Merge remote-tracking branch 'origin/master' into drm-misc-fixes

Pick up 4.14-rc1

Signed-off-by: Sean Paul <seanpaul@chromium.org>

228 files changed, 13198 insertions, 5038 deletions

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 234fe01904e7..3726205c8704 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -34,6 +34,15 @@ config INFINIBAND_USER_ACCESS
 	  libibverbs, libibcm and a hardware driver library from
 	  <http://www.openfabrics.org/git/>.
 
+config INFINIBAND_EXP_USER_ACCESS
+	bool "Allow experimental support for Infiniband ABI"
+	depends on INFINIBAND_USER_ACCESS
+	---help---
+	  IOCTL based ABI support for Infiniband. This allows userspace
+	  to invoke the experimental IOCTL based ABI.
+	  These commands are parsed via per-device parsing tree and
+	  enables per-device features.
+
 config INFINIBAND_USER_MEM
 	bool
 	depends on INFINIBAND_USER_ACCESS != n
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index e3cdafff8ece..b4df164f71a6 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -11,7 +11,8 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o \
-				security.o
+				security.o nldev.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
@@ -31,4 +32,5 @@ ib_umad-y :=			user_mad.o
 ib_ucm-y :=			ucm.o
 
 ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
-				rdma_core.o uverbs_std_types.o
+				rdma_core.o uverbs_std_types.o uverbs_ioctl.o \
+				uverbs_ioctl_merge.o
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 437522ca97b4..12523f630b61 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -130,13 +130,11 @@ static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
-
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	if (ib_nl_is_good_ip_resp(nlh))
@@ -186,7 +184,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
 
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
-	ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
 
 	/* Make the request retry, so when we get the response from userspace
 	 * we will have something.
@@ -326,7 +324,7 @@ static void queue_req(struct addr_req *req)
 static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
 			  const void *daddr, u32 seq, u16 family)
 {
-	if (ibnl_chk_listeners(RDMA_NL_GROUP_LS))
+	if (rdma_nl_chk_listeners(RDMA_NL_GROUP_LS))
 		return -EADDRNOTAVAIL;
 
 	/* We fill in what we can, the response will fill the rest */
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index efc94304dee3..77515638c55c 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -1199,30 +1199,23 @@ int ib_cache_setup_one(struct ib_device *device)
 	device->cache.ports =
 		kzalloc(sizeof(*device->cache.ports) *
 			(rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL);
-	if (!device->cache.ports) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!device->cache.ports)
+		return -ENOMEM;
 
 	err = gid_table_setup_one(device);
-	if (err)
-		goto out;
+	if (err) {
+		kfree(device->cache.ports);
+		device->cache.ports = NULL;
+		return err;
+	}
 
 	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p)
 		ib_cache_update(device, p + rdma_start_port(device), true);
 
 	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
 			      device, ib_cache_event);
-	err = ib_register_event_handler(&device->cache.event_handler);
-	if (err)
-		goto err;
-
+	ib_register_event_handler(&device->cache.event_handler);
 	return 0;
-
-err:
-	gid_table_cleanup_one(device);
-out:
-	return err;
 }
 
 void ib_cache_release_one(struct ib_device *device)
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 2b4d613a3474..4c4b46586af2 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -373,11 +373,19 @@ out:
 	return ret;
 }
 
-static int cm_alloc_response_msg(struct cm_port *port,
-				 struct ib_mad_recv_wc *mad_recv_wc,
-				 struct ib_mad_send_buf **msg)
+static struct ib_mad_send_buf *cm_alloc_response_msg_no_ah(struct cm_port *port,
+							   struct ib_mad_recv_wc *mad_recv_wc)
+{
+	return ib_create_send_mad(port->mad_agent, 1, mad_recv_wc->wc->pkey_index,
+				  0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
+				  GFP_ATOMIC,
+				  IB_MGMT_BASE_VERSION);
+}
+
+static int cm_create_response_msg_ah(struct cm_port *port,
+				     struct ib_mad_recv_wc *mad_recv_wc,
+				     struct ib_mad_send_buf *msg)
 {
-	struct ib_mad_send_buf *m;
 	struct ib_ah *ah;
 
 	ah = ib_create_ah_from_wc(port->mad_agent->qp->pd, mad_recv_wc->wc,
@@ -385,27 +393,40 @@ static int cm_alloc_response_msg(struct cm_port *port,
 	if (IS_ERR(ah))
 		return PTR_ERR(ah);
 
-	m = ib_create_send_mad(port->mad_agent, 1, mad_recv_wc->wc->pkey_index,
-			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-			       GFP_ATOMIC,
-			       IB_MGMT_BASE_VERSION);
-	if (IS_ERR(m)) {
-		rdma_destroy_ah(ah);
-		return PTR_ERR(m);
-	}
-	m->ah = ah;
-	*msg = m;
+	msg->ah = ah;
 	return 0;
 }
 
 static void cm_free_msg(struct ib_mad_send_buf *msg)
 {
-	rdma_destroy_ah(msg->ah);
+	if (msg->ah)
+		rdma_destroy_ah(msg->ah);
 	if (msg->context[0])
 		cm_deref_id(msg->context[0]);
 	ib_free_send_mad(msg);
 }
 
+static int cm_alloc_response_msg(struct cm_port *port,
+				 struct ib_mad_recv_wc *mad_recv_wc,
+				 struct ib_mad_send_buf **msg)
+{
+	struct ib_mad_send_buf *m;
+	int ret;
+
+	m = cm_alloc_response_msg_no_ah(port, mad_recv_wc);
+	if (IS_ERR(m))
+		return PTR_ERR(m);
+
+	ret = cm_create_response_msg_ah(port, mad_recv_wc, m);
+	if (ret) {
+		cm_free_msg(m);
+		return ret;
+	}
+
+	*msg = m;
+	return 0;
+}
+
 static void * cm_copy_private_data(const void *private_data,
 				   u8 private_data_len)
 {
@@ -1175,6 +1196,11 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 {
 	struct sa_path_rec *pri_path = param->primary_path;
 	struct sa_path_rec *alt_path = param->alternate_path;
+	bool pri_ext = false;
+
+	if (pri_path->rec_type == SA_PATH_REC_TYPE_OPA)
+		pri_ext = opa_is_extended_lid(pri_path->opa.dlid,
+					      pri_path->opa.slid);
 
 	cm_format_mad_hdr(&req_msg->hdr, CM_REQ_ATTR_ID,
 			  cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_REQ));
@@ -1202,18 +1228,24 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 		cm_req_set_srq(req_msg, param->srq);
 	}
 
+	req_msg->primary_local_gid = pri_path->sgid;
+	req_msg->primary_remote_gid = pri_path->dgid;
+	if (pri_ext) {
+		req_msg->primary_local_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.slid));
+		req_msg->primary_remote_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.dlid));
+	}
 	if (pri_path->hop_limit <= 1) {
-		req_msg->primary_local_lid =
+		req_msg->primary_local_lid = pri_ext ? 0 :
 			htons(ntohl(sa_path_get_slid(pri_path)));
-		req_msg->primary_remote_lid =
+		req_msg->primary_remote_lid = pri_ext ? 0 :
 			htons(ntohl(sa_path_get_dlid(pri_path)));
 	} else {
 		/* Work-around until there's a way to obtain remote LID info */
 		req_msg->primary_local_lid = IB_LID_PERMISSIVE;
 		req_msg->primary_remote_lid = IB_LID_PERMISSIVE;
 	}
-	req_msg->primary_local_gid = pri_path->sgid;
-	req_msg->primary_remote_gid = pri_path->dgid;
 	cm_req_set_primary_flow_label(req_msg, pri_path->flow_label);
 	cm_req_set_primary_packet_rate(req_msg, pri_path->rate);
 	req_msg->primary_traffic_class = pri_path->traffic_class;
@@ -1225,17 +1257,29 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 			       pri_path->packet_life_time));
 
 	if (alt_path) {
+		bool alt_ext = false;
+
+		if (alt_path->rec_type == SA_PATH_REC_TYPE_OPA)
+			alt_ext = opa_is_extended_lid(alt_path->opa.dlid,
+						      alt_path->opa.slid);
+
+		req_msg->alt_local_gid = alt_path->sgid;
+		req_msg->alt_remote_gid = alt_path->dgid;
+		if (alt_ext) {
+			req_msg->alt_local_gid.global.interface_id
+				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.slid));
+			req_msg->alt_remote_gid.global.interface_id
+				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.dlid));
+		}
 		if (alt_path->hop_limit <= 1) {
-			req_msg->alt_local_lid =
+			req_msg->alt_local_lid = alt_ext ? 0 :
 				htons(ntohl(sa_path_get_slid(alt_path)));
-			req_msg->alt_remote_lid =
+			req_msg->alt_remote_lid = alt_ext ? 0 :
 				htons(ntohl(sa_path_get_dlid(alt_path)));
 		} else {
 			req_msg->alt_local_lid = IB_LID_PERMISSIVE;
 			req_msg->alt_remote_lid = IB_LID_PERMISSIVE;
 		}
-		req_msg->alt_local_gid = alt_path->sgid;
-		req_msg->alt_remote_gid = alt_path->dgid;
 		cm_req_set_alt_flow_label(req_msg,
 					  alt_path->flow_label);
 		cm_req_set_alt_packet_rate(req_msg, alt_path->rate);
@@ -1405,16 +1449,63 @@ static inline int cm_is_active_peer(__be64 local_ca_guid, __be64 remote_ca_guid,
 		 (be32_to_cpu(local_qpn) > be32_to_cpu(remote_qpn))));
 }
 
+static bool cm_req_has_alt_path(struct cm_req_msg *req_msg)
+{
+	return ((req_msg->alt_local_lid) ||
+		(ib_is_opa_gid(&req_msg->alt_local_gid)));
+}
+
+static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num,
+				 struct sa_path_rec *path, union ib_gid *gid)
+{
+	if (ib_is_opa_gid(gid) && rdma_cap_opa_ah(ib_device, port_num))
+		path->rec_type = SA_PATH_REC_TYPE_OPA;
+	else
+		path->rec_type = SA_PATH_REC_TYPE_IB;
+}
+
+static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg,
+					struct sa_path_rec *primary_path,
+					struct sa_path_rec *alt_path)
+{
+	u32 lid;
+
+	if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(primary_path,
+				 htonl(ntohs(req_msg->primary_local_lid)));
+		sa_path_set_slid(primary_path,
+				 htonl(ntohs(req_msg->primary_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&req_msg->primary_local_gid);
+		sa_path_set_dlid(primary_path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&req_msg->primary_remote_gid);
+		sa_path_set_slid(primary_path, cpu_to_be32(lid));
+	}
+
+	if (!cm_req_has_alt_path(req_msg))
+		return;
+
+	if (alt_path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(alt_path,
+				 htonl(ntohs(req_msg->alt_local_lid)));
+		sa_path_set_slid(alt_path,
+				 htonl(ntohs(req_msg->alt_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&req_msg->alt_local_gid);
+		sa_path_set_dlid(alt_path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&req_msg->alt_remote_gid);
+		sa_path_set_slid(alt_path, cpu_to_be32(lid));
+	}
+}
+
 static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 				     struct sa_path_rec *primary_path,
 				     struct sa_path_rec *alt_path)
 {
 	primary_path->dgid = req_msg->primary_local_gid;
 	primary_path->sgid = req_msg->primary_remote_gid;
-	sa_path_set_dlid(primary_path,
-			 htonl(ntohs(req_msg->primary_local_lid)));
-	sa_path_set_slid(primary_path,
-			 htonl(ntohs(req_msg->primary_remote_lid)));
 	primary_path->flow_label = cm_req_get_primary_flow_label(req_msg);
 	primary_path->hop_limit = req_msg->primary_hop_limit;
 	primary_path->traffic_class = req_msg->primary_traffic_class;
@@ -1431,13 +1522,9 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 	primary_path->packet_life_time -= (primary_path->packet_life_time > 0);
 	primary_path->service_id = req_msg->service_id;
 
-	if (req_msg->alt_local_lid) {
+	if (cm_req_has_alt_path(req_msg)) {
 		alt_path->dgid = req_msg->alt_local_gid;
 		alt_path->sgid = req_msg->alt_remote_gid;
-		sa_path_set_dlid(alt_path,
-				 htonl(ntohs(req_msg->alt_local_lid)));
-		sa_path_set_slid(alt_path,
-				 htonl(ntohs(req_msg->alt_remote_lid)));
 		alt_path->flow_label = cm_req_get_alt_flow_label(req_msg);
 		alt_path->hop_limit = req_msg->alt_hop_limit;
 		alt_path->traffic_class = req_msg->alt_traffic_class;
@@ -1454,6 +1541,7 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 		alt_path->packet_life_time -= (alt_path->packet_life_time > 0);
 		alt_path->service_id = req_msg->service_id;
 	}
+	cm_format_path_lid_from_req(req_msg, primary_path, alt_path);
 }
 
 static u16 cm_get_bth_pkey(struct cm_work *work)
@@ -1703,7 +1791,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 {
 	if (!cm_req_get_primary_subnet_local(req_msg)) {
 		if (req_msg->primary_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->primary_local_lid = cpu_to_be16(wc->slid);
+			req_msg->primary_local_lid = ib_lid_be16(wc->slid);
 			cm_req_set_primary_sl(req_msg, wc->sl);
 		}
 
@@ -1713,7 +1801,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 
 	if (!cm_req_get_alt_subnet_local(req_msg)) {
 		if (req_msg->alt_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->alt_local_lid = cpu_to_be16(wc->slid);
+			req_msg->alt_local_lid = ib_lid_be16(wc->slid);
 			cm_req_set_alt_sl(req_msg, wc->sl);
 		}
 
@@ -1784,9 +1872,12 @@ static int cm_req_handler(struct cm_work *work)
 					 dev_net(gid_attr.ndev));
 			dev_put(gid_attr.ndev);
 		} else {
-			work->path[0].rec_type = SA_PATH_REC_TYPE_IB;
+			cm_path_set_rec_type(work->port->cm_dev->ib_device,
+					     work->port->port_num,
+					     &work->path[0],
+					     &req_msg->primary_local_gid);
 		}
-		if (req_msg->alt_local_lid)
+		if (cm_req_has_alt_path(req_msg))
 			work->path[1].rec_type = work->path[0].rec_type;
 		cm_format_paths_from_req(req_msg, &work->path[0],
 					 &work->path[1]);
@@ -1811,16 +1902,19 @@ static int cm_req_handler(struct cm_work *work)
 					 dev_net(gid_attr.ndev));
 			dev_put(gid_attr.ndev);
 		} else {
-			work->path[0].rec_type = SA_PATH_REC_TYPE_IB;
+			cm_path_set_rec_type(work->port->cm_dev->ib_device,
+					     work->port->port_num,
+					     &work->path[0],
+					     &req_msg->primary_local_gid);
 		}
-		if (req_msg->alt_local_lid)
+		if (cm_req_has_alt_path(req_msg))
 			work->path[1].rec_type = work->path[0].rec_type;
 		ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
 			       &work->path[0].sgid, sizeof work->path[0].sgid,
 			       NULL, 0);
 		goto rejected;
 	}
-	if (req_msg->alt_local_lid) {
+	if (cm_req_has_alt_path(req_msg)) {
 		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av,
 					 cm_id_priv);
 		if (ret) {
@@ -2424,7 +2518,8 @@ static int cm_dreq_handler(struct cm_work *work)
 	case IB_CM_TIMEWAIT:
 		atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
 				counter[CM_DREQ_COUNTER]);
-		if (cm_alloc_response_msg(work->port, work->mad_recv_wc, &msg))
+		msg = cm_alloc_response_msg_no_ah(work->port, work->mad_recv_wc);
+		if (IS_ERR(msg))
 			goto unlock;
 
 		cm_format_drep((struct cm_drep_msg *) msg->mad, cm_id_priv,
@@ -2432,7 +2527,8 @@ static int cm_dreq_handler(struct cm_work *work)
 			       cm_id_priv->private_data_len);
 		spin_unlock_irq(&cm_id_priv->lock);
 
-		if (ib_post_send_mad(msg, NULL))
+		if (cm_create_response_msg_ah(work->port, work->mad_recv_wc, msg) ||
+		    ib_post_send_mad(msg, NULL))
 			cm_free_msg(msg);
 		goto deref;
 	case IB_CM_DREQ_RCVD:
@@ -2843,6 +2939,11 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg,
 			  const void *private_data,
 			  u8 private_data_len)
 {
+	bool alt_ext = false;
+
+	if (alternate_path->rec_type == SA_PATH_REC_TYPE_OPA)
+		alt_ext = opa_is_extended_lid(alternate_path->opa.dlid,
+					      alternate_path->opa.slid);
 	cm_format_mad_hdr(&lap_msg->hdr, CM_LAP_ATTR_ID,
 			  cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_LAP));
 	lap_msg->local_comm_id = cm_id_priv->id.local_id;
@@ -2856,6 +2957,12 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg,
 		htons(ntohl(sa_path_get_dlid(alternate_path)));
 	lap_msg->alt_local_gid = alternate_path->sgid;
 	lap_msg->alt_remote_gid = alternate_path->dgid;
+	if (alt_ext) {
+		lap_msg->alt_local_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.slid));
+		lap_msg->alt_remote_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.dlid));
+	}
 	cm_lap_set_flow_label(lap_msg, alternate_path->flow_label);
 	cm_lap_set_traffic_class(lap_msg, alternate_path->traffic_class);
 	lap_msg->alt_hop_limit = alternate_path->hop_limit;
@@ -2924,16 +3031,29 @@ out:	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 }
 EXPORT_SYMBOL(ib_send_cm_lap);
 
+static void cm_format_path_lid_from_lap(struct cm_lap_msg *lap_msg,
+					struct sa_path_rec *path)
+{
+	u32 lid;
+
+	if (path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid)));
+		sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&lap_msg->alt_local_gid);
+		sa_path_set_dlid(path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&lap_msg->alt_remote_gid);
+		sa_path_set_slid(path, cpu_to_be32(lid));
+	}
+}
+
 static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 				    struct sa_path_rec *path,
 				    struct cm_lap_msg *lap_msg)
 {
-	memset(path, 0, sizeof *path);
-	path->rec_type = SA_PATH_REC_TYPE_IB;
 	path->dgid = lap_msg->alt_local_gid;
 	path->sgid = lap_msg->alt_remote_gid;
-	sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid)));
-	sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid)));
 	path->flow_label = cm_lap_get_flow_label(lap_msg);
 	path->hop_limit = lap_msg->alt_hop_limit;
 	path->traffic_class = cm_lap_get_traffic_class(lap_msg);
@@ -2947,6 +3067,7 @@ static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 	path->packet_life_time_selector = IB_SA_EQ;
 	path->packet_life_time = cm_lap_get_local_ack_timeout(lap_msg);
 	path->packet_life_time -= (path->packet_life_time > 0);
+	cm_format_path_lid_from_lap(lap_msg, path);
 }
 
 static int cm_lap_handler(struct cm_work *work)
@@ -2965,6 +3086,11 @@ static int cm_lap_handler(struct cm_work *work)
 		return -EINVAL;
 
 	param = &work->cm_event.param.lap_rcvd;
+	memset(&work->path[0], 0, sizeof(work->path[1]));
+	cm_path_set_rec_type(work->port->cm_dev->ib_device,
+			     work->port->port_num,
+			     &work->path[0],
+			     &lap_msg->alt_local_gid);
 	param->alternate_path = &work->path[0];
 	cm_format_path_from_lap(cm_id_priv, param->alternate_path, lap_msg);
 	work->cm_event.private_data = &lap_msg->private_data;
@@ -2980,7 +3106,8 @@ static int cm_lap_handler(struct cm_work *work)
 	case IB_CM_MRA_LAP_SENT:
 		atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
 				counter[CM_LAP_COUNTER]);
-		if (cm_alloc_response_msg(work->port, work->mad_recv_wc, &msg))
+		msg = cm_alloc_response_msg_no_ah(work->port, work->mad_recv_wc);
+		if (IS_ERR(msg))
 			goto unlock;
 
 		cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
@@ -2990,7 +3117,8 @@ static int cm_lap_handler(struct cm_work *work)
 			      cm_id_priv->private_data_len);
 		spin_unlock_irq(&cm_id_priv->lock);
 
-		if (ib_post_send_mad(msg, NULL))
+		if (cm_create_response_msg_ah(work->port, work->mad_recv_wc, msg) ||
+		    ib_post_send_mad(msg, NULL))
 			cm_free_msg(msg);
 		goto deref;
 	case IB_CM_LAP_RCVD:
@@ -4201,7 +4329,7 @@ static int __init ib_cm_init(void)
 		goto error1;
 	}
 
-	cm.wq = create_workqueue("ib_cm");
+	cm.wq = alloc_workqueue("ib_cm", 0, 1);
 	if (!cm.wq) {
 		ret = -ENOMEM;
 		goto error2;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 0eb393237ba2..852c8fec8088 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -72,6 +72,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_MAX_CM_RETRIES 15
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 #define CMA_IBOE_PACKET_LIFETIME 18
+#define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP
 
 static const char * const cma_events[] = {
 	[RDMA_CM_EVENT_ADDR_RESOLVED]	 = "address resolved",
@@ -3998,7 +3999,8 @@ static void iboe_mcast_work_handler(struct work_struct *work)
 	kfree(mw);
 }
 
-static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid)
+static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid,
+			      enum ib_gid_type gid_type)
 {
 	struct sockaddr_in *sin = (struct sockaddr_in *)addr;
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
@@ -4008,8 +4010,8 @@ static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid)
 	} else if (addr->sa_family == AF_INET6) {
 		memcpy(mgid, &sin6->sin6_addr, sizeof *mgid);
 	} else {
-		mgid->raw[0] = 0xff;
-		mgid->raw[1] = 0x0e;
+		mgid->raw[0] = (gid_type == IB_GID_TYPE_IB) ? 0xff : 0;
+		mgid->raw[1] = (gid_type == IB_GID_TYPE_IB) ? 0x0e : 0;
 		mgid->raw[2] = 0;
 		mgid->raw[3] = 0;
 		mgid->raw[4] = 0;
@@ -4050,7 +4052,9 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 		goto out1;
 	}
 
-	cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid);
+	gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
+		   rdma_start_port(id_priv->cma_dev->device)];
+	cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid, gid_type);
 
 	mc->multicast.ib->rec.pkey = cpu_to_be16(0xffff);
 	if (id_priv->id.ps == RDMA_PS_UDP)
@@ -4066,8 +4070,6 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 	mc->multicast.ib->rec.hop_limit = 1;
 	mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu);
 
-	gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
-		   rdma_start_port(id_priv->cma_dev->device)];
 	if (addr->sa_family == AF_INET) {
 		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
 			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
@@ -4280,8 +4282,12 @@ static void cma_add_one(struct ib_device *device)
 	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);
+		if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE))
+			cma_dev->default_gid_type[i - rdma_start_port(device)] =
+				CMA_PREFERRED_ROCE_GID_TYPE;
+		else
+			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;
 	}
 
@@ -4452,9 +4458,8 @@ out:
 	return skb->len;
 }
 
-static const struct ibnl_client_cbs cma_cb_table[] = {
-	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats,
-				       .module = THIS_MODULE },
+static const struct rdma_nl_cbs cma_cb_table[] = {
+	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 
 static int cma_init_net(struct net *net)
@@ -4506,9 +4511,7 @@ static int __init cma_init(void)
 	if (ret)
 		goto err;
 
-	if (ibnl_add_client(RDMA_NL_RDMA_CM, ARRAY_SIZE(cma_cb_table),
-			    cma_cb_table))
-		pr_warn("RDMA CMA: failed to add netlink callback\n");
+	rdma_nl_register(RDMA_NL_RDMA_CM, cma_cb_table);
 	cma_configfs_init();
 
 	return 0;
@@ -4525,7 +4528,7 @@ err_wq:
 static void __exit cma_cleanup(void)
 {
 	cma_configfs_exit();
-	ibnl_remove_client(RDMA_NL_RDMA_CM);
+	rdma_nl_unregister(RDMA_NL_RDMA_CM);
 	ib_unregister_client(&cma_client);
 	unregister_netdevice_notifier(&cma_nb);
 	rdma_addr_unregister_client(&addr_client);
@@ -4534,5 +4537,7 @@ static void __exit cma_cleanup(void)
 	destroy_workqueue(cma_wq);
 }
 
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_RDMA_CM, 1);
+
 module_init(cma_init);
 module_exit(cma_cleanup);
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 11ae67514e13..a1d687a664f8 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -38,6 +38,7 @@
 #include <linux/cgroup_rdma.h>
 
 #include <rdma/ib_verbs.h>
+#include <rdma/opa_addr.h>
 #include <rdma/ib_mad.h>
 #include "mad_priv.h"
 
@@ -102,6 +103,14 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 			      roce_netdev_callback cb,
 			      void *cookie);
 
+typedef int (*nldev_callback)(struct ib_device *device,
+			      struct sk_buff *skb,
+			      struct netlink_callback *cb,
+			      unsigned int idx);
+
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb);
+
 enum ib_cache_gid_default_mode {
 	IB_CACHE_GID_DEFAULT_MODE_SET,
 	IB_CACHE_GID_DEFAULT_MODE_DELETE
@@ -179,8 +188,8 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
-int ibnl_init(void);
-void ibnl_cleanup(void);
+int rdma_nl_init(void);
+void rdma_nl_exit(void);
 
 /**
  * Check if there are any listeners to the netlink group
@@ -190,11 +199,14 @@ void ibnl_cleanup(void);
 int ibnl_chk_listeners(unsigned int group);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb);
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack);
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 
 int ib_get_cached_subnet_prefix(struct ib_device *device,
 				u8                port_num,
@@ -301,4 +313,9 @@ static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map,
 	return 0;
 }
 #endif
+
+struct ib_device *__ib_device_get_by_index(u32 ifindex);
+/* RDMA device netlink */
+void nldev_init(void);
+void nldev_exit(void);
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index a5dfab6adf49..84fc32a2c8b3 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -134,6 +134,17 @@ static int ib_device_check_mandatory(struct ib_device *device)
 	return 0;
 }
 
+struct ib_device *__ib_device_get_by_index(u32 index)
+{
+	struct ib_device *device;
+
+	list_for_each_entry(device, &device_list, core_list)
+		if (device->index == index)
+			return device;
+
+	return NULL;
+}
+
 static struct ib_device *__ib_device_get_by_name(const char *name)
 {
 	struct ib_device *device;
@@ -145,7 +156,6 @@ static struct ib_device *__ib_device_get_by_name(const char *name)
 	return NULL;
 }
 
-
 static int alloc_name(char *name)
 {
 	unsigned long *inuse;
@@ -326,10 +336,10 @@ static int read_port_immutable(struct ib_device *device)
 	return 0;
 }
 
-void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len)
+void ib_get_device_fw_str(struct ib_device *dev, char *str)
 {
 	if (dev->get_dev_fw_str)
-		dev->get_dev_fw_str(dev, str, str_len);
+		dev->get_dev_fw_str(dev, str);
 	else
 		str[0] = '\0';
 }
@@ -395,6 +405,30 @@ static int ib_security_change(struct notifier_block *nb, unsigned long event,
 }
 
 /**
+ *	__dev_new_index	-	allocate an device index
+ *
+ *	Returns a suitable unique value for a new device interface
+ *	number.  It assumes that there are less than 2^32-1 ib devices
+ *	will be present in the system.
+ */
+static u32 __dev_new_index(void)
+{
+	/*
+	 * The device index to allow stable naming.
+	 * Similar to struct net -> ifindex.
+	 */
+	static u32 index;
+
+	for (;;) {
+		if (!(++index))
+			index = 1;
+
+		if (!__ib_device_get_by_index(index))
+			return index;
+	}
+}
+
+/**
  * ib_register_device - Register an IB device with IB core
  * @device:Device to register
  *
@@ -489,9 +523,10 @@ int ib_register_device(struct ib_device *device,
 	device->reg_state = IB_DEV_REGISTERED;
 
 	list_for_each_entry(client, &client_list, list)
-		if (client->add && !add_client_context(device, client))
+		if (!add_client_context(device, client) && client->add)
 			client->add(device);
 
+	device->index = __dev_new_index();
 	down_write(&lists_rwsem);
 	list_add_tail(&device->core_list, &device_list);
 	up_write(&lists_rwsem);
@@ -537,10 +572,11 @@ void ib_unregister_device(struct ib_device *device)
 	}
 	up_read(&lists_rwsem);
 
-	mutex_unlock(&device_mutex);
-
 	ib_device_unregister_rdmacg(device);
 	ib_device_unregister_sysfs(device);
+
+	mutex_unlock(&device_mutex);
+
 	ib_cache_cleanup_one(device);
 
 	ib_security_destroy_port_pkey_list(device);
@@ -577,7 +613,7 @@ int ib_register_client(struct ib_client *client)
 	mutex_lock(&device_mutex);
 
 	list_for_each_entry(device, &device_list, core_list)
-		if (client->add && !add_client_context(device, client))
+		if (!add_client_context(device, client) && client->add)
 			client->add(device);
 
 	down_write(&lists_rwsem);
@@ -711,7 +747,7 @@ EXPORT_SYMBOL(ib_set_client_data);
  * chapter 11 of the InfiniBand Architecture Specification).  This
  * callback may occur in interrupt context.
  */
-int ib_register_event_handler  (struct ib_event_handler *event_handler)
+void ib_register_event_handler(struct ib_event_handler *event_handler)
 {
 	unsigned long flags;
 
@@ -719,8 +755,6 @@ int ib_register_event_handler  (struct ib_event_handler *event_handler)
 	list_add_tail(&event_handler->list,
 		      &event_handler->device->event_handler_list);
 	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
-
-	return 0;
 }
 EXPORT_SYMBOL(ib_register_event_handler);
 
@@ -731,15 +765,13 @@ EXPORT_SYMBOL(ib_register_event_handler);
  * Unregister an event handler registered with
  * ib_register_event_handler().
  */
-int ib_unregister_event_handler(struct ib_event_handler *event_handler)
+void ib_unregister_event_handler(struct ib_event_handler *event_handler)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
 	list_del(&event_handler->list);
 	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
-
-	return 0;
 }
 EXPORT_SYMBOL(ib_unregister_event_handler);
 
@@ -893,6 +925,31 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 }
 
 /**
+ * ib_enum_all_devs - enumerate all ib_devices
+ * @cb: Callback to call for each found ib_device
+ *
+ * Enumerates all ib_devices and calls callback() on each device.
+ */
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb)
+{
+	struct ib_device *dev;
+	unsigned int idx = 0;
+	int ret = 0;
+
+	down_read(&lists_rwsem);
+	list_for_each_entry(dev, &device_list, core_list) {
+		ret = nldev_cb(dev, skb, cb, idx);
+		if (ret)
+			break;
+		idx++;
+	}
+
+	up_read(&lists_rwsem);
+	return ret;
+}
+
+/**
  * ib_query_pkey - Get P_Key table entry
  * @device:Device to query
  * @port_num:Port number to query
@@ -944,14 +1001,17 @@ int ib_modify_port(struct ib_device *device,
 		   u8 port_num, int port_modify_mask,
 		   struct ib_port_modify *port_modify)
 {
-	if (!device->modify_port)
-		return -ENOSYS;
+	int rc;
 
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	return device->modify_port(device, port_num, port_modify_mask,
-				   port_modify);
+	if (device->modify_port)
+		rc = device->modify_port(device, port_num, port_modify_mask,
+					   port_modify);
+	else
+		rc = rdma_protocol_roce(device, port_num) ? 0 : -ENOSYS;
+	return rc;
 }
 EXPORT_SYMBOL(ib_modify_port);
 
@@ -1086,29 +1146,21 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
-static struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp,
-		.module = THIS_MODULE },
+		.doit = ib_nl_handle_resolve_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout,
-		.module = THIS_MODULE },
+		.doit = ib_nl_handle_set_timeout,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp,
-		.module = THIS_MODULE },
+		.doit = ib_nl_handle_ip_res_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 };
 
-static int ib_add_ibnl_clients(void)
-{
-	return ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ibnl_ls_cb_table),
-			       ibnl_ls_cb_table);
-}
-
-static void ib_remove_ibnl_clients(void)
-{
-	ibnl_remove_client(RDMA_NL_LS);
-}
-
 static int __init ib_core_init(void)
 {
 	int ret;
@@ -1130,9 +1182,9 @@ static int __init ib_core_init(void)
 		goto err_comp;
 	}
 
-	ret = ibnl_init();
+	ret = rdma_nl_init();
 	if (ret) {
-		pr_warn("Couldn't init IB netlink interface\n");
+		pr_warn("Couldn't init IB netlink interface: err %d\n", ret);
 		goto err_sysfs;
 	}
 
@@ -1154,24 +1206,18 @@ static int __init ib_core_init(void)
 		goto err_mad;
 	}
 
-	ret = ib_add_ibnl_clients();
-	if (ret) {
-		pr_warn("Couldn't register ibnl clients\n");
-		goto err_sa;
-	}
-
 	ret = register_lsm_notifier(&ibdev_lsm_nb);
 	if (ret) {
 		pr_warn("Couldn't register LSM notifier. ret %d\n", ret);
-		goto err_ibnl_clients;
+		goto err_sa;
 	}
 
+	nldev_init();
+	rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
 	ib_cache_setup();
 
 	return 0;
 
-err_ibnl_clients:
-	ib_remove_ibnl_clients();
 err_sa:
 	ib_sa_cleanup();
 err_mad:
@@ -1179,7 +1225,7 @@ err_mad:
 err_addr:
 	addr_cleanup();
 err_ibnl:
-	ibnl_cleanup();
+	rdma_nl_exit();
 err_sysfs:
 	class_unregister(&ib_class);
 err_comp:
@@ -1191,18 +1237,21 @@ err:
 
 static void __exit ib_core_cleanup(void)
 {
-	unregister_lsm_notifier(&ibdev_lsm_nb);
 	ib_cache_cleanup();
-	ib_remove_ibnl_clients();
+	nldev_exit();
+	rdma_nl_unregister(RDMA_NL_LS);
+	unregister_lsm_notifier(&ibdev_lsm_nb);
 	ib_sa_cleanup();
 	ib_mad_cleanup();
 	addr_cleanup();
-	ibnl_cleanup();
+	rdma_nl_exit();
 	class_unregister(&ib_class);
 	destroy_workqueue(ib_comp_wq);
 	/* Make sure that any pending umem accounting work is done. */
 	destroy_workqueue(ib_wq);
 }
 
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4);
+
 module_init(ib_core_init);
 module_exit(ib_core_cleanup);
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 31661b5c1743..fcf42f6bb82a 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -80,7 +80,7 @@ const char *__attribute_const__ iwcm_reject_msg(int reason)
 }
 EXPORT_SYMBOL(iwcm_reject_msg);
 
-static struct ibnl_client_cbs iwcm_nl_cb_table[] = {
+static struct rdma_nl_cbs iwcm_nl_cb_table[] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
@@ -1175,13 +1175,9 @@ static int __init iw_cm_init(void)
 	ret = iwpm_init(RDMA_NL_IWCM);
 	if (ret)
 		pr_err("iw_cm: couldn't init iwpm\n");
-
-	ret = ibnl_add_client(RDMA_NL_IWCM, ARRAY_SIZE(iwcm_nl_cb_table),
-			      iwcm_nl_cb_table);
-	if (ret)
-		pr_err("iw_cm: couldn't register netlink callbacks\n");
-
-	iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", WQ_MEM_RECLAIM);
+	else
+		rdma_nl_register(RDMA_NL_IWCM, iwcm_nl_cb_table);
+	iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", 0);
 	if (!iwcm_wq)
 		return -ENOMEM;
 
@@ -1200,9 +1196,11 @@ static void __exit iw_cm_cleanup(void)
 {
 	unregister_net_sysctl_table(iwcm_ctl_table_hdr);
 	destroy_workqueue(iwcm_wq);
-	ibnl_remove_client(RDMA_NL_IWCM);
+	rdma_nl_unregister(RDMA_NL_IWCM);
 	iwpm_exit(RDMA_NL_IWCM);
 }
 
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_IWCM, 2);
+
 module_init(iw_cm_init);
 module_exit(iw_cm_cleanup);
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index a0e7c16d8bd8..30825bb9b8e9 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -42,7 +42,6 @@ int iwpm_valid_pid(void)
 {
 	return iwpm_user_pid > 0;
 }
-EXPORT_SYMBOL(iwpm_valid_pid);
 
 /*
  * iwpm_register_pid - Send a netlink query to user space
@@ -104,7 +103,7 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
 		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNAVAILABLE;
@@ -122,7 +121,6 @@ pid_query_error:
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_register_pid);
 
 /*
  * iwpm_add_mapping - Send a netlink add mapping message
@@ -174,7 +172,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto add_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
@@ -191,7 +189,6 @@ add_mapping_error:
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_add_mapping);
 
 /*
  * iwpm_add_and_query_mapping - Send a netlink add and query
@@ -251,7 +248,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto query_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";
@@ -267,7 +264,6 @@ query_mapping_error:
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_add_and_query_mapping);
 
 /*
  * iwpm_remove_mapping - Send a netlink remove mapping message
@@ -312,7 +308,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 	if (ret)
 		goto remove_mapping_error;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
@@ -328,7 +324,6 @@ remove_mapping_error:
 		dev_kfree_skb_any(skb);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remove_mapping);
 
