15 @@ static int srp_reset_device(struct scsi_cmnd *scmnd)
 	struct srp_target_port *target = host_to_target(scmnd->device->host);
 	struct srp_rdma_ch *ch;
 	int i;
+	u8 status;
 
 	shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n");
 
 	ch = &target->ch[0];
 	if (srp_send_tsk_mgmt(ch, SRP_TAG_NO_REQ, scmnd->device->lun,
-			      SRP_TSK_LUN_RESET))
+			      SRP_TSK_LUN_RESET, &status))
 		return FAILED;
-	if (ch->tsk_mgmt_status)
+	if (status)
 		return FAILED;
 
 	for (i = 0; i < target->ch_count; i++) {
@@ -2664,9 +2688,8 @@ static int srp_slave_alloc(struct scsi_device *sdev)
 	struct Scsi_Host *shost = sdev->host;
 	struct srp_target_port *target = host_to_target(shost);
 	struct srp_device *srp_dev = target->srp_host->srp_dev;
-	struct ib_device *ibdev = srp_dev->dev;
 
-	if (!(ibdev->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG))
+	if (true)
 		blk_queue_virt_boundary(sdev->request_queue,
 					~srp_dev->mr_page_mask);
 
@@ -2869,6 +2892,7 @@ static struct scsi_host_template srp_template = {
 	.info				= srp_target_info,
 	.queuecommand			= srp_queuecommand,
 	.change_queue_depth             = srp_change_queue_depth,
+	.eh_timed_out			= srp_timed_out,
 	.eh_abort_handler		= srp_abort,
 	.eh_device_reset_handler	= srp_reset_device,
 	.eh_host_reset_handler		= srp_reset_host,
@@ -2909,7 +2933,7 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 	sprintf(target->target_name, "SRP.T10:%016llX",
 		be64_to_cpu(target->id_ext));
 
-	if (scsi_add_host(target->scsi_host, host->srp_dev->dev->dma_device))
+	if (scsi_add_host(target->scsi_host, host->srp_dev->dev->dev.parent))
 		return -ENODEV;
 
 	memcpy(ids.port_id, &target->id_ext, 8);
@@ -3421,11 +3445,12 @@ static ssize_t srp_create_target(struct device *dev,
 			ret = srp_connect_ch(ch, multich);
 			if (ret) {
 				shost_printk(KERN_ERR, target->scsi_host,
-					     PFX "Connection %d/%d failed\n",
+					     PFX "Connection %d/%d to %pI6 failed\n",
 					     ch_start + cpu_idx,
-					     target->ch_count);
+					     target->ch_count,
+					     ch->target->orig_dgid.raw);
 				if (node_idx == 0 && cpu_idx == 0) {
-					goto err_disconnect;
+					goto free_ch;
 				} else {
 					srp_free_ch_ib(target, ch);
 					srp_free_req_data(target, ch);
@@ -3472,6 +3497,7 @@ put:
 err_disconnect:
 	srp_disconnect_target(target);
 
+free_ch:
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
 		srp_free_ch_ib(target, ch);
@@ -3520,7 +3546,7 @@ static struct srp_host *srp_add_port(struct srp_device *device, u8 port)
 	host->port = port;
 
 	host->dev.class = &srp_class;
-	host->dev.parent = device->dev->dma_device;
+	host->dev.parent = device->dev->dev.parent;
 	dev_set_name(&host->dev, "srp-%s-%d", device->dev->name, port);
 
 	if (device_register(&host->dev))
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 21c69695f9d4..32ed40db3ca2 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -163,6 +163,7 @@ struct srp_rdma_ch {
 	int			max_ti_iu_len;
 	int			comp_vector;
 
+	u64			tsk_mgmt_tag;
 	struct completion	tsk_mgmt_done;
 	u8			tsk_mgmt_status;
 	bool			connected;
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index d21ba9d857c3..7e314c2f2071 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -500,6 +500,7 @@ static int srpt_refresh_port(struct srpt_port *sport)
 	struct ib_mad_reg_req reg_req;
 	struct ib_port_modify port_modify;
 	struct ib_port_attr port_attr;
+	__be16 *guid;
 	int ret;
 
 	memset(&port_modify, 0, sizeof(port_modify));
@@ -522,10 +523,17 @@ static int srpt_refresh_port(struct srpt_port *sport)
 	if (ret)
 		goto err_query_port;
 