 /* netlink attribute policy for the received response to register pid request */
 static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = {
@@ -397,7 +392,6 @@ register_pid_response_exit:
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_register_pid_cb);
 
 /* netlink attribute policy for the received response to add mapping request */
 static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = {
@@ -466,7 +460,6 @@ add_mapping_response_exit:
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_add_mapping_cb);
 
 /* netlink attribute policy for the response to add and query mapping request
  * and response with remote address info */
@@ -558,7 +551,6 @@ query_mapping_response_exit:
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb);
 
 /*
  * iwpm_remote_info_cb - Process a port mapper message, containing
@@ -627,7 +619,6 @@ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 			"remote_info: Mapped remote sockaddr:");
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remote_info_cb);
 
 /* netlink attribute policy for the received request for mapping info */
 static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = {
@@ -677,7 +668,6 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_mapping_info_cb);
 
 /* netlink attribute policy for the received mapping info ack */
 static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = {
@@ -707,7 +697,6 @@ int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_ack_mapping_info_cb);
 
 /* netlink attribute policy for the received port mapper error message */
 static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = {
@@ -751,4 +740,3 @@ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_mapping_error_cb);
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index f13870e69ccd..c81c55942626 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -54,8 +54,6 @@ static struct iwpm_admin_data iwpm_admin;
 int iwpm_init(u8 nl_client)
 {
 	int ret = 0;
-	if (iwpm_valid_client(nl_client))
-		return -EINVAL;
 	mutex_lock(&iwpm_admin_lock);
 	if (atomic_read(&iwpm_admin.refcount) == 0) {
 		iwpm_hash_bucket = kzalloc(IWPM_MAPINFO_HASH_SIZE *
@@ -83,7 +81,6 @@ init_exit:
 	}
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_init);
 
 static void free_hash_bucket(void);
 static void free_reminfo_bucket(void);
@@ -109,7 +106,6 @@ int iwpm_exit(u8 nl_client)
 	iwpm_set_registration(nl_client, IWPM_REG_UNDEF);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_exit);
 
 static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *,
 					       struct sockaddr_storage *);
@@ -148,7 +144,6 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_create_mapinfo);
 
 int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr,
 			struct sockaddr_storage *mapped_local_addr)
@@ -184,7 +179,6 @@ remove_mapinfo_exit:
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remove_mapinfo);
 
 static void free_hash_bucket(void)
 {
@@ -297,7 +291,6 @@ get_remote_info_exit:
 	spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_get_remote_info);
 
 struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
 					u8 nl_client, gfp_t gfp)
@@ -383,15 +376,11 @@ int iwpm_get_nlmsg_seq(void)
 
 int iwpm_valid_client(u8 nl_client)
 {
-	if (nl_client >= RDMA_NL_NUM_CLIENTS)
-		return 0;
 	return iwpm_admin.client_list[nl_client];
 }
 
 void iwpm_set_valid(u8 nl_client, int valid)
 {
-	if (nl_client >= RDMA_NL_NUM_CLIENTS)
-		return;
 	iwpm_admin.client_list[nl_client] = valid;
 }
 
@@ -608,7 +597,7 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
 				&mapping_num, IWPM_NLA_MAPINFO_SEND_NUM);
 	if (ret)
 		goto mapinfo_num_error;
-	ret = ibnl_unicast(skb, nlh, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";
@@ -637,7 +626,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
 		return -ENOMEM;
 	}
 	nlh->nlmsg_type = NLMSG_DONE;
-	ret = ibnl_unicast(skb, (struct nlmsghdr *)skb->data, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret)
 		pr_warn("%s Unable to send a nlmsg\n", __func__);
 	return ret;
diff --git a/drivers/infiniband/core/mad_rmpp.c b/drivers/infiniband/core/mad_rmpp.c
index 0d3cca0a8890..e5cf09c66fe6 100644
--- a/drivers/infiniband/core/mad_rmpp.c
+++ b/drivers/infiniband/core/mad_rmpp.c
@@ -64,7 +64,7 @@ struct mad_rmpp_recv {
 
 	__be64 tid;
 	u32 src_qp;
-	u16 slid;
+	u32 slid;
 	u8 mgmt_class;
 	u8 class_version;
 	u8 method;
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 94931c474d41..b12e58787c3d 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2017 Mellanox Technologies Inc.  All rights reserved.
  * Copyright (c) 2010 Voltaire Inc.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -37,239 +38,267 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <rdma/rdma_netlink.h>
+#include <linux/module.h>
 #include "core_priv.h"
 
-struct ibnl_client {
-	struct list_head		list;
-	int				index;
-	int				nops;
-	const struct ibnl_client_cbs   *cb_table;
-};
+#include "core_priv.h"
 
-static DEFINE_MUTEX(ibnl_mutex);
+static DEFINE_MUTEX(rdma_nl_mutex);
 static struct sock *nls;
-static LIST_HEAD(client_list);
+static struct {
+	const struct rdma_nl_cbs   *cb_table;
+} rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
-int ibnl_chk_listeners(unsigned int group)
+int rdma_nl_chk_listeners(unsigned int group)
 {
-	if (netlink_has_listeners(nls, group) == 0)
-		return -1;
-	return 0;
+	return (netlink_has_listeners(nls, group)) ? 0 : -1;
 }
+EXPORT_SYMBOL(rdma_nl_chk_listeners);
 
-int ibnl_add_client(int index, int nops,
-		    const struct ibnl_client_cbs cb_table[])
+static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 {
-	struct ibnl_client *cur;
-	struct ibnl_client *nl_client;
+	static const unsigned int max_num_ops[RDMA_NL_NUM_CLIENTS] = {
+		[RDMA_NL_RDMA_CM] = RDMA_NL_RDMA_CM_NUM_OPS,
+		[RDMA_NL_IWCM] = RDMA_NL_IWPM_NUM_OPS,
+		[RDMA_NL_LS] = RDMA_NL_LS_NUM_OPS,
+		[RDMA_NL_NLDEV] = RDMA_NLDEV_NUM_OPS,
+	};
 
-	nl_client = kmalloc(sizeof *nl_client, GFP_KERNEL);
-	if (!nl_client)
-		return -ENOMEM;
+	/*
+	 * This BUILD_BUG_ON is intended to catch addition of new
+	 * RDMA netlink protocol without updating the array above.
+	 */
+	BUILD_BUG_ON(RDMA_NL_NUM_CLIENTS != 6);
 
-	nl_client->index	= index;
-	nl_client->nops		= nops;
-	nl_client->cb_table	= cb_table;
+	if (type >= RDMA_NL_NUM_CLIENTS)
+		return false;
 
-	mutex_lock(&ibnl_mutex);
+	return (op < max_num_ops[type]) ? true : false;
+}
 
-	list_for_each_entry(cur, &client_list, list) {
-		if (cur->index == index) {
-			pr_warn("Client for %d already exists\n", index);
-			mutex_unlock(&ibnl_mutex);
-			kfree(nl_client);
-			return -EINVAL;
-		}
+static bool is_nl_valid(unsigned int type, unsigned int op)
+{
+	const struct rdma_nl_cbs *cb_table;
+
+	if (!is_nl_msg_valid(type, op))
+		return false;
+
+	cb_table = rdma_nl_types[type].cb_table;
+#ifdef CONFIG_MODULES
+	if (!cb_table) {
+		mutex_unlock(&rdma_nl_mutex);
+		request_module("rdma-netlink-subsys-%d", type);
+		mutex_lock(&rdma_nl_mutex);
+		cb_table = rdma_nl_types[type].cb_table;
 	}
+#endif
 
-	list_add_tail(&nl_client->list, &client_list);
-
-	mutex_unlock(&ibnl_mutex);
-
-	return 0;
+	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
+		return false;
+	return true;
 }
-EXPORT_SYMBOL(ibnl_add_client);
 
-int ibnl_remove_client(int index)
+void rdma_nl_register(unsigned int index,
+		      const struct rdma_nl_cbs cb_table[])
 {
-	struct ibnl_client *cur, *next;
-
-	mutex_lock(&ibnl_mutex);
-	list_for_each_entry_safe(cur, next, &client_list, list) {
-		if (cur->index == index) {
-			list_del(&(cur->list));
-			mutex_unlock(&ibnl_mutex);
-			kfree(cur);
-			return 0;
-		}
+	mutex_lock(&rdma_nl_mutex);
+	if (!is_nl_msg_valid(index, 0)) {
+		/*
+		 * All clients are not interesting in success/failure of
+		 * this call. They want to see the print to error log and
+		 * continue their initialization. Print warning for them,
+		 * because it is programmer's error to be here.
+		 */
+		mutex_unlock(&rdma_nl_mutex);
+		WARN(true,
+		     "The not-valid %u index was supplied to RDMA netlink\n",
+		     index);
+		return;
 	}
-	pr_warn("Can't remove callback for client idx %d. Not found\n", index);
-	mutex_unlock(&ibnl_mutex);
 
-	return -EINVAL;
+	if (rdma_nl_types[index].cb_table) {
+		mutex_unlock(&rdma_nl_mutex);
+		WARN(true,
+		     "The %u index is already registered in RDMA netlink\n",
+		     index);
+		return;
+	}
+
+	rdma_nl_types[index].cb_table = cb_table;
+	mutex_unlock(&rdma_nl_mutex);
+}
+EXPORT_SYMBOL(rdma_nl_register);
+
+void rdma_nl_unregister(unsigned int index)
+{
+	mutex_lock(&rdma_nl_mutex);
+	rdma_nl_types[index].cb_table = NULL;
+	mutex_unlock(&rdma_nl_mutex);
 }
-EXPORT_SYMBOL(ibnl_remove_client);
+EXPORT_SYMBOL(rdma_nl_unregister);
 
 void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 		   int len, int client, int op, int flags)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
-			 len, flags);
+	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), len, flags);
 	if (!*nlh)
-		goto out_nlmsg_trim;
-	(*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail;
+		return NULL;
 	return nlmsg_data(*nlh);
-
-out_nlmsg_trim:
-	nlmsg_trim(skb, prev_tail);
-	return NULL;
 }
 EXPORT_SYMBOL(ibnl_put_msg);
 
 int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		  int len, void *data, int type)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	if (nla_put(skb, type, len, data))
-		goto nla_put_failure;
-	nlh->nlmsg_len += skb_tail_pointer(skb) - prev_tail;
+	if (nla_put(skb, type, len, data)) {
+		nlmsg_cancel(skb, nlh);
+		return -EMSGSIZE;
+	}
 	return 0;
-
-nla_put_failure:
-	nlmsg_trim(skb, prev_tail - nlh->nlmsg_len);
-	return -EMSGSIZE;
 }
 EXPORT_SYMBOL(ibnl_put_attr);
 
-static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
-			struct netlink_ext_ack *extack)
+static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			   struct netlink_ext_ack *extack)
 {
-	struct ibnl_client *client;
 	int type = nlh->nlmsg_type;
-	int index = RDMA_NL_GET_CLIENT(type);
+	unsigned int index = RDMA_NL_GET_CLIENT(type);
 	unsigned int op = RDMA_NL_GET_OP(type);
+	const struct rdma_nl_cbs *cb_table;
+
+	if (!is_nl_valid(index, op))
+		return -EINVAL;
+
+	cb_table = rdma_nl_types[index].cb_table;
 
-	list_for_each_entry(client, &client_list, list) {
-		if (client->index == index) {
-			if (op >= client->nops || !client->cb_table[op].dump)
-				return -EINVAL;
-
-			/*
-			 * For response or local service set_timeout request,
-			 * there is no need to use netlink_dump_start.
-			 */
-			if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-			    (index == RDMA_NL_LS &&
-			     op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
-				struct netlink_callback cb = {
-					.skb = skb,
-					.nlh = nlh,
-					.dump = client->cb_table[op].dump,
-					.module = client->cb_table[op].module,
-				};
-
-				return cb.dump(skb, &cb);
-			}
-
-			{
-				struct netlink_dump_control c = {
-					.dump = client->cb_table[op].dump,
-					.module = client->cb_table[op].module,
-				};
-				return netlink_dump_start(nls, skb, nlh, &c);
-			}
-		}
+	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
+	    !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+
+	/* FIXME: Convert IWCM to properly handle doit callbacks */
+	if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM ||
+	    index == RDMA_NL_IWCM) {
+		struct netlink_dump_control c = {
+			.dump = cb_table[op].dump,
+		};
+		return netlink_dump_start(nls, skb, nlh, &c);
 	}
 
-	pr_info("Index %d wasn't found in client list\n", index);
-	return -EINVAL;
+	if (cb_table[op].doit)
+		return cb_table[op].doit(skb, nlh, extack);
+
+	return 0;
 }
 
-static void ibnl_rcv_reply_skb(struct sk_buff *skb)
+/*
+ * This function is similar to netlink_rcv_skb with one exception:
+ * It calls to the callback for the netlink messages without NLM_F_REQUEST
+ * flag. These messages are intended for RDMA_NL_LS consumer, so it is allowed
+ * for that consumer only.
+ */
+static int rdma_nl_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
+						   struct nlmsghdr *,
+						   struct netlink_ext_ack *))
 {
+	struct netlink_ext_ack extack = {};
 	struct nlmsghdr *nlh;
-	int msglen;
+	int err;
 
-	/*
-	 * Process responses until there is no more message or the first
-	 * request. Generally speaking, it is not recommended to mix responses
-	 * with requests.
-	 */
 	while (skb->len >= nlmsg_total_size(0)) {
+		int msglen;
+
 		nlh = nlmsg_hdr(skb);
+		err = 0;
 
 		if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len)
-			return;
-
-		/* Handle response only */
-		if (nlh->nlmsg_flags & NLM_F_REQUEST)
-			return;
-
-		ibnl_rcv_msg(skb, nlh, NULL);
+			return 0;
 
+		/*
+		 * Generally speaking, the only requests are handled
+		 * by the kernel, but RDMA_NL_LS is different, because it
+		 * runs backward netlink scheme. Kernel initiates messages
+		 * and waits for reply with data to keep pathrecord cache
+		 * in sync.
+		 */
+		if (!(nlh->nlmsg_flags & NLM_F_REQUEST) &&
+		    (RDMA_NL_GET_CLIENT(nlh->nlmsg_type) != RDMA_NL_LS))
+			goto ack;
+
+		/* Skip control messages */
+		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
+			goto ack;
+
+		err = cb(skb, nlh, &extack);
+		if (err == -EINTR)
+			goto skip;
+
+ack:
+		if (nlh->nlmsg_flags & NLM_F_ACK || err)
+			netlink_ack(skb, nlh, err, &extack);
+
+skip:
 		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 		if (msglen > skb->len)
 			msglen = skb->len;
 		skb_pull(skb, msglen);
 	}
+
+	return 0;
 }
 
-static void ibnl_rcv(struct sk_buff *skb)
+static void rdma_nl_rcv(struct sk_buff *skb)
 {
-	mutex_lock(&ibnl_mutex);
-	ibnl_rcv_reply_skb(skb);
-	netlink_rcv_skb(skb, &ibnl_rcv_msg);
-	mutex_unlock(&ibnl_mutex);
+	mutex_lock(&rdma_nl_mutex);
+	rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg);
+	mutex_unlock(&rdma_nl_mutex);
 }
 
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid)
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid)
+{
+	int err;
+
+	err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT);
+	return (err < 0) ? err : 0;
+}
+EXPORT_SYMBOL(rdma_nl_unicast);
+
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid)
 {
 	int err;
 
 	err = netlink_unicast(nls, skb, pid, 0);
 	return (err < 0) ? err : 0;
 }
-EXPORT_SYMBOL(ibnl_unicast);
+EXPORT_SYMBOL(rdma_nl_unicast_wait);
 
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags)
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags)
 {
 	return nlmsg_multicast(nls, skb, 0, group, flags);
 }
-EXPORT_SYMBOL(ibnl_multicast);
+EXPORT_SYMBOL(rdma_nl_multicast);
 
-int __init ibnl_init(void)
+int __init rdma_nl_init(void)
 {
 	struct netlink_kernel_cfg cfg = {
-		.input	= ibnl_rcv,
+		.input	= rdma_nl_rcv,
 	};
 
 	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
-	if (!nls) {
-		pr_warn("Failed to create netlink socket\n");
+	if (!nls)
 		return -ENOMEM;
-	}
 
 	nls->sk_sndtimeo = 10 * HZ;
 	return 0;
 }
 
-void ibnl_cleanup(void)
+void rdma_nl_exit(void)
 {
-	struct ibnl_client *cur, *next;
+	int idx;
 
-	mutex_lock(&ibnl_mutex);
-	list_for_each_entry_safe(cur, next, &client_list, list) {
-		list_del(&(cur->list));
-		kfree(cur);
-	}
-	mutex_unlock(&ibnl_mutex);
+	for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
+		rdma_nl_unregister(idx);
 
 	netlink_kernel_release(nls);
 }
+
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_RDMA);
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
new file mode 100644
index 000000000000..3ba24c428c3b
--- /dev/null
+++ b/drivers/infiniband/core/nldev.c
@@ -0,0 +1,325 @@
+/*
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ *
+ * 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.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * 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/module.h>
+#include <net/netlink.h>
+#include <rdma/rdma_netlink.h>
+
+#include "core_priv.h"
+
+static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
+	[RDMA_NLDEV_ATTR_DEV_INDEX]     = { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_DEV_NAME]	= { .type = NLA_NUL_STRING,
+					    .len = IB_DEVICE_NAME_MAX - 1},
+	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_FW_VERSION]	= { .type = NLA_NUL_STRING,
+					    .len = IB_FW_VERSION_NAME_MAX - 1},
+	[RDMA_NLDEV_ATTR_NODE_GUID]	= { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_SUBNET_PREFIX]	= { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_LID]		= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_SM_LID]	= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_LMC]		= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_PORT_STATE]	= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 },
+};
+
+static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
+{
+	char fw[IB_FW_VERSION_NAME_MAX];
+
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device)))
+		return -EMSGSIZE;
+
+	BUILD_BUG_ON(sizeof(device->attrs.device_cap_flags) != sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      device->attrs.device_cap_flags, 0))
+		return -EMSGSIZE;
+
+	ib_get_device_fw_str(device, fw);
+	/* Device without FW has strlen(fw) */
+	if (strlen(fw) && nla_put_string(msg, RDMA_NLDEV_ATTR_FW_VERSION, fw))
+		return -EMSGSIZE;
+
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_NODE_GUID,
+			      be64_to_cpu(device->node_guid), 0))
+		return -EMSGSIZE;
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,
+			      be64_to_cpu(device->attrs.sys_image_guid), 0))
+		return -EMSGSIZE;
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int fill_port_info(struct sk_buff *msg,
+			  struct ib_device *device, u32 port)
+{
+	struct ib_port_attr attr;
+	int ret;
+
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
+		return -EMSGSIZE;
+
+	ret = ib_query_port(device, port, &attr);
+	if (ret)
+		return ret;
+
+	BUILD_BUG_ON(sizeof(attr.port_cap_flags) > sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      (u64)attr.port_cap_flags, 0))
+		return -EMSGSIZE;
+	if (rdma_protocol_ib(device, port) &&
+	    nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX,
+			      attr.subnet_prefix, 0))
+		return -EMSGSIZE;
+	if (rdma_protocol_ib(device, port)) {
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_LID, attr.lid))
+			return -EMSGSIZE;
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_SM_LID, attr.sm_lid))
+			return -EMSGSIZE;
+		if (nla_put_u8(msg, RDMA_NLDEV_ATTR_LMC, attr.lmc))
+			return -EMSGSIZE;
+	}
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_STATE, attr.state))
+		return -EMSGSIZE;
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_PHYS_STATE, attr.phys_state))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_dev_info(msg, device);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
+static int _nldev_get_dumpit(struct ib_device *device,
+			     struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     unsigned int idx)
+{
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+
+	if (idx < start)
+		return 0;
+
+	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, NLM_F_MULTI);
+
+	if (fill_dev_info(skb, device)) {
+		nlmsg_cancel(skb, nlh);
+		goto out;
+	}
+
+	nlmsg_end(skb, nlh);
+
+	idx++;
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
+static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	/*
+	 * There is no need to take lock, because
+	 * we are relying on ib_core's lists_rwsem
+	 */
+	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
+}
+
+static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	u32 port;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	if (!rdma_is_port_valid(device, port))
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_port_info(msg, device, port);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
+static int nldev_port_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+	u32 idx = 0;
+	u32 ifindex;
+	int err;
+	u32 p;
+
+	err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, NULL);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(ifindex);
+	if (!device)
+		return -EINVAL;
+
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
+		/*
+		 * The dumpit function returns all information from specific
+		 * index. This specific index is taken from the netlink
+		 * messages request sent by user and it is available
+		 * in cb->args[0].
+		 *
+		 * Usually, the user doesn't fill this field and it causes
+		 * to return everything.
+		 *
+		 */
+		if (idx < start) {
+			idx++;
+			continue;
+		}
+
+		nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+				cb->nlh->nlmsg_seq,
+				RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+						 RDMA_NLDEV_CMD_PORT_GET),
+				0, NLM_F_MULTI);
+
+		if (fill_port_info(skb, device, p)) {
+			nlmsg_cancel(skb, nlh);
+			goto out;
+		}
+		idx++;
+		nlmsg_end(skb, nlh);
+	}
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
+static const struct rdma_nl_cbs nldev_cb_table[] = {
+	[RDMA_NLDEV_CMD_GET] = {
+		.doit = nldev_get_doit,
+		.dump = nldev_get_dumpit,
+	},
+	[RDMA_NLDEV_CMD_PORT_GET] = {
+		.doit = nldev_port_get_doit,
+		.dump = nldev_port_get_dumpit,
+	},
+};
+
+void __init nldev_init(void)
+{
+	rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table);
+}
+
+void __exit nldev_exit(void)
+{
+	rdma_nl_unregister(RDMA_NL_NLDEV);
+}
+
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_NLDEV, 5);
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 41c31a2bf093..85b5ee4defa4 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -35,10 +35,57 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/uverbs_types.h>
 #include <linux/rcupdate.h>
+#include <rdma/uverbs_ioctl.h>
+#include <rdma/rdma_user_ioctl.h>
 #include "uverbs.h"
 #include "core_priv.h"
 #include "rdma_core.h"
 
+int uverbs_ns_idx(u16 *id, unsigned int ns_count)
+{
+	int ret = (*id & UVERBS_ID_NS_MASK) >> UVERBS_ID_NS_SHIFT;
+
+	if (ret >= ns_count)
+		return -EINVAL;
+
+	*id &= ~UVERBS_ID_NS_MASK;
+	return ret;
+}
+
+const struct uverbs_object_spec *uverbs_get_object(const struct ib_device *ibdev,
+						   uint16_t object)
+{
+	const struct uverbs_root_spec *object_hash = ibdev->specs_root;
+	const struct uverbs_object_spec_hash *objects;
+	int ret = uverbs_ns_idx(&object, object_hash->num_buckets);
+
+	if (ret < 0)
+		return NULL;
+
+	objects = object_hash->object_buckets[ret];
+
+	if (object >= objects->num_objects)
+		return NULL;
+
+	return objects->objects[object];
+}
+
+const struct uverbs_method_spec *uverbs_get_method(const struct uverbs_object_spec *object,
+						   uint16_t method)
+{
+	const struct uverbs_method_spec_hash *methods;
+	int ret = uverbs_ns_idx(&method, object->num_buckets);
+
+	if (ret < 0)
+		return NULL;
+
+	methods = object->method_buckets[ret];
+	if (method >= methods->num_methods)
+		return NULL;
+
+	return methods->methods[method];
+}
+
 void uverbs_uobject_get(struct ib_uobject *uobject)
 {
 	kref_get(&uobject->ref);
@@ -404,6 +451,41 @@ int __must_check rdma_remove_commit_uobject(struct ib_uobject *uobj)
 	return ret;
 }
 
+static int null_obj_type_class_remove_commit(struct ib_uobject *uobj,
+					     enum rdma_remove_reason why)
+{
+	return 0;
+}
+
+static const struct uverbs_obj_type null_obj_type = {
+	.type_class = &((const struct uverbs_obj_type_class){
+			.remove_commit = null_obj_type_class_remove_commit,
+			/* be cautious */
+			.needs_kfree_rcu = true}),
+};
+
+int rdma_explicit_destroy(struct ib_uobject *uobject)
+{
+	int ret;
+	struct ib_ucontext *ucontext = uobject->context;
+
+	/* Cleanup is running. Calling this should have been impossible */
+	if (!down_read_trylock(&ucontext->cleanup_rwsem)) {
+		WARN(true, "ib_uverbs: Cleanup is running while removing an uobject\n");
+		return 0;
+	}
+	lockdep_check(uobject, true);
+	ret = uobject->type->type_class->remove_commit(uobject,
+						       RDMA_REMOVE_DESTROY);
+	if (ret)
+		return ret;
+
+	uobject->type = &null_obj_type;
+
+	up_read(&ucontext->cleanup_rwsem);
+	return 0;
+}
+
 static void alloc_commit_idr_uobject(struct ib_uobject *uobj)
 {
 	uverbs_uobject_add(uobj);
@@ -625,3 +707,100 @@ const struct uverbs_obj_type_class uverbs_fd_class = {
 	.needs_kfree_rcu = false,
 };
 
+struct ib_uobject *uverbs_get_uobject_from_context(const struct uverbs_obj_type *type_attrs,
+						   struct ib_ucontext *ucontext,
+						   enum uverbs_obj_access access,
+						   int id)
+{
+	switch (access) {
+	case UVERBS_ACCESS_READ:
+		return rdma_lookup_get_uobject(type_attrs, ucontext, id, false);
+	case UVERBS_ACCESS_DESTROY:
+	case UVERBS_ACCESS_WRITE:
+		return rdma_lookup_get_uobject(type_attrs, ucontext, id, true);
+	case UVERBS_ACCESS_NEW:
+		return rdma_alloc_begin_uobject(type_attrs, ucontext);
+	default:
+		WARN_ON(true);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+}
+
+int uverbs_finalize_object(struct ib_uobject *uobj,
+			   enum uverbs_obj_access access,
+			   bool commit)
+{
+	int ret = 0;
+
+	/*
+	 * refcounts should be handled at the object level and not at the
+	 * uobject level. Refcounts of the objects themselves are done in
+	 * handlers.
+	 */
+
+	switch (access) {
+	case UVERBS_ACCESS_READ:
+		rdma_lookup_put_uobject(uobj, false);
+		break;
+	case UVERBS_ACCESS_WRITE:
+		rdma_lookup_put_uobject(uobj, true);
+		break;
+	case UVERBS_ACCESS_DESTROY:
+		if (commit)
+			ret = rdma_remove_commit_uobject(uobj);
+		else
+			rdma_lookup_put_uobject(uobj, true);
+		break;
+	case UVERBS_ACCESS_NEW:
+		if (commit)
+			ret = rdma_alloc_commit_uobject(uobj);
+		else
+			rdma_alloc_abort_uobject(uobj);
+		break;
+	default:
+		WARN_ON(true);
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+int uverbs_finalize_objects(struct uverbs_attr_bundle *attrs_bundle,
+			    struct uverbs_attr_spec_hash * const *spec_hash,
+			    size_t num,
+			    bool commit)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < num; i++) {
+		struct uverbs_attr_bundle_hash *curr_bundle =
+			&attrs_bundle->hash[i];
+		const struct uverbs_attr_spec_hash *curr_spec_bucket =
+			spec_hash[i];
+		unsigned int j;
+
+		for (j = 0; j < curr_bundle->num_attrs; j++) {
+			struct uverbs_attr *attr;
+			const struct uverbs_attr_spec *spec;
+
+			if (!uverbs_attr_is_valid_in_hash(curr_bundle, j))
+				continue;
+
+			attr = &curr_bundle->attrs[j];
+			spec = &curr_spec_bucket->attrs[j];
+
+			if (spec->type == UVERBS_ATTR_TYPE_IDR ||
+			    spec->type == UVERBS_ATTR_TYPE_FD) {
+				int current_ret;
+
+				current_ret = uverbs_finalize_object(attr->obj_attr.uobject,
+								     spec->obj.access,
+								     commit);
+				if (!ret)
+					ret = current_ret;
+			}
+		}
+	}
+	return ret;
+}
diff --git a/drivers/infiniband/core/rdma_core.h b/drivers/infiniband/core/rdma_core.h
index 1b82e7ff7fe8..1efcf93238dd 100644
--- a/drivers/infiniband/core/rdma_core.h
+++ b/drivers/infiniband/core/rdma_core.h
@@ -39,9 +39,15 @@
 
 #include <linux/idr.h>
 #include <rdma/uverbs_types.h>
+#include <rdma/uverbs_ioctl.h>
 #include <rdma/ib_verbs.h>
 #include <linux/mutex.h>
 
+int uverbs_ns_idx(u16 *id, unsigned int ns_count);
+const struct uverbs_object_spec *uverbs_get_object(const struct ib_device *ibdev,
+						   uint16_t object);
+const struct uverbs_method_spec *uverbs_get_method(const struct uverbs_object_spec *object,
+						   uint16_t method);
 /*
  * These functions initialize the context and cleanups its uobjects.
  * The context has a list of objects which is protected by a mutex
@@ -75,4 +81,40 @@ void uverbs_uobject_put(struct ib_uobject *uobject);
  */
 void uverbs_close_fd(struct file *f);
 
+/*
+ * Get an ib_uobject that corresponds to the given id from ucontext, assuming
+ * the object is from the given type. Lock it to the required access when
+ * applicable.
+ * This function could create (access == NEW), destroy (access == DESTROY)
+ * or unlock (access == READ || access == WRITE) objects if required.
+ * The action will be finalized only when uverbs_finalize_object or
+ * uverbs_finalize_objects are called.
+ */
+struct ib_uobject *uverbs_get_uobject_from_context(const struct uverbs_obj_type *type_attrs,
+						   struct ib_ucontext *ucontext,
+						   enum uverbs_obj_access access,
+						   int id);
+int uverbs_finalize_object(struct ib_uobject *uobj,
+			   enum uverbs_obj_access access,
+			   bool commit);
+/*
+ * Note that certain finalize stages could return a status:
+ *   (a) alloc_commit could return a failure if the object is committed at the
+ *       same time when the context is destroyed.
+ *   (b) remove_commit could fail if the object wasn't destroyed successfully.
+ * Since multiple objects could be finalized in one transaction, it is very NOT
+ * recommended to have several finalize actions which have side effects.
+ * For example, it's NOT recommended to have a certain action which has both
+ * a commit action and a destroy action or two destroy objects in the same
+ * action. The rule of thumb is to have one destroy or commit action with
+ * multiple lookups.
+ * The first non zero return value of finalize_object is returned from this
+ * function. For example, this could happen when we couldn't destroy an
+ * object.
+ */
+int uverbs_finalize_objects(struct uverbs_attr_bundle *attrs_bundle,
+			    struct uverbs_attr_spec_hash * const *spec_hash,
+			    size_t num,
+			    bool commit);
+
 #endif /* RDMA_CORE_H */
diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index 94a9eefb3cfc..90e3889b7fbe 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -44,6 +44,8 @@
 
 static struct workqueue_struct *gid_cache_wq;
 
+static struct workqueue_struct *gid_cache_wq;
+
 enum gid_op_type {
 	GID_DEL = 0,
 	GID_ADD
diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index dbfd854c32c9..6ca607e8e293 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -643,6 +643,30 @@ void rdma_rw_ctx_destroy_signature(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 }
 EXPORT_SYMBOL(rdma_rw_ctx_destroy_signature);
 
+/**
+ * rdma_rw_mr_factor - return number of MRs required for a payload
+ * @device:	device handling the connection
+ * @port_num:	port num to which the connection is bound
+ * @maxpages:	maximum payload pages per rdma_rw_ctx
+ *
+ * Returns the number of MRs the device requires to move @maxpayload
+ * bytes. The returned value is used during transport creation to
+ * compute max_rdma_ctxts and the size of the transport's Send and
+ * Send Completion Queues.
+ */
+unsigned int rdma_rw_mr_factor(struct ib_device *device, u8 port_num,
+			       unsigned int maxpages)
+{
+	unsigned int mr_pages;
+
+	if (rdma_rw_can_use_mr(device, port_num))
+		mr_pages = rdma_rw_fr_page_list_len(device);
+	else
+		mr_pages = device->attrs.max_sge_rd;
+	return DIV_ROUND_UP(maxpages, mr_pages);
+}
+EXPORT_SYMBOL(rdma_rw_mr_factor);
+
 void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr)
 {
 	u32 factor;
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 70fa4cabe48e..ab5e1024fea9 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -50,6 +50,7 @@
 #include <uapi/rdma/ib_user_sa.h>
 #include <rdma/ib_marshall.h>
 #include <rdma/ib_addr.h>
+#include <rdma/opa_addr.h>
 #include "sa.h"
 #include "core_priv.h"
 
@@ -861,7 +862,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
 	if (!ret)
 		ret = len;
 	else
@@ -1021,9 +1022,9 @@ static void ib_nl_request_timeout(struct work_struct *work)
 }
 
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	int timeout, delta, abs_delta;
 	const struct nlattr *attr;
 	unsigned long flags;
@@ -1033,8 +1034,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 	int ret;
 
 	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
@@ -1098,9 +1098,9 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb)
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	unsigned long flags;
 	struct ib_sa_query *query;
 	struct ib_mad_send_buf *send_buf;
@@ -1109,8 +1109,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb,
 	int ret;
 
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	spin_lock_irqsave(&ib_nl_request_lock, flags);
@@ -1241,6 +1240,11 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 	ah_attr->type = rdma_ah_find_type(device, port_num);
 
 	rdma_ah_set_dlid(ah_attr, be32_to_cpu(sa_path_get_dlid(rec)));
+
+	if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) &&
+	    (rdma_ah_get_dlid(ah_attr) == be16_to_cpu(IB_LID_PERMISSIVE)))
+		rdma_ah_set_make_grd(ah_attr, true);
+
 	rdma_ah_set_sl(ah_attr, rec->sl);
 	rdma_ah_set_path_bits(ah_attr, be32_to_cpu(sa_path_get_slid(rec)) &
 			      get_src_path_mask(device, port_num));
@@ -1420,7 +1424,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 
 	if ((query->flags & IB_SA_ENABLE_LOCAL_SERVICE) &&
 	    (!(query->flags & IB_SA_QUERY_OPA))) {
-		if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) {
+		if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) {
 			if (!ib_nl_make_request(query, gfp_mask))
 				return id;
 		}
@@ -2290,12 +2294,15 @@ static void update_sm_ah(struct work_struct *work)
 	rdma_ah_set_sl(&ah_attr, port_attr.sm_sl);
 	rdma_ah_set_port_num(&ah_attr, port->port_num);
 	if (port_attr.grh_required) {
-		rdma_ah_set_ah_flags(&ah_attr, IB_AH_GRH);
-
-		rdma_ah_set_subnet_prefix(&ah_attr,
-					  cpu_to_be64(port_attr.subnet_prefix));
-		rdma_ah_set_interface_id(&ah_attr,
-					 cpu_to_be64(IB_SA_WELL_KNOWN_GUID));
+		if (ah_attr.type == RDMA_AH_ATTR_TYPE_OPA) {
+			rdma_ah_set_make_grd(&ah_attr, true);
+		} else {
+			rdma_ah_set_ah_flags(&ah_attr, IB_AH_GRH);
+			rdma_ah_set_subnet_prefix(&ah_attr,
+						  cpu_to_be64(port_attr.subnet_prefix));
+			rdma_ah_set_interface_id(&ah_attr,
+						 cpu_to_be64(IB_SA_WELL_KNOWN_GUID));
+		}
 	}
 
 	new_ah->ah = rdma_create_ah(port->agent->qp->pd, &ah_attr);
@@ -2410,8 +2417,7 @@ static void ib_sa_add_one(struct ib_device *device)
 	 */
 
 	INIT_IB_EVENT_HANDLER(&sa_dev->event_handler, device, ib_sa_event);
-	if (ib_register_event_handler(&sa_dev->event_handler))
-		goto err;
+	ib_register_event_handler(&sa_dev->event_handler);
 
 	for (i = 0; i <= e - s; ++i) {
 		if (rdma_cap_ib_sa(device, i + 1))
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 7ebe1ef23652..abc5ab581f82 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -1210,8 +1210,8 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
 {
 	struct ib_device *dev = container_of(device, struct ib_device, dev);
 
-	ib_get_device_fw_str(dev, buf, PAGE_SIZE);
-	strlcat(buf, "\n", PAGE_SIZE);
+	ib_get_device_fw_str(dev, buf);
+	strlcat(buf, "\n", IB_FW_VERSION_NAME_MAX);
 	return strlen(buf);
 }
 
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index 112099c86a19..f2a7f62c2834 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -618,7 +618,7 @@ static ssize_t ib_ucm_init_qp_attr(struct ib_ucm_file *file,
 	if (result)
 		goto out;
 
-	ib_copy_qp_attr_to_user(&resp, &qp_attr);
+	ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr);
 
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,
 			 &resp, sizeof(resp)))
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 276f0ef835bd..eb85b546e223 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -248,14 +248,15 @@ static void ucma_copy_conn_event(struct rdma_ucm_conn_param *dst,
 	dst->qp_num = src->qp_num;
 }
 
-static void ucma_copy_ud_event(struct rdma_ucm_ud_param *dst,
+static void ucma_copy_ud_event(struct ib_device *device,
+			       struct rdma_ucm_ud_param *dst,
 			       struct rdma_ud_param *src)
 {
 	if (src->private_data_len)
 		memcpy(dst->private_data, src->private_data,
 		       src->private_data_len);
 	dst->private_data_len = src->private_data_len;
-	ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr);
 	dst->qp_num = src->qp_num;
 	dst->qkey = src->qkey;
 }
@@ -335,7 +336,8 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
 	uevent->resp.event = event->event;
 	uevent->resp.status = event->status;
 	if (cm_id->qp_type == IB_QPT_UD)
-		ucma_copy_ud_event(&uevent->resp.param.ud, &event->param.ud);
+		ucma_copy_ud_event(cm_id->device, &uevent->resp.param.ud,
+				   &event->param.ud);
 	else
 		ucma_copy_conn_event(&uevent->resp.param.conn,
 				     &event->param.conn);
@@ -1157,7 +1159,7 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file,
 	if (ret)
 		goto out;
 
-	ib_copy_qp_attr_to_user(&resp, &qp_attr);
+	ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr);
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,
 			 &resp, sizeof(resp)))
 		ret = -EFAULT;
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 8c4ec564e495..55e8f5ed8b3c 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -166,24 +166,6 @@ static int invalidate_page_trampoline(struct ib_umem *item, u64 start,
 	return 0;
 }
 
-static void ib_umem_notifier_invalidate_page(struct mmu_notifier *mn,
-					     struct mm_struct *mm,
-					     unsigned long address)
-{
-	struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn);
-
-	if (!context->invalidate_range)
-		return;
-
-	ib_ucontext_notifier_start_account(context);
-	down_read(&context->umem_rwsem);
-	rbt_ib_umem_for_each_in_range(&context->umem_tree, address,
-				      address + PAGE_SIZE,
-				      invalidate_page_trampoline, NULL);
-	up_read(&context->umem_rwsem);
-	ib_ucontext_notifier_end_account(context);
-}
-
 static int invalidate_range_start_trampoline(struct ib_umem *item, u64 start,
 					     u64 end, void *cookie)
 {
@@ -237,7 +219,6 @@ static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn,
 
 static const struct mmu_notifier_ops ib_umem_notifiers = {
 	.release                    = ib_umem_notifier_release,
-	.invalidate_page            = ib_umem_notifier_invalidate_page,
 	.invalidate_range_start     = ib_umem_notifier_invalidate_range_start,
 	.invalidate_range_end       = ib_umem_notifier_invalidate_range_end,
 };
diff --git a/drivers/infiniband/core/umem_rbtree.c b/drivers/infiniband/core/umem_rbtree.c
index d176597b4d78..fc801920e341 100644
--- a/drivers/infiniband/core/umem_rbtree.c
+++ b/drivers/infiniband/core/umem_rbtree.c
@@ -72,7 +72,7 @@ INTERVAL_TREE_DEFINE(struct umem_odp_node, rb, u64, __subtree_last,
 /* @last is not a part of the interval. See comment for function
  * node_last.
  */
-int rbt_ib_umem_for_each_in_range(struct rb_root *root,
+int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
 				  u64 start, u64 last,
 				  umem_call_back cb,
 				  void *cookie)
@@ -95,7 +95,7 @@ int rbt_ib_umem_for_each_in_range(struct rb_root *root,
 }
 EXPORT_SYMBOL(rbt_ib_umem_for_each_in_range);
 
-struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root *root,
+struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root_cached *root,
 				       u64 addr, u64 length)
 {
 	struct umem_odp_node *node;
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 36a6f5c8914c..c1696e6084b2 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -229,7 +229,7 @@ static void recv_handler(struct ib_mad_agent *agent,
 	packet->mad.hdr.status	   = 0;
 	packet->mad.hdr.length	   = hdr_size(file) + mad_recv_wc->mad_len;
 	packet->mad.hdr.qpn	   = cpu_to_be32(mad_recv_wc->wc->src_qp);
-	packet->mad.hdr.lid	   = cpu_to_be16(mad_recv_wc->wc->slid);
+	packet->mad.hdr.lid	   = ib_lid_be16(mad_recv_wc->wc->slid);
 	packet->mad.hdr.sl	   = mad_recv_wc->wc->sl;
 	packet->mad.hdr.path_bits  = mad_recv_wc->wc->dlid_path_bits;
 	packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index;
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 64d494a64daf..37c8903e7fd0 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -100,6 +100,7 @@ struct ib_uverbs_device {
 	struct mutex				lists_mutex; /* protect lists */
 	struct list_head			uverbs_file_list;
 	struct list_head			uverbs_events_file_list;
+	struct uverbs_root_spec			*specs_root;
 };
 
 struct ib_uverbs_event_queue {
@@ -218,6 +219,8 @@ int uverbs_dealloc_mw(struct ib_mw *mw);
 void ib_uverbs_detach_umcast(struct ib_qp *qp,
 			     struct ib_uqp_object *uobj);
 
+long ib_uverbs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+
 struct ib_uverbs_flow_spec {
 	union {
 		union {
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index c551d2b275fd..4ab30d832ac5 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -91,9 +91,10 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 		goto err;
 	}
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	ret = ib_rdmacg_try_charge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
 	if (ret)
@@ -117,7 +118,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	ucontext->closing = 0;
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	ucontext->umem_tree = RB_ROOT;
+	ucontext->umem_tree = RB_ROOT_CACHED;
 	init_rwsem(&ucontext->umem_rwsem);
 	ucontext->odp_mrs_count = 0;
 	INIT_LIST_HEAD(&ucontext->no_private_counters);
@@ -275,8 +276,14 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file,
 	resp.bad_pkey_cntr   = attr.bad_pkey_cntr;
 	resp.qkey_viol_cntr  = attr.qkey_viol_cntr;
 	resp.pkey_tbl_len    = attr.pkey_tbl_len;
-	resp.lid 	     = attr.lid;
-	resp.sm_lid 	     = attr.sm_lid;
+
+	if (rdma_cap_opa_ah(ib_dev, cmd.port_num)) {
+		resp.lid     = OPA_TO_IB_UCAST_LID(attr.lid);
+		resp.sm_lid  = OPA_TO_IB_UCAST_LID(attr.sm_lid);
+	} else {
+		resp.lid     = ib_lid_cpu16(attr.lid);
+		resp.sm_lid  = ib_lid_cpu16(attr.sm_lid);
+	}
 	resp.lmc 	     = attr.lmc;
 	resp.max_vl_num      = attr.max_vl_num;
 	resp.sm_sl 	     = attr.sm_sl;
@@ -313,9 +320,10 @@ ssize_t ib_uverbs_alloc_pd(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	uobj  = uobj_alloc(uobj_get_type(pd), file->ucontext);
 	if (IS_ERR(uobj))
@@ -482,9 +490,10 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof  resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	mutex_lock(&file->device->xrcd_tree_mutex);
 
@@ -646,9 +655,10 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	if ((cmd.start & ~PAGE_MASK) != (cmd.hca_va & ~PAGE_MASK))
 		return -EINVAL;
@@ -740,7 +750,8 @@ ssize_t ib_uverbs_rereg_mr(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&udata, buf + sizeof(cmd),
 		   (unsigned long) cmd.response + sizeof(resp),
-		   in_len - sizeof(cmd), out_len - sizeof(resp));
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	if (cmd.flags & ~IB_MR_REREG_SUPPORTED || !cmd.flags)
 		return -EINVAL;
@@ -1015,7 +1026,7 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file,
 	cq->uobject       = &obj->uobject;
 	cq->comp_handler  = ib_uverbs_comp_handler;
 	cq->event_handler = ib_uverbs_cq_event_handler;
-	cq->cq_context    = &ev_file->ev_queue;
+	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
 	atomic_set(&cq->usecnt, 0);
 
 	obj->uobject.object = cq;
@@ -1080,7 +1091,8 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&uhw, buf + sizeof(cmd),
 		   (unsigned long)cmd.response + sizeof(resp),
-		   in_len - sizeof(cmd), out_len - sizeof(resp));
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	memset(&cmd_ex, 0, sizeof(cmd_ex));
 	cmd_ex.user_handle = cmd.user_handle;
@@ -1161,9 +1173,10 @@ ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	cq = uobj_get_obj_read(cq, cmd.cq_handle, file->ucontext);
 	if (!cq)
@@ -1185,7 +1198,8 @@ out:
 	return ret ? ret : in_len;
 }
 
-static int copy_wc_to_user(void __user *dest, struct ib_wc *wc)
+static int copy_wc_to_user(struct ib_device *ib_dev, void __user *dest,
+			   struct ib_wc *wc)
 {
 	struct ib_uverbs_wc tmp;
 
@@ -1199,7 +1213,10 @@ static int copy_wc_to_user(void __user *dest, struct ib_wc *wc)
 	tmp.src_qp		= wc->src_qp;
 	tmp.wc_flags		= wc->wc_flags;
 	tmp.pkey_index		= wc->pkey_index;
-	tmp.slid		= wc->slid;
+	if (rdma_cap_opa_ah(ib_dev, wc->port_num))
+		tmp.slid	= OPA_TO_IB_UCAST_LID(wc->slid);
+	else
+		tmp.slid	= ib_lid_cpu16(wc->slid);
 	tmp.sl			= wc->sl;
 	tmp.dlid_path_bits	= wc->dlid_path_bits;
 	tmp.port_num		= wc->port_num;
@@ -1243,7 +1260,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file,
 		if (!ret)
 			break;
 
-		ret = copy_wc_to_user(data_ptr, &wc);
+		ret = copy_wc_to_user(ib_dev, data_ptr, &wc);
 		if (ret)
 			goto out_put;
 
@@ -1383,8 +1400,9 @@ static int create_qp(struct ib_uverbs_file *file,
 		attr.rwq_ind_tbl = ind_tbl;
 	}
 
-	if ((cmd_sz >= offsetof(typeof(*cmd), reserved1) +
-		       sizeof(cmd->reserved1)) && cmd->reserved1) {
+	if (cmd_sz > sizeof(*cmd) &&
+	    !ib_is_udata_cleared(ucore, sizeof(*cmd),
+				 cmd_sz - sizeof(*cmd))) {
 		ret = -EOPNOTSUPP;
 		goto err_put;
 	}
@@ -1420,7 +1438,7 @@ static int create_qp(struct ib_uverbs_file *file,
 			if (cmd->is_srq) {
 				srq = uobj_get_obj_read(srq, cmd->srq_handle,
 							file->ucontext);
-				if (!srq || srq->srq_type != IB_SRQT_BASIC) {
+				if (!srq || srq->srq_type == IB_SRQT_XRC) {
 					ret = -EINVAL;
 					goto err_put;
 				}
@@ -1482,11 +1500,21 @@ static int create_qp(struct ib_uverbs_file *file,
 				IB_QP_CREATE_MANAGED_SEND |
 				IB_QP_CREATE_MANAGED_RECV |
 				IB_QP_CREATE_SCATTER_FCS |
-				IB_QP_CREATE_CVLAN_STRIPPING)) {
+				IB_QP_CREATE_CVLAN_STRIPPING |
+				IB_QP_CREATE_SOURCE_QPN)) {
 		ret = -EINVAL;
 		goto err_put;
 	}
 
+	if (attr.create_flags & IB_QP_CREATE_SOURCE_QPN) {
+		if (!capable(CAP_NET_RAW)) {
+			ret = -EPERM;
+			goto err_put;
+		}
+
+		attr.source_qpn = cmd->source_qpn;
+	}
+
 	buf = (void *)cmd + sizeof(*cmd);
 	if (cmd_sz > sizeof(*cmd))
 		if (!(buf[0] == 0 && !memcmp(buf, buf + 1,
@@ -1522,6 +1550,7 @@ static int create_qp(struct ib_uverbs_file *file,
 		qp->qp_type	  = attr.qp_type;
 		atomic_set(&qp->usecnt, 0);
 		atomic_inc(&pd->usecnt);
+		qp->port = 0;
 		if (attr.send_cq)
 			atomic_inc(&attr.send_cq->usecnt);
 		if (attr.recv_cq)
@@ -1721,9 +1750,10 @@ ssize_t ib_uverbs_open_qp(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	obj  = (struct ib_uqp_object *)uobj_alloc(uobj_get_type(qp),
 						  file->ucontext);
@@ -1790,6 +1820,28 @@ err_put:
 	return ret;
 }
 
+static void copy_ah_attr_to_uverbs(struct ib_uverbs_qp_dest *uverb_attr,
+				   struct rdma_ah_attr *rdma_attr)
+{
+	const struct ib_global_route   *grh;
+
+	uverb_attr->dlid              = rdma_ah_get_dlid(rdma_attr);
+	uverb_attr->sl                = rdma_ah_get_sl(rdma_attr);
+	uverb_attr->src_path_bits     = rdma_ah_get_path_bits(rdma_attr);
+	uverb_attr->static_rate       = rdma_ah_get_static_rate(rdma_attr);
+	uverb_attr->is_global         = !!(rdma_ah_get_ah_flags(rdma_attr) &
+					 IB_AH_GRH);
+	if (uverb_attr->is_global) {
+		grh = rdma_ah_read_grh(rdma_attr);
+		memcpy(uverb_attr->dgid, grh->dgid.raw, 16);
+		uverb_attr->flow_label        = grh->flow_label;
+		uverb_attr->sgid_index        = grh->sgid_index;
+		uverb_attr->hop_limit         = grh->hop_limit;
+		uverb_attr->traffic_class     = grh->traffic_class;
+	}
+	uverb_attr->port_num          = rdma_ah_get_port_num(rdma_attr);
+}
+
 ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file,
 			   struct ib_device *ib_dev,
 			   const char __user *buf, int in_len,
@@ -1800,7 +1852,6 @@ ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file,
 	struct ib_qp                   *qp;
 	struct ib_qp_attr              *attr;
 	struct ib_qp_init_attr         *init_attr;
-	const struct ib_global_route   *grh;
 	int                            ret;
 
 	if (copy_from_user(&cmd, buf, sizeof cmd))
@@ -1850,39 +1901,8 @@ ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file,
 	resp.alt_port_num           = attr->alt_port_num;
 	resp.alt_timeout            = attr->alt_timeout;
 
-	resp.dest.dlid              = rdma_ah_get_dlid(&attr->ah_attr);
-	resp.dest.sl                = rdma_ah_get_sl(&attr->ah_attr);
-	resp.dest.src_path_bits     = rdma_ah_get_path_bits(&attr->ah_attr);
-	resp.dest.static_rate       = rdma_ah_get_static_rate(&attr->ah_attr);
-	resp.dest.is_global         = !!(rdma_ah_get_ah_flags(&attr->ah_attr) &
-					 IB_AH_GRH);
-	if (resp.dest.is_global) {
-		grh = rdma_ah_read_grh(&attr->ah_attr);
-		memcpy(resp.dest.dgid, grh->dgid.raw, 16);
-		resp.dest.flow_label        = grh->flow_label;
-		resp.dest.sgid_index        = grh->sgid_index;
-		resp.dest.hop_limit         = grh->hop_limit;
-		resp.dest.traffic_class     = grh->traffic_class;
-	}
-	resp.dest.port_num          = rdma_ah_get_port_num(&attr->ah_attr);
-
-	resp.alt_dest.dlid          = rdma_ah_get_dlid(&attr->alt_ah_attr);
-	resp.alt_dest.sl            = rdma_ah_get_sl(&attr->alt_ah_attr);
-	resp.alt_dest.src_path_bits = rdma_ah_get_path_bits(&attr->alt_ah_attr);
-	resp.alt_dest.static_rate
-			= rdma_ah_get_static_rate(&attr->alt_ah_attr);
-	resp.alt_dest.is_global
-			= !!(rdma_ah_get_ah_flags(&attr->alt_ah_attr) &
-						  IB_AH_GRH);
-	if (resp.alt_dest.is_global) {
-		grh = rdma_ah_read_grh(&attr->alt_ah_attr);
-		memcpy(resp.alt_dest.dgid, grh->dgid.raw, 16);
-		resp.alt_dest.flow_label    = grh->flow_label;
-		resp.alt_dest.sgid_index    = grh->sgid_index;
-		resp.alt_dest.hop_limit     = grh->hop_limit;
-		resp.alt_dest.traffic_class = grh->traffic_class;
-	}
-	resp.alt_dest.port_num      = rdma_ah_get_port_num(&attr->alt_ah_attr);
+	copy_ah_attr_to_uverbs(&resp.dest, &attr->ah_attr);
+	copy_ah_attr_to_uverbs(&resp.alt_dest, &attr->alt_ah_attr);
 
 	resp.max_send_wr            = init_attr->cap.max_send_wr;
 	resp.max_recv_wr            = init_attr->cap.max_recv_wr;
@@ -1916,6 +1936,29 @@ static int modify_qp_mask(enum ib_qp_type qp_type, int mask)
 	}
 }
 
+static void copy_ah_attr_from_uverbs(struct ib_device *dev,
+				     struct rdma_ah_attr *rdma_attr,
+				     struct ib_uverbs_qp_dest *uverb_attr)
+{
+	rdma_attr->type = rdma_ah_find_type(dev, uverb_attr->port_num);
+	if (uverb_attr->is_global) {
+		rdma_ah_set_grh(rdma_attr, NULL,
+				uverb_attr->flow_label,
+				uverb_attr->sgid_index,
+				uverb_attr->hop_limit,
+				uverb_attr->traffic_class);
+		rdma_ah_set_dgid_raw(rdma_attr, uverb_attr->dgid);
+	} else {
+		rdma_ah_set_ah_flags(rdma_attr, 0);
+	}
+	rdma_ah_set_dlid(rdma_attr, uverb_attr->dlid);
+	rdma_ah_set_sl(rdma_attr, uverb_attr->sl);
+	rdma_ah_set_path_bits(rdma_attr, uverb_attr->src_path_bits);
+	rdma_ah_set_static_rate(rdma_attr, uverb_attr->static_rate);
+	rdma_ah_set_port_num(rdma_attr, uverb_attr->port_num);
+	rdma_ah_set_make_grd(rdma_attr, false);
+}
+
 static int modify_qp(struct ib_uverbs_file *file,
 		     struct ib_uverbs_ex_modify_qp *cmd, struct ib_udata *udata)
 {
@@ -1962,47 +2005,13 @@ static int modify_qp(struct ib_uverbs_file *file,
 	attr->alt_timeout	  = cmd->base.alt_timeout;
 	attr->rate_limit	  = cmd->rate_limit;
 
-	attr->ah_attr.type = rdma_ah_find_type(qp->device,
-					       cmd->base.dest.port_num);
-	if (cmd->base.dest.is_global) {
-		rdma_ah_set_grh(&attr->ah_attr, NULL,
-				cmd->base.dest.flow_label,
-				cmd->base.dest.sgid_index,
-				cmd->base.dest.hop_limit,
-				cmd->base.dest.traffic_class);
-		rdma_ah_set_dgid_raw(&attr->ah_attr, cmd->base.dest.dgid);
-	} else {
-		rdma_ah_set_ah_flags(&attr->ah_attr, 0);
-	}
-	rdma_ah_set_dlid(&attr->ah_attr, cmd->base.dest.dlid);
-	rdma_ah_set_sl(&attr->ah_attr, cmd->base.dest.sl);
-	rdma_ah_set_path_bits(&attr->ah_attr, cmd->base.dest.src_path_bits);
-	rdma_ah_set_static_rate(&attr->ah_attr, cmd->base.dest.static_rate);
-	rdma_ah_set_port_num(&attr->ah_attr,
-			     cmd->base.dest.port_num);
-
-	attr->alt_ah_attr.type = rdma_ah_find_type(qp->device,
-						   cmd->base.dest.port_num);
-	if (cmd->base.alt_dest.is_global) {
-		rdma_ah_set_grh(&attr->alt_ah_attr, NULL,
-				cmd->base.alt_dest.flow_label,
-				cmd->base.alt_dest.sgid_index,
-				cmd->base.alt_dest.hop_limit,
-				cmd->base.alt_dest.traffic_class);
-		rdma_ah_set_dgid_raw(&attr->alt_ah_attr,
-				     cmd->base.alt_dest.dgid);
-	} else {
-		rdma_ah_set_ah_flags(&attr->alt_ah_attr, 0);
-	}
+	if (cmd->base.attr_mask & IB_QP_AV)
+		copy_ah_attr_from_uverbs(qp->device, &attr->ah_attr,
+					 &cmd->base.dest);
 
-	rdma_ah_set_dlid(&attr->alt_ah_attr, cmd->base.alt_dest.dlid);
-	rdma_ah_set_sl(&attr->alt_ah_attr, cmd->base.alt_dest.sl);
-	rdma_ah_set_path_bits(&attr->alt_ah_attr,
-			      cmd->base.alt_dest.src_path_bits);
-	rdma_ah_set_static_rate(&attr->alt_ah_attr,
-				cmd->base.alt_dest.static_rate);
-	rdma_ah_set_port_num(&attr->alt_ah_attr,
-			     cmd->base.alt_dest.port_num);
+	if (cmd->base.attr_mask & IB_QP_ALT_PATH)
+		copy_ah_attr_from_uverbs(qp->device, &attr->alt_ah_attr,
+					 &cmd->base.alt_dest);
 
 	ret = ib_modify_qp_with_udata(qp, attr,
 				      modify_qp_mask(qp->qp_type,
@@ -2034,7 +2043,8 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 		return -EOPNOTSUPP;
 
 	INIT_UDATA(&udata, buf + sizeof(cmd.base), NULL,
-		   in_len - sizeof(cmd.base), out_len);
+		   in_len - sizeof(cmd.base) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len);
 
 	ret = modify_qp(file, &cmd, &udata);
 	if (ret)
@@ -2540,7 +2550,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&udata, buf + sizeof(cmd),
 		   (unsigned long)cmd.response + sizeof(resp),
-		   in_len - sizeof(cmd), out_len - sizeof(resp));
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	uobj  = uobj_alloc(uobj_get_type(ah), file->ucontext);
 	if (IS_ERR(uobj))
@@ -2553,6 +2564,7 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	}
 
 	attr.type = rdma_ah_find_type(ib_dev, cmd.attr.port_num);
+	rdma_ah_set_make_grd(&attr, false);
 	rdma_ah_set_dlid(&attr, cmd.attr.dlid);
 	rdma_ah_set_sl(&attr, cmd.attr.sl);
 	rdma_ah_set_path_bits(&attr, cmd.attr.src_path_bits);
@@ -3469,6 +3481,9 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
+	if (cmd->srq_type == IB_SRQT_TM)
+		attr.ext.tag_matching.max_num_tags = cmd->max_num_tags;
+
 	if (cmd->srq_type == IB_SRQT_XRC) {
 		xrcd_uobj = uobj_get_read(uobj_get_type(xrcd), cmd->xrcd_handle,
 					  file->ucontext);
@@ -3485,10 +3500,12 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 
 		obj->uxrcd = container_of(xrcd_uobj, struct ib_uxrcd_object, uobject);
 		atomic_inc(&obj->uxrcd->refcnt);
+	}
 
-		attr.ext.xrc.cq  = uobj_get_obj_read(cq, cmd->cq_handle,
-						     file->ucontext);
-		if (!attr.ext.xrc.cq) {
+	if (ib_srq_has_cq(cmd->srq_type)) {
+		attr.ext.cq  = uobj_get_obj_read(cq, cmd->cq_handle,
+						 file->ucontext);
+		if (!attr.ext.cq) {
 			ret = -EINVAL;
 			goto err_put_xrcd;
 		}
@@ -3523,10 +3540,13 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 	srq->event_handler = attr.event_handler;
 	srq->srq_context   = attr.srq_context;
 
+	if (ib_srq_has_cq(cmd->srq_type)) {
+		srq->ext.cq       = attr.ext.cq;
+		atomic_inc(&attr.ext.cq->usecnt);
+	}
+
 	if (cmd->srq_type == IB_SRQT_XRC) {
-		srq->ext.xrc.cq   = attr.ext.xrc.cq;
 		srq->ext.xrc.xrcd = attr.ext.xrc.xrcd;
-		atomic_inc(&attr.ext.xrc.cq->usecnt);
 		atomic_inc(&attr.ext.xrc.xrcd->usecnt);
 	}
 
@@ -3549,10 +3569,12 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 		goto err_copy;
 	}
 
-	if (cmd->srq_type == IB_SRQT_XRC) {
+	if (cmd->srq_type == IB_SRQT_XRC)
 		uobj_put_read(xrcd_uobj);
-		uobj_put_obj_read(attr.ext.xrc.cq);
-	}
+
+	if (ib_srq_has_cq(cmd->srq_type))
+		uobj_put_obj_read(attr.ext.cq);
+
 	uobj_put_obj_read(pd);
 	uobj_alloc_commit(&obj->uevent.uobject);
 
@@ -3565,8 +3587,8 @@ err_put:
 	uobj_put_obj_read(pd);
 
 err_put_cq:
-	if (cmd->srq_type == IB_SRQT_XRC)
-		uobj_put_obj_read(attr.ext.xrc.cq);
+	if (ib_srq_has_cq(cmd->srq_type))
+		uobj_put_obj_read(attr.ext.cq);
 