+	sport->port_guid_wwn.priv = sport;
+	guid = (__be16 *)&sport->gid.global.interface_id;
 	snprintf(sport->port_guid, sizeof(sport->port_guid),
-		"0x%016llx%016llx",
-		be64_to_cpu(sport->gid.global.subnet_prefix),
-		be64_to_cpu(sport->gid.global.interface_id));
+		 "%04x:%04x:%04x:%04x",
+		 be16_to_cpu(guid[0]), be16_to_cpu(guid[1]),
+		 be16_to_cpu(guid[2]), be16_to_cpu(guid[3]));
+	sport->port_gid_wwn.priv = sport;
+	snprintf(sport->port_gid, sizeof(sport->port_gid),
+		 "0x%016llx%016llx",
+		 be64_to_cpu(sport->gid.global.subnet_prefix),
+		 be64_to_cpu(sport->gid.global.interface_id));
 
 	if (!sport->mad_agent) {
 		memset(&reg_req, 0, sizeof(reg_req));
@@ -1838,6 +1846,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id,
 	struct srp_login_rej *rej;
 	struct ib_cm_rep_param *rep_param;
 	struct srpt_rdma_ch *ch, *tmp_ch;
+	__be16 *guid;
 	u32 it_iu_len;
 	int i, ret = 0;
 
@@ -1983,26 +1992,30 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id,
 		goto destroy_ib;
 	}
 
-	/*
-	 * Use the initator port identifier as the session name, when
-	 * checking against se_node_acl->initiatorname[] this can be
-	 * with or without preceeding '0x'.
-	 */
+	guid = (__be16 *)&param->primary_path->sgid.global.interface_id;
+	snprintf(ch->ini_guid, sizeof(ch->ini_guid), "%04x:%04x:%04x:%04x",
+		 be16_to_cpu(guid[0]), be16_to_cpu(guid[1]),
+		 be16_to_cpu(guid[2]), be16_to_cpu(guid[3]));
 	snprintf(ch->sess_name, sizeof(ch->sess_name), "0x%016llx%016llx",
 			be64_to_cpu(*(__be64 *)ch->i_port_id),
 			be64_to_cpu(*(__be64 *)(ch->i_port_id + 8)));
 
 	pr_debug("registering session %s\n", ch->sess_name);
 
-	ch->sess = target_alloc_session(&sport->port_tpg_1, 0, 0,
+	if (sport->port_guid_tpg.se_tpg_wwn)
+		ch->sess = target_alloc_session(&sport->port_guid_tpg, 0, 0,
+						TARGET_PROT_NORMAL,
+						ch->ini_guid, ch, NULL);
+	if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess))
+		ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0,
 					TARGET_PROT_NORMAL, ch->sess_name, ch,
 					NULL);
 	/* Retry without leading "0x" */
-	if (IS_ERR(ch->sess))
-		ch->sess = target_alloc_session(&sport->port_tpg_1, 0, 0,
+	if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess))
+		ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0,
 						TARGET_PROT_NORMAL,
 						ch->sess_name + 2, ch, NULL);
-	if (IS_ERR(ch->sess)) {
+	if (IS_ERR_OR_NULL(ch->sess)) {
 		pr_info("Rejected login because no ACL has been configured yet for initiator %s.\n",
 			ch->sess_name);
 		rej->reason = cpu_to_be32((PTR_ERR(ch->sess) == -ENOMEM) ?
@@ -2420,7 +2433,7 @@ static int srpt_release_sdev(struct srpt_device *sdev)
 	return 0;
 }
 
-static struct srpt_port *__srpt_lookup_port(const char *name)
+static struct se_wwn *__srpt_lookup_wwn(const char *name)
 {
 	struct ib_device *dev;
 	struct srpt_device *sdev;
@@ -2435,23 +2448,25 @@ static struct srpt_port *__srpt_lookup_port(const char *name)
 		for (i = 0; i < dev->phys_port_cnt; i++) {
 			sport = &sdev->port[i];
 
-			if (!strcmp(sport->port_guid, name))
-				return sport;
+			if (strcmp(sport->port_guid, name) == 0)
+				return &sport->port_guid_wwn;
+			if (strcmp(sport->port_gid, name) == 0)
+				return &sport->port_gid_wwn;
 		}
 	}
 
 	return NULL;
 }
 
-static struct srpt_port *srpt_lookup_port(const char *name)
+static struct se_wwn *srpt_lookup_wwn(const char *name)
 {
-	struct srpt_port *sport;
+	struct se_wwn *wwn;
 
 	spin_lock(&srpt_dev_lock);
-	sport = __srpt_lookup_port(name);
+	wwn = __srpt_lookup_wwn(name);
 	spin_unlock(&srpt_dev_lock);
 
-	return sport;
+	return wwn;
 }
 
 /**
@@ -2464,8 +2479,7 @@ static void srpt_add_one(struct ib_device *device)
 	struct ib_srq_init_attr srq_attr;
 	int i;
 
-	pr_debug("device = %p, device->dma_ops = %p\n", device,
-		 device->dma_ops);
+	pr_debug("device = %p\n", device);
 
 	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
 	if (!sdev)
@@ -2643,11 +2657,19 @@ static char *srpt_get_fabric_name(void)
 	return "srpt";
 }
 