 err_put_xrcd:
 	if (cmd->srq_type == IB_SRQT_XRC) {
@@ -3596,6 +3618,7 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
+	memset(&xcmd, 0, sizeof(xcmd));
 	xcmd.response	 = cmd.response;
 	xcmd.user_handle = cmd.user_handle;
 	xcmd.srq_type	 = IB_SRQT_BASIC;
@@ -3604,10 +3627,10 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file,
 	xcmd.max_sge	 = cmd.max_sge;
 	xcmd.srq_limit	 = cmd.srq_limit;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr),
-		   out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	ret = __uverbs_create_xsrq(file, ib_dev, &xcmd, &udata);
 	if (ret)
@@ -3631,10 +3654,10 @@ ssize_t ib_uverbs_create_xsrq(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr),
-		   out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	ret = __uverbs_create_xsrq(file, ib_dev, &cmd, &udata);
 	if (ret)
@@ -3845,6 +3868,16 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 
 	resp.raw_packet_caps = attr.raw_packet_caps;
 	resp.response_length += sizeof(resp.raw_packet_caps);
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps))
+		goto end;
+
+	resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size;
+	resp.xrq_caps.max_num_tags      = attr.xrq_caps.max_num_tags;
+	resp.xrq_caps.max_ops		= attr.xrq_caps.max_ops;
+	resp.xrq_caps.max_sge		= attr.xrq_caps.max_sge;
+	resp.xrq_caps.flags		= attr.xrq_caps.flags;
+	resp.response_length += sizeof(resp.xrq_caps);
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;
diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
new file mode 100644
index 000000000000..5286ad57d903
--- /dev/null
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -0,0 +1,364 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies 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 <rdma/rdma_user_ioctl.h>
+#include <rdma/uverbs_ioctl.h>
+#include "rdma_core.h"
+#include "uverbs.h"
+
+static int uverbs_process_attr(struct ib_device *ibdev,
+			       struct ib_ucontext *ucontext,
+			       const struct ib_uverbs_attr *uattr,
+			       u16 attr_id,
+			       const struct uverbs_attr_spec_hash *attr_spec_bucket,
+			       struct uverbs_attr_bundle_hash *attr_bundle_h,
+			       struct ib_uverbs_attr __user *uattr_ptr)
+{
+	const struct uverbs_attr_spec *spec;
+	struct uverbs_attr *e;
+	const struct uverbs_object_spec *object;
+	struct uverbs_obj_attr *o_attr;
+	struct uverbs_attr *elements = attr_bundle_h->attrs;
+
+	if (uattr->reserved)
+		return -EINVAL;
+
+	if (attr_id >= attr_spec_bucket->num_attrs) {
+		if (uattr->flags & UVERBS_ATTR_F_MANDATORY)
+			return -EINVAL;
+		else
+			return 0;
+	}
+
+	spec = &attr_spec_bucket->attrs[attr_id];
+	e = &elements[attr_id];
+	e->uattr = uattr_ptr;
+
+	switch (spec->type) {
+	case UVERBS_ATTR_TYPE_PTR_IN:
+	case UVERBS_ATTR_TYPE_PTR_OUT:
+		if (uattr->len < spec->len ||
+		    (!(spec->flags & UVERBS_ATTR_SPEC_F_MIN_SZ) &&
+		     uattr->len > spec->len))
+			return -EINVAL;
+
+		e->ptr_attr.data = uattr->data;
+		e->ptr_attr.len = uattr->len;
+		e->ptr_attr.flags = uattr->flags;
+		break;
+
+	case UVERBS_ATTR_TYPE_IDR:
+		if (uattr->data >> 32)
+			return -EINVAL;
+	/* fall through */
+	case UVERBS_ATTR_TYPE_FD:
+		if (uattr->len != 0 || !ucontext || uattr->data > INT_MAX)
+			return -EINVAL;
+
+		o_attr = &e->obj_attr;
+		object = uverbs_get_object(ibdev, spec->obj.obj_type);
+		if (!object)
+			return -EINVAL;
+		o_attr->type = object->type_attrs;
+
+		o_attr->id = (int)uattr->data;
+		o_attr->uobject = uverbs_get_uobject_from_context(
+					o_attr->type,
+					ucontext,
+					spec->obj.access,
+					o_attr->id);
+
+		if (IS_ERR(o_attr->uobject))
+			return PTR_ERR(o_attr->uobject);
+
+		if (spec->obj.access == UVERBS_ACCESS_NEW) {
+			u64 id = o_attr->uobject->id;
+
+			/* Copy the allocated id to the user-space */
+			if (put_user(id, &e->uattr->data)) {
+				uverbs_finalize_object(o_attr->uobject,
+						       UVERBS_ACCESS_NEW,
+						       false);
+				return -EFAULT;
+			}
+		}
+
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	set_bit(attr_id, attr_bundle_h->valid_bitmap);
+	return 0;
+}
+
+static int uverbs_uattrs_process(struct ib_device *ibdev,
+				 struct ib_ucontext *ucontext,
+				 const struct ib_uverbs_attr *uattrs,
+				 size_t num_uattrs,
+				 const struct uverbs_method_spec *method,
+				 struct uverbs_attr_bundle *attr_bundle,
+				 struct ib_uverbs_attr __user *uattr_ptr)
+{
+	size_t i;
+	int ret = 0;
+	int num_given_buckets = 0;
+
+	for (i = 0; i < num_uattrs; i++) {
+		const struct ib_uverbs_attr *uattr = &uattrs[i];
+		u16 attr_id = uattr->attr_id;
+		struct uverbs_attr_spec_hash *attr_spec_bucket;
+
+		ret = uverbs_ns_idx(&attr_id, method->num_buckets);
+		if (ret < 0) {
+			if (uattr->flags & UVERBS_ATTR_F_MANDATORY) {
+				uverbs_finalize_objects(attr_bundle,
+							method->attr_buckets,
+							num_given_buckets,
+							false);
+				return ret;
+			}
+			continue;
+		}
+
+		/*
+		 * ret is the found ns, so increase num_given_buckets if
+		 * necessary.
+		 */
+		if (ret >= num_given_buckets)
+			num_given_buckets = ret + 1;
+
+		attr_spec_bucket = method->attr_buckets[ret];
+		ret = uverbs_process_attr(ibdev, ucontext, uattr, attr_id,
+					  attr_spec_bucket, &attr_bundle->hash[ret],
+					  uattr_ptr++);
+		if (ret) {
+			uverbs_finalize_objects(attr_bundle,
+						method->attr_buckets,
+						num_given_buckets,
+						false);
+			return ret;
+		}
+	}
+
+	return num_given_buckets;
+}
+
+static int uverbs_validate_kernel_mandatory(const struct uverbs_method_spec *method_spec,
+					    struct uverbs_attr_bundle *attr_bundle)
+{
+	unsigned int i;
+
+	for (i = 0; i < attr_bundle->num_buckets; i++) {
+		struct uverbs_attr_spec_hash *attr_spec_bucket =
+			method_spec->attr_buckets[i];
+
+		if (!bitmap_subset(attr_spec_bucket->mandatory_attrs_bitmask,
+				   attr_bundle->hash[i].valid_bitmap,
+				   attr_spec_bucket->num_attrs))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int uverbs_handle_method(struct ib_uverbs_attr __user *uattr_ptr,
+				const struct ib_uverbs_attr *uattrs,
+				size_t num_uattrs,
+				struct ib_device *ibdev,
+				struct ib_uverbs_file *ufile,
+				const struct uverbs_method_spec *method_spec,
+				struct uverbs_attr_bundle *attr_bundle)
+{
+	int ret;
+	int finalize_ret;
+	int num_given_buckets;
+
+	num_given_buckets = uverbs_uattrs_process(ibdev, ufile->ucontext, uattrs,
+						  num_uattrs, method_spec,
+						  attr_bundle, uattr_ptr);
+	if (num_given_buckets <= 0)
+		return -EINVAL;
+
+	attr_bundle->num_buckets = num_given_buckets;
+	ret = uverbs_validate_kernel_mandatory(method_spec, attr_bundle);
+	if (ret)
+		goto cleanup;
+
+	ret = method_spec->handler(ibdev, ufile, attr_bundle);
+cleanup:
+	finalize_ret = uverbs_finalize_objects(attr_bundle,
+					       method_spec->attr_buckets,
+					       attr_bundle->num_buckets,
+					       !ret);
+
+	return ret ? ret : finalize_ret;
+}
+
+#define UVERBS_OPTIMIZE_USING_STACK_SZ  256
+static long ib_uverbs_cmd_verbs(struct ib_device *ib_dev,
+				struct ib_uverbs_file *file,
+				struct ib_uverbs_ioctl_hdr *hdr,
+				void __user *buf)
+{
+	const struct uverbs_object_spec *object_spec;
+	const struct uverbs_method_spec *method_spec;
+	long err = 0;
+	unsigned int i;
+	struct {
+		struct ib_uverbs_attr		*uattrs;
+		struct uverbs_attr_bundle	*uverbs_attr_bundle;
+	} *ctx = NULL;
+	struct uverbs_attr *curr_attr;
+	unsigned long *curr_bitmap;
+	size_t ctx_size;
+#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ
+	uintptr_t data[UVERBS_OPTIMIZE_USING_STACK_SZ / sizeof(uintptr_t)];
+#endif
+
+	if (hdr->reserved)
+		return -EINVAL;
+
+	object_spec = uverbs_get_object(ib_dev, hdr->object_id);
+	if (!object_spec)
+		return -EOPNOTSUPP;
+
+	method_spec = uverbs_get_method(object_spec, hdr->method_id);
+	if (!method_spec)
+		return -EOPNOTSUPP;
+
+	if ((method_spec->flags & UVERBS_ACTION_FLAG_CREATE_ROOT) ^ !file->ucontext)
+		return -EINVAL;
+
+	ctx_size = sizeof(*ctx) +
+		   sizeof(struct uverbs_attr_bundle) +
+		   sizeof(struct uverbs_attr_bundle_hash) * method_spec->num_buckets +
+		   sizeof(*ctx->uattrs) * hdr->num_attrs +
+		   sizeof(*ctx->uverbs_attr_bundle->hash[0].attrs) *
+		   method_spec->num_child_attrs +
+		   sizeof(*ctx->uverbs_attr_bundle->hash[0].valid_bitmap) *
+			(method_spec->num_child_attrs / BITS_PER_LONG +
+			 method_spec->num_buckets);
+
+#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ
+	if (ctx_size <= UVERBS_OPTIMIZE_USING_STACK_SZ)
+		ctx = (void *)data;
+
+	if (!ctx)
+#endif
+	ctx = kmalloc(ctx_size, GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->uverbs_attr_bundle = (void *)ctx + sizeof(*ctx);
+	ctx->uattrs = (void *)(ctx->uverbs_attr_bundle + 1) +
+			      (sizeof(ctx->uverbs_attr_bundle->hash[0]) *
+			       method_spec->num_buckets);
+	curr_attr = (void *)(ctx->uattrs + hdr->num_attrs);
+	curr_bitmap = (void *)(curr_attr + method_spec->num_child_attrs);
+
+	/*
+	 * We just fill the pointers and num_attrs here. The data itself will be
+	 * filled at a later stage (uverbs_process_attr)
+	 */
+	for (i = 0; i < method_spec->num_buckets; i++) {
+		unsigned int curr_num_attrs = method_spec->attr_buckets[i]->num_attrs;
+
+		ctx->uverbs_attr_bundle->hash[i].attrs = curr_attr;
+		curr_attr += curr_num_attrs;
+		ctx->uverbs_attr_bundle->hash[i].num_attrs = curr_num_attrs;
+		ctx->uverbs_attr_bundle->hash[i].valid_bitmap = curr_bitmap;
+		bitmap_zero(curr_bitmap, curr_num_attrs);
+		curr_bitmap += BITS_TO_LONGS(curr_num_attrs);
+	}
+
+	err = copy_from_user(ctx->uattrs, buf,
+			     sizeof(*ctx->uattrs) * hdr->num_attrs);
+	if (err) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	err = uverbs_handle_method(buf, ctx->uattrs, hdr->num_attrs, ib_dev,
+				   file, method_spec, ctx->uverbs_attr_bundle);
+out:
+#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ
+	if (ctx_size > UVERBS_OPTIMIZE_USING_STACK_SZ)
+#endif
+	kfree(ctx);
+	return err;
+}
+
+#define IB_UVERBS_MAX_CMD_SZ 4096
+
+long ib_uverbs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	struct ib_uverbs_file *file = filp->private_data;
+	struct ib_uverbs_ioctl_hdr __user *user_hdr =
+		(struct ib_uverbs_ioctl_hdr __user *)arg;
+	struct ib_uverbs_ioctl_hdr hdr;
+	struct ib_device *ib_dev;
+	int srcu_key;
+	long err;
+
+	srcu_key = srcu_read_lock(&file->device->disassociate_srcu);
+	ib_dev = srcu_dereference(file->device->ib_dev,
+				  &file->device->disassociate_srcu);
+	if (!ib_dev) {
+		err = -EIO;
+		goto out;
+	}
+
+	if (cmd == RDMA_VERBS_IOCTL) {
+		err = copy_from_user(&hdr, user_hdr, sizeof(hdr));
+
+		if (err || hdr.length > IB_UVERBS_MAX_CMD_SZ ||
+		    hdr.length != sizeof(hdr) + hdr.num_attrs * sizeof(struct ib_uverbs_attr)) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (hdr.reserved) {
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+
+		err = ib_uverbs_cmd_verbs(ib_dev, file, &hdr,
+					  (__user void *)arg + sizeof(hdr));
+	} else {
+		err = -ENOIOCTLCMD;
+	}
+out:
+	srcu_read_unlock(&file->device->disassociate_srcu, srcu_key);
+
+	return err;
+}
diff --git a/drivers/infiniband/core/uverbs_ioctl_merge.c b/drivers/infiniband/core/uverbs_ioctl_merge.c
new file mode 100644
index 000000000000..76ddb6564578
--- /dev/null
+++ b/drivers/infiniband/core/uverbs_ioctl_merge.c
@@ -0,0 +1,665 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies 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 <rdma/uverbs_ioctl.h>
+#include <rdma/rdma_user_ioctl.h>
+#include <linux/bitops.h>
+#include "uverbs.h"
+
+#define UVERBS_NUM_NS (UVERBS_ID_NS_MASK >> UVERBS_ID_NS_SHIFT)
+#define GET_NS_ID(idx) (((idx) & UVERBS_ID_NS_MASK) >> UVERBS_ID_NS_SHIFT)
+#define GET_ID(idx) ((idx) & ~UVERBS_ID_NS_MASK)
+
+#define _for_each_element(elem, tmpi, tmpj, hashes, num_buckets_offset,	       \
+			  buckets_offset)				       \
+	for (tmpj = 0,							       \
+	     elem = (*(const void ***)((hashes)[tmpi] +			       \
+				       (buckets_offset)))[0];	               \
+	     tmpj < *(size_t *)((hashes)[tmpi] + (num_buckets_offset));        \
+	     tmpj++)						               \
+		if ((elem = ((*(const void ***)(hashes[tmpi] +		       \
+						(buckets_offset)))[tmpj])))
+
+/*
+ * Iterate all elements of a few @hashes. The number of given hashes is
+ * indicated by @num_hashes. The offset of the number of buckets in the hash is
+ * represented by @num_buckets_offset, while the offset of the buckets array in
+ * the hash structure is represented by @buckets_offset. tmpi and tmpj are two
+ * short (or int) based indices that are given by the user. tmpi iterates over
+ * the different hashes. @elem points the current element in the hashes[tmpi]
+ * bucket we are looping on. To be honest, @hashes representation isn't exactly
+ * a hash, but more a collection of elements. These elements' ids are treated
+ * in a hash like manner, where the first upper bits are the bucket number.
+ * These elements are later mapped into a perfect-hash.
+ */
+#define for_each_element(elem, tmpi, tmpj, hashes, num_hashes,                 \
+			 num_buckets_offset, buckets_offset)		       \
+	for (tmpi = 0; tmpi < (num_hashes); tmpi++)		               \
+		_for_each_element(elem, tmpi, tmpj, hashes, num_buckets_offset,\
+				  buckets_offset)
+
+#define get_elements_iterators_entry_above(iters, num_elements, elements,     \
+					  num_objects_fld, objects_fld, bucket,\
+					  min_id)			       \
+	get_elements_above_id((const void **)iters, num_elements,       \
+				     (const void **)(elements),		       \
+				     offsetof(typeof(**elements),	       \
+					      num_objects_fld),		       \
+				     offsetof(typeof(**elements), objects_fld),\
+				     offsetof(typeof(***(*elements)->objects_fld), id),\
+				     bucket, min_id)
+
+#define get_objects_above_id(iters, num_trees, trees, bucket, min_id)	       \
+	get_elements_iterators_entry_above(iters, num_trees, trees,	       \
+					   num_objects, objects, bucket, min_id)
+
+#define get_methods_above_id(method_iters, num_iters, iters, bucket, min_id)\
+	get_elements_iterators_entry_above(method_iters, num_iters, iters,     \
+					   num_methods, methods, bucket, min_id)
+
+#define get_attrs_above_id(attrs_iters, num_iters, iters, bucket, min_id)\
+	get_elements_iterators_entry_above(attrs_iters, num_iters, iters,      \
+					   num_attrs, attrs, bucket, min_id)
+
+/*
+ * get_elements_above_id get a few hashes represented by @elements and
+ * @num_elements. The hashes fields are described by @num_offset, @data_offset
+ * and @id_offset in the same way as required by for_each_element. The function
+ * returns an array of @iters, represents an array of elements in the hashes
+ * buckets, which their ids are the smallest ids in all hashes but are all
+ * larger than the id given by min_id. Elements are only added to the iters
+ * array if their id belongs to the bucket @bucket. The number of elements in
+ * the returned array is returned by the function. @min_id is also updated to
+ * reflect the new min_id of all elements in iters.
+ */
+static size_t get_elements_above_id(const void **iters,
+				    unsigned int num_elements,
+				    const void **elements,
+				    size_t num_offset,
+				    size_t data_offset,
+				    size_t id_offset,
+				    u16 bucket,
+				    short *min_id)
+{
+	size_t num_iters = 0;
+	short min = SHRT_MAX;
+	const void *elem;
+	int i, j, last_stored = -1;
+
+	for_each_element(elem, i, j, elements, num_elements, num_offset,
+			 data_offset) {
+		u16 id = *(u16 *)(elem + id_offset);
+
+		if (GET_NS_ID(id) != bucket)
+			continue;
+
+		if (GET_ID(id) < *min_id ||
+		    (min != SHRT_MAX && GET_ID(id) > min))
+			continue;
+
+		/*
+		 * We first iterate all hashes represented by @elements. When
+		 * we do, we try to find an element @elem in the bucket @bucket
+		 * which its id is min. Since we can't ensure the user sorted
+		 * the elements in increasing order, we override this hash's
+		 * minimal id element we found, if a new element with a smaller
+		 * id was just found.
+		 */
+		iters[last_stored == i ? num_iters - 1 : num_iters++] = elem;
+		last_stored = i;
+		min = GET_ID(id);
+	}
+
+	/*
+	 * We only insert to our iters array an element, if its id is smaller
+	 * than all previous ids. Therefore, the final iters array is sorted so
+	 * that smaller ids are in the end of the array.
+	 * Therefore, we need to clean the beginning of the array to make sure
+	 * all ids of final elements are equal to min.
+	 */
+	for (i = num_iters - 1; i >= 0 &&
+	     GET_ID(*(u16 *)(iters[i] + id_offset)) == min; i--)
+		;
+
+	num_iters -= i + 1;
+	memmove(iters, iters + i + 1, sizeof(*iters) * num_iters);
+
+	*min_id = min;
+	return num_iters;
+}
+
+#define find_max_element_entry_id(num_elements, elements, num_objects_fld, \
+				  objects_fld, bucket)			   \
+	find_max_element_id(num_elements, (const void **)(elements),	   \
+			    offsetof(typeof(**elements), num_objects_fld),    \
+			    offsetof(typeof(**elements), objects_fld),	      \
+			    offsetof(typeof(***(*elements)->objects_fld), id),\
+			    bucket)
+
+static short find_max_element_ns_id(unsigned int num_elements,
+				    const void **elements,
+				    size_t num_offset,
+				    size_t data_offset,
+				    size_t id_offset)
+{
+	short max_ns = SHRT_MIN;
+	const void *elem;
+	int i, j;
+
+	for_each_element(elem, i, j, elements, num_elements, num_offset,
+			 data_offset) {
+		u16 id = *(u16 *)(elem + id_offset);
+
+		if (GET_NS_ID(id) > max_ns)
+			max_ns = GET_NS_ID(id);
+	}
+
+	return max_ns;
+}
+
+static short find_max_element_id(unsigned int num_elements,
+				 const void **elements,
+				 size_t num_offset,
+				 size_t data_offset,
+				 size_t id_offset,
+				 u16 bucket)
+{
+	short max_id = SHRT_MIN;
+	const void *elem;
+	int i, j;
+
+	for_each_element(elem, i, j, elements, num_elements, num_offset,
+			 data_offset) {
+		u16 id = *(u16 *)(elem + id_offset);
+
+		if (GET_NS_ID(id) == bucket &&
+		    GET_ID(id) > max_id)
+			max_id = GET_ID(id);
+	}
+	return max_id;
+}
+
+#define find_max_element_entry_id(num_elements, elements, num_objects_fld,   \
+				  objects_fld, bucket)			      \
+	find_max_element_id(num_elements, (const void **)(elements),	      \
+			    offsetof(typeof(**elements), num_objects_fld),    \
+			    offsetof(typeof(**elements), objects_fld),	      \
+			    offsetof(typeof(***(*elements)->objects_fld), id),\
+			    bucket)
+
+#define find_max_element_ns_entry_id(num_elements, elements,		    \
+				     num_objects_fld, objects_fld)	    \
+	find_max_element_ns_id(num_elements, (const void **)(elements),	    \
+			      offsetof(typeof(**elements), num_objects_fld),\
+			      offsetof(typeof(**elements), objects_fld),    \
+			      offsetof(typeof(***(*elements)->objects_fld), id))
+
+/*
+ * find_max_xxxx_ns_id gets a few elements. Each element is described by an id
+ * which its upper bits represents a namespace. It finds the max namespace. This
+ * could be used in order to know how many buckets do we need to allocate. If no
+ * elements exist, SHRT_MIN is returned. Namespace represents here different
+ * buckets. The common example is "common bucket" and "driver bucket".
+ *
+ * find_max_xxxx_id gets a few elements and a bucket. Each element is described
+ * by an id which its upper bits represent a namespace. It returns the max id
+ * which is contained in the same namespace defined in @bucket. This could be
+ * used in order to know how many elements do we need to allocate in the bucket.
+ * If no elements exist, SHRT_MIN is returned.
+ */
+
+#define find_max_object_id(num_trees, trees, bucket)			\
+		find_max_element_entry_id(num_trees, trees, num_objects,\
+					  objects, bucket)
+#define find_max_object_ns_id(num_trees, trees)			\
+		find_max_element_ns_entry_id(num_trees, trees,		\
+					     num_objects, objects)
+
+#define find_max_method_id(num_iters, iters, bucket)			\
+		find_max_element_entry_id(num_iters, iters, num_methods,\
+					  methods, bucket)
+#define find_max_method_ns_id(num_iters, iters)			\
+		find_max_element_ns_entry_id(num_iters, iters,		\
+					     num_methods, methods)
+
+#define find_max_attr_id(num_iters, iters, bucket)			\
+		find_max_element_entry_id(num_iters, iters, num_attrs,  \
+					  attrs, bucket)
+#define find_max_attr_ns_id(num_iters, iters)				\
+		find_max_element_ns_entry_id(num_iters, iters,		\
+					     num_attrs, attrs)
+
+static void free_method(struct uverbs_method_spec *method)
+{
+	unsigned int i;
+
+	if (!method)
+		return;
+
+	for (i = 0; i < method->num_buckets; i++)
+		kfree(method->attr_buckets[i]);
+
+	kfree(method);
+}
+
+#define IS_ATTR_OBJECT(attr) ((attr)->type == UVERBS_ATTR_TYPE_IDR || \
+			      (attr)->type == UVERBS_ATTR_TYPE_FD)
+
+/*
+ * This function gets array of size @num_method_defs which contains pointers to
+ * method definitions @method_defs. The function allocates an
+ * uverbs_method_spec structure and initializes its number of buckets and the
+ * elements in buckets to the correct attributes. While doing that, it
+ * validates that there aren't conflicts between attributes of different
+ * method_defs.
+ */
+static struct uverbs_method_spec *build_method_with_attrs(const struct uverbs_method_def **method_defs,
+							  size_t num_method_defs)
+{
+	int bucket_idx;
+	int max_attr_buckets = 0;
+	size_t num_attr_buckets = 0;
+	int res = 0;
+	struct uverbs_method_spec *method = NULL;
+	const struct uverbs_attr_def **attr_defs;
+	unsigned int num_of_singularities = 0;
+
+	max_attr_buckets = find_max_attr_ns_id(num_method_defs, method_defs);
+	if (max_attr_buckets >= 0)
+		num_attr_buckets = max_attr_buckets + 1;
+
+	method = kzalloc(sizeof(*method) +
+			 num_attr_buckets * sizeof(*method->attr_buckets),
+			 GFP_KERNEL);
+	if (!method)
+		return ERR_PTR(-ENOMEM);
+
+	method->num_buckets = num_attr_buckets;
+	attr_defs = kcalloc(num_method_defs, sizeof(*attr_defs), GFP_KERNEL);
+	if (!attr_defs) {
+		res = -ENOMEM;
+		goto free_method;
+	}
+	for (bucket_idx = 0; bucket_idx < method->num_buckets; bucket_idx++) {
+		short min_id = SHRT_MIN;
+		int attr_max_bucket = 0;
+		struct uverbs_attr_spec_hash *hash = NULL;
+
+		attr_max_bucket = find_max_attr_id(num_method_defs, method_defs,
+						   bucket_idx);
+		if (attr_max_bucket < 0)
+			continue;
+
+		hash = kzalloc(sizeof(*hash) +
+			       ALIGN(sizeof(*hash->attrs) * (attr_max_bucket + 1),
+				     sizeof(long)) +
+			       BITS_TO_LONGS(attr_max_bucket) * sizeof(long),
+			       GFP_KERNEL);
+		if (!hash) {
+			res = -ENOMEM;
+			goto free;
+		}
+		hash->num_attrs = attr_max_bucket + 1;
+		method->num_child_attrs += hash->num_attrs;
+		hash->mandatory_attrs_bitmask = (void *)(hash + 1) +
+						 ALIGN(sizeof(*hash->attrs) *
+						       (attr_max_bucket + 1),
+						       sizeof(long));
+
+		method->attr_buckets[bucket_idx] = hash;
+
+		do {
+			size_t			 num_attr_defs;
+			struct uverbs_attr_spec	*attr;
+			bool attr_obj_with_special_access;
+
+			num_attr_defs =
+				get_attrs_above_id(attr_defs,
+						   num_method_defs,
+						   method_defs,
+						   bucket_idx,
+						   &min_id);
+			/* Last attr in bucket */
+			if (!num_attr_defs)
+				break;
+
+			if (num_attr_defs > 1) {
+				/*
+				 * We don't allow two attribute definitions for
+				 * the same attribute. This is usually a
+				 * programmer error. If required, it's better to
+				 * just add a new attribute to capture the new
+				 * semantics.
+				 */
+				res = -EEXIST;
+				goto free;
+			}
+
+			attr = &hash->attrs[min_id];
+			memcpy(attr, &attr_defs[0]->attr, sizeof(*attr));
+
+			attr_obj_with_special_access = IS_ATTR_OBJECT(attr) &&
+				   (attr->obj.access == UVERBS_ACCESS_NEW ||
+				    attr->obj.access == UVERBS_ACCESS_DESTROY);
+			num_of_singularities +=  !!attr_obj_with_special_access;
+			if (WARN(num_of_singularities > 1,
+				 "ib_uverbs: Method contains more than one object attr (%d) with new/destroy access\n",
+				 min_id) ||
+			    WARN(attr_obj_with_special_access &&
+				 !(attr->flags & UVERBS_ATTR_SPEC_F_MANDATORY),
+				 "ib_uverbs: Tried to merge attr (%d) but it's an object with new/destroy aceess but isn't mandatory\n",
+				 min_id) ||
+			    WARN(IS_ATTR_OBJECT(attr) &&
+				 attr->flags & UVERBS_ATTR_SPEC_F_MIN_SZ,
+				 "ib_uverbs: Tried to merge attr (%d) but it's an object with min_sz flag\n",
+				 min_id)) {
+				res = -EINVAL;
+				goto free;
+			}
+
+			if (attr->flags & UVERBS_ATTR_SPEC_F_MANDATORY)
+				set_bit(min_id, hash->mandatory_attrs_bitmask);
+			min_id++;
+
+		} while (1);
+	}
+	kfree(attr_defs);
+	return method;
+
+free:
+	kfree(attr_defs);
+free_method:
+	free_method(method);
+	return ERR_PTR(res);
+}
+
+static void free_object(struct uverbs_object_spec *object)
+{
+	unsigned int i, j;
+
+	if (!object)
+		return;
+
+	for (i = 0; i < object->num_buckets; i++) {
+		struct uverbs_method_spec_hash	*method_buckets =
+			object->method_buckets[i];
+
+		if (!method_buckets)
+			continue;
+
+		for (j = 0; j < method_buckets->num_methods; j++)
+			free_method(method_buckets->methods[j]);
+
+		kfree(method_buckets);
+	}
+
+	kfree(object);
+}
+
+/*
+ * This function gets array of size @num_object_defs which contains pointers to
+ * object definitions @object_defs. The function allocated an
+ * uverbs_object_spec structure and initialize its number of buckets and the
+ * elements in buckets to the correct methods. While doing that, it
+ * sorts out the correct relationship between conflicts in the same method.
+ */
+static struct uverbs_object_spec *build_object_with_methods(const struct uverbs_object_def **object_defs,
+							    size_t num_object_defs)
+{
+	u16 bucket_idx;
+	int max_method_buckets = 0;
+	u16 num_method_buckets = 0;
+	int res = 0;
+	struct uverbs_object_spec *object = NULL;
+	const struct uverbs_method_def **method_defs;
+
+	max_method_buckets = find_max_method_ns_id(num_object_defs, object_defs);
+	if (max_method_buckets >= 0)
+		num_method_buckets = max_method_buckets + 1;
+
+	object = kzalloc(sizeof(*object) +
+			 num_method_buckets *
+			 sizeof(*object->method_buckets), GFP_KERNEL);
+	if (!object)
+		return ERR_PTR(-ENOMEM);
+
+	object->num_buckets = num_method_buckets;
+	method_defs = kcalloc(num_object_defs, sizeof(*method_defs), GFP_KERNEL);
+	if (!method_defs) {
+		res = -ENOMEM;
+		goto free_object;
+	}
+
+	for (bucket_idx = 0; bucket_idx < object->num_buckets; bucket_idx++) {
+		short min_id = SHRT_MIN;
+		int methods_max_bucket = 0;
+		struct uverbs_method_spec_hash *hash = NULL;
+
+		methods_max_bucket = find_max_method_id(num_object_defs, object_defs,
+							bucket_idx);
+		if (methods_max_bucket < 0)
+			continue;
+
+		hash = kzalloc(sizeof(*hash) +
+			       sizeof(*hash->methods) * (methods_max_bucket + 1),
+			       GFP_KERNEL);
+		if (!hash) {
+			res = -ENOMEM;
+			goto free;
+		}
+
+		hash->num_methods = methods_max_bucket + 1;
+		object->method_buckets[bucket_idx] = hash;
+
+		do {
+			size_t				num_method_defs;
+			struct uverbs_method_spec	*method;
+			int i;
+
+			num_method_defs =
+				get_methods_above_id(method_defs,
+						     num_object_defs,
+						     object_defs,
+						     bucket_idx,
+						     &min_id);
+			/* Last method in bucket */
+			if (!num_method_defs)
+				break;
+
+			method = build_method_with_attrs(method_defs,
+							 num_method_defs);
+			if (IS_ERR(method)) {
+				res = PTR_ERR(method);
+				goto free;
+			}
+
+			/*
+			 * The last tree which is given as an argument to the
+			 * merge overrides previous method handler.
+			 * Therefore, we iterate backwards and search for the
+			 * first handler which != NULL. This also defines the
+			 * set of flags used for this handler.
+			 */
+			for (i = num_object_defs - 1;
+			     i >= 0 && !method_defs[i]->handler; i--)
+				;
+			hash->methods[min_id++] = method;
+			/* NULL handler isn't allowed */
+			if (WARN(i < 0,
+				 "ib_uverbs: tried to merge function id %d, but all handlers are NULL\n",
+				 min_id)) {
+				res = -EINVAL;
+				goto free;
+			}
+			method->handler = method_defs[i]->handler;
+			method->flags = method_defs[i]->flags;
+
+		} while (1);
+	}
+	kfree(method_defs);
+	return object;
+
+free:
+	kfree(method_defs);
+free_object:
+	free_object(object);
+	return ERR_PTR(res);
+}
+
+void uverbs_free_spec_tree(struct uverbs_root_spec *root)
+{
+	unsigned int i, j;
+
+	if (!root)
+		return;
+
+	for (i = 0; i < root->num_buckets; i++) {
+		struct uverbs_object_spec_hash *object_hash =
+			root->object_buckets[i];
+
+		if (!object_hash)
+			continue;
+
+		for (j = 0; j < object_hash->num_objects; j++)
+			free_object(object_hash->objects[j]);
+
+		kfree(object_hash);
+	}
+
+	kfree(root);
+}
+EXPORT_SYMBOL(uverbs_free_spec_tree);
+
+struct uverbs_root_spec *uverbs_alloc_spec_tree(unsigned int num_trees,
+						const struct uverbs_object_tree_def **trees)
+{
+	u16 bucket_idx;
+	short max_object_buckets = 0;
+	size_t num_objects_buckets = 0;
+	struct uverbs_root_spec *root_spec = NULL;
+	const struct uverbs_object_def **object_defs;
+	int i;
+	int res = 0;
+
+	max_object_buckets = find_max_object_ns_id(num_trees, trees);
+	/*
+	 * Devices which don't want to support ib_uverbs, should just allocate
+	 * an empty parsing tree. Every user-space command won't hit any valid
+	 * entry in the parsing tree and thus will fail.
+	 */
+	if (max_object_buckets >= 0)
+		num_objects_buckets = max_object_buckets + 1;
+
+	root_spec = kzalloc(sizeof(*root_spec) +
+			    num_objects_buckets * sizeof(*root_spec->object_buckets),
+			    GFP_KERNEL);
+	if (!root_spec)
+		return ERR_PTR(-ENOMEM);
+	root_spec->num_buckets = num_objects_buckets;
+
+	object_defs = kcalloc(num_trees, sizeof(*object_defs),
+			      GFP_KERNEL);
+	if (!object_defs) {
+		res = -ENOMEM;
+		goto free_root;
+	}
+
+	for (bucket_idx = 0; bucket_idx < root_spec->num_buckets; bucket_idx++) {
+		short min_id = SHRT_MIN;
+		short objects_max_bucket;
+		struct uverbs_object_spec_hash *hash = NULL;
+
+		objects_max_bucket = find_max_object_id(num_trees, trees,
+							bucket_idx);
+		if (objects_max_bucket < 0)
+			continue;
+
+		hash = kzalloc(sizeof(*hash) +
+			       sizeof(*hash->objects) * (objects_max_bucket + 1),
+			       GFP_KERNEL);
+		if (!hash) {
+			res = -ENOMEM;
+			goto free;
+		}
+		hash->num_objects = objects_max_bucket + 1;
+		root_spec->object_buckets[bucket_idx] = hash;
+
+		do {
+			size_t				num_object_defs;
+			struct uverbs_object_spec	*object;
+
+			num_object_defs = get_objects_above_id(object_defs,
+							       num_trees,
+							       trees,
+							       bucket_idx,
+							       &min_id);
+			/* Last object in bucket */
+			if (!num_object_defs)
+				break;
+
+			object = build_object_with_methods(object_defs,
+							   num_object_defs);
+			if (IS_ERR(object)) {
+				res = PTR_ERR(object);
+				goto free;
+			}
+
+			/*
+			 * The last tree which is given as an argument to the
+			 * merge overrides previous object's type_attrs.
+			 * Therefore, we iterate backwards and search for the
+			 * first type_attrs which != NULL.
+			 */
+			for (i = num_object_defs - 1;
+			     i >= 0 && !object_defs[i]->type_attrs; i--)
+				;
+			/*
+			 * NULL is a valid type_attrs. It means an object we
+			 * can't instantiate (like DEVICE).
+			 */
+			object->type_attrs = i < 0 ? NULL :
+				object_defs[i]->type_attrs;
+
+			hash->objects[min_id++] = object;
+		} while (1);
+	}
+
+	kfree(object_defs);
+	return root_spec;
+
+free:
+	kfree(object_defs);
+free_root:
+	uverbs_free_spec_tree(root_spec);
+	return ERR_PTR(res);
+}
+EXPORT_SYMBOL(uverbs_alloc_spec_tree);
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index c023e2c81b8f..dc2aed6fb21b 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -49,6 +49,7 @@
 #include <linux/uaccess.h>
 
 #include <rdma/ib.h>
+#include <rdma/uverbs_std_types.h>
 
 #include "uverbs.h"
 #include "core_priv.h"
@@ -595,7 +596,6 @@ struct file *ib_uverbs_alloc_async_event_file(struct ib_uverbs_file *uverbs_file
 {
 	struct ib_uverbs_async_event_file *ev_file;
 	struct file *filp;
-	int ret;
 
 	ev_file = kzalloc(sizeof(*ev_file), GFP_KERNEL);
 	if (!ev_file)
@@ -621,21 +621,11 @@ struct file *ib_uverbs_alloc_async_event_file(struct ib_uverbs_file *uverbs_file
 	INIT_IB_EVENT_HANDLER(&uverbs_file->event_handler,
 			      ib_dev,
 			      ib_uverbs_event_handler);
-	ret = ib_register_event_handler(&uverbs_file->event_handler);
-	if (ret)
-		goto err_put_file;
-
+	ib_register_event_handler(&uverbs_file->event_handler);
 	/* At that point async file stuff was fully set */
 
 	return filp;
 
-err_put_file:
-	fput(filp);
-	kref_put(&uverbs_file->async_file->ref,
-		 ib_uverbs_release_async_event_file);
-	uverbs_file->async_file = NULL;
-	return ERR_PTR(ret);
-
 err_put_refs:
 	kref_put(&ev_file->uverbs_file->ref, ib_uverbs_release_file);
 	kref_put(&ev_file->ref, ib_uverbs_release_async_event_file);
@@ -949,6 +939,9 @@ static const struct file_operations uverbs_fops = {
 	.open	 = ib_uverbs_open,
 	.release = ib_uverbs_close,
 	.llseek	 = no_llseek,
+#if IS_ENABLED(CONFIG_INFINIBAND_EXP_USER_ACCESS)
+	.unlocked_ioctl = ib_uverbs_ioctl,
+#endif
 };
 
 static const struct file_operations uverbs_mmap_fops = {
@@ -958,6 +951,9 @@ static const struct file_operations uverbs_mmap_fops = {
 	.open	 = ib_uverbs_open,
 	.release = ib_uverbs_close,
 	.llseek	 = no_llseek,
+#if IS_ENABLED(CONFIG_INFINIBAND_EXP_USER_ACCESS)
+	.unlocked_ioctl = ib_uverbs_ioctl,
+#endif
 };
 
 static struct ib_client uverbs_client = {
@@ -1108,6 +1104,18 @@ static void ib_uverbs_add_one(struct ib_device *device)
 	if (device_create_file(uverbs_dev->dev, &dev_attr_abi_version))
 		goto err_class;
 
+	if (!device->specs_root) {
+		const struct uverbs_object_tree_def *default_root[] = {
+			uverbs_default_get_objects()};
+
+		uverbs_dev->specs_root = uverbs_alloc_spec_tree(1,
+								default_root);
+		if (IS_ERR(uverbs_dev->specs_root))
+			goto err_class;
+
+		device->specs_root = uverbs_dev->specs_root;
+	}
+
 	ib_set_client_data(device, &uverbs_client, uverbs_dev);
 
 	return;
@@ -1153,7 +1161,6 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 		kref_get(&file->ref);
 		mutex_unlock(&uverbs_dev->lists_mutex);
 
-		ib_uverbs_event_handler(&file->event_handler, &event);
 
 		mutex_lock(&file->cleanup_mutex);
 		ucontext = file->ucontext;
@@ -1170,6 +1177,7 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 			 * for example due to freeing the resources
 			 * (e.g mmput).
 			 */
+			ib_uverbs_event_handler(&file->event_handler, &event);
 			ib_dev->disassociate_ucontext(ucontext);
 			mutex_lock(&file->cleanup_mutex);
 			ib_uverbs_cleanup_ucontext(file, ucontext, true);
@@ -1239,6 +1247,11 @@ static void ib_uverbs_remove_one(struct ib_device *device, void *client_data)
 		ib_uverbs_comp_dev(uverbs_dev);
 	if (wait_clients)
 		wait_for_completion(&uverbs_dev->comp);
+	if (uverbs_dev->specs_root) {
+		uverbs_free_spec_tree(uverbs_dev->specs_root);
+		device->specs_root = NULL;
+	}
+
 	kobject_put(&uverbs_dev->kobj);
 }
 
diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c
index 94fd989c9060..bd0acf376af0 100644
--- a/drivers/infiniband/core/uverbs_marshall.c
+++ b/drivers/infiniband/core/uverbs_marshall.c
@@ -33,10 +33,47 @@
 #include <linux/export.h>
 #include <rdma/ib_marshall.h>
 
-void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
-			     struct rdma_ah_attr *src)
+#define OPA_DEFAULT_GID_PREFIX cpu_to_be64(0xfe80000000000000ULL)
+static int rdma_ah_conv_opa_to_ib(struct ib_device *dev,
+				  struct rdma_ah_attr *ib,
+				  struct rdma_ah_attr *opa)
 {
+	struct ib_port_attr port_attr;
+	int ret = 0;
+
+	/* Do structure copy and the over-write fields */
+	*ib = *opa;
+
+	ib->type = RDMA_AH_ATTR_TYPE_IB;
+	rdma_ah_set_grh(ib, NULL, 0, 0, 1, 0);
+
+	if (ib_query_port(dev, opa->port_num, &port_attr)) {
+		/* Set to default subnet to indicate error */
+		rdma_ah_set_subnet_prefix(ib, OPA_DEFAULT_GID_PREFIX);
+		ret = -EINVAL;
+	} else {
+		rdma_ah_set_subnet_prefix(ib,
+					  cpu_to_be64(port_attr.subnet_prefix));
+	}
+	rdma_ah_set_interface_id(ib, OPA_MAKE_ID(rdma_ah_get_dlid(opa)));
+	return ret;
+}
+
+void ib_copy_ah_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_ah_attr *dst,
+			     struct rdma_ah_attr *ah_attr)
+{
+	struct rdma_ah_attr *src = ah_attr;
+	struct rdma_ah_attr conv_ah;
+
 	memset(&dst->grh.reserved, 0, sizeof(dst->grh.reserved));
+
+	if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) &&
+	    (rdma_ah_get_dlid(ah_attr) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+	    (!rdma_ah_conv_opa_to_ib(device, &conv_ah, ah_attr)))
+		src = &conv_ah;
+
 	dst->dlid		   = rdma_ah_get_dlid(src);
 	dst->sl			   = rdma_ah_get_sl(src);
 	dst->src_path_bits	   = rdma_ah_get_path_bits(src);
@@ -57,7 +94,8 @@ void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
 }
 EXPORT_SYMBOL(ib_copy_ah_attr_to_user);
 
-void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
+void ib_copy_qp_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_qp_attr *dst,
 			     struct ib_qp_attr *src)
 {
 	dst->qp_state	        = src->qp_state;
@@ -76,8 +114,8 @@ void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
 	dst->max_recv_sge	= src->cap.max_recv_sge;
 	dst->max_inline_data	= src->cap.max_inline_data;
 
-	ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
-	ib_copy_ah_attr_to_user(&dst->alt_ah_attr, &src->alt_ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->alt_ah_attr, &src->alt_ah_attr);
 
 	dst->pkey_index		= src->pkey_index;
 	dst->alt_pkey_index	= src->alt_pkey_index;
diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index ef293379f37a..0a98579700ec 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -209,67 +209,244 @@ static int uverbs_hot_unplug_completion_event_file(struct ib_uobject_file *uobj_
 	return 0;
 };
 
-const struct uverbs_obj_fd_type uverbs_type_attrs_comp_channel = {
-	.type = UVERBS_TYPE_ALLOC_FD(sizeof(struct ib_uverbs_completion_event_file), 0),
-	.context_closed = uverbs_hot_unplug_completion_event_file,
-	.fops = &uverbs_event_fops,
-	.name = "[infinibandevent]",
-	.flags = O_RDONLY,
-};
+/*
+ * This spec is used in order to pass information to the hardware driver in a
+ * legacy way. Every verb that could get driver specific data should get this
+ * spec.
+ */
+static const struct uverbs_attr_def uverbs_uhw_compat_in =
+	UVERBS_ATTR_PTR_IN_SZ(UVERBS_UHW_IN, 0, UA_FLAGS(UVERBS_ATTR_SPEC_F_MIN_SZ));
+static const struct uverbs_attr_def uverbs_uhw_compat_out =
+	UVERBS_ATTR_PTR_OUT_SZ(UVERBS_UHW_OUT, 0, UA_FLAGS(UVERBS_ATTR_SPEC_F_MIN_SZ));
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_cq = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_ucq_object), 0),
-	.destroy_object = uverbs_free_cq,
-};
+static void create_udata(struct uverbs_attr_bundle *ctx,
+			 struct ib_udata *udata)
+{
+	/*
+	 * This is for ease of conversion. The purpose is to convert all drivers
+	 * to use uverbs_attr_bundle instead of ib_udata.
+	 * Assume attr == 0 is input and attr == 1 is output.
+	 */
+	void __user *inbuf;
+	size_t inbuf_len = 0;
+	void __user *outbuf;
+	size_t outbuf_len = 0;
+	const struct uverbs_attr *uhw_in =
+		uverbs_attr_get(ctx, UVERBS_UHW_IN);
+	const struct uverbs_attr *uhw_out =
+		uverbs_attr_get(ctx, UVERBS_UHW_OUT);
+
+	if (!IS_ERR(uhw_in)) {
+		inbuf = uhw_in->ptr_attr.ptr;
+		inbuf_len = uhw_in->ptr_attr.len;
+	}
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_qp = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uqp_object), 0),
-	.destroy_object = uverbs_free_qp,
-};
+	if (!IS_ERR(uhw_out)) {
+		outbuf = uhw_out->ptr_attr.ptr;
+		outbuf_len = uhw_out->ptr_attr.len;
+	}
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_mw = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_mw,
-};
+	INIT_UDATA_BUF_OR_NULL(udata, inbuf, outbuf, inbuf_len, outbuf_len);
+}
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_mr = {
-	/* 1 is used in order to free the MR after all the MWs */
-	.type = UVERBS_TYPE_ALLOC_IDR(1),
-	.destroy_object = uverbs_free_mr,
-};
+static int uverbs_create_cq_handler(struct ib_device *ib_dev,
+				    struct ib_uverbs_file *file,
+				    struct uverbs_attr_bundle *attrs)
+{
+	struct ib_ucontext *ucontext = file->ucontext;
+	struct ib_ucq_object           *obj;
+	struct ib_udata uhw;
+	int ret;
+	u64 user_handle;
+	struct ib_cq_init_attr attr = {};
+	struct ib_cq                   *cq;
+	struct ib_uverbs_completion_event_file    *ev_file = NULL;
+	const struct uverbs_attr *ev_file_attr;
+	struct ib_uobject *ev_file_uobj;
+
+	if (!(ib_dev->uverbs_cmd_mask & 1ULL << IB_USER_VERBS_CMD_CREATE_CQ))
+		return -EOPNOTSUPP;
+
+	ret = uverbs_copy_from(&attr.comp_vector, attrs, CREATE_CQ_COMP_VECTOR);
+	if (!ret)
+		ret = uverbs_copy_from(&attr.cqe, attrs, CREATE_CQ_CQE);
+	if (!ret)
+		ret = uverbs_copy_from(&user_handle, attrs, CREATE_CQ_USER_HANDLE);
+	if (ret)
+		return ret;
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_srq = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_usrq_object), 0),
-	.destroy_object = uverbs_free_srq,
-};
+	/* Optional param, if it doesn't exist, we get -ENOENT and skip it */
+	if (uverbs_copy_from(&attr.flags, attrs, CREATE_CQ_FLAGS) == -EFAULT)
+		return -EFAULT;
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_ah = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_ah,
-};
+	ev_file_attr = uverbs_attr_get(attrs, CREATE_CQ_COMP_CHANNEL);
+	if (!IS_ERR(ev_file_attr)) {
+		ev_file_uobj = ev_file_attr->obj_attr.uobject;
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_flow = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_flow,
-};
+		ev_file = container_of(ev_file_uobj,
+				       struct ib_uverbs_completion_event_file,
+				       uobj_file.uobj);
+		uverbs_uobject_get(ev_file_uobj);
+	}
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_wq = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uwq_object), 0),
-	.destroy_object = uverbs_free_wq,
-};
+	if (attr.comp_vector >= ucontext->ufile->device->num_comp_vectors) {
+		ret = -EINVAL;
+		goto err_event_file;
+	}
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_rwq_ind_table = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_rwq_ind_tbl,
-};
+	obj = container_of(uverbs_attr_get(attrs, CREATE_CQ_HANDLE)->obj_attr.uobject,
+			   typeof(*obj), uobject);
+	obj->uverbs_file	   = ucontext->ufile;
+	obj->comp_events_reported  = 0;
+	obj->async_events_reported = 0;
+	INIT_LIST_HEAD(&obj->comp_list);
+	INIT_LIST_HEAD(&obj->async_list);
+
+	/* Temporary, only until drivers get the new uverbs_attr_bundle */
+	create_udata(attrs, &uhw);
+
+	cq = ib_dev->create_cq(ib_dev, &attr, ucontext, &uhw);
+	if (IS_ERR(cq)) {
+		ret = PTR_ERR(cq);
+		goto err_event_file;
+	}
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_xrcd = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uxrcd_object), 0),
-	.destroy_object = uverbs_free_xrcd,
-};
+	cq->device        = ib_dev;
+	cq->uobject       = &obj->uobject;
+	cq->comp_handler  = ib_uverbs_comp_handler;
+	cq->event_handler = ib_uverbs_cq_event_handler;
+	cq->cq_context    = &ev_file->ev_queue;
+	obj->uobject.object = cq;
+	obj->uobject.user_handle = user_handle;
+	atomic_set(&cq->usecnt, 0);
+
+	ret = uverbs_copy_to(attrs, CREATE_CQ_RESP_CQE, &cq->cqe);
+	if (ret)
+		goto err_cq;
 
-const struct uverbs_obj_idr_type uverbs_type_attrs_pd = {
-	/* 2 is used in order to free the PD after MRs */
-	.type = UVERBS_TYPE_ALLOC_IDR(2),
-	.destroy_object = uverbs_free_pd,
+	return 0;
+err_cq:
+	ib_destroy_cq(cq);
+
+err_event_file:
+	if (ev_file)
+		uverbs_uobject_put(ev_file_uobj);
+	return ret;
 };
+
+static DECLARE_UVERBS_METHOD(
+	uverbs_method_cq_create, UVERBS_CQ_CREATE, uverbs_create_cq_handler,
+	&UVERBS_ATTR_IDR(CREATE_CQ_HANDLE, UVERBS_OBJECT_CQ, UVERBS_ACCESS_NEW,
+			 UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_CQE, u32,
+			    UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_USER_HANDLE, u64,
+			    UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_FD(CREATE_CQ_COMP_CHANNEL, UVERBS_OBJECT_COMP_CHANNEL,
+			UVERBS_ACCESS_READ),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_COMP_VECTOR, u32,
+			    UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_FLAGS, u32),
+	&UVERBS_ATTR_PTR_OUT(CREATE_CQ_RESP_CQE, u32,
+			     UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&uverbs_uhw_compat_in, &uverbs_uhw_compat_out);
+
+static int uverbs_destroy_cq_handler(struct ib_device *ib_dev,
+				     struct ib_uverbs_file *file,
+				     struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uverbs_destroy_cq_resp resp;
+	struct ib_uobject *uobj =
+		uverbs_attr_get(attrs, DESTROY_CQ_HANDLE)->obj_attr.uobject;
+	struct ib_ucq_object *obj = container_of(uobj, struct ib_ucq_object,
+						 uobject);
+	int ret;
+
+	if (!(ib_dev->uverbs_cmd_mask & 1ULL << IB_USER_VERBS_CMD_DESTROY_CQ))
+		return -EOPNOTSUPP;
+
+	ret = rdma_explicit_destroy(uobj);
+	if (ret)
+		return ret;
+
+	resp.comp_events_reported  = obj->comp_events_reported;
+	resp.async_events_reported = obj->async_events_reported;
+
+	return uverbs_copy_to(attrs, DESTROY_CQ_RESP, &resp);
+}
+
+static DECLARE_UVERBS_METHOD(
+	uverbs_method_cq_destroy, UVERBS_CQ_DESTROY, uverbs_destroy_cq_handler,
+	&UVERBS_ATTR_IDR(DESTROY_CQ_HANDLE, UVERBS_OBJECT_CQ,
+			 UVERBS_ACCESS_DESTROY,
+			 UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_OUT(DESTROY_CQ_RESP, struct ib_uverbs_destroy_cq_resp,
+			     UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_comp_channel,
+		      UVERBS_OBJECT_COMP_CHANNEL,
+		      &UVERBS_TYPE_ALLOC_FD(0,
+					      sizeof(struct ib_uverbs_completion_event_file),
+					      uverbs_hot_unplug_completion_event_file,
+					      &uverbs_event_fops,
+					      "[infinibandevent]", O_RDONLY));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_cq, UVERBS_OBJECT_CQ,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_ucq_object), 0,
+						  uverbs_free_cq),
+		      &uverbs_method_cq_create,
+		      &uverbs_method_cq_destroy);
+
+DECLARE_UVERBS_OBJECT(uverbs_object_qp, UVERBS_OBJECT_QP,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uqp_object), 0,
+						  uverbs_free_qp));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_mw, UVERBS_OBJECT_MW,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_mw));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_mr, UVERBS_OBJECT_MR,
+		      /* 1 is used in order to free the MR after all the MWs */
+		      &UVERBS_TYPE_ALLOC_IDR(1, uverbs_free_mr));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_srq, UVERBS_OBJECT_SRQ,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_usrq_object), 0,
+						  uverbs_free_srq));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_ah, UVERBS_OBJECT_AH,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_ah));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_flow, UVERBS_OBJECT_FLOW,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_flow));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_wq, UVERBS_OBJECT_WQ,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uwq_object), 0,
+						  uverbs_free_wq));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_rwq_ind_table,
+		      UVERBS_OBJECT_RWQ_IND_TBL,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_rwq_ind_tbl));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_xrcd, UVERBS_OBJECT_XRCD,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uxrcd_object), 0,
+						  uverbs_free_xrcd));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_pd, UVERBS_OBJECT_PD,
+		      /* 2 is used in order to free the PD after MRs */
+		      &UVERBS_TYPE_ALLOC_IDR(2, uverbs_free_pd));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_device, UVERBS_OBJECT_DEVICE, NULL);
+
+DECLARE_UVERBS_OBJECT_TREE(uverbs_default_objects,
+			   &uverbs_object_device,
+			   &uverbs_object_pd,
+			   &uverbs_object_mr,
+			   &uverbs_object_comp_channel,
+			   &uverbs_object_cq,
+			   &uverbs_object_qp,
+			   &uverbs_object_ah,
+			   &uverbs_object_mw,
+			   &uverbs_object_srq,
+			   &uverbs_object_flow,
+			   &uverbs_object_wq,
+			   &uverbs_object_rwq_ind_table,
+			   &uverbs_object_xrcd);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 7f8fe443df46..ee9e27dc799b 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -180,39 +180,29 @@ EXPORT_SYMBOL(ib_rate_to_mbps);
 __attribute_const__ enum rdma_transport_type
 rdma_node_get_transport(enum rdma_node_type node_type)
 {
-	switch (node_type) {
-	case RDMA_NODE_IB_CA:
-	case RDMA_NODE_IB_SWITCH:
-	case RDMA_NODE_IB_ROUTER:
-		return RDMA_TRANSPORT_IB;
-	case RDMA_NODE_RNIC:
-		return RDMA_TRANSPORT_IWARP;
-	case RDMA_NODE_USNIC:
+
+	if (node_type == RDMA_NODE_USNIC)
 		return RDMA_TRANSPORT_USNIC;
-	case RDMA_NODE_USNIC_UDP:
+	if (node_type == RDMA_NODE_USNIC_UDP)
 		return RDMA_TRANSPORT_USNIC_UDP;
-	default:
-		BUG();
-		return 0;
-	}
+	if (node_type == RDMA_NODE_RNIC)
+		return RDMA_TRANSPORT_IWARP;
+
+	return RDMA_TRANSPORT_IB;
 }
 EXPORT_SYMBOL(rdma_node_get_transport);
 
 enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_num)
 {
+	enum rdma_transport_type lt;
 	if (device->get_link_layer)
 		return device->get_link_layer(device, port_num);
 
-	switch (rdma_node_get_transport(device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	lt = rdma_node_get_transport(device->node_type);
+	if (lt == RDMA_TRANSPORT_IB)
 		return IB_LINK_LAYER_INFINIBAND;
-	case RDMA_TRANSPORT_IWARP:
-	case RDMA_TRANSPORT_USNIC:
-	case RDMA_TRANSPORT_USNIC_UDP:
-		return IB_LINK_LAYER_ETHERNET;
-	default:
-		return IB_LINK_LAYER_UNSPECIFIED;
-	}
+
+	return IB_LINK_LAYER_ETHERNET;
 }
 EXPORT_SYMBOL(rdma_port_get_link_layer);
 
@@ -478,6 +468,8 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 	union ib_gid dgid;
 	union ib_gid sgid;
 
+	might_sleep();
+
 	memset(ah_attr, 0, sizeof *ah_attr);
 	ah_attr->type = rdma_ah_find_type(device, port_num);
 	if (rdma_cap_eth_ah(device, port_num)) {
@@ -632,11 +624,13 @@ struct ib_srq *ib_create_srq(struct ib_pd *pd,
 		srq->event_handler = srq_init_attr->event_handler;
 		srq->srq_context   = srq_init_attr->srq_context;
 		srq->srq_type      = srq_init_attr->srq_type;
+		if (ib_srq_has_cq(srq->srq_type)) {
+			srq->ext.cq   = srq_init_attr->ext.cq;
+			atomic_inc(&srq->ext.cq->usecnt);
+		}
 		if (srq->srq_type == IB_SRQT_XRC) {
 			srq->ext.xrc.xrcd = srq_init_attr->ext.xrc.xrcd;
-			srq->ext.xrc.cq   = srq_init_attr->ext.xrc.cq;
 			atomic_inc(&srq->ext.xrc.xrcd->usecnt);
-			atomic_inc(&srq->ext.xrc.cq->usecnt);
 		}
 		atomic_inc(&pd->usecnt);
 		atomic_set(&srq->usecnt, 0);
@@ -677,18 +671,18 @@ int ib_destroy_srq(struct ib_srq *srq)
 
 	pd = srq->pd;
 	srq_type = srq->srq_type;
-	if (srq_type == IB_SRQT_XRC) {
+	if (ib_srq_has_cq(srq_type))
+		cq = srq->ext.cq;
+	if (srq_type == IB_SRQT_XRC)
 		xrcd = srq->ext.xrc.xrcd;
-		cq = srq->ext.xrc.cq;
-	}
 
 	ret = srq->device->destroy_srq(srq);
 	if (!ret) {
 		atomic_dec(&pd->usecnt);
-		if (srq_type == IB_SRQT_XRC) {
+		if (srq_type == IB_SRQT_XRC)
 			atomic_dec(&xrcd->usecnt);
+		if (ib_srq_has_cq(srq_type))
 			atomic_dec(&cq->usecnt);
-		}
 	}
 
 	return ret;
@@ -838,6 +832,7 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd,
 	spin_lock_init(&qp->mr_lock);
 	INIT_LIST_HEAD(&qp->rdma_mrs);
 	INIT_LIST_HEAD(&qp->sig_mrs);
+	qp->port = 0;
 
 	if (qp_init_attr->qp_type == IB_QPT_XRC_TGT)
 		return ib_create_xrc_qp(qp, qp_init_attr);
@@ -1243,6 +1238,18 @@ int ib_resolve_eth_dmac(struct ib_device *device,
 	if (rdma_link_local_addr((struct in6_addr *)grh->dgid.raw)) {
 		rdma_get_ll_mac((struct in6_addr *)grh->dgid.raw,
 				ah_attr->roce.dmac);
+		return 0;
+	}
+	if (rdma_is_multicast_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) {
+		if (ipv6_addr_v4mapped((struct in6_addr *)ah_attr->grh.dgid.raw)) {
+			__be32 addr = 0;
+
+			memcpy(&addr, ah_attr->grh.dgid.raw + 12, 4);
+			ip_eth_mc_map(addr, (char *)ah_attr->roce.dmac);
+		} else {
+			ipv6_eth_mc_map((struct in6_addr *)ah_attr->grh.dgid.raw,
+					(char *)ah_attr->roce.dmac);
+		}
 	} else {
 		union ib_gid		sgid;
 		struct ib_gid_attr	sgid_attr;
@@ -1297,10 +1304,69 @@ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr,
 		if (ret)
 			return ret;
 	}
-	return ib_security_modify_qp(qp, attr, attr_mask, udata);
+	ret = ib_security_modify_qp(qp, attr, attr_mask, udata);
+	if (!ret && (attr_mask & IB_QP_PORT))
+		qp->port = attr->port_num;
+
+	return ret;
 }
 EXPORT_SYMBOL(ib_modify_qp_with_udata);
 
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width)
+{
+	int rc;
+	u32 netdev_speed;
+	struct net_device *netdev;
+	struct ethtool_link_ksettings lksettings;
+
+	if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET)
+		return -EINVAL;
+
+	if (!dev->get_netdev)
+		return -EOPNOTSUPP;
+
+	netdev = dev->get_netdev(dev, port_num);
+	if (!netdev)
+		return -ENODEV;
+
+	rtnl_lock();
+	rc = __ethtool_get_link_ksettings(netdev, &lksettings);
+	rtnl_unlock();
+
+	dev_put(netdev);
+
+	if (!rc) {
+		netdev_speed = lksettings.base.speed;
+	} else {
+		netdev_speed = SPEED_1000;
+		pr_warn("%s speed is unknown, defaulting to %d\n", netdev->name,
+			netdev_speed);
+	}
+
+	if (netdev_speed <= SPEED_1000) {
+		*width = IB_WIDTH_1X;
+		*speed = IB_SPEED_SDR;
+	} else if (netdev_speed <= SPEED_10000) {
+		*width = IB_WIDTH_1X;
+		*speed = IB_SPEED_FDR10;
+	} else if (netdev_speed <= SPEED_20000) {
+		*width = IB_WIDTH_4X;
+		*speed = IB_SPEED_DDR;
+	} else if (netdev_speed <= SPEED_25000) {
+		*width = IB_WIDTH_1X;
+		*speed = IB_SPEED_EDR;
+	} else if (netdev_speed <= SPEED_40000) {
+		*width = IB_WIDTH_4X;
+		*speed = IB_SPEED_FDR10;
+	} else {
+		*width = IB_WIDTH_4X;
+		*speed = IB_SPEED_EDR;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ib_get_eth_speed);
+
 int ib_modify_qp(struct ib_qp *qp,
 		 struct ib_qp_attr *qp_attr,
 		 int qp_attr_mask)
@@ -1568,15 +1634,53 @@ EXPORT_SYMBOL(ib_dealloc_fmr);
 
 /* Multicast groups */
 
+static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid)
+{
+	struct ib_qp_init_attr init_attr = {};
+	struct ib_qp_attr attr = {};
+	int num_eth_ports = 0;
+	int port;
+
+	/* If QP state >= init, it is assigned to a port and we can check this
+	 * port only.
+	 */
+	if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) {
+		if (attr.qp_state >= IB_QPS_INIT) {
+			if (qp->device->get_link_layer(qp->device, attr.port_num) !=
+			    IB_LINK_LAYER_INFINIBAND)
+				return true;
+			goto lid_check;
+		}
+	}
+
+	/* Can't get a quick answer, iterate over all ports */
+	for (port = 0; port < qp->device->phys_port_cnt; port++)
+		if (qp->device->get_link_layer(qp->device, port) !=
+		    IB_LINK_LAYER_INFINIBAND)
+			num_eth_ports++;
+
+	/* If we have at lease one Ethernet port, RoCE annex declares that
+	 * multicast LID should be ignored. We can't tell at this step if the
+	 * QP belongs to an IB or Ethernet port.
+	 */
+	if (num_eth_ports)
+		return true;
+
+	/* If all the ports are IB, we can check according to IB spec. */
+lid_check:
+	return !(lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
+		 lid == be16_to_cpu(IB_LID_PERMISSIVE));
+}
+
 int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 {
 	int ret;
 
 	if (!qp->device->attach_mcast)
 		return -ENOSYS;
-	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
-	    lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
-	    lid == be16_to_cpu(IB_LID_PERMISSIVE))
+
+	if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) ||
+	    qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid))
 		return -EINVAL;
 
 	ret = qp->device->attach_mcast(qp, gid, lid);
@@ -1592,9 +1696,9 @@ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 
 	if (!qp->device->detach_mcast)
 		return -ENOSYS;
-	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
-	    lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
-	    lid == be16_to_cpu(IB_LID_PERMISSIVE))
+
+	if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) ||
+	    qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid))
 		return -EINVAL;
 
 	ret = qp->device->detach_mcast(qp, gid, lid);
diff --git a/drivers/infiniband/hw/bnxt_re/Kconfig b/drivers/infiniband/hw/bnxt_re/Kconfig
index 19982a4a9bba..18f5ed082f41 100644
--- a/drivers/infiniband/hw/bnxt_re/Kconfig
+++ b/drivers/infiniband/hw/bnxt_re/Kconfig
@@ -1,6 +1,7 @@
 config INFINIBAND_BNXT_RE
     tristate "Broadcom Netxtreme HCA support"
     depends on ETHERNET && NETDEVICES && PCI && INET && DCB
+    depends on MAY_USE_DEVLINK
     select NET_VENDOR_BROADCOM
     select BNXT
     ---help---
diff --git a/drivers/infiniband/hw/bnxt_re/Makefile b/drivers/infiniband/hw/bnxt_re/Makefile
index 036f84efbc73..afbaa0e20670 100644
--- a/drivers/infiniband/hw/bnxt_re/Makefile
+++ b/drivers/infiniband/hw/bnxt_re/Makefile
@@ -3,4 +3,4 @@ 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
+	     qplib_sp.o qplib_fp.o  hw_counters.o
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index 85527532c49d..b3ad37fec578 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -85,7 +85,7 @@ struct bnxt_re_sqp_entries {
 };
 
 #define BNXT_RE_MIN_MSIX		2
-#define BNXT_RE_MAX_MSIX		16
+#define BNXT_RE_MAX_MSIX		9
 #define BNXT_RE_AEQ_IDX			0
 #define BNXT_RE_NQ_IDX			1
 
@@ -116,7 +116,7 @@ struct bnxt_re_dev {
 	struct bnxt_qplib_rcfw		rcfw;
 
 	/* NQ */
-	struct bnxt_qplib_nq		nq;
+	struct bnxt_qplib_nq		nq[BNXT_RE_MAX_MSIX];
 
 	/* Device Resources */
 	struct bnxt_qplib_dev_attr	dev_attr;
@@ -140,6 +140,7 @@ struct bnxt_re_dev {
 	struct bnxt_re_qp		*qp1_sqp;
 	struct bnxt_re_ah		*sqp_ah;
 	struct bnxt_re_sqp_entries sqp_tbl[1024];
+	atomic_t nq_alloc_cnt;
 };
 
 #define to_bnxt_re_dev(ptr, member)	\
diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c
new file mode 100644
index 000000000000..7b28219eba46
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c
@@ -0,0 +1,114 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS''
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+ * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Description: Statistics
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/prefetch.h>
+#include <linux/delay.h>
+
+#include <rdma/ib_addr.h>
+
+#include "bnxt_ulp.h"
+#include "roce_hsi.h"
+#include "qplib_res.h"
+#include "qplib_sp.h"
+#include "qplib_fp.h"
+#include "qplib_rcfw.h"
+#include "bnxt_re.h"
+#include "hw_counters.h"
+
+static const char * const bnxt_re_stat_name[] = {
+	[BNXT_RE_ACTIVE_QP]           =  "active_qps",
+	[BNXT_RE_ACTIVE_SRQ]          =  "active_srqs",
+	[BNXT_RE_ACTIVE_CQ]           =  "active_cqs",
+	[BNXT_RE_ACTIVE_MR]           =  "active_mrs",
+	[BNXT_RE_ACTIVE_MW]           =  "active_mws",
+	[BNXT_RE_RX_PKTS]             =  "rx_pkts",
+	[BNXT_RE_RX_BYTES]            =  "rx_bytes",
+	[BNXT_RE_TX_PKTS]             =  "tx_pkts",
+	[BNXT_RE_TX_BYTES]            =  "tx_bytes",
+	[BNXT_RE_RECOVERABLE_ERRORS]  =  "recoverable_errors"
+};
+
+int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
+			    struct rdma_hw_stats *stats,
+			    u8 port, int index)
+{
+	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
+	struct ctx_hw_stats *bnxt_re_stats = rdev->qplib_ctx.stats.dma;
+
+	if (!port || !stats)
+		return -EINVAL;
+
+	stats->value[BNXT_RE_ACTIVE_QP] = atomic_read(&rdev->qp_count);
+	stats->value[BNXT_RE_ACTIVE_SRQ] = atomic_read(&rdev->srq_count);
+	stats->value[BNXT_RE_ACTIVE_CQ] = atomic_read(&rdev->cq_count);
+	stats->value[BNXT_RE_ACTIVE_MR] = atomic_read(&rdev->mr_count);
+	stats->value[BNXT_RE_ACTIVE_MW] = atomic_read(&rdev->mw_count);
+	if (bnxt_re_stats) {
+		stats->value[BNXT_RE_RECOVERABLE_ERRORS] =
+			le64_to_cpu(bnxt_re_stats->tx_bcast_pkts);
+		stats->value[BNXT_RE_RX_PKTS] =
+			le64_to_cpu(bnxt_re_stats->rx_ucast_pkts);
+		stats->value[BNXT_RE_RX_BYTES] =
+			le64_to_cpu(bnxt_re_stats->rx_ucast_bytes);
+		stats->value[BNXT_RE_TX_PKTS] =
+			le64_to_cpu(bnxt_re_stats->tx_ucast_pkts);
+		stats->value[BNXT_RE_TX_BYTES] =
+			le64_to_cpu(bnxt_re_stats->tx_ucast_bytes);
+	}
+	return ARRAY_SIZE(bnxt_re_stat_name);
+}
+
+struct rdma_hw_stats *bnxt_re_ib_alloc_hw_stats(struct ib_device *ibdev,
+						u8 port_num)
+{
+	BUILD_BUG_ON(ARRAY_SIZE(bnxt_re_stat_name) != BNXT_RE_NUM_COUNTERS);
+	/* We support only per port stats */
+	if (!port_num)
+		return NULL;
+
+	return rdma_alloc_hw_stats_struct(bnxt_re_stat_name,
+					  ARRAY_SIZE(bnxt_re_stat_name),
+					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.h b/drivers/infiniband/hw/bnxt_re/hw_counters.h
new file mode 100644
index 000000000000..be0dc0093b58
--- /dev/null
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.h
@@ -0,0 +1,62 @@
+/*
+ * Broadcom NetXtreme-E RoCE driver.
+ *
+ * Copyright (c) 2016 - 2017, Broadcom. All rights reserved.  The term
+ * Broadcom refers to Broadcom Limited and/or its subsidiaries.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS''
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+ * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Description: Statistics (header)
+ *
+ */
+
+#ifndef __BNXT_RE_HW_STATS_H__
+#define __BNXT_RE_HW_STATS_H__
+
+enum bnxt_re_hw_stats {
+	BNXT_RE_ACTIVE_QP,
+	BNXT_RE_ACTIVE_SRQ,
+	BNXT_RE_ACTIVE_CQ,
+	BNXT_RE_ACTIVE_MR,
+	BNXT_RE_ACTIVE_MW,
+	BNXT_RE_RX_PKTS,
+	BNXT_RE_RX_BYTES,
+	BNXT_RE_TX_PKTS,
+	BNXT_RE_TX_BYTES,
+	BNXT_RE_RECOVERABLE_ERRORS,
+	BNXT_RE_NUM_COUNTERS
+};
+
+struct rdma_hw_stats *bnxt_re_ib_alloc_hw_stats(struct ib_device *ibdev,
+						u8 port_num);
+int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
+			    struct rdma_hw_stats *stats,
+			    u8 port, int index);
+#endif /* __BNXT_RE_HW_STATS_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index f0e01b3ac711..01eee15bbd65 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -223,50 +223,6 @@ int bnxt_re_modify_device(struct ib_device *ibdev,
 	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)
@@ -308,25 +264,9 @@ int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num,
 	 * 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;
-	}
+		if (ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed,
+				     &port_attr->active_width))
+			return -EINVAL;
 	return 0;
 }
 
@@ -846,6 +786,7 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp)
 	struct bnxt_re_dev *rdev = qp->rdev;
 	int rc;
 
+	bnxt_qplib_del_flush_qp(&qp->qplib_qp);
 	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
 	if (rc) {
 		dev_err(rdev_to_dev(rdev), "Failed to destroy HW QP");
@@ -860,6 +801,7 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp)
 			return rc;
 		}
 
+		bnxt_qplib_del_flush_qp(&qp->qplib_qp);
 		rc = bnxt_qplib_destroy_qp(&rdev->qplib_res,
 					   &rdev->qp1_sqp->qplib_qp);
 		if (rc) {
@@ -969,7 +911,6 @@ static struct bnxt_re_ah *bnxt_re_create_shadow_qp_ah
 	if (!ah)
 		return NULL;
 
-	memset(ah, 0, sizeof(*ah));
 	ah->rdev = rdev;
 	ah->qplib_ah.pd = &pd->qplib_pd;
 
@@ -1016,7 +957,6 @@ static struct bnxt_re_qp *bnxt_re_create_shadow_qp
 	if (!qp)
 		return NULL;
 
-	memset(qp, 0, sizeof(*qp));
 	qp->rdev = rdev;
 
 	/* Initialize the shadow QP structure from the QP1 values */
@@ -1404,6 +1344,21 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		}
 		qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_STATE;
 		qp->qplib_qp.state = __from_ib_qp_state(qp_attr->qp_state);
+
+		if (!qp->sumem &&
+		    qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+			dev_dbg(rdev_to_dev(rdev),
+				"Move QP = %p to flush list\n",
+				qp);
+			bnxt_qplib_add_flush_qp(&qp->qplib_qp);
+		}
+		if (!qp->sumem &&
+		    qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_RESET) {
+			dev_dbg(rdev_to_dev(rdev),
+				"Move QP = %p out of flush list\n",
+				qp);
+			bnxt_qplib_del_flush_qp(&qp->qplib_qp);
+		}
 	}
 	if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) {
 		qp->qplib_qp.modify_flags |=
@@ -2333,6 +2288,7 @@ 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;
+	struct bnxt_qplib_nq *nq = cq->qplib_cq.nq;
 
 	rc = bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
 	if (rc) {
@@ -2347,7 +2303,7 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq)
 		kfree(cq);
 	}
 	atomic_dec(&rdev->cq_count);
-	rdev->nq.budget--;
+	nq->budget--;
 	return 0;
 }
 
@@ -2361,6 +2317,8 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
 	struct bnxt_re_cq *cq = NULL;
 	int rc, entries;
 	int cqe = attr->cqe;
+	struct bnxt_qplib_nq *nq = NULL;
+	unsigned int nq_alloc_cnt;
 
 	/* Validate CQ fields */
 	if (cqe < 1 || cqe > dev_attr->max_cq_wqes) {
@@ -2412,8 +2370,15 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
 		cq->qplib_cq.sghead = NULL;
 		cq->qplib_cq.nmap = 0;
 	}
+	/*
+	 * Allocating the NQ in a round robin fashion. nq_alloc_cnt is a
+	 * used for getting the NQ index.
+	 */
+	nq_alloc_cnt = atomic_inc_return(&rdev->nq_alloc_cnt);
+	nq = &rdev->nq[nq_alloc_cnt % (rdev->num_msix - 1)];
 	cq->qplib_cq.max_wqe = entries;
-	cq->qplib_cq.cnq_hw_ring_id = rdev->nq.ring_id;
+	cq->qplib_cq.cnq_hw_ring_id = nq->ring_id;
+	cq->qplib_cq.nq	= nq;
 
 	rc = bnxt_qplib_create_cq(&rdev->qplib_res, &cq->qplib_cq);
 	if (rc) {
@@ -2423,7 +2388,7 @@ struct ib_cq *bnxt_re_create_cq(struct ib_device *ibdev,
 
 	cq->ib_cq.cqe = entries;
 	cq->cq_period = cq->qplib_cq.period;
-	rdev->nq.budget++;
+	nq->budget++;
 
 	atomic_inc(&rdev->cq_count);
 
@@ -2921,6 +2886,10 @@ int bnxt_re_poll_cq(struct ib_cq *ib_cq, int num_entries, struct ib_wc *wc)
 					sq->send_phantom = false;
 			}
 		}
+		if (ncqe < budget)
+			ncqe += bnxt_qplib_process_flush_list(&cq->qplib_cq,
+							      cqe + ncqe,
+							      budget - ncqe);
 
 		if (!ncqe)
 			break;
@@ -3410,7 +3379,7 @@ int bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
 					    &rdev->qplib_res.dpi_tbl,
 					    &uctx->dpi);
 		if (rc)
-			dev_err(rdev_to_dev(rdev), "Deallocte HW DPI failed!");
+			dev_err(rdev_to_dev(rdev), "Deallocate HW DPI failed!");
 			/* Don't fail, continue*/
 		uctx->dpi.dbr = NULL;
 	}
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index a0bb7e33d7ca..1df11ed272ea 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -141,9 +141,6 @@ int bnxt_re_modify_device(struct ib_device *ibdev,
 			  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,
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index ceae2d92fb08..82d1cbc27aee 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -64,13 +64,14 @@
 #include "ib_verbs.h"
 #include <rdma/bnxt_re-abi.h>
 #include "bnxt.h"
+#include "hw_counters.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);
@@ -162,7 +163,7 @@ static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait)
 
 static int bnxt_re_request_msix(struct bnxt_re_dev *rdev)
 {
-	int rc = 0, num_msix_want = BNXT_RE_MIN_MSIX, num_msix_got;
+	int rc = 0, num_msix_want = BNXT_RE_MAX_MSIX, num_msix_got;
 	struct bnxt_en_dev *en_dev;
 
 	if (!rdev)
@@ -170,6 +171,8 @@ static int bnxt_re_request_msix(struct bnxt_re_dev *rdev)
 
 	en_dev = rdev->en_dev;
 
+	num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus());
+
 	rtnl_lock();
 	num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP,
 							 rdev->msix_entries,
@@ -474,7 +477,6 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 	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;
@@ -513,6 +515,8 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 	ibdev->alloc_ucontext		= bnxt_re_alloc_ucontext;
 	ibdev->dealloc_ucontext		= bnxt_re_dealloc_ucontext;
 	ibdev->mmap			= bnxt_re_mmap;
+	ibdev->get_hw_stats             = bnxt_re_ib_get_hw_stats;
+	ibdev->alloc_hw_stats           = bnxt_re_ib_alloc_hw_stats;
 
 	return ib_register_device(ibdev, NULL);
 }
@@ -653,8 +657,12 @@ static int bnxt_re_cqn_handler(struct bnxt_qplib_nq *nq,
 
 static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
 {
-	if (rdev->nq.hwq.max_elements)
-		bnxt_qplib_disable_nq(&rdev->nq);
+	int i;
+
+	if (rdev->nq[0].hwq.max_elements) {
+		for (i = 1; i < rdev->num_msix; i++)
+			bnxt_qplib_disable_nq(&rdev->nq[i - 1]);
+	}
 
 	if (rdev->qplib_res.rcfw)
 		bnxt_qplib_cleanup_res(&rdev->qplib_res);
@@ -662,31 +670,41 @@ static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
 
 static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
 {
-	int rc = 0;
+	int rc = 0, i;
 
 	bnxt_qplib_init_res(&rdev->qplib_res);
 
-	if (rdev->msix_entries[BNXT_RE_NQ_IDX].vector <= 0)
-		return -EINVAL;
+	for (i = 1; i < rdev->num_msix ; i++) {
+		rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1],
+					  i - 1, rdev->msix_entries[i].vector,
+					  rdev->msix_entries[i].db_offset,
+					  &bnxt_re_cqn_handler, NULL);
 
-	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 with rc = 0x%x", rc);
+			goto fail;
+		}
+	}
+	return 0;
+fail:
+	return rc;
+}
 
-	if (rc)
-		dev_err(rdev_to_dev(rdev), "Failed to enable NQ: %#x", rc);
+static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev, bool lock_wait)
+{
+	int i;
 
-	return rc;
+	for (i = 0; i < rdev->num_msix - 1; i++) {
+		bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, lock_wait);
+		bnxt_qplib_free_nq(&rdev->nq[i]);
+	}
 }
 
 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);
-	}
+	bnxt_re_free_nq_res(rdev, lock_wait);
+
 	if (rdev->qplib_res.dpi_tbl.max) {
 		bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
 				       &rdev->qplib_res.dpi_tbl,
@@ -700,7 +718,7 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev, bool lock_wait)
 
 static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 {
-	int rc = 0;
+	int rc = 0, i;
 
 	/* Configure and allocate resources for qplib */
 	rdev->qplib_res.rcfw = &rdev->rcfw;
@@ -717,30 +735,42 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 				  &rdev->dpi_privileged,
 				  rdev);
 	if (rc)
-		goto fail;
+		goto dealloc_res;
 
-	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;
+	for (i = 0; i < rdev->num_msix - 1; i++) {
+		rdev->nq[i].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[i]);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev), "Alloc Failed NQ%d rc:%#x",
+				i, rc);
+			goto dealloc_dpi;
+		}
+		rc = bnxt_re_net_ring_alloc
+			(rdev, rdev->nq[i].hwq.pbl[PBL_LVL_0].pg_map_arr,
+			 rdev->nq[i].hwq.pbl[rdev->nq[i].hwq.level].pg_count,
+			 HWRM_RING_ALLOC_CMPL,
+			 BNXT_QPLIB_NQE_MAX_CNT - 1,
+			 rdev->msix_entries[i + 1].ring_idx,
+			 &rdev->nq[i].ring_id);
+		if (rc) {
+			dev_err(rdev_to_dev(rdev),
+				"Failed to allocate NQ fw id with rc = 0x%x",
+				rc);
+			goto free_nq;
+		}
 	}
 	return 0;
 free_nq:
-	bnxt_qplib_free_nq(&rdev->nq);
+	for (i = 0; i < rdev->num_msix - 1; i++)
+		bnxt_qplib_free_nq(&rdev->nq[i]);
+dealloc_dpi:
+	bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
+			       &rdev->qplib_res.dpi_tbl,
+			       &rdev->dpi_privileged);
+dealloc_res:
+	bnxt_qplib_free_res(&rdev->qplib_res);
+
 fail:
 	rdev->qplib_res.rcfw = NULL;
 	return rc;
@@ -835,6 +865,42 @@ static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev)
 	mutex_unlock(&rdev->qp_lock);
 }
 
+static int bnxt_re_update_gid(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+	struct bnxt_qplib_gid gid;
+	u16 gid_idx, index;
+	int rc = 0;
+
+	if (!test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
+		return 0;
+
+	if (!sgid_tbl) {
+		dev_err(rdev_to_dev(rdev), "QPLIB: SGID table not allocated");
+		return -EINVAL;
+	}
+
+	for (index = 0; index < sgid_tbl->active; index++) {
+		gid_idx = sgid_tbl->hw_id[index];
+
+		if (!memcmp(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero,
+			    sizeof(bnxt_qplib_gid_zero)))
+			continue;
+		/* need to modify the VLAN enable setting of non VLAN GID only
+		 * as setting is done for VLAN GID while adding GID
+		 */
+		if (sgid_tbl->vlan[index])
+			continue;
+
+		memcpy(&gid, &sgid_tbl->tbl[index], sizeof(gid));
+
+		rc = bnxt_qplib_update_sgid(sgid_tbl, &gid, gid_idx,
+					    rdev->qplib_res.netdev->dev_addr);
+	}
+
+	return rc;
+}
+
 static u32 bnxt_re_get_priority_mask(struct bnxt_re_dev *rdev)
 {
 	u32 prio_map = 0, tmp_map = 0;
@@ -854,8 +920,6 @@ static u32 bnxt_re_get_priority_mask(struct bnxt_re_dev *rdev)
 	tmp_map = dcb_ieee_getapp_mask(netdev, &app);
 	prio_map |= tmp_map;
 
-	if (!prio_map)
-		prio_map = -EFAULT;
 	return prio_map;
 }
 
@@ -881,10 +945,7 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev)
 	int rc;
 
 	/* Get priority for roce */
-	rc = bnxt_re_get_priority_mask(rdev);
-	if (rc < 0)
-		return rc;
-	prio_map = (u8)rc;
+	prio_map = bnxt_re_get_priority_mask(rdev);
 
 	if (prio_map == rdev->cur_prio_map)
 		return 0;
@@ -906,6 +967,16 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev)
 		return rc;
 	}
 
+	/* Actual priorities are not programmed as they are already
+	 * done by L2 driver; just enable or disable priority vlan tagging
+	 */
+	if ((prio_map == 0 && rdev->qplib_res.prio) ||
+	    (prio_map != 0 && !rdev->qplib_res.prio)) {
+		rdev->qplib_res.prio = prio_map ? true : false;
+
+		bnxt_re_update_gid(rdev);
+	}
+
 	return 0;
 }
 