+static struct srpt_port *srpt_tpg_to_sport(struct se_portal_group *tpg)
+{
+	return tpg->se_tpg_wwn->priv;
+}
+
 static char *srpt_get_fabric_wwn(struct se_portal_group *tpg)
 {
-	struct srpt_port *sport = container_of(tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(tpg);
 
-	return sport->port_guid;
+	WARN_ON_ONCE(tpg != &sport->port_guid_tpg &&
+		     tpg != &sport->port_gid_tpg);
+	return tpg == &sport->port_guid_tpg ? sport->port_guid :
+		sport->port_gid;
 }
 
 static u16 srpt_get_tag(struct se_portal_group *tpg)
@@ -2737,6 +2759,19 @@ static int srpt_get_tcm_cmd_state(struct se_cmd *se_cmd)
 	return srpt_get_cmd_state(ioctx);
 }
 
+static int srpt_parse_guid(u64 *guid, const char *name)
+{
+	u16 w[4];
+	int ret = -EINVAL;
+
+	if (sscanf(name, "%hx:%hx:%hx:%hx", &w[0], &w[1], &w[2], &w[3]) != 4)
+		goto out;
+	*guid = get_unaligned_be64(w);
+	ret = 0;
+out:
+	return ret;
+}
+
 /**
  * srpt_parse_i_port_id() - Parse an initiator port ID.
  * @name: ASCII representation of a 128-bit initiator port ID.
@@ -2772,20 +2807,23 @@ out:
  */
 static int srpt_init_nodeacl(struct se_node_acl *se_nacl, const char *name)
 {
+	u64 guid;
 	u8 i_port_id[16];
+	int ret;
 
-	if (srpt_parse_i_port_id(i_port_id, name) < 0) {
+	ret = srpt_parse_guid(&guid, name);
+	if (ret < 0)
+		ret = srpt_parse_i_port_id(i_port_id, name);
+	if (ret < 0)
 		pr_err("invalid initiator port ID %s\n", name);
-		return -EINVAL;
-	}
-	return 0;
+	return ret;
 }
 
 static ssize_t srpt_tpg_attrib_srp_max_rdma_size_show(struct config_item *item,
 		char *page)
 {
 	struct se_portal_group *se_tpg = attrib_to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 
 	return sprintf(page, "%u\n", sport->port_attrib.srp_max_rdma_size);
 }
@@ -2794,7 +2832,7 @@ static ssize_t srpt_tpg_attrib_srp_max_rdma_size_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	struct se_portal_group *se_tpg = attrib_to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 	unsigned long val;
 	int ret;
 
@@ -2822,7 +2860,7 @@ static ssize_t srpt_tpg_attrib_srp_max_rsp_size_show(struct config_item *item,
 		char *page)
 {
 	struct se_portal_group *se_tpg = attrib_to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 
 	return sprintf(page, "%u\n", sport->port_attrib.srp_max_rsp_size);
 }
@@ -2831,7 +2869,7 @@ static ssize_t srpt_tpg_attrib_srp_max_rsp_size_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	struct se_portal_group *se_tpg = attrib_to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 	unsigned long val;
 	int ret;
 
@@ -2859,7 +2897,7 @@ static ssize_t srpt_tpg_attrib_srp_sq_size_show(struct config_item *item,
 		char *page)
 {
 	struct se_portal_group *se_tpg = attrib_to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 
 	return sprintf(page, "%u\n", sport->port_attrib.srp_sq_size);
 }
@@ -2868,7 +2906,7 @@ static ssize_t srpt_tpg_attrib_srp_sq_size_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	struct se_portal_group *se_tpg = attrib_to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 	unsigned long val;
 	int ret;
 
@@ -2906,7 +2944,7 @@ static struct configfs_attribute *srpt_tpg_attrib_attrs[] = {
 static ssize_t srpt_tpg_enable_show(struct config_item *item, char *page)
 {
 	struct se_portal_group *se_tpg = to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 
 	return snprintf(page, PAGE_SIZE, "%d\n", (sport->enabled) ? 1: 0);
 }
@@ -2915,7 +2953,7 @@ static ssize_t srpt_tpg_enable_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	struct se_portal_group *se_tpg = to_tpg(item);
-	struct srpt_port *sport = container_of(se_tpg, struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(se_tpg);
 	struct srpt_device *sdev = sport->sdev;
 	struct srpt_rdma_ch *ch;
 	unsigned long tmp;
@@ -2967,15 +3005,19 @@ static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn,
 					     struct config_group *group,
 					     const char *name)
 {
-	struct srpt_port *sport = container_of(wwn, struct srpt_port, port_wwn);
+	struct srpt_port *sport = wwn->priv;
+	static struct se_portal_group *tpg;
 	int res;
 