@@ -998,7 +1069,8 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev)
 	/* 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);
+	rc = bnxt_qplib_alloc_rcfw_channel(rdev->en_dev->pdev, &rdev->rcfw,
+					   BNXT_RE_MAX_QPC_COUNT);
 	if (rc)
 		goto fail;
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 9af1514e5944..e8afc47f8949 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -51,6 +51,168 @@
 #include "qplib_fp.h"
 
 static void bnxt_qplib_arm_cq_enable(struct bnxt_qplib_cq *cq);
+static void __clean_cq(struct bnxt_qplib_cq *cq, u64 qp);
+
+static void bnxt_qplib_cancel_phantom_processing(struct bnxt_qplib_qp *qp)
+{
+	qp->sq.condition = false;
+	qp->sq.send_phantom = false;
+	qp->sq.single = false;
+}
+
+/* Flush list */
+static void __bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_cq *scq, *rcq;
+
+	scq = qp->scq;
+	rcq = qp->rcq;
+
+	if (!qp->sq.flushed) {
+		dev_dbg(&scq->hwq.pdev->dev,
+			"QPLIB: FP: Adding to SQ Flush list = %p",
+			qp);
+		bnxt_qplib_cancel_phantom_processing(qp);
+		list_add_tail(&qp->sq_flush, &scq->sqf_head);
+		qp->sq.flushed = true;
+	}
+	if (!qp->srq) {
+		if (!qp->rq.flushed) {
+			dev_dbg(&rcq->hwq.pdev->dev,
+				"QPLIB: FP: Adding to RQ Flush list = %p",
+				qp);
+			list_add_tail(&qp->rq_flush, &rcq->rqf_head);
+			qp->rq.flushed = true;
+		}
+	}
+}
+
+void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp,
+				 unsigned long *flags)
+	__acquires(&qp->scq->hwq.lock) __acquires(&qp->rcq->hwq.lock)
+{
+	spin_lock_irqsave(&qp->scq->hwq.lock, *flags);
+	if (qp->scq == qp->rcq)
+		__acquire(&qp->rcq->hwq.lock);
+	else
+		spin_lock(&qp->rcq->hwq.lock);
+}
+
+void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp,
+				 unsigned long *flags)
+	__releases(&qp->scq->hwq.lock) __releases(&qp->rcq->hwq.lock)
+{
+	if (qp->scq == qp->rcq)
+		__release(&qp->rcq->hwq.lock);
+	else
+		spin_unlock(&qp->rcq->hwq.lock);
+	spin_unlock_irqrestore(&qp->scq->hwq.lock, *flags);
+}
+
+static struct bnxt_qplib_cq *bnxt_qplib_find_buddy_cq(struct bnxt_qplib_qp *qp,
+						      struct bnxt_qplib_cq *cq)
+{
+	struct bnxt_qplib_cq *buddy_cq = NULL;
+
+	if (qp->scq == qp->rcq)
+		buddy_cq = NULL;
+	else if (qp->scq == cq)
+		buddy_cq = qp->rcq;
+	else
+		buddy_cq = qp->scq;
+	return buddy_cq;
+}
+
+static void bnxt_qplib_lock_buddy_cq(struct bnxt_qplib_qp *qp,
+				     struct bnxt_qplib_cq *cq)
+	__acquires(&buddy_cq->hwq.lock)
+{
+	struct bnxt_qplib_cq *buddy_cq = NULL;
+
+	buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq);
+	if (!buddy_cq)
+		__acquire(&cq->hwq.lock);
+	else
+		spin_lock(&buddy_cq->hwq.lock);
+}
+
+static void bnxt_qplib_unlock_buddy_cq(struct bnxt_qplib_qp *qp,
+				       struct bnxt_qplib_cq *cq)
+	__releases(&buddy_cq->hwq.lock)
+{
+	struct bnxt_qplib_cq *buddy_cq = NULL;
+
+	buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq);
+	if (!buddy_cq)
+		__release(&cq->hwq.lock);
+	else
+		spin_unlock(&buddy_cq->hwq.lock);
+}
+
+void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp)
+{
+	unsigned long flags;
+
+	bnxt_qplib_acquire_cq_locks(qp, &flags);
+	__bnxt_qplib_add_flush_qp(qp);
+	bnxt_qplib_release_cq_locks(qp, &flags);
+}
+
+static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp)
+{
+	struct bnxt_qplib_cq *scq, *rcq;
+
+	scq = qp->scq;
+	rcq = qp->rcq;
+
+	if (qp->sq.flushed) {
+		qp->sq.flushed = false;
+		list_del(&qp->sq_flush);
+	}
+	if (!qp->srq) {
+		if (qp->rq.flushed) {
+			qp->rq.flushed = false;
+			list_del(&qp->rq_flush);
+		}
+	}
+}
+
+void bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp)
+{
+	unsigned long flags;
+
+	bnxt_qplib_acquire_cq_locks(qp, &flags);
+	__clean_cq(qp->scq, (u64)(unsigned long)qp);
+	qp->sq.hwq.prod = 0;
+	qp->sq.hwq.cons = 0;
+	__clean_cq(qp->rcq, (u64)(unsigned long)qp);
+	qp->rq.hwq.prod = 0;
+	qp->rq.hwq.cons = 0;
+
+	__bnxt_qplib_del_flush_qp(qp);
+	bnxt_qplib_release_cq_locks(qp, &flags);
+}
+
+static void bnxt_qpn_cqn_sched_task(struct work_struct *work)
+{
+	struct bnxt_qplib_nq_work *nq_work =
+			container_of(work, struct bnxt_qplib_nq_work, work);
+
+	struct bnxt_qplib_cq *cq = nq_work->cq;
+	struct bnxt_qplib_nq *nq = nq_work->nq;
+
+	if (cq && nq) {
+		spin_lock_bh(&cq->compl_lock);
+		if (atomic_read(&cq->arm_state) && nq->cqn_handler) {
+			dev_dbg(&nq->pdev->dev,
+				"%s:Trigger cq  = %p event nq = %p\n",
+				__func__, cq, nq);
+			nq->cqn_handler(nq, cq);
+		}
+		spin_unlock_bh(&cq->compl_lock);
+	}
+	kfree(nq_work);
+}
 
 static void bnxt_qplib_free_qp_hdr_buf(struct bnxt_qplib_res *res,
 				       struct bnxt_qplib_qp *qp)
@@ -119,6 +281,7 @@ 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;
+	struct bnxt_qplib_cq *cq;
 	int num_cqne_processed = 0;
 	u32 sw_cons, raw_cons;
 	u16 type;
@@ -143,15 +306,17 @@ static void bnxt_qplib_service_nq(unsigned long data)
 			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)))
+			cq = (struct bnxt_qplib_cq *)(unsigned long)q_handle;
+			bnxt_qplib_arm_cq_enable(cq);
+			spin_lock_bh(&cq->compl_lock);
+			atomic_set(&cq->arm_state, 0);
+			if (!nq->cqn_handler(nq, (cq)))
 				num_cqne_processed++;
 			else
 				dev_warn(&nq->pdev->dev,
 					 "QPLIB: cqn - type 0x%x not handled",
 					 type);
+			spin_unlock_bh(&cq->compl_lock);
 			break;
 		}
 		case NQ_BASE_TYPE_DBQ_EVENT:
@@ -190,12 +355,17 @@ static irqreturn_t bnxt_qplib_nq_irq(int irq, void *dev_instance)
 
 void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
 {
+	if (nq->cqn_wq) {
+		destroy_workqueue(nq->cqn_wq);
+		nq->cqn_wq = NULL;
+	}
 	/* Make sure the HW is stopped! */
 	synchronize_irq(nq->vector);
 	tasklet_disable(&nq->worker);
 	tasklet_kill(&nq->worker);
 
 	if (nq->requested) {
+		irq_set_affinity_hint(nq->vector, NULL);
 		free_irq(nq->vector, nq);
 		nq->requested = false;
 	}
@@ -209,14 +379,14 @@ 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 nq_idx, 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;
+	int rc = -1;
 
 	nq->pdev = pdev;
 	nq->vector = msix_vector;
@@ -227,14 +397,31 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 
 	tasklet_init(&nq->worker, bnxt_qplib_service_nq, (unsigned long)nq);
 
+	/* Have a task to schedule CQ notifiers in post send case */
+	nq->cqn_wq  = create_singlethread_workqueue("bnxt_qplib_nq");
+	if (!nq->cqn_wq)
+		goto fail;
+
 	nq->requested = false;
-	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, "bnxt_qplib_nq", nq);
+	memset(nq->name, 0, 32);
+	sprintf(nq->name, "bnxt_qplib_nq-%d", nq_idx);
+	rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, nq->name, nq);
 	if (rc) {
 		dev_err(&nq->pdev->dev,
 			"Failed to request IRQ for NQ: %#x", rc);
 		bnxt_qplib_disable_nq(nq);
 		goto fail;
 	}
+
+	cpumask_clear(&nq->mask);
+	cpumask_set_cpu(nq_idx, &nq->mask);
+	rc = irq_set_affinity_hint(nq->vector, &nq->mask);
+	if (rc) {
+		dev_warn(&nq->pdev->dev,
+			 "QPLIB: set affinity failed; vector: %d nq_idx: %d\n",
+			 nq->vector, nq_idx);
+	}
+
 	nq->requested = true;
 	nq->bar_reg = NQ_CONS_PCI_BAR_REGION;
 	nq->bar_reg_off = bar_reg_offset;
@@ -258,8 +445,10 @@ fail:
 
 void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq)
 {
-	if (nq->hwq.max_elements)
+	if (nq->hwq.max_elements) {
 		bnxt_qplib_free_hwq(nq->pdev, &nq->hwq);
+		nq->hwq.max_elements = 0;
+	}
 }
 
 int bnxt_qplib_alloc_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq)
@@ -401,8 +590,8 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 
 	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;
+	rcfw->qp_tbl[qp->id].qp_id = qp->id;
+	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
 
 	return 0;
 
@@ -615,8 +804,10 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 
 	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;
+	INIT_LIST_HEAD(&qp->sq_flush);
+	INIT_LIST_HEAD(&qp->rq_flush);
+	rcfw->qp_tbl[qp->id].qp_id = qp->id;
+	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
 
 	return 0;
 
@@ -963,13 +1154,19 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
 	u16 cmd_flags = 0;
 	int rc;
 
+	rcfw->qp_tbl[qp->id].qp_id = BNXT_QPLIB_QP_ID_INVALID;
+	rcfw->qp_tbl[qp->id].qp_handle = NULL;
+
 	RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags);
 
 	req.qp_cid = cpu_to_le32(qp->id);
 	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
 					  (void *)&resp, NULL, 0);
-	if (rc)
+	if (rc) {
+		rcfw->qp_tbl[qp->id].qp_id = qp->id;
+		rcfw->qp_tbl[qp->id].qp_handle = qp;
 		return rc;
+	}
 
 	/* Must walk the associated CQs to nullified the QP ptr */
 	spin_lock_irqsave(&qp->scq->hwq.lock, flags);
@@ -1074,14 +1271,21 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 	struct bnxt_qplib_swq *swq;
 	struct sq_send *hw_sq_send_hdr, **hw_sq_send_ptr;
 	struct sq_sge *hw_sge;
+	struct bnxt_qplib_nq_work *nq_work = NULL;
+	bool sch_handler = false;
 	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 (qp->state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+			sch_handler = true;
+			dev_dbg(&sq->hwq.pdev->dev,
+				"%s Error QP. Scheduling for poll_cq\n",
+				__func__);
+			goto queue_err;
+		}
 	}
 
 	if (bnxt_qplib_queue_full(sq)) {
@@ -1301,12 +1505,35 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 			((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) &
 			 SQ_PSN_SEARCH_NEXT_PSN_MASK));
 	}
-
+queue_err:
+	if (sch_handler) {
+		/* Store the ULP info in the software structures */
+		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;
+	}
 	sq->hwq.prod++;
-
 	qp->wqe_cnt++;
 
 done:
+	if (sch_handler) {
+		nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC);
+		if (nq_work) {
+			nq_work->cq = qp->scq;
+			nq_work->nq = qp->scq->nq;
+			INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task);
+			queue_work(qp->scq->nq->cqn_wq, &nq_work->work);
+		} else {
+			dev_err(&sq->hwq.pdev->dev,
+				"QPLIB: FP: Failed to allocate SQ nq_work!");
+			rc = -ENOMEM;
+		}
+	}
 	return rc;
 }
 
@@ -1334,15 +1561,17 @@ int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp,
 	struct bnxt_qplib_q *rq = &qp->rq;
 	struct rq_wqe *rqe, **rqe_ptr;
 	struct sq_sge *hw_sge;
+	struct bnxt_qplib_nq_work *nq_work = NULL;
+	bool sch_handler = false;
 	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;
+		sch_handler = true;
+		dev_dbg(&rq->hwq.pdev->dev,
+			"%s Error QP. Scheduling for poll_cq\n",
+			__func__);
+		goto queue_err;
 	}
 	if (bnxt_qplib_queue_full(rq)) {
 		dev_err(&rq->hwq.pdev->dev,
@@ -1378,7 +1607,27 @@ int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp,
 	/* Supply the rqe->wr_id index to the wr_id_tbl for now */
 	rqe->wr_id[0] = cpu_to_le32(sw_prod);
 
+queue_err:
+	if (sch_handler) {
+		/* Store the ULP info in the software structures */
+		sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
+		rq->swq[sw_prod].wr_id = wqe->wr_id;
+	}
+
 	rq->hwq.prod++;
+	if (sch_handler) {
+		nq_work = kzalloc(sizeof(*nq_work), GFP_ATOMIC);
+		if (nq_work) {
+			nq_work->cq = qp->rcq;
+			nq_work->nq = qp->rcq->nq;
+			INIT_WORK(&nq_work->work, bnxt_qpn_cqn_sched_task);
+			queue_work(qp->rcq->nq->cqn_wq, &nq_work->work);
+		} else {
+			dev_err(&rq->hwq.pdev->dev,
+				"QPLIB: FP: Failed to allocate RQ nq_work!");
+			rc = -ENOMEM;
+		}
+	}
 done:
 	return rc;
 }
@@ -1471,6 +1720,9 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
 	cq->dbr_base = res->dpi_tbl.dbr_bar_reg_iomem;
 	cq->period = BNXT_QPLIB_QUEUE_START_PERIOD;
 	init_waitqueue_head(&cq->waitq);
+	INIT_LIST_HEAD(&cq->sqf_head);
+	INIT_LIST_HEAD(&cq->rqf_head);
+	spin_lock_init(&cq->compl_lock);
 
 	bnxt_qplib_arm_cq_enable(cq);
 	return 0;
@@ -1513,9 +1765,13 @@ static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp,
 	while (*budget) {
 		sw_cons = HWQ_CMP(sq->hwq.cons, &sq->hwq);
 		if (sw_cons == sw_prod) {
-			sq->flush_in_progress = false;
 			break;
 		}
+		/* Skip the FENCE WQE completions */
+		if (sq->swq[sw_cons].wr_id == BNXT_QPLIB_FENCE_WRID) {
+			bnxt_qplib_cancel_phantom_processing(qp);
+			goto skip_compl;
+		}
 		memset(cqe, 0, sizeof(*cqe));
 		cqe->status = CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR;
 		cqe->opcode = CQ_BASE_CQE_TYPE_REQ;
@@ -1525,6 +1781,7 @@ static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp,
 		cqe->type = sq->swq[sw_cons].type;
 		cqe++;
 		(*budget)--;
+skip_compl:
 		sq->hwq.cons++;
 	}
 	*pcqe = cqe;
@@ -1536,11 +1793,24 @@ static int __flush_sq(struct bnxt_qplib_q *sq, struct bnxt_qplib_qp *qp,
 }
 
 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 **pcqe, int *budget)
 {
 	struct bnxt_qplib_cqe *cqe;
 	u32 sw_prod, sw_cons;
 	int rc = 0;
+	int opcode = 0;
+
+	switch (qp->type) {
+	case CMDQ_CREATE_QP1_TYPE_GSI:
+		opcode = CQ_BASE_CQE_TYPE_RES_RAWETH_QP1;
+		break;
+	case CMDQ_CREATE_QP_TYPE_RC:
+		opcode = CQ_BASE_CQE_TYPE_RES_RC;
+		break;
+	case CMDQ_CREATE_QP_TYPE_UD:
+		opcode = CQ_BASE_CQE_TYPE_RES_UD;
+		break;
+	}
 
 	/* Flush the rest of the RQ */
 	sw_prod = HWQ_CMP(rq->hwq.prod, &rq->hwq);
@@ -1567,6 +1837,21 @@ static int __flush_rq(struct bnxt_qplib_q *rq, struct bnxt_qplib_qp *qp,
 	return rc;
 }
 
+void bnxt_qplib_mark_qp_error(void *qp_handle)
+{
+	struct bnxt_qplib_qp *qp = qp_handle;
+
+	if (!qp)
+		return;
+
+	/* Must block new posting of SQ and RQ */
+	qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR;
+	bnxt_qplib_cancel_phantom_processing(qp);
+
+	/* Add qp to flush list of the CQ */
+	__bnxt_qplib_add_flush_qp(qp);
+}
+
 /* Note: SQE is valid from sw_sq_cons up to cqe_sq_cons (exclusive)
  *       CQE is track from sw_cq_cons to max_element but valid only if VALID=1
  */
@@ -1694,10 +1979,12 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 			cqe_sq_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;
 
+	if (qp->sq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
 	/* Require to walk the sq's swq to fabricate CQEs for all previously
 	 * signaled SWQEs due to CQE aggregation from the current sq cons
 	 * to the cqe_sq_cons
@@ -1733,11 +2020,9 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 				sw_sq_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;
-			sq->condition = false;
-			sq->single = false;
+			bnxt_qplib_lock_buddy_cq(qp, cq);
+			bnxt_qplib_mark_qp_error(qp);
+			bnxt_qplib_unlock_buddy_cq(qp, cq);
 		} else {
 			if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
 				/* Before we complete, do WA 9060 */
@@ -1768,15 +2053,6 @@ out:
 	 * the WC for this CQE
 	 */
 	sq->single = false;
-	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;
 }
@@ -1798,6 +2074,12 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq,
 		dev_err(&cq->hwq.pdev->dev, "QPLIB: process_cq RC qp is NULL");
 		return -EINVAL;
 	}
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
+
 	cqe = *pcqe;
 	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
 	cqe->length = le32_to_cpu(hwcqe->length);
@@ -1817,8 +2099,6 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq,
 			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++;
@@ -1827,12 +2107,13 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq,
 	*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;
+		 /* Add qp to flush list of the CQ */
+		bnxt_qplib_lock_buddy_cq(qp, cq);
+		__bnxt_qplib_add_flush_qp(qp);
+		bnxt_qplib_unlock_buddy_cq(qp, cq);
 	}
+
+done:
 	return rc;
 }
 
@@ -1853,6 +2134,11 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq,
 		dev_err(&cq->hwq.pdev->dev, "QPLIB: process_cq UD qp is NULL");
 		return -EINVAL;
 	}
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
 	cqe = *pcqe;
 	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
 	cqe->length = le32_to_cpu(hwcqe->length);
@@ -1876,8 +2162,6 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq,
 			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++;
@@ -1886,12 +2170,12 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq,
 	*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;
+		/* Add qp to flush list of the CQ */
+		bnxt_qplib_lock_buddy_cq(qp, cq);
+		__bnxt_qplib_add_flush_qp(qp);
+		bnxt_qplib_unlock_buddy_cq(qp, cq);
 	}
+done:
 	return rc;
 }
 
@@ -1932,6 +2216,11 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq,
 			"QPLIB: process_cq Raw/QP1 qp is NULL");
 		return -EINVAL;
 	}
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
+		goto done;
+	}
 	cqe = *pcqe;
 	cqe->opcode = hwcqe->cqe_type_toggle & CQ_BASE_CQE_TYPE_MASK;
 	cqe->flags = le16_to_cpu(hwcqe->flags);
@@ -1960,8 +2249,6 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq,
 			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++;
@@ -1970,13 +2257,13 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq,
 	*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;
+		/* Add qp to flush list of the CQ */
+		bnxt_qplib_lock_buddy_cq(qp, cq);
+		__bnxt_qplib_add_flush_qp(qp);
+		bnxt_qplib_unlock_buddy_cq(qp, cq);
 	}
+
+done:
 	return rc;
 }
 
@@ -1990,7 +2277,6 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq,
 	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)
@@ -2005,6 +2291,7 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq,
 			"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;
 
@@ -2023,9 +2310,12 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq,
 			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;
+
+	if (qp->sq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
+		goto sq_done;
+	}
 
 	/* Terminal CQE can also include aggregated successful CQEs prior.
 	 * So we must complete all CQEs from the current sq's cons to the
@@ -2055,11 +2345,6 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq,
 		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;
@@ -2075,26 +2360,23 @@ do_rq:
 			cqe_cons, rq->hwq.max_elements);
 		goto done;
 	}
+
+	if (qp->rq.flushed) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"%s: QPLIB: QP in Flush QP = %p\n", __func__, qp);
+		rc = 0;
+		goto done;
+	}
+
 	/* Terminal CQE requires all posted RQEs to complete with FLUSHED_ERR
 	 * from the current rq->cons to the rq->prod regardless what the
 	 * rq->cons the terminal CQE indicates
 	 */
-	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;
+	/* Add qp to flush list of the CQ */
+	bnxt_qplib_lock_buddy_cq(qp, cq);
+	__bnxt_qplib_add_flush_qp(qp);
+	bnxt_qplib_unlock_buddy_cq(qp, cq);
 done:
 	return rc;
 }
@@ -2115,6 +2397,33 @@ static int bnxt_qplib_cq_process_cutoff(struct bnxt_qplib_cq *cq,
 	return 0;
 }
 
+int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq,
+				  struct bnxt_qplib_cqe *cqe,
+				  int num_cqes)
+{
+	struct bnxt_qplib_qp *qp = NULL;
+	u32 budget = num_cqes;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cq->hwq.lock, flags);
+	list_for_each_entry(qp, &cq->sqf_head, sq_flush) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"QPLIB: FP: Flushing SQ QP= %p",
+			qp);
+		__flush_sq(&qp->sq, qp, &cqe, &budget);
+	}
+
+	list_for_each_entry(qp, &cq->rqf_head, rq_flush) {
+		dev_dbg(&cq->hwq.pdev->dev,
+			"QPLIB: FP: Flushing RQ QP= %p",
+			qp);
+		__flush_rq(&qp->rq, qp, &cqe, &budget);
+	}
+	spin_unlock_irqrestore(&cq->hwq.lock, flags);
+
+	return num_cqes - budget;
+}
+
 int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe,
 		       int num_cqes, struct bnxt_qplib_qp **lib_qp)
 {
@@ -2205,6 +2514,7 @@ void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type)
 	spin_lock_irqsave(&cq->hwq.lock, flags);
 	if (arm_type)
 		bnxt_qplib_arm_cq(cq, arm_type);
-
+	/* Using cq->arm_state variable to track whether to issue cq handler */
+	atomic_set(&cq->arm_state, 1);
 	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
index 19176e06c98a..8ead70ca1c1d 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -220,19 +220,20 @@ struct bnxt_qplib_q {
 	u16				q_full_delta;
 	u16				max_sge;
 	u32				psn;
-	bool				flush_in_progress;
 	bool				condition;
 	bool				single;
 	bool				send_phantom;
 	u32				phantom_wqe_cnt;
 	u32				phantom_cqe_cnt;
 	u32				next_cq_cons;
+	bool				flushed;
 };
 
 struct bnxt_qplib_qp {
 	struct bnxt_qplib_pd		*pd;
 	struct bnxt_qplib_dpi		*dpi;
 	u64				qp_handle;
+#define        BNXT_QPLIB_QP_ID_INVALID        0xFFFFFFFF
 	u32				id;
 	u8				type;
 	u8				sig_type;
@@ -296,6 +297,8 @@ struct bnxt_qplib_qp {
 	dma_addr_t			sq_hdr_buf_map;
 	void				*rq_hdr_buf;
 	dma_addr_t			rq_hdr_buf_map;
+	struct list_head		sq_flush;
+	struct list_head		rq_flush;
 };
 
 #define BNXT_QPLIB_MAX_CQE_ENTRY_SIZE	sizeof(struct cq_base)
@@ -351,6 +354,7 @@ struct bnxt_qplib_cq {
 	u16				period;
 	struct bnxt_qplib_hwq		hwq;
 	u32				cnq_hw_ring_id;
+	struct bnxt_qplib_nq		*nq;
 	bool				resize_in_progress;
 	struct scatterlist		*sghead;
 	u32				nmap;
@@ -360,6 +364,9 @@ struct bnxt_qplib_cq {
 	unsigned long			flags;
 #define CQ_FLAGS_RESIZE_IN_PROG		1
 	wait_queue_head_t		waitq;
+	struct list_head		sqf_head, rqf_head;
+	atomic_t			arm_state;
+	spinlock_t			compl_lock; /* synch CQ handlers */
 };
 
 #define BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE	sizeof(struct xrrq_irrq)
@@ -400,6 +407,7 @@ struct bnxt_qplib_nq {
 	struct pci_dev			*pdev;
 
 	int				vector;
+	cpumask_t			mask;
 	int				budget;
 	bool				requested;
 	struct tasklet_struct		worker;
@@ -417,11 +425,19 @@ struct bnxt_qplib_nq {
 						(struct bnxt_qplib_nq *nq,
 						 void *srq,
 						 u8 event);
+	struct workqueue_struct         *cqn_wq;
+	char                            name[32];
+};
+
+struct bnxt_qplib_nq_work {
+	struct work_struct      work;
+	struct bnxt_qplib_nq    *nq;
+	struct bnxt_qplib_cq    *cq;
 };
 
 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 nq_idx, 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,
@@ -453,4 +469,13 @@ bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq);
 void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type);
 void bnxt_qplib_free_nq(struct bnxt_qplib_nq *nq);
 int bnxt_qplib_alloc_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq);
+void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp);
+void bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp);
+void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp,
+				 unsigned long *flags);
+void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp,
+				 unsigned long *flags);
+int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq,
+				  struct bnxt_qplib_cqe *cqe,
+				  int num_cqes);
 #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
index 16e42754dbec..391bb7006e8f 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -44,6 +44,9 @@
 #include "roce_hsi.h"
 #include "qplib_res.h"
 #include "qplib_rcfw.h"
+#include "qplib_sp.h"
+#include "qplib_fp.h"
+
 static void bnxt_qplib_service_creq(unsigned long data);
 
 /* Hardware communication channel */
@@ -279,16 +282,29 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 				       struct creq_qp_event *qp_event)
 {
 	struct bnxt_qplib_hwq *cmdq = &rcfw->cmdq;
+	struct creq_qp_error_notification *err_event;
 	struct bnxt_qplib_crsq *crsqe;
 	unsigned long flags;
+	struct bnxt_qplib_qp *qp;
 	u16 cbit, blocked = 0;
 	u16 cookie;
 	__le16  mcookie;
+	u32 qp_id;
 
 	switch (qp_event->event) {
 	case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION:
+		err_event = (struct creq_qp_error_notification *)qp_event;
+		qp_id = le32_to_cpu(err_event->xid);
+		qp = rcfw->qp_tbl[qp_id].qp_handle;
 		dev_dbg(&rcfw->pdev->dev,
 			"QPLIB: Received QP error notification");
+		dev_dbg(&rcfw->pdev->dev,
+			"QPLIB: qpid 0x%x, req_err=0x%x, resp_err=0x%x\n",
+			qp_id, err_event->req_err_state_reason,
+			err_event->res_err_state_reason);
+		bnxt_qplib_acquire_cq_locks(qp, &flags);
+		bnxt_qplib_mark_qp_error(qp);
+		bnxt_qplib_release_cq_locks(qp, &flags);
 		break;
 	default:
 		/* Command Response */
@@ -507,6 +523,7 @@ skip_ctx_setup:
 
 void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
 {
+	kfree(rcfw->qp_tbl);
 	kfree(rcfw->crsqe_tbl);
 	bnxt_qplib_free_hwq(rcfw->pdev, &rcfw->cmdq);
 	bnxt_qplib_free_hwq(rcfw->pdev, &rcfw->creq);
@@ -514,7 +531,8 @@ 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)
+				  struct bnxt_qplib_rcfw *rcfw,
+				  int qp_tbl_sz)
 {
 	rcfw->pdev = pdev;
 	rcfw->creq.max_elements = BNXT_QPLIB_CREQE_MAX_CNT;
@@ -541,6 +559,12 @@ int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev,
 	if (!rcfw->crsqe_tbl)
 		goto fail;
 
+	rcfw->qp_tbl_size = qp_tbl_sz;
+	rcfw->qp_tbl = kcalloc(qp_tbl_sz, sizeof(struct bnxt_qplib_qp_node),
+			       GFP_KERNEL);
+	if (!rcfw->qp_tbl)
+		goto fail;
+
 	return 0;
 
 fail:
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 09ce121770cd..0ed312f17c8d 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -148,6 +148,11 @@ struct bnxt_qplib_rcfw_sbuf {
 	u32 size;
 };
 
+struct bnxt_qplib_qp_node {
+	u32 qp_id;              /* QP id */
+	void *qp_handle;        /* ptr to qplib_qp */
+};
+
 /* RCFW Communication Channels */
 struct bnxt_qplib_rcfw {
 	struct pci_dev		*pdev;
@@ -181,11 +186,13 @@ struct bnxt_qplib_rcfw {
 	/* Actual Cmd and Resp Queues */
 	struct bnxt_qplib_hwq	cmdq;
 	struct bnxt_qplib_crsq	*crsqe_tbl;
+	int qp_tbl_size;
+	struct bnxt_qplib_qp_node *qp_tbl;
 };
 
 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);
+				  struct bnxt_qplib_rcfw *rcfw, int qp_tbl_sz);
 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,
@@ -207,4 +214,5 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
 int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 			 struct bnxt_qplib_ctx *ctx, int is_virtfn);
+void bnxt_qplib_mark_qp_error(void *qp_handle);
 #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
index 62447b3badec..4e101704e801 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -468,9 +468,11 @@ static void bnxt_qplib_free_sgid_tbl(struct bnxt_qplib_res *res,
 	kfree(sgid_tbl->tbl);
 	kfree(sgid_tbl->hw_id);
 	kfree(sgid_tbl->ctx);
+	kfree(sgid_tbl->vlan);
 	sgid_tbl->tbl = NULL;
 	sgid_tbl->hw_id = NULL;
 	sgid_tbl->ctx = NULL;
+	sgid_tbl->vlan = NULL;
 	sgid_tbl->max = 0;
 	sgid_tbl->active = 0;
 }
@@ -491,8 +493,15 @@ static int bnxt_qplib_alloc_sgid_tbl(struct bnxt_qplib_res *res,
 	if (!sgid_tbl->ctx)
 		goto out_free2;
 
+	sgid_tbl->vlan = kcalloc(max, sizeof(u8), GFP_KERNEL);
+	if (!sgid_tbl->vlan)
+		goto out_free3;
+
 	sgid_tbl->max = max;
 	return 0;
+out_free3:
+	kfree(sgid_tbl->ctx);
+	sgid_tbl->ctx = NULL;
 out_free2:
 	kfree(sgid_tbl->hw_id);
 	sgid_tbl->hw_id = NULL;
@@ -514,6 +523,7 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res,
 	}
 	memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max);
 	memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
+	memset(sgid_tbl->vlan, 0, sizeof(u8) * sgid_tbl->max);
 	sgid_tbl->active = 0;
 }
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 2e4855509719..e87207526d2c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -116,6 +116,7 @@ struct bnxt_qplib_sgid_tbl {
 	u16				max;
 	u16				active;
 	void				*ctx;
+	u8				*vlan;
 };
 
 struct bnxt_qplib_pkey_tbl {
@@ -188,6 +189,7 @@ struct bnxt_qplib_res {
 	struct bnxt_qplib_sgid_tbl	sgid_tbl;
 	struct bnxt_qplib_pkey_tbl	pkey_tbl;
 	struct bnxt_qplib_dpi_tbl	dpi_tbl;
+	bool				prio;
 };
 
 #define to_bnxt_qplib(ptr, type, member)	\
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index ef91ab786dd4..e277e54a05eb 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -213,6 +213,7 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 	}
 	memcpy(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero,
 	       sizeof(bnxt_qplib_gid_zero));
+	sgid_tbl->vlan[index] = 0;
 	sgid_tbl->active--;
 	dev_dbg(&res->pdev->dev,
 		"QPLIB: SGID deleted hw_id[0x%x] = 0x%x active = 0x%x",
@@ -265,28 +266,32 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 		struct cmdq_add_gid req;
 		struct creq_add_gid_resp resp;
 		u16 cmd_flags = 0;
-		u32 temp32[4];
-		u16 temp16[3];
 		int rc;
 
 		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);
+		req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]);
+		req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]);
+		req.gid[2] = cpu_to_be32(((u32 *)gid->data)[1]);
+		req.gid[3] = cpu_to_be32(((u32 *)gid->data)[0]);
+		/*
+		 * driver should ensure that all RoCE traffic is always VLAN
+		 * tagged if RoCE traffic is running on non-zero VLAN ID or
+		 * RoCE traffic is running on non-zero Priority.
+		 */
+		if ((vlan_id != 0xFFFF) || res->prio) {
+			if (vlan_id != 0xFFFF)
+				req.vlan = cpu_to_le16
+				(vlan_id & CMDQ_ADD_GID_VLAN_VLAN_ID_MASK);
+			req.vlan |= cpu_to_le16
+					(CMDQ_ADD_GID_VLAN_TPID_TPID_8100 |
+					 CMDQ_ADD_GID_VLAN_VLAN_EN);
+		}
 
 		/* MAC in network format */
-		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]);
+		req.src_mac[0] = cpu_to_be16(((u16 *)smac)[0]);
+		req.src_mac[1] = cpu_to_be16(((u16 *)smac)[1]);
+		req.src_mac[2] = cpu_to_be16(((u16 *)smac)[2]);
 
 		rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
 						  (void *)&resp, NULL, 0);
@@ -297,6 +302,9 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 	/* Add GID to the sgid_tbl */
 	memcpy(&sgid_tbl->tbl[free_idx], gid, sizeof(*gid));
 	sgid_tbl->active++;
+	if (vlan_id != 0xFFFF)
+		sgid_tbl->vlan[free_idx] = 1;
+
 	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);
@@ -306,6 +314,43 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 	return 0;
 }
 
+int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			   struct bnxt_qplib_gid *gid, u16 gid_idx,
+			   u8 *smac)
+{
+	struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl,
+						   struct bnxt_qplib_res,
+						   sgid_tbl);
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
+	struct creq_modify_gid_resp resp;
+	struct cmdq_modify_gid req;
+	int rc;
+	u16 cmd_flags = 0;
+
+	RCFW_CMD_PREP(req, MODIFY_GID, cmd_flags);
+
+	req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]);
+	req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]);
+	req.gid[2] = cpu_to_be32(((u32 *)gid->data)[1]);
+	req.gid[3] = cpu_to_be32(((u32 *)gid->data)[0]);
+	if (res->prio) {
+		req.vlan |= cpu_to_le16
+			(CMDQ_ADD_GID_VLAN_TPID_TPID_8100 |
+			 CMDQ_ADD_GID_VLAN_VLAN_EN);
+	}
+
+	/* MAC in network format */
+	req.src_mac[0] = cpu_to_be16(((u16 *)smac)[0]);
+	req.src_mac[1] = cpu_to_be16(((u16 *)smac)[1]);
+	req.src_mac[2] = cpu_to_be16(((u16 *)smac)[2]);
+
+	req.gid_index = cpu_to_le16(gid_idx);
+
+	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
+					  (void *)&resp, NULL, 0);
+	return rc;
+}
+
 /* pkeys */
 int bnxt_qplib_get_pkey(struct bnxt_qplib_res *res,
 			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 index,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index 2ce7e2a32cf0..11322582f5e4 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -135,6 +135,8 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 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_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
+			   struct bnxt_qplib_gid *gid, u16 gid_idx, u8 *smac);
 int bnxt_qplib_get_pkey(struct bnxt_qplib_res *res,
 			struct bnxt_qplib_pkey_tbl *pkey_tbl, u16 index,
 			u16 *pkey);
diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
index fc23477ac52f..eeb55b2db57e 100644
--- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -1473,8 +1473,8 @@ struct cmdq_modify_gid {
 	u8 resp_size;
 	u8 reserved8;
 	__le64 resp_addr;
-	__le32 gid[4];
-	__le16 src_mac[3];
+	__be32 gid[4];
+	__be16 src_mac[3];
 	__le16 vlan;
 	#define CMDQ_MODIFY_GID_VLAN_VLAN_ID_MASK		    0xfffUL
 	#define CMDQ_MODIFY_GID_VLAN_VLAN_ID_SFT		    0
diff --git a/drivers/infiniband/hw/cxgb3/iwch.c b/drivers/infiniband/hw/cxgb3/iwch.c
index 47b2ce2ef203..591de319c178 100644
--- a/drivers/infiniband/hw/cxgb3/iwch.c
+++ b/drivers/infiniband/hw/cxgb3/iwch.c
@@ -45,7 +45,6 @@
 MODULE_AUTHOR("Boyd Faulkner, Steve Wise");
 MODULE_DESCRIPTION("Chelsio T3 RDMA Driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 
 static void open_rnic_dev(struct t3cdev *);
 static void close_rnic_dev(struct t3cdev *);
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 0cd0c1fa27d4..099e76f3758a 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -1336,8 +1336,7 @@ static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str,
-			       size_t str_len)
+static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str)
 {
 	struct iwch_dev *iwch_dev = to_iwch_dev(ibdev);
 	struct ethtool_drvinfo info;
@@ -1345,7 +1344,7 @@ static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str,
 
 	pr_debug("%s dev 0x%p\n", __func__, iwch_dev);
 	lldev->ethtool_ops->get_drvinfo(lldev, &info);
-	snprintf(str, str_len, "%s", info.fw_version);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version);
 }
 
 int iwch_register_device(struct iwch_dev *dev)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index e49b34c3b136..ceaa2fa54d32 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2871,7 +2871,6 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		return 0;
 
 	pr_debug("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
-	BUG_ON(!ep);
 
 	/* The cm_id may be null if we failed to connect */
 	mutex_lock(&ep->com.mutex);
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index ae0b79aeea2e..fc886f81b885 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -44,7 +44,6 @@
 MODULE_AUTHOR("Steve Wise");
 MODULE_DESCRIPTION("Chelsio T4/T5 RDMA Driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 
 static int allow_db_fc_on_t5;
 module_param(allow_db_fc_on_t5, int, 0644);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 5332f06b99ba..c2fba76becd4 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -661,7 +661,7 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 	rhp = php->rhp;
 
 	if (mr_type != IB_MR_TYPE_MEM_REG ||
-	    max_num_sg > t4_max_fr_depth(&rhp->rdev.lldi.ulptx_memwrite_dsgl &&
+	    max_num_sg > t4_max_fr_depth(rhp->rdev.lldi.ulptx_memwrite_dsgl &&
 					 use_dsgl))
 		return ERR_PTR(-EINVAL);
 
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 0771e9a4d061..346e8334279a 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -517,14 +517,13 @@ static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *dev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev,
 						 ibdev);
 	pr_debug("%s dev 0x%p\n", __func__, dev);
 
-	snprintf(str, str_len, "%u.%u.%u.%u",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u.%u",
 		 FW_HDR_FW_VER_MAJOR_G(c4iw_dev->rdev.lldi.fw_vers),
 		 FW_HDR_FW_VER_MINOR_G(c4iw_dev->rdev.lldi.fw_vers),
 		 FW_HDR_FW_VER_MICRO_G(c4iw_dev->rdev.lldi.fw_vers),
diff --git a/drivers/infiniband/hw/hfi1/Kconfig b/drivers/infiniband/hw/hfi1/Kconfig
index f6ea0881765a..7b146b67a80f 100644
--- a/drivers/infiniband/hw/hfi1/Kconfig
+++ b/drivers/infiniband/hw/hfi1/Kconfig
@@ -13,13 +13,6 @@ config HFI1_DEBUG_SDMA_ORDER
 	---help---
 	This is a debug flag to test for out of order
 	sdma completions for unit testing
-config HFI1_VERBS_31BIT_PSN
-	bool "HFI1 enable 31 bit PSN"
-	depends on INFINIBAND_HFI1
-	default y
-	---help---
-	Setting this enables 31 BIT PSN
-	For verbs RC/UC
 config SDMA_VERBOSITY
 	bool "Config SDMA Verbosity"
 	depends on INFINIBAND_HFI1
diff --git a/drivers/infiniband/hw/hfi1/Makefile b/drivers/infiniband/hw/hfi1/Makefile
index 88085f65432e..66d538c033b0 100644
--- a/drivers/infiniband/hw/hfi1/Makefile
+++ b/drivers/infiniband/hw/hfi1/Makefile
@@ -8,7 +8,7 @@
 obj-$(CONFIG_INFINIBAND_HFI1) += hfi1.o
 
 hfi1-y := affinity.o chip.o device.o driver.o efivar.o \
-	eprom.o file_ops.o firmware.o \
+	eprom.o exp_rcv.o file_ops.o firmware.o \
 	init.o intr.o mad.o mmu_rb.o pcie.o pio.o pio_copy.o platform.o \
 	qp.o qsfp.o rc.o ruc.o sdma.o sysfs.o trace.o \
 	uc.o ud.o user_exp_rcv.o user_pages.o user_sdma.o verbs.o \
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index e2cd2cd3b28a..a97055dd4fbd 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -335,10 +335,10 @@ static void hfi1_update_sdma_affinity(struct hfi1_msix_entry *msix, int cpu)
 	sde->cpu = cpu;
 	cpumask_clear(&msix->mask);
 	cpumask_set_cpu(cpu, &msix->mask);
-	dd_dev_dbg(dd, "IRQ vector: %u, type %s engine %u -> cpu: %d\n",
-		   msix->msix.vector, irq_type_names[msix->type],
+	dd_dev_dbg(dd, "IRQ: %u, type %s engine %u -> cpu: %d\n",
+		   msix->irq, irq_type_names[msix->type],
 		   sde->this_idx, cpu);
-	irq_set_affinity_hint(msix->msix.vector, &msix->mask);
+	irq_set_affinity_hint(msix->irq, &msix->mask);
 
 	/*
 	 * Set the new cpu in the hfi1_affinity_node and clean
@@ -387,7 +387,7 @@ static void hfi1_setup_sdma_notifier(struct hfi1_msix_entry *msix)
 {
 	struct irq_affinity_notify *notify = &msix->notify;
 
-	notify->irq = msix->msix.vector;
+	notify->irq = msix->irq;
 	notify->notify = hfi1_irq_notifier_notify;
 	notify->release = hfi1_irq_notifier_release;
 
@@ -472,10 +472,10 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 	}
 
 	cpumask_set_cpu(cpu, &msix->mask);
-	dd_dev_info(dd, "IRQ vector: %u, type %s %s -> cpu: %d\n",
-		    msix->msix.vector, irq_type_names[msix->type],
+	dd_dev_info(dd, "IRQ: %u, type %s %s -> cpu: %d\n",
+		    msix->irq, irq_type_names[msix->type],
 		    extra, cpu);
-	irq_set_affinity_hint(msix->msix.vector, &msix->mask);
+	irq_set_affinity_hint(msix->irq, &msix->mask);
 
 	if (msix->type == IRQ_SDMA) {
 		sde->cpu = cpu;
@@ -533,7 +533,7 @@ void hfi1_put_irq_affinity(struct hfi1_devdata *dd,
 		}
 	}
 
-	irq_set_affinity_hint(msix->msix.vector, NULL);
+	irq_set_affinity_hint(msix->irq, NULL);
 	cpumask_clear(&msix->mask);
 	mutex_unlock(&node_affinity.lock);
 }
diff --git a/drivers/infiniband/hw/hfi1/affinity.h b/drivers/infiniband/hw/hfi1/affinity.h
index e78c7aa094e0..2a1e374169c0 100644
--- a/drivers/infiniband/hw/hfi1/affinity.h
+++ b/drivers/infiniband/hw/hfi1/affinity.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -75,24 +75,26 @@ struct hfi1_msix_entry;
 /* Initialize non-HT cpu cores mask */
 void init_real_cpu_mask(void);
 /* Initialize driver affinity data */
-int hfi1_dev_affinity_init(struct hfi1_devdata *);
+int hfi1_dev_affinity_init(struct hfi1_devdata *dd);
 /*
  * Set IRQ affinity to a CPU. The function will determine the
  * CPU and set the affinity to it.
  */
-int hfi1_get_irq_affinity(struct hfi1_devdata *, struct hfi1_msix_entry *);
+int hfi1_get_irq_affinity(struct hfi1_devdata *dd,
+			  struct hfi1_msix_entry *msix);
 /*
  * Remove the IRQ's CPU affinity. This function also updates
  * any internal CPU tracking data
  */
-void hfi1_put_irq_affinity(struct hfi1_devdata *, struct hfi1_msix_entry *);
+void hfi1_put_irq_affinity(struct hfi1_devdata *dd,
+			   struct hfi1_msix_entry *msix);
 /*
  * Determine a CPU affinity for a user process, if the process does not
  * have an affinity set yet.
  */
-int hfi1_get_proc_affinity(int);
+int hfi1_get_proc_affinity(int node);
 /* Release a CPU used by a user process. */
-void hfi1_put_proc_affinity(int);
+void hfi1_put_proc_affinity(int cpu);
 
 struct hfi1_affinity_node {
 	int node;
diff --git a/drivers/infiniband/hw/hfi1/aspm.h b/drivers/infiniband/hw/hfi1/aspm.h
index 794e6814a531..522b40ed9937 100644
--- a/drivers/infiniband/hw/hfi1/aspm.h
+++ b/drivers/infiniband/hw/hfi1/aspm.h
@@ -237,14 +237,17 @@ static inline void aspm_disable_all(struct hfi1_devdata *dd)
 {
 	struct hfi1_ctxtdata *rcd;
 	unsigned long flags;
-	unsigned i;
+	u16 i;
 
 	for (i = 0; i < dd->first_dyn_alloc_ctxt; i++) {
-		rcd = dd->rcd[i];
-		del_timer_sync(&rcd->aspm_timer);
-		spin_lock_irqsave(&rcd->aspm_lock, flags);
-		rcd->aspm_intr_enable = false;
-		spin_unlock_irqrestore(&rcd->aspm_lock, flags);
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (rcd) {
+			del_timer_sync(&rcd->aspm_timer);
+			spin_lock_irqsave(&rcd->aspm_lock, flags);
+			rcd->aspm_intr_enable = false;
+			spin_unlock_irqrestore(&rcd->aspm_lock, flags);
+			hfi1_rcd_put(rcd);
+		}
 	}
 
 	aspm_disable(dd);
@@ -256,7 +259,7 @@ static inline void aspm_enable_all(struct hfi1_devdata *dd)
 {
 	struct hfi1_ctxtdata *rcd;
 	unsigned long flags;
-	unsigned i;
+	u16 i;
 
 	aspm_enable(dd);
 
@@ -264,11 +267,14 @@ static inline void aspm_enable_all(struct hfi1_devdata *dd)
 		return;
 
 	for (i = 0; i < dd->first_dyn_alloc_ctxt; i++) {
-		rcd = dd->rcd[i];
-		spin_lock_irqsave(&rcd->aspm_lock, flags);
-		rcd->aspm_intr_enable = true;
-		rcd->aspm_enabled = true;
-		spin_unlock_irqrestore(&rcd->aspm_lock, flags);
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (rcd) {
+			spin_lock_irqsave(&rcd->aspm_lock, flags);
+			rcd->aspm_intr_enable = true;
+			rcd->aspm_enabled = true;
+			spin_unlock_irqrestore(&rcd->aspm_lock, flags);
+			hfi1_rcd_put(rcd);
+		}
 	}
 }
 
@@ -284,13 +290,18 @@ static inline void aspm_ctx_init(struct hfi1_ctxtdata *rcd)
 
 static inline void aspm_init(struct hfi1_devdata *dd)
 {
-	unsigned i;
+	struct hfi1_ctxtdata *rcd;
+	u16 i;
 
 	spin_lock_init(&dd->aspm_lock);
 	dd->aspm_supported = aspm_hw_l1_supported(dd);
 
-	for (i = 0; i < dd->first_dyn_alloc_ctxt; i++)
-		aspm_ctx_init(dd->rcd[i]);
+	for (i = 0; i < dd->first_dyn_alloc_ctxt; i++) {
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (rcd)
+			aspm_ctx_init(rcd);
+		hfi1_rcd_put(rcd);
+	}
 
 	/* Start with ASPM disabled */
 	aspm_hw_set_l1_ent_latency(dd);
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 94b54850ec75..b2ed4b9cda6e 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1012,14 +1012,15 @@ static struct flag_table dc8051_info_err_flags[] = {
  */
 static struct flag_table dc8051_info_host_msg_flags[] = {
 	FLAG_ENTRY0("Host request done", 0x0001),
-	FLAG_ENTRY0("BC SMA message", 0x0002),
-	FLAG_ENTRY0("BC PWR_MGM message", 0x0004),
+	FLAG_ENTRY0("BC PWR_MGM message", 0x0002),
+	FLAG_ENTRY0("BC SMA message", 0x0004),
 	FLAG_ENTRY0("BC Unknown message (BCC)", 0x0008),
 	FLAG_ENTRY0("BC Unknown message (LCB)", 0x0010),
 	FLAG_ENTRY0("External device config request", 0x0020),
 	FLAG_ENTRY0("VerifyCap all frames received", 0x0040),
 	FLAG_ENTRY0("LinkUp achieved", 0x0080),
 	FLAG_ENTRY0("Link going down", 0x0100),
+	FLAG_ENTRY0("Link width downgraded", 0x0200),
 };
 
 static u32 encoded_size(u32 size);
@@ -1064,8 +1065,13 @@ static int do_8051_command(struct hfi1_devdata *dd, u32 type, u64 in_data,
 static int read_idle_sma(struct hfi1_devdata *dd, u64 *data);
 static int thermal_init(struct hfi1_devdata *dd);
 
+static void update_statusp(struct hfi1_pportdata *ppd, u32 state);
 static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 				  int msecs);
+static void log_state_transition(struct hfi1_pportdata *ppd, u32 state);
+static void log_physical_state(struct hfi1_pportdata *ppd, u32 state);
+static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state,
+				   int msecs);
 static void read_planned_down_reason_code(struct hfi1_devdata *dd, u8 *pdrrc);
 static void read_link_down_reason(struct hfi1_devdata *dd, u8 *ldr);
 static void handle_temp_err(struct hfi1_devdata *dd);
@@ -1294,25 +1300,71 @@ CNTR_ELEM(#name, \
 	  CNTR_SYNTH, \
 	  access_ibp_##cntr)
 
+/**
+ * hfi_addr_from_offset - return addr for readq/writeq
+ * @dd - the dd device
+ * @offset - the offset of the CSR within bar0
+ *
+ * This routine selects the appropriate base address
+ * based on the indicated offset.
+ */
+static inline void __iomem *hfi1_addr_from_offset(
+	const struct hfi1_devdata *dd,
+	u32 offset)
+{
+	if (offset >= dd->base2_start)
+		return dd->kregbase2 + (offset - dd->base2_start);
+	return dd->kregbase1 + offset;
+}
+
+/**
+ * read_csr - read CSR at the indicated offset
+ * @dd - the dd device
+ * @offset - the offset of the CSR within bar0
+ *
+ * Return: the value read or all FF's if there
+ * is no mapping
+ */
 u64 read_csr(const struct hfi1_devdata *dd, u32 offset)
 {
-	if (dd->flags & HFI1_PRESENT) {
-		return readq((void __iomem *)dd->kregbase + offset);
-	}
+	if (dd->flags & HFI1_PRESENT)
+		return readq(hfi1_addr_from_offset(dd, offset));
 	return -1;
 }
 
+/**
+ * write_csr - write CSR at the indicated offset
+ * @dd - the dd device
+ * @offset - the offset of the CSR within bar0
+ * @value - value to write
+ */
 void write_csr(const struct hfi1_devdata *dd, u32 offset, u64 value)
 {
-	if (dd->flags & HFI1_PRESENT)
-		writeq(value, (void __iomem *)dd->kregbase + offset);
+	if (dd->flags & HFI1_PRESENT) {
+		void __iomem *base = hfi1_addr_from_offset(dd, offset);
+
+		/* avoid write to RcvArray */
+		if (WARN_ON(offset >= RCV_ARRAY && offset < dd->base2_start))
+			return;
+		writeq(value, base);
+	}
 }
 
+/**
+ * get_csr_addr - return te iomem address for offset
+ * @dd - the dd device
+ * @offset - the offset of the CSR within bar0
+ *
+ * Return: The iomem address to use in subsequent
+ * writeq/readq operations.
+ */
 void __iomem *get_csr_addr(
-	struct hfi1_devdata *dd,
+	const struct hfi1_devdata *dd,
 	u32 offset)
 {
-	return (void __iomem *)dd->kregbase + offset;
+	if (dd->flags & HFI1_PRESENT)
+		return hfi1_addr_from_offset(dd, offset);
+	return NULL;
 }
 
 static inline u64 read_write_csr(const struct hfi1_devdata *dd, u32 csr,
@@ -5496,7 +5548,7 @@ static void update_rcverr_timer(unsigned long opaque)
 		set_link_down_reason(
 		ppd, OPA_LINKDOWN_REASON_EXCESSIVE_BUFFER_OVERRUN, 0,
 		OPA_LINKDOWN_REASON_EXCESSIVE_BUFFER_OVERRUN);
-		queue_work(ppd->hfi1_wq, &ppd->link_bounce_work);
+		queue_work(ppd->link_wq, &ppd->link_bounce_work);
 	}
 	dd->rcv_ovfl_cnt = (u32)cur_ovfl_cnt;
 
@@ -6051,7 +6103,7 @@ static void handle_qsfp_int(struct hfi1_devdata *dd, u32 src_ctx, u64 reg)
 				 * will not happen. We have to do it here
 				 * before turning the DC off.
 				 */
-				queue_work(ppd->hfi1_wq, &ppd->link_down_work);
+				queue_work(ppd->link_wq, &ppd->link_down_work);
 			}
 		} else {
 			dd_dev_info(dd, "%s: QSFP module inserted\n",
@@ -6086,7 +6138,7 @@ static void handle_qsfp_int(struct hfi1_devdata *dd, u32 src_ctx, u64 reg)
 
 	/* Schedule the QSFP work only if there is a cable attached. */
 	if (qsfp_mod_present(ppd))
-		queue_work(ppd->hfi1_wq, &ppd->qsfp_info.qsfp_work);
+		queue_work(ppd->link_wq, &ppd->qsfp_info.qsfp_work);
 }
 
 static int request_host_lcb_access(struct hfi1_devdata *dd)
@@ -6735,13 +6787,17 @@ static void wait_for_freeze_status(struct hfi1_devdata *dd, int freeze)
 static void rxe_freeze(struct hfi1_devdata *dd)
 {
 	int i;
+	struct hfi1_ctxtdata *rcd;
 
 	/* disable port */
 	clear_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
 
 	/* disable all receive contexts */
-	for (i = 0; i < dd->num_rcv_contexts; i++)
-		hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_DIS, i);
+	for (i = 0; i < dd->num_rcv_contexts; i++) {
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_DIS, rcd);
+		hfi1_rcd_put(rcd);
+	}
 }
 
 /*
@@ -6753,21 +6809,24 @@ static void rxe_freeze(struct hfi1_devdata *dd)
 static void rxe_kernel_unfreeze(struct hfi1_devdata *dd)
 {
 	u32 rcvmask;
-	int i;
+	u16 i;
+	struct hfi1_ctxtdata *rcd;
 
 	/* enable all kernel contexts */
 	for (i = 0; i < dd->num_rcv_contexts; i++) {
-		struct hfi1_ctxtdata *rcd = dd->rcd[i];
+		rcd = hfi1_rcd_get_by_index(dd, i);
 
 		/* Ensure all non-user contexts(including vnic) are enabled */
-		if (!rcd || !rcd->sc || (rcd->sc->type == SC_USER))
+		if (!rcd || !rcd->sc || (rcd->sc->type == SC_USER)) {
+			hfi1_rcd_put(rcd);
 			continue;
-
+		}
 		rcvmask = HFI1_RCVCTRL_CTXT_ENB;
 		/* HFI1_RCVCTRL_TAILUPD_[ENB|DIS] needs to be set explicitly */
-		rcvmask |= HFI1_CAP_KGET_MASK(dd->rcd[i]->flags, DMA_RTAIL) ?
+		rcvmask |= HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ?
 			HFI1_RCVCTRL_TAILUPD_ENB : HFI1_RCVCTRL_TAILUPD_DIS;
-		hfi1_rcvctrl(dd, rcvmask, i);
+		hfi1_rcvctrl(dd, rcvmask, rcd);
+		hfi1_rcd_put(rcd);
 	}
 
 	/* enable port */
@@ -6906,7 +6965,7 @@ static void reset_neighbor_info(struct hfi1_pportdata *ppd)
 
 static const char * const link_down_reason_strs[] = {
 	[OPA_LINKDOWN_REASON_NONE] = "None",
-	[OPA_LINKDOWN_REASON_RCV_ERROR_0] = "Recive error 0",
+	[OPA_LINKDOWN_REASON_RCV_ERROR_0] = "Receive error 0",
 	[OPA_LINKDOWN_REASON_BAD_PKT_LEN] = "Bad packet length",
 	[OPA_LINKDOWN_REASON_PKT_TOO_LONG] = "Packet too long",
 	[OPA_LINKDOWN_REASON_PKT_TOO_SHORT] = "Packet too short",
@@ -6996,6 +7055,7 @@ void handle_link_down(struct work_struct *work)
 	/* Go offline first, then deal with reading/writing through 8051 */
 	was_up = !!(ppd->host_link_state & HLS_UP);
 	set_link_state(ppd, HLS_DN_OFFLINE);
+	xchg(&ppd->is_link_down_queued, 0);
 
 	if (was_up) {
 		lcl_reason = 0;
@@ -7330,7 +7390,7 @@ void handle_verify_cap(struct work_struct *work)
 	struct hfi1_devdata *dd = ppd->dd;
 	u64 reg;
 	u8 power_management;
-	u8 continious;
+	u8 continuous;
 	u8 vcu;
 	u8 vau;
 	u8 z;
@@ -7349,7 +7409,7 @@ void handle_verify_cap(struct work_struct *work)
 	lcb_shutdown(dd, 0);
 	adjust_lcb_for_fpga_serdes(dd);
 
-	read_vc_remote_phy(dd, &power_management, &continious);
+	read_vc_remote_phy(dd, &power_management, &continuous);
 	read_vc_remote_fabric(dd, &vau, &z, &vcu, &vl15buf,
 			      &partner_supported_crc);
 	read_vc_remote_link_width(dd, &remote_tx_rate, &link_widths);
@@ -7363,7 +7423,7 @@ void handle_verify_cap(struct work_struct *work)
 	get_link_widths(dd, &active_tx, &active_rx);
 	dd_dev_info(dd,
 		    "Peer PHY: power management 0x%x, continuous updates 0x%x\n",
-		    (int)power_management, (int)continious);
+		    (int)power_management, (int)continuous);
 	dd_dev_info(dd,
 		    "Peer Fabric: vAU %d, Z %d, vCU %d, vl15 credits 0x%x, CRC sizes 0x%x\n",
 		    (int)vau, (int)z, (int)vcu, (int)vl15buf,
@@ -7689,12 +7749,12 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg)
 			host_msg &= ~(u64)HOST_REQ_DONE;
 		}
 		if (host_msg & BC_SMA_MSG) {
-			queue_work(ppd->hfi1_wq, &ppd->sma_message_work);
+			queue_work(ppd->link_wq, &ppd->sma_message_work);
 			host_msg &= ~(u64)BC_SMA_MSG;
 		}
 		if (host_msg & LINKUP_ACHIEVED) {
 			dd_dev_info(dd, "8051: Link up\n");
-			queue_work(ppd->hfi1_wq, &ppd->link_up_work);
+			queue_work(ppd->link_wq, &ppd->link_up_work);
 			host_msg &= ~(u64)LINKUP_ACHIEVED;
 		}
 		if (host_msg & EXT_DEVICE_CFG_REQ) {
@@ -7702,7 +7762,7 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg)
 			host_msg &= ~(u64)EXT_DEVICE_CFG_REQ;
 		}
 		if (host_msg & VERIFY_CAP_FRAME) {
-			queue_work(ppd->hfi1_wq, &ppd->link_vc_work);
+			queue_work(ppd->link_wq, &ppd->link_vc_work);
 			host_msg &= ~(u64)VERIFY_CAP_FRAME;
 		}
 		if (host_msg & LINK_GOING_DOWN) {
@@ -7717,7 +7777,7 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg)
 			host_msg &= ~(u64)LINK_GOING_DOWN;
 		}
 		if (host_msg & LINK_WIDTH_DOWNGRADED) {
-			queue_work(ppd->hfi1_wq, &ppd->link_downgrade_work);
+			queue_work(ppd->link_wq, &ppd->link_downgrade_work);
 			host_msg &= ~(u64)LINK_WIDTH_DOWNGRADED;
 		}
 		if (host_msg) {
@@ -7752,15 +7812,22 @@ static void handle_8051_interrupt(struct hfi1_devdata *dd, u32 unused, u64 reg)
 	if (queue_link_down) {
 		/*
 		 * if the link is already going down or disabled, do not
-		 * queue another
+		 * queue another. If there's a link down entry already
+		 * queued, don't queue another one.
 		 */
 		if ((ppd->host_link_state &
 		    (HLS_GOING_OFFLINE | HLS_LINK_COOLDOWN)) ||
 		    ppd->link_enabled == 0) {
-			dd_dev_info(dd, "%s: not queuing link down\n",
-				    __func__);
+			dd_dev_info(dd, "%s: not queuing link down. host_link_state %x, link_enabled %x\n",
+				    __func__, ppd->host_link_state,
+				    ppd->link_enabled);
 		} else {
-			queue_work(ppd->hfi1_wq, &ppd->link_down_work);
+			if (xchg(&ppd->is_link_down_queued, 1) == 1)
+				dd_dev_info(dd,
+					    "%s: link down request already queued\n",
+					    __func__);
+			else
+				queue_work(ppd->link_wq, &ppd->link_down_work);
 		}
 	}
 }
@@ -7968,7 +8035,7 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg)
 		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);
+		queue_work(ppd->link_wq, &ppd->link_bounce_work);
 	}
 }
 
@@ -8052,7 +8119,7 @@ static void is_rcv_avail_int(struct hfi1_devdata *dd, unsigned int source)
 	char *err_detail;
 
 	if (likely(source < dd->num_rcv_contexts)) {
-		rcd = dd->rcd[source];
+		rcd = hfi1_rcd_get_by_index(dd, source);
 		if (rcd) {
 			/* Check for non-user contexts, including vnic */
 			if ((source < dd->first_dyn_alloc_ctxt) ||
@@ -8060,6 +8127,8 @@ static void is_rcv_avail_int(struct hfi1_devdata *dd, unsigned int source)
 				rcd->do_interrupt(rcd, 0);
 			else
 				handle_user_interrupt(rcd);
+
+			hfi1_rcd_put(rcd);
 			return;	/* OK */
 		}
 		/* received an interrupt, but no rcd */
@@ -8081,12 +8150,14 @@ static void is_rcv_urgent_int(struct hfi1_devdata *dd, unsigned int source)
 	char *err_detail;
 
 	if (likely(source < dd->num_rcv_contexts)) {
-		rcd = dd->rcd[source];
+		rcd = hfi1_rcd_get_by_index(dd, source);
 		if (rcd) {
 			/* only pay attention to user urgent interrupts */
 			if ((source >= dd->first_dyn_alloc_ctxt) &&
 			    (!rcd->sc || (rcd->sc->type == SC_USER)))
 				handle_user_interrupt(rcd);
+
+			hfi1_rcd_put(rcd);
 			return;	/* OK */
 		}
 		/* received an interrupt, but no rcd */
@@ -8219,8 +8290,8 @@ static irqreturn_t sdma_interrupt(int irq, void *data)
 		/* handle the interrupt(s) */
 		sdma_engine_interrupt(sde, status);
 	} else {
-		dd_dev_err(dd, "SDMA engine %u interrupt, but no status bits set\n",
-			   sde->this_idx);
+		dd_dev_err_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n",
+				       sde->this_idx);
 	}
 	return IRQ_HANDLED;
 }
@@ -8291,7 +8362,7 @@ static irqreturn_t receive_context_interrupt(int irq, void *data)
 	int disposition;
 	int present;
 
-	trace_hfi1_receive_interrupt(dd, rcd->ctxt);
+	trace_hfi1_receive_interrupt(dd, rcd);
 	this_cpu_inc(*dd->int_counter);
 	aspm_ctx_disable(rcd);
 
@@ -8781,6 +8852,20 @@ static void read_remote_device_id(struct hfi1_devdata *dd, u16 *device_id,
 			& REMOTE_DEVICE_REV_MASK;
 }
 
+int write_host_interface_version(struct hfi1_devdata *dd, u8 version)
+{
+	u32 frame;
+	u32 mask;
+
+	mask = (HOST_INTERFACE_VERSION_MASK << HOST_INTERFACE_VERSION_SHIFT);
+	read_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG, &frame);
+	/* Clear, then set field */
+	frame &= ~mask;
+	frame |= ((u32)version << HOST_INTERFACE_VERSION_SHIFT);
+	return load_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG,
+				frame);
+}
+
 void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor,
 		      u8 *ver_patch)
 {
@@ -9257,12 +9342,6 @@ int start_link(struct hfi1_pportdata *ppd)
 	 */
 	tune_serdes(ppd);
 
-	if (!ppd->link_enabled) {
-		dd_dev_info(ppd->dd,
-			    "%s: stopping link start because link is disabled\n",
-			    __func__);
-		return 0;
-	}
 	if (!ppd->driver_link_ready) {
 		dd_dev_info(ppd->dd,
 			    "%s: stopping link start because driver is not ready\n",
@@ -9373,13 +9452,13 @@ static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,
 
 	if ((qsfp_interrupt_status[0] & QSFP_HIGH_TEMP_ALARM) ||
 	    (qsfp_interrupt_status[0] & QSFP_HIGH_TEMP_WARNING))
-		dd_dev_info(dd, "%s: QSFP cable temperature too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: QSFP cable temperature too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[0] & QSFP_LOW_TEMP_ALARM) ||
 	    (qsfp_interrupt_status[0] & QSFP_LOW_TEMP_WARNING))
-		dd_dev_info(dd, "%s: QSFP cable temperature too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: QSFP cable temperature too low\n",
+			   __func__);
 
 	/*
 	 * The remaining alarms/warnings don't matter if the link is down.
@@ -9389,75 +9468,75 @@ static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,
 
 	if ((qsfp_interrupt_status[1] & QSFP_HIGH_VCC_ALARM) ||
 	    (qsfp_interrupt_status[1] & QSFP_HIGH_VCC_WARNING))
-		dd_dev_info(dd, "%s: QSFP supply voltage too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: QSFP supply voltage too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[1] & QSFP_LOW_VCC_ALARM) ||
 	    (qsfp_interrupt_status[1] & QSFP_LOW_VCC_WARNING))
-		dd_dev_info(dd, "%s: QSFP supply voltage too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: QSFP supply voltage too low\n",
+			   __func__);
 
 	/* Byte 2 is vendor specific */
 
 	if ((qsfp_interrupt_status[3] & QSFP_HIGH_POWER_ALARM) ||
 	    (qsfp_interrupt_status[3] & QSFP_HIGH_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable RX channel 1/2 power too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable RX channel 1/2 power too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[3] & QSFP_LOW_POWER_ALARM) ||
 	    (qsfp_interrupt_status[3] & QSFP_LOW_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable RX channel 1/2 power too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable RX channel 1/2 power too low\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[4] & QSFP_HIGH_POWER_ALARM) ||
 	    (qsfp_interrupt_status[4] & QSFP_HIGH_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable RX channel 3/4 power too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable RX channel 3/4 power too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[4] & QSFP_LOW_POWER_ALARM) ||
 	    (qsfp_interrupt_status[4] & QSFP_LOW_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable RX channel 3/4 power too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable RX channel 3/4 power too low\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[5] & QSFP_HIGH_BIAS_ALARM) ||
 	    (qsfp_interrupt_status[5] & QSFP_HIGH_BIAS_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 1/2 bias too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 1/2 bias too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[5] & QSFP_LOW_BIAS_ALARM) ||
 	    (qsfp_interrupt_status[5] & QSFP_LOW_BIAS_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 1/2 bias too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 1/2 bias too low\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[6] & QSFP_HIGH_BIAS_ALARM) ||
 	    (qsfp_interrupt_status[6] & QSFP_HIGH_BIAS_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 3/4 bias too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 3/4 bias too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[6] & QSFP_LOW_BIAS_ALARM) ||
 	    (qsfp_interrupt_status[6] & QSFP_LOW_BIAS_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 3/4 bias too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 3/4 bias too low\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[7] & QSFP_HIGH_POWER_ALARM) ||
 	    (qsfp_interrupt_status[7] & QSFP_HIGH_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 1/2 power too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 1/2 power too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[7] & QSFP_LOW_POWER_ALARM) ||
 	    (qsfp_interrupt_status[7] & QSFP_LOW_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 1/2 power too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 1/2 power too low\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[8] & QSFP_HIGH_POWER_ALARM) ||
 	    (qsfp_interrupt_status[8] & QSFP_HIGH_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 3/4 power too high\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 3/4 power too high\n",
+			   __func__);
 
 	if ((qsfp_interrupt_status[8] & QSFP_LOW_POWER_ALARM) ||
 	    (qsfp_interrupt_status[8] & QSFP_LOW_POWER_WARNING))
-		dd_dev_info(dd, "%s: Cable TX channel 3/4 power too low\n",
-			    __func__);
+		dd_dev_err(dd, "%s: Cable TX channel 3/4 power too low\n",
+			   __func__);
 
 	/* Bytes 9-10 and 11-12 are reserved */
 	/* Bytes 13-15 are vendor specific */
@@ -9480,6 +9559,13 @@ void qsfp_event(struct work_struct *work)
 	if (!qsfp_mod_present(ppd))
 		return;
 
+	if (ppd->host_link_state == HLS_DN_DISABLE) {
+		dd_dev_info(ppd->dd,
+			    "%s: stopping link start because link is disabled\n",
+			    __func__);
+		return;
+	}
+
 	/*
 	 * Turn DC back on after cable has been re-inserted. Up until
 	 * now, the DC has been in reset to save power.
@@ -9635,7 +9721,7 @@ static void try_start_link(struct hfi1_pportdata *ppd)
 			    "QSFP not responding, waiting and retrying %d\n",
 			    (int)ppd->qsfp_retry_count);
 		ppd->qsfp_retry_count++;
-		queue_delayed_work(ppd->hfi1_wq, &ppd->start_link_work,
+		queue_delayed_work(ppd->link_wq, &ppd->start_link_work,
 				   msecs_to_jiffies(QSFP_RETRY_WAIT));
 		return;
 	}
@@ -9742,17 +9828,6 @@ static inline int init_cpu_counters(struct hfi1_devdata *dd)
 	return 0;
 }
 
-static const char * const pt_names[] = {
-	"expected",
-	"eager",
-	"invalid"
-};
-
-static const char *pt_name(u32 type)
-{
-	return type >= ARRAY_SIZE(pt_names) ? "unknown" : pt_names[type];
-}
-
 /*
  * index is the index into the receive array
  */
@@ -9760,35 +9835,34 @@ void hfi1_put_tid(struct hfi1_devdata *dd, u32 index,
 		  u32 type, unsigned long pa, u16 order)
 {
 	u64 reg;
-	void __iomem *base = (dd->rcvarray_wc ? dd->rcvarray_wc :
-			      (dd->kregbase + RCV_ARRAY));
 
 	if (!(dd->flags & HFI1_PRESENT))
 		goto done;
 
-	if (type == PT_INVALID) {
+	if (type == PT_INVALID || type == PT_INVALID_FLUSH) {
 		pa = 0;
+		order = 0;
 	} else if (type > PT_INVALID) {
 		dd_dev_err(dd,
 			   "unexpected receive array type %u for index %u, not handled\n",
 			   type, index);
 		goto done;
 	}
-
-	hfi1_cdbg(TID, "type %s, index 0x%x, pa 0x%lx, bsize 0x%lx",
-		  pt_name(type), index, pa, (unsigned long)order);
+	trace_hfi1_put_tid(dd, index, type, pa, order);
 
 #define RT_ADDR_SHIFT 12	/* 4KB kernel address boundary */
 	reg = RCV_ARRAY_RT_WRITE_ENABLE_SMASK
 		| (u64)order << RCV_ARRAY_RT_BUF_SIZE_SHIFT
 		| ((pa >> RT_ADDR_SHIFT) & RCV_ARRAY_RT_ADDR_MASK)
 					<< RCV_ARRAY_RT_ADDR_SHIFT;
-	writeq(reg, base + (index * 8));
+	trace_hfi1_write_rcvarray(dd->rcvarray_wc + (index * 8), reg);
+	writeq(reg, dd->rcvarray_wc + (index * 8));
 
-	if (type == PT_EAGER)
+	if (type == PT_EAGER || type == PT_INVALID_FLUSH || (index & 3) == 3)
 		/*
-		 * Eager entries are written one-by-one so we have to push them
-		 * after we write the entry.
+		 * Eager entries are written and flushed
+		 *
+		 * Expected entries are flushed every 4 writes
 		 */
 		flush_wc();
 done:
@@ -9810,15 +9884,6 @@ void hfi1_clear_tids(struct hfi1_ctxtdata *rcd)
 		hfi1_put_tid(dd, i, PT_INVALID, 0, 0);
 }
 
-struct ib_header *hfi1_get_msgheader(
-	struct hfi1_devdata *dd, __le32 *rhf_addr)
-{
-	u32 offset = rhf_hdrq_offset(rhf_to_cpu(rhf_addr));
-
-	return (struct ib_header *)
-		(rhf_addr - dd->rhf_offset + offset);
-}
-
 static const char * const ib_cfg_name_strings[] = {
 	"HFI1_IB_CFG_LIDLMC",
 	"HFI1_IB_CFG_LWID_DG_ENB",
@@ -10010,10 +10075,16 @@ static void set_lidlmc(struct hfi1_pportdata *ppd)
 	struct hfi1_devdata *dd = ppd->dd;
 	u32 mask = ~((1U << ppd->lmc) - 1);
 	u64 c1 = read_csr(ppd->dd, DCC_CFG_PORT_CONFIG1);
+	u32 lid;
 