-	/* Initialize sport->port_wwn and sport->port_tpg_1 */
-	res = core_tpg_register(&sport->port_wwn, &sport->port_tpg_1, SCSI_PROTOCOL_SRP);
+	WARN_ON_ONCE(wwn != &sport->port_guid_wwn &&
+		     wwn != &sport->port_gid_wwn);
+	tpg = wwn == &sport->port_guid_wwn ? &sport->port_guid_tpg :
+		&sport->port_gid_tpg;
+	res = core_tpg_register(wwn, tpg, SCSI_PROTOCOL_SRP);
 	if (res)
 		return ERR_PTR(res);
 
-	return &sport->port_tpg_1;
+	return tpg;
 }
 
 /**
@@ -2984,11 +3026,10 @@ static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn,
  */
 static void srpt_drop_tpg(struct se_portal_group *tpg)
 {
-	struct srpt_port *sport = container_of(tpg,
-				struct srpt_port, port_tpg_1);
+	struct srpt_port *sport = srpt_tpg_to_sport(tpg);
 
 	sport->enabled = false;
-	core_tpg_deregister(&sport->port_tpg_1);
+	core_tpg_deregister(tpg);
 }
 
 /**
@@ -2999,19 +3040,7 @@ static struct se_wwn *srpt_make_tport(struct target_fabric_configfs *tf,
 				      struct config_group *group,
 				      const char *name)
 {
-	struct srpt_port *sport;
-	int ret;
-
-	sport = srpt_lookup_port(name);
-	pr_debug("make_tport(%s)\n", name);
-	ret = -EINVAL;
-	if (!sport)
-		goto err;
-
-	return &sport->port_wwn;
-
-err:
-	return ERR_PTR(ret);
+	return srpt_lookup_wwn(name) ? : ERR_PTR(-EINVAL);
 }
 
 /**
@@ -3020,9 +3049,6 @@ err:
  */
 static void srpt_drop_tport(struct se_wwn *wwn)
 {
-	struct srpt_port *sport = container_of(wwn, struct srpt_port, port_wwn);
-
-	pr_debug("drop_tport(%s\n", config_item_name(&sport->port_wwn.wwn_group.cg_item));
 }
 
 static ssize_t srpt_wwn_version_show(struct config_item *item, char *buf)
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index 581878782854..cc1183851af5 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -258,6 +258,7 @@ enum rdma_ch_state {
  *                 against concurrent modification by the cm_id spinlock.
  * @sess:          Session information associated with this SRP channel.
  * @sess_name:     Session name.
+ * @ini_guid:      Initiator port GUID.
  * @release_work:  Allows scheduling of srpt_release_channel().
  * @release_done:  Enables waiting for srpt_release_channel() completion.
  */
@@ -284,6 +285,7 @@ struct srpt_rdma_ch {
 	struct list_head	cmd_wait_list;
 	struct se_session	*sess;
 	u8			sess_name[36];
+	u8			ini_guid[24];
 	struct work_struct	release_work;
 	struct completion	*release_done;
 };
@@ -306,28 +308,34 @@ struct srpt_port_attrib {
  * @mad_agent: per-port management datagram processing information.
  * @enabled:   Whether or not this target port is enabled.
  * @port_guid: ASCII representation of Port GUID
+ * @port_gid:  ASCII representation of Port GID
  * @port:      one-based port number.
  * @sm_lid:    cached value of the port's sm_lid.
  * @lid:       cached value of the port's lid.
  * @gid:       cached value of the port's gid.
  * @port_acl_lock spinlock for port_acl_list:
  * @work:      work structure for refreshing the aforementioned cached values.
- * @port_tpg_1 Target portal group = 1 data.
- * @port_wwn:  Target core WWN data.
+ * @port_guid_tpg: TPG associated with target port GUID.
+ * @port_guid_wwn: WWN associated with target port GUID.
+ * @port_gid_tpg:  TPG associated with target port GID.
+ * @port_gid_wwn:  WWN associated with target port GID.
  * @port_acl_list: Head of the list with all node ACLs for this port.
  */
 struct srpt_port {
 	struct srpt_device	*sdev;
 	struct ib_mad_agent	*mad_agent;
 	bool			enabled;
-	u8			port_guid[64];
+	u8			port_guid[24];
+	u8			port_gid[64];
 	u8			port;
 	u16			sm_lid;
 	u16			lid;
 	union ib_gid		gid;
 	struct work_struct	work;
-	struct se_portal_group	port_tpg_1;
-	struct se_wwn		port_wwn;
+	struct se_portal_group	port_guid_tpg;
+	struct se_wwn		port_guid_wwn;
+	struct se_portal_group	port_gid_tpg;
+	struct se_wwn		port_gid_wwn;
 	struct srpt_port_attrib port_attrib;
 };