+	/*
+	 * Program 0 in CSR if port lid is extended. This prevents
+	 * 9B packets being sent out for large lids.
+	 */
+	lid = (ppd->lid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) ? 0 : ppd->lid;
 	c1 &= ~(DCC_CFG_PORT_CONFIG1_TARGET_DLID_SMASK
 		| DCC_CFG_PORT_CONFIG1_DLID_MASK_SMASK);
-	c1 |= ((ppd->lid & DCC_CFG_PORT_CONFIG1_TARGET_DLID_MASK)
+	c1 |= ((lid & DCC_CFG_PORT_CONFIG1_TARGET_DLID_MASK)
 			<< DCC_CFG_PORT_CONFIG1_TARGET_DLID_SHIFT) |
 	      ((mask & DCC_CFG_PORT_CONFIG1_DLID_MASK_MASK)
 			<< DCC_CFG_PORT_CONFIG1_DLID_MASK_SHIFT);
@@ -10024,7 +10095,7 @@ static void set_lidlmc(struct hfi1_pportdata *ppd)
 	 */
 	sreg = ((mask & SEND_CTXT_CHECK_SLID_MASK_MASK) <<
 			SEND_CTXT_CHECK_SLID_MASK_SHIFT) |
-	       (((ppd->lid & mask) & SEND_CTXT_CHECK_SLID_VALUE_MASK) <<
+	       (((lid & mask) & SEND_CTXT_CHECK_SLID_VALUE_MASK) <<
 			SEND_CTXT_CHECK_SLID_VALUE_SHIFT);
 
 	for (i = 0; i < dd->chip_send_contexts; i++) {
@@ -10034,29 +10105,7 @@ static void set_lidlmc(struct hfi1_pportdata *ppd)
 	}
 
 	/* Now we have to do the same thing for the sdma engines */
-	sdma_update_lmc(dd, mask, ppd->lid);
-}
-
-static int wait_phy_linkstate(struct hfi1_devdata *dd, u32 state, u32 msecs)
-{
-	unsigned long timeout;
-	u32 curr_state;
-
-	timeout = jiffies + msecs_to_jiffies(msecs);
-	while (1) {
-		curr_state = read_physical_state(dd);
-		if (curr_state == state)
-			break;
-		if (time_after(jiffies, timeout)) {
-			dd_dev_err(dd,
-				   "timeout waiting for phy link state 0x%x, current state is 0x%x\n",
-				   state, curr_state);
-			return -ETIMEDOUT;
-		}
-		usleep_range(1950, 2050); /* sleep 2ms-ish */
-	}
-
-	return 0;
+	sdma_update_lmc(dd, mask, lid);
 }
 
 static const char *state_completed_string(u32 completed)
@@ -10238,8 +10287,10 @@ static void force_logical_link_state_down(struct hfi1_pportdata *ppd)
 	write_csr(dd, DC_LCB_CFG_ALLOW_LINK_UP, 0);
 	write_csr(dd, DC_LCB_CFG_IGNORE_LOST_RCLK, 0);
 
-	/* call again to adjust ppd->statusp, if needed */
-	get_logical_state(ppd);
+	/* adjust ppd->statusp, if needed */
+	update_statusp(ppd, IB_PORT_DOWN);
+
+	dd_dev_info(ppd->dd, "logical state forced to LINK_DOWN\n");
 }
 
 /*
@@ -10253,49 +10304,35 @@ static void force_logical_link_state_down(struct hfi1_pportdata *ppd)
 static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 {
 	struct hfi1_devdata *dd = ppd->dd;
-	u32 pstate, previous_state;
+	u32 previous_state;
 	int ret;
-	int do_transition;
-	int do_wait;
 
 	update_lcb_cache(dd);
 
 	previous_state = ppd->host_link_state;
 	ppd->host_link_state = HLS_GOING_OFFLINE;
-	pstate = read_physical_state(dd);
-	if (pstate == PLS_OFFLINE) {
-		do_transition = 0;	/* in right state */
-		do_wait = 0;		/* ...no need to wait */
-	} else if ((pstate & 0xf0) == PLS_OFFLINE) {
-		do_transition = 0;	/* in an offline transient state */
-		do_wait = 1;		/* ...wait for it to settle */
-	} else {
-		do_transition = 1;	/* need to move to offline */
-		do_wait = 1;		/* ...will need to wait */
-	}
 
-	if (do_transition) {
-		ret = set_physical_link_state(dd,
-					      (rem_reason << 8) | PLS_OFFLINE);
+	/* start offline transition */
+	ret = set_physical_link_state(dd, (rem_reason << 8) | PLS_OFFLINE);
 
-		if (ret != HCMD_SUCCESS) {
-			dd_dev_err(dd,
-				   "Failed to transition to Offline link state, return %d\n",
-				   ret);
-			return -EINVAL;
-		}
-		if (ppd->offline_disabled_reason ==
-				HFI1_ODR_MASK(OPA_LINKDOWN_REASON_NONE))
-			ppd->offline_disabled_reason =
-			HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT);
+	if (ret != HCMD_SUCCESS) {
+		dd_dev_err(dd,
+			   "Failed to transition to Offline link state, return %d\n",
+			   ret);
+		return -EINVAL;
 	}
+	if (ppd->offline_disabled_reason ==
+			HFI1_ODR_MASK(OPA_LINKDOWN_REASON_NONE))
+		ppd->offline_disabled_reason =
+		HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT);
 
-	if (do_wait) {
-		/* it can take a while for the link to go down */
-		ret = wait_phy_linkstate(dd, PLS_OFFLINE, 10000);
-		if (ret < 0)
-			return ret;
-	}
+	/*
+	 * Wait for offline transition. It can take a while for
+	 * the link to go down.
+	 */
+	ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000);
+	if (ret < 0)
+		return ret;
 
 	/*
 	 * Now in charge of LCB - must be after the physical state is
@@ -10415,11 +10452,11 @@ static const char *link_state_reason_name(struct hfi1_pportdata *ppd, u32 state)
 }
 
 /*
- * driver_physical_state - convert the driver's notion of a port's
+ * driver_pstate - convert the driver's notion of a port's
  * state (an HLS_*) into a physical state (a {IB,OPA}_PORTPHYSSTATE_*).
  * Return -1 (converted to a u32) to indicate error.
  */
-u32 driver_physical_state(struct hfi1_pportdata *ppd)
+u32 driver_pstate(struct hfi1_pportdata *ppd)
 {
 	switch (ppd->host_link_state) {
 	case HLS_UP_INIT:
@@ -10449,11 +10486,11 @@ u32 driver_physical_state(struct hfi1_pportdata *ppd)
 }
 
 /*
- * driver_logical_state - convert the driver's notion of a port's
+ * driver_lstate - convert the driver's notion of a port's
  * state (an HLS_*) into a logical state (a IB_PORT_*). Return -1
  * (converted to a u32) to indicate error.
  */
-u32 driver_logical_state(struct hfi1_pportdata *ppd)
+u32 driver_lstate(struct hfi1_pportdata *ppd)
 {
 	if (ppd->host_link_state && (ppd->host_link_state & HLS_DOWN))
 		return IB_PORT_DOWN;
@@ -10484,6 +10521,14 @@ void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason,
 }
 
 /*
+ * Verify if BCT for data VLs is non-zero.
+ */
+static inline bool data_vls_operational(struct hfi1_pportdata *ppd)
+{
+	return !!ppd->actual_vls_operational;
+}
+
+/*
  * Change the physical and/or logical link state.
  *
  * Do not call this routine while inside an interrupt.  It contains
@@ -10545,38 +10590,58 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 			goto unexpected;
 		}
 
+		/*
+		 * Wait for Link_Up physical state.
+		 * Physical and Logical states should already be
+		 * be transitioned to LinkUp and LinkInit respectively.
+		 */
+		ret = wait_physical_linkstate(ppd, PLS_LINKUP, 1000);
+		if (ret) {
+			dd_dev_err(dd,
+				   "%s: physical state did not change to LINK-UP\n",
+				   __func__);
+			break;
+		}
+
 		ret = wait_logical_linkstate(ppd, IB_PORT_INIT, 1000);
 		if (ret) {
 			dd_dev_err(dd,
 				   "%s: logical state did not change to INIT\n",
 				   __func__);
-		} else {
-			/* clear old transient LINKINIT_REASON code */
-			if (ppd->linkinit_reason >= OPA_LINKINIT_REASON_CLEAR)
-				ppd->linkinit_reason =
-					OPA_LINKINIT_REASON_LINKUP;
+			break;
+		}
 
-			/* enable the port */
-			add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
+		/* clear old transient LINKINIT_REASON code */
+		if (ppd->linkinit_reason >= OPA_LINKINIT_REASON_CLEAR)
+			ppd->linkinit_reason =
+				OPA_LINKINIT_REASON_LINKUP;
 
-			handle_linkup_change(dd, 1);
-			ppd->host_link_state = HLS_UP_INIT;
-		}
+		/* enable the port */
+		add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
+
+		handle_linkup_change(dd, 1);
+		ppd->host_link_state = HLS_UP_INIT;
 		break;
 	case HLS_UP_ARMED:
 		if (ppd->host_link_state != HLS_UP_INIT)
 			goto unexpected;
 
-		ppd->host_link_state = HLS_UP_ARMED;
+		if (!data_vls_operational(ppd)) {
+			dd_dev_err(dd,
+				   "%s: data VLs not operational\n", __func__);
+			ret = -EINVAL;
+			break;
+		}
+
 		set_logical_state(dd, LSTATE_ARMED);
 		ret = wait_logical_linkstate(ppd, IB_PORT_ARMED, 1000);
 		if (ret) {
-			/* logical state didn't change, stay at init */
-			ppd->host_link_state = HLS_UP_INIT;
 			dd_dev_err(dd,
 				   "%s: logical state did not change to ARMED\n",
 				   __func__);
+			break;
 		}
+		ppd->host_link_state = HLS_UP_ARMED;
 		/*
 		 * The simulator does not currently implement SMA messages,
 		 * so neighbor_normal is not set.  Set it here when we first
@@ -10589,18 +10654,16 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 		if (ppd->host_link_state != HLS_UP_ARMED)
 			goto unexpected;
 
-		ppd->host_link_state = HLS_UP_ACTIVE;
 		set_logical_state(dd, LSTATE_ACTIVE);
 		ret = wait_logical_linkstate(ppd, IB_PORT_ACTIVE, 1000);
 		if (ret) {
-			/* logical state didn't change, stay at armed */
-			ppd->host_link_state = HLS_UP_ARMED;
 			dd_dev_err(dd,
 				   "%s: logical state did not change to ACTIVE\n",
 				   __func__);
 		} else {
 			/* tell all engines to go running */
 			sdma_all_running(dd);
+			ppd->host_link_state = HLS_UP_ACTIVE;
 
 			/* Signal the IB layer that the port has went active */
 			event.device = &dd->verbs_dev.rdi.ibdev;
@@ -10658,6 +10721,8 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 		 */
 		if (ret)
 			goto_offline(ppd, 0);
+		else
+			log_physical_state(ppd, PLS_POLLING);
 		break;
 	case HLS_DN_DISABLE:
 		/* link is disabled */
@@ -10682,6 +10747,13 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 				ret = -EINVAL;
 				break;
 			}
+			ret = wait_physical_linkstate(ppd, PLS_DISABLED, 10000);
+			if (ret) {
+				dd_dev_err(dd,
+					   "%s: physical state did not change to DISABLED\n",
+					   __func__);
+				break;
+			}
 			dc_shutdown(dd);
 		}
 		ppd->host_link_state = HLS_DN_DISABLE;
@@ -10699,6 +10771,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 		if (ppd->host_link_state != HLS_DN_POLL)
 			goto unexpected;
 		ppd->host_link_state = HLS_VERIFY_CAP;
+		log_physical_state(ppd, PLS_CONFIGPHY_VERIFYCAP);
 		break;
 	case HLS_GOING_UP:
 		if (ppd->host_link_state != HLS_VERIFY_CAP)
@@ -11693,16 +11766,18 @@ static u32 encoded_size(u32 size)
 	return 0x1;	/* if invalid, go with the minimum size */
 }
 
-void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op, int ctxt)
+void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
+		  struct hfi1_ctxtdata *rcd)
 {
-	struct hfi1_ctxtdata *rcd;
 	u64 rcvctrl, reg;
 	int did_enable = 0;
+	u16 ctxt;
 
-	rcd = dd->rcd[ctxt];
 	if (!rcd)
 		return;
 
+	ctxt = rcd->ctxt;
+
 	hfi1_cdbg(RCVCTRL, "ctxt %d op 0x%x", ctxt, op);
 
 	rcvctrl = read_kctxt_csr(dd, ctxt, RCV_CTXT_CTRL);
@@ -12604,20 +12679,8 @@ const char *opa_pstate_name(u32 pstate)
 	return "unknown";
 }
 
-/*
- * Read the hardware link state and set the driver's cached value of it.
- * Return the (new) current value.
- */
-u32 get_logical_state(struct hfi1_pportdata *ppd)
+static void update_statusp(struct hfi1_pportdata *ppd, u32 state)
 {
-	u32 new_state;
-
-	new_state = chip_to_opa_lstate(ppd->dd, read_logical_state(ppd->dd));
-	if (new_state != ppd->lstate) {
-		dd_dev_info(ppd->dd, "logical state changed to %s (0x%x)\n",
-			    opa_lstate_name(new_state), new_state);
-		ppd->lstate = new_state;
-	}
 	/*
 	 * Set port status flags in the page mapped into userspace
 	 * memory. Do it here to ensure a reliable state - this is
@@ -12627,7 +12690,7 @@ u32 get_logical_state(struct hfi1_pportdata *ppd)
 	 * function.
 	 */
 	if (ppd->statusp) {
-		switch (ppd->lstate) {
+		switch (state) {
 		case IB_PORT_DOWN:
 		case IB_PORT_INIT:
 			*ppd->statusp &= ~(HFI1_STATUS_IB_CONF |
@@ -12641,10 +12704,9 @@ u32 get_logical_state(struct hfi1_pportdata *ppd)
 			break;
 		}
 	}
-	return ppd->lstate;
 }
 
-/**
+/*
  * wait_logical_linkstate - wait for an IB link state change to occur
  * @ppd: port device
  * @state: the state to wait for
@@ -12658,35 +12720,88 @@ static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 				  int msecs)
 {
 	unsigned long timeout;
+	u32 new_state;
 
 	timeout = jiffies + msecs_to_jiffies(msecs);
 	while (1) {
-		if (get_logical_state(ppd) == state)
-			return 0;
-		if (time_after(jiffies, timeout))
+		new_state = chip_to_opa_lstate(ppd->dd,
+					       read_logical_state(ppd->dd));
+		if (new_state == state)
 			break;
+		if (time_after(jiffies, timeout)) {
+			dd_dev_err(ppd->dd,
+				   "timeout waiting for link state 0x%x\n",
+				   state);
+			return -ETIMEDOUT;
+		}
 		msleep(20);
 	}
-	dd_dev_err(ppd->dd, "timeout waiting for link state 0x%x\n", state);
 
-	return -ETIMEDOUT;
+	update_statusp(ppd, state);
+	dd_dev_info(ppd->dd,
+		    "logical state changed to %s (0x%x)\n",
+		    opa_lstate_name(state),
+		    state);
+	return 0;
 }
 
-u8 hfi1_ibphys_portstate(struct hfi1_pportdata *ppd)
+static void log_state_transition(struct hfi1_pportdata *ppd, u32 state)
 {
-	u32 pstate;
-	u32 ib_pstate;
+	u32 ib_pstate = chip_to_opa_pstate(ppd->dd, state);
 
-	pstate = read_physical_state(ppd->dd);
-	ib_pstate = chip_to_opa_pstate(ppd->dd, pstate);
-	if (ppd->last_pstate != ib_pstate) {
-		dd_dev_info(ppd->dd,
-			    "%s: physical state changed to %s (0x%x), phy 0x%x\n",
-			    __func__, opa_pstate_name(ib_pstate), ib_pstate,
-			    pstate);
-		ppd->last_pstate = ib_pstate;
+	dd_dev_info(ppd->dd,
+		    "physical state changed to %s (0x%x), phy 0x%x\n",
+		    opa_pstate_name(ib_pstate), ib_pstate, state);
+}
+
+/*
+ * Read the physical hardware link state and check if it matches host
+ * drivers anticipated state.
+ */
+static void log_physical_state(struct hfi1_pportdata *ppd, u32 state)
+{
+	u32 read_state = read_physical_state(ppd->dd);
+
+	if (read_state == state) {
+		log_state_transition(ppd, state);
+	} else {
+		dd_dev_err(ppd->dd,
+			   "anticipated phy link state 0x%x, read 0x%x\n",
+			   state, read_state);
 	}
-	return ib_pstate;
+}
+
+/*
+ * wait_physical_linkstate - wait for an physical link state change to occur
+ * @ppd: port device
+ * @state: the state to wait for
+ * @msecs: the number of milliseconds to wait
+ *
+ * Wait up to msecs milliseconds for physical link state change to occur.
+ * Returns 0 if state reached, otherwise -ETIMEDOUT.
+ */
+static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state,
+				   int msecs)
+{
+	u32 read_state;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(msecs);
+	while (1) {
+		read_state = read_physical_state(ppd->dd);
+		if (read_state == state)
+			break;
+		if (time_after(jiffies, timeout)) {
+			dd_dev_err(ppd->dd,
+				   "timeout waiting for phy link state 0x%x\n",
+				   state);
+			return -ETIMEDOUT;
+		}
+		usleep_range(1950, 2050); /* sleep 2ms-ish */
+	}
+
+	log_state_transition(ppd, state);
+	return 0;
 }
 
 #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
@@ -12809,30 +12924,24 @@ static void clean_up_interrupts(struct hfi1_devdata *dd)
 		for (i = 0; i < dd->num_msix_entries; i++, me++) {
 			if (!me->arg) /* => no irq, no affinity */
 				continue;
-			hfi1_put_irq_affinity(dd, &dd->msix_entries[i]);
-			free_irq(me->msix.vector, me->arg);
+			hfi1_put_irq_affinity(dd, me);
+			free_irq(me->irq, me->arg);
 		}
+
+		/* clean structures */
+		kfree(dd->msix_entries);
+		dd->msix_entries = NULL;
+		dd->num_msix_entries = 0;
 	} else {
 		/* INTx */
 		if (dd->requested_intx_irq) {
 			free_irq(dd->pcidev->irq, dd);
 			dd->requested_intx_irq = 0;
 		}
-	}
-
-	/* turn off interrupts */
-	if (dd->num_msix_entries) {
-		/* MSI-X */
-		pci_disable_msix(dd->pcidev);
-	} else {
-		/* INTx */
 		disable_intx(dd->pcidev);
 	}
 
-	/* clean structures */
-	kfree(dd->msix_entries);
-	dd->msix_entries = NULL;
-	dd->num_msix_entries = 0;
+	pci_free_irq_vectors(dd->pcidev);
 }
 
 /*
@@ -12953,7 +13062,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd)
 			me->type = IRQ_SDMA;
 		} else if (first_rx <= i && i < last_rx) {
 			idx = i - first_rx;
-			rcd = dd->rcd[idx];
+			rcd = hfi1_rcd_get_by_index(dd, idx);
 			if (rcd) {
 				/*
 				 * Set the interrupt register and mask for this
@@ -12972,6 +13081,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd)
 				remap_intr(dd, IS_RCVAVAIL_START + idx, i);
 				me->type = IRQ_RCVCTXT;
 				rcd->msix_intr = i;
+				hfi1_rcd_put(rcd);
 			}
 		} else {
 			/* not in our expected range - complain, then
@@ -12986,13 +13096,21 @@ static int request_msix_irqs(struct hfi1_devdata *dd)
 			continue;
 		/* make sure the name is terminated */
 		me->name[sizeof(me->name) - 1] = 0;
+		me->irq = pci_irq_vector(dd->pcidev, i);
+		/*
+		 * On err return me->irq.  Don't need to clear this
+		 * because 'arg' has not been set, and cleanup will
+		 * do the right thing.
+		 */
+		if (me->irq < 0)
+			return me->irq;
 
-		ret = request_threaded_irq(me->msix.vector, handler, thread, 0,
+		ret = request_threaded_irq(me->irq, handler, thread, 0,
 					   me->name, arg);
 		if (ret) {
 			dd_dev_err(dd,
-				   "unable to allocate %s interrupt, vector %d, index %d, err %d\n",
-				   err_info, me->msix.vector, idx, ret);
+				   "unable to allocate %s interrupt, irq %d, index %d, err %d\n",
+				   err_info, me->irq, idx, ret);
 			return ret;
 		}
 		/*
@@ -13003,8 +13121,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd)
 
 		ret = hfi1_get_irq_affinity(dd, me);
 		if (ret)
-			dd_dev_err(dd,
-				   "unable to pin IRQ %d\n", ret);
+			dd_dev_err(dd, "unable to pin IRQ %d\n", ret);
 	}
 
 	return ret;
@@ -13023,7 +13140,7 @@ void hfi1_vnic_synchronize_irq(struct hfi1_devdata *dd)
 		struct hfi1_ctxtdata *rcd = dd->vnic.ctxt[i];
 		struct hfi1_msix_entry *me = &dd->msix_entries[rcd->msix_intr];
 
-		synchronize_irq(me->msix.vector);
+		synchronize_irq(me->irq);
 	}
 }
 
@@ -13036,7 +13153,7 @@ void hfi1_reset_vnic_msix_info(struct hfi1_ctxtdata *rcd)
 		return;
 
 	hfi1_put_irq_affinity(dd, me);
-	free_irq(me->msix.vector, me->arg);
+	free_irq(me->irq, me->arg);
 
 	me->arg = NULL;
 }
@@ -13064,14 +13181,19 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd)
 		 DRIVER_NAME "_%d kctxt%d", dd->unit, idx);
 	me->name[sizeof(me->name) - 1] = 0;
 	me->type = IRQ_RCVCTXT;
-
+	me->irq = pci_irq_vector(dd->pcidev, rcd->msix_intr);
+	if (me->irq < 0) {
+		dd_dev_err(dd, "vnic irq vector request (idx %d) fail %d\n",
+			   idx, me->irq);
+		return;
+	}
 	remap_intr(dd, IS_RCVAVAIL_START + idx, rcd->msix_intr);
 
-	ret = request_threaded_irq(me->msix.vector, receive_context_interrupt,
+	ret = request_threaded_irq(me->irq, receive_context_interrupt,
 				   receive_context_thread, 0, me->name, arg);
 	if (ret) {
-		dd_dev_err(dd, "vnic irq request (vector %d, idx %d) fail %d\n",
-			   me->msix.vector, idx, ret);
+		dd_dev_err(dd, "vnic irq request (irq %d, idx %d) fail %d\n",
+			   me->irq, idx, ret);
 		return;
 	}
 	/*
@@ -13084,7 +13206,7 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd)
 	if (ret) {
 		dd_dev_err(dd,
 			   "unable to pin IRQ %d\n", ret);
-		free_irq(me->msix.vector, me->arg);
+		free_irq(me->irq, me->arg);
 	}
 }
 
@@ -13107,9 +13229,8 @@ static void reset_interrupts(struct hfi1_devdata *dd)
 
 static int set_up_interrupts(struct hfi1_devdata *dd)
 {
-	struct hfi1_msix_entry *entries;
-	u32 total, request;
-	int i, ret;
+	u32 total;
+	int ret, request;
 	int single_interrupt = 0; /* we expect to have all the interrupts */
 
 	/*
@@ -13121,39 +13242,31 @@ static int set_up_interrupts(struct hfi1_devdata *dd)
 	 */
 	total = 1 + dd->num_sdma + dd->n_krcv_queues + HFI1_NUM_VNIC_CTXT;
 
-	entries = kcalloc(total, sizeof(*entries), GFP_KERNEL);
-	if (!entries) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-	/* 1-1 MSI-X entry assignment */
-	for (i = 0; i < total; i++)
-		entries[i].msix.entry = i;
-
 	/* ask for MSI-X interrupts */
-	request = total;
-	request_msix(dd, &request, entries);
-
-	if (request == 0) {
+	request = request_msix(dd, total);
+	if (request < 0) {
+		ret = request;
+		goto fail;
+	} else if (request == 0) {
 		/* using INTx */
 		/* dd->num_msix_entries already zero */
-		kfree(entries);
 		single_interrupt = 1;
 		dd_dev_err(dd, "MSI-X failed, using INTx interrupts\n");
+	} else if (request < total) {
+		/* using MSI-X, with reduced interrupts */
+		dd_dev_err(dd, "reduced interrupt found, wanted %u, got %u\n",
+			   total, request);
+		ret = -EINVAL;
+		goto fail;
 	} else {
-		/* using MSI-X */
-		dd->num_msix_entries = request;
-		dd->msix_entries = entries;
-
-		if (request != total) {
-			/* using MSI-X, with reduced interrupts */
-			dd_dev_err(
-				dd,
-				"cannot handle reduced interrupt case, want %u, got %u\n",
-				total, request);
-			ret = -EINVAL;
+		dd->msix_entries = kcalloc(total, sizeof(*dd->msix_entries),
+					   GFP_KERNEL);
+		if (!dd->msix_entries) {
+			ret = -ENOMEM;
 			goto fail;
 		}
+		/* using MSI-X */
+		dd->num_msix_entries = total;
 		dd_dev_info(dd, "%u MSI-X interrupts allocated\n", total);
 	}
 
@@ -13396,8 +13509,7 @@ static void write_uninitialized_csrs_and_memories(struct hfi1_devdata *dd)
 
 	/* RcvArray */
 	for (i = 0; i < dd->chip_rcv_array_count; i++)
-		write_csr(dd, RCV_ARRAY + (8 * i),
-			  RCV_ARRAY_RT_WRITE_ENABLE_SMASK);
+		hfi1_put_tid(dd, i, PT_INVALID_FLUSH, 0, 0);
 
 	/* RcvQPMapTable */
 	for (i = 0; i < 32; i++)
@@ -13831,9 +13943,10 @@ static void init_sc2vl_tables(struct hfi1_devdata *dd)
  * a reset following the (possible) FLR in this routine.
  *
  */
-static void init_chip(struct hfi1_devdata *dd)
+static int init_chip(struct hfi1_devdata *dd)
 {
 	int i;
+	int ret = 0;
 
 	/*
 	 * Put the HFI CSRs in a known state.
@@ -13881,12 +13994,22 @@ static void init_chip(struct hfi1_devdata *dd)
 		pcie_flr(dd->pcidev);
 
 		/* restore command and BARs */
-		restore_pci_variables(dd);
+		ret = restore_pci_variables(dd);
+		if (ret) {
+			dd_dev_err(dd, "%s: Could not restore PCI variables\n",
+				   __func__);
+			return ret;
+		}
 
 		if (is_ax(dd)) {
 			dd_dev_info(dd, "Resetting CSRs with FLR\n");
 			pcie_flr(dd->pcidev);
-			restore_pci_variables(dd);
+			ret = restore_pci_variables(dd);
+			if (ret) {
+				dd_dev_err(dd, "%s: Could not restore PCI variables\n",
+					   __func__);
+				return ret;
+			}
 		}
 	} else {
 		dd_dev_info(dd, "Resetting CSRs with writes\n");
@@ -13914,6 +14037,7 @@ static void init_chip(struct hfi1_devdata *dd)
 	write_csr(dd, ASIC_QSFP1_OUT, 0x1f);
 	write_csr(dd, ASIC_QSFP2_OUT, 0x1f);
 	init_chip_resources(dd);
+	return ret;
 }
 
 static void init_early_variables(struct hfi1_devdata *dd)
@@ -14365,6 +14489,7 @@ void hfi1_deinit_vnic_rsm(struct hfi1_devdata *dd)
 static void init_rxe(struct hfi1_devdata *dd)
 {
 	struct rsm_map_table *rmt;
+	u64 val;
 
 	/* enable all receive errors */
 	write_csr(dd, RCV_ERR_MASK, ~0ull);
@@ -14389,6 +14514,11 @@ static void init_rxe(struct hfi1_devdata *dd)
 	 * (64 bytes).  Max_Payload_Size is possibly modified upward in
 	 * tune_pcie_caps() which is called after this routine.
 	 */
+
+	/* Have 16 bytes (4DW) of bypass header available in header queue */
+	val = read_csr(dd, RCV_BYPASS);
+	val |= (4ull << 16);
+	write_csr(dd, RCV_BYPASS, val);
 }
 
 static void init_other(struct hfi1_devdata *dd)
@@ -14470,99 +14600,86 @@ static void init_txe(struct hfi1_devdata *dd)
 		write_csr(dd, SEND_CM_TIMER_CTRL, HFI1_CREDIT_RETURN_RATE);
 }
 
-int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt, u16 jkey)
+int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd,
+		       u16 jkey)
 {
-	struct hfi1_ctxtdata *rcd = dd->rcd[ctxt];
-	unsigned sctxt;
-	int ret = 0;
+	u8 hw_ctxt;
 	u64 reg;
 
-	if (!rcd || !rcd->sc) {
-		ret = -EINVAL;
-		goto done;
-	}
-	sctxt = rcd->sc->hw_context;
+	if (!rcd || !rcd->sc)
+		return -EINVAL;
+
+	hw_ctxt = rcd->sc->hw_context;
 	reg = SEND_CTXT_CHECK_JOB_KEY_MASK_SMASK | /* mask is always 1's */
 		((jkey & SEND_CTXT_CHECK_JOB_KEY_VALUE_MASK) <<
 		 SEND_CTXT_CHECK_JOB_KEY_VALUE_SHIFT);
 	/* JOB_KEY_ALLOW_PERMISSIVE is not allowed by default */
 	if (HFI1_CAP_KGET_MASK(rcd->flags, ALLOW_PERM_JKEY))
 		reg |= SEND_CTXT_CHECK_JOB_KEY_ALLOW_PERMISSIVE_SMASK;
-	write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_JOB_KEY, reg);
+	write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_JOB_KEY, reg);
 	/*
 	 * Enable send-side J_KEY integrity check, unless this is A0 h/w
 	 */
 	if (!is_ax(dd)) {
-		reg = read_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE);
+		reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE);
 		reg |= SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK;
-		write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE, reg);
+		write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE, reg);
 	}
 
 	/* Enable J_KEY check on receive context. */
 	reg = RCV_KEY_CTRL_JOB_KEY_ENABLE_SMASK |
 		((jkey & RCV_KEY_CTRL_JOB_KEY_VALUE_MASK) <<
 		 RCV_KEY_CTRL_JOB_KEY_VALUE_SHIFT);
-	write_kctxt_csr(dd, ctxt, RCV_KEY_CTRL, reg);
-done:
-	return ret;
+	write_kctxt_csr(dd, rcd->ctxt, RCV_KEY_CTRL, reg);
+
+	return 0;
 }
 
-int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt)
+int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 {
-	struct hfi1_ctxtdata *rcd = dd->rcd[ctxt];
-	unsigned sctxt;
-	int ret = 0;
+	u8 hw_ctxt;
 	u64 reg;
 
-	if (!rcd || !rcd->sc) {
-		ret = -EINVAL;
-		goto done;
-	}
-	sctxt = rcd->sc->hw_context;
-	write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_JOB_KEY, 0);
+	if (!rcd || !rcd->sc)
+		return -EINVAL;
+
+	hw_ctxt = rcd->sc->hw_context;
+	write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_JOB_KEY, 0);
 	/*
 	 * Disable send-side J_KEY integrity check, unless this is A0 h/w.
 	 * This check would not have been enabled for A0 h/w, see
 	 * set_ctxt_jkey().
 	 */
 	if (!is_ax(dd)) {
-		reg = read_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE);
+		reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE);
 		reg &= ~SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK;
-		write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE, reg);
+		write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE, reg);
 	}
 	/* Turn off the J_KEY on the receive side */
-	write_kctxt_csr(dd, ctxt, RCV_KEY_CTRL, 0);
-done:
-	return ret;
+	write_kctxt_csr(dd, rcd->ctxt, RCV_KEY_CTRL, 0);
+
+	return 0;
 }
 
-int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, unsigned ctxt, u16 pkey)
+int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd,
+		       u16 pkey)
 {
-	struct hfi1_ctxtdata *rcd;
-	unsigned sctxt;
-	int ret = 0;
+	u8 hw_ctxt;
 	u64 reg;
 
-	if (ctxt < dd->num_rcv_contexts) {
-		rcd = dd->rcd[ctxt];
-	} else {
-		ret = -EINVAL;
-		goto done;
-	}
-	if (!rcd || !rcd->sc) {
-		ret = -EINVAL;
-		goto done;
-	}
-	sctxt = rcd->sc->hw_context;
+	if (!rcd || !rcd->sc)
+		return -EINVAL;
+
+	hw_ctxt = rcd->sc->hw_context;
 	reg = ((u64)pkey & SEND_CTXT_CHECK_PARTITION_KEY_VALUE_MASK) <<
 		SEND_CTXT_CHECK_PARTITION_KEY_VALUE_SHIFT;
-	write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_PARTITION_KEY, reg);
-	reg = read_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE);
+	write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_PARTITION_KEY, reg);
+	reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE);
 	reg |= SEND_CTXT_CHECK_ENABLE_CHECK_PARTITION_KEY_SMASK;
 	reg &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_KDETH_PACKETS_SMASK;
-	write_kctxt_csr(dd, sctxt, SEND_CTXT_CHECK_ENABLE, reg);
-done:
-	return ret;
+	write_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE, reg);
+
+	return 0;
 }
 
 int hfi1_clear_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt)
@@ -14573,9 +14690,6 @@ int hfi1_clear_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt)
 	if (!ctxt || !ctxt->sc)
 		return -EINVAL;
 
-	if (ctxt->ctxt >= dd->num_rcv_contexts)
-		return -EINVAL;
-
 	hw_ctxt = ctxt->sc->hw_context;
 	reg = read_kctxt_csr(dd, hw_ctxt, SEND_CTXT_CHECK_ENABLE);
 	reg &= ~SEND_CTXT_CHECK_ENABLE_CHECK_PARTITION_KEY_SMASK;
@@ -14773,7 +14887,6 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 		}
 		ppd->vls_supported = num_vls;
 		ppd->vls_operational = ppd->vls_supported;
-		ppd->actual_vls_operational = ppd->vls_supported;
 		/* Set the default MTU. */
 		for (vl = 0; vl < num_vls; vl++)
 			dd->vld[vl].mtu = hfi1_max_mtu;
@@ -14782,7 +14895,6 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 		 * Set the initial values to reasonable default, will be set
 		 * for real when link is up.
 		 */
-		ppd->lstate = IB_PORT_DOWN;
 		ppd->overrun_threshold = 0x4;
 		ppd->phy_error_threshold = 0xf;
 		ppd->port_crc_mode_enabled = link_crc_mask;
@@ -14793,7 +14905,6 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 		/* start in offline */
 		ppd->host_link_state = HLS_DN_OFFLINE;
 		init_vl_arb_caches(ppd);
-		ppd->last_pstate = 0xff; /* invalid value */
 	}
 
 	dd->link_default = HLS_DN_POLL;
@@ -14807,6 +14918,11 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	if (ret < 0)
 		goto bail_free;
 
+	/* Save PCI space registers to rewrite after device reset */
+	ret = save_pci_variables(dd);
+	if (ret < 0)
+		goto bail_cleanup;
+
 	/* verify that reads actually work, save revision for reset check */
 	dd->revision = read_csr(dd, CCE_REVISION);
 	if (dd->revision == ~(u64)0) {
@@ -14899,7 +15015,9 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 		goto bail_cleanup;
 
 	/* obtain chip sizes, reset chip CSRs */
-	init_chip(dd);
+	ret = init_chip(dd);
+	if (ret)
+		goto bail_cleanup;
 
 	/* read in the PCIe link speed information */
 	ret = pcie_speeds(dd);
@@ -14974,10 +15092,16 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	if (ret)
 		goto bail_cleanup;
 
-	ret = hfi1_create_ctxts(dd);
+	ret = hfi1_create_kctxts(dd);
 	if (ret)
 		goto bail_cleanup;
 
+	/*
+	 * Initialize aspm, to be done after gen3 transition and setting up
+	 * contexts and before enabling interrupts
+	 */
+	aspm_init(dd);
+
 	dd->rcvhdrsize = DEFAULT_RCVHDRSIZE;
 	/*
 	 * rcd[0] is guaranteed to be valid by this point. Also, all
@@ -14996,7 +15120,7 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 			goto bail_cleanup;
 	}
 
-	/* use contexts created by hfi1_create_ctxts */
+	/* use contexts created by hfi1_create_kctxts */
 	ret = set_up_interrupts(dd);
 	if (ret)
 		goto bail_cleanup;
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index cbe455d9ab8b..b8345a60a0fb 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -384,6 +384,7 @@
 #define VERIFY_CAP_LOCAL_FABRIC	     0x08
 #define VERIFY_CAP_LOCAL_LINK_WIDTH  0x09
 #define LOCAL_DEVICE_ID		     0x0a
+#define RESERVED_REGISTERS	     0x0b
 #define LOCAL_LNI_INFO		     0x0c
 #define REMOTE_LNI_INFO              0x0d
 #define MISC_STATUS		     0x0e
@@ -506,6 +507,9 @@
 #define DOWN_REMOTE_REASON_SHIFT 16
 #define DOWN_REMOTE_REASON_MASK  0xff
 
+#define HOST_INTERFACE_VERSION_SHIFT 16
+#define HOST_INTERFACE_VERSION_MASK  0xff
+
 /* verify capability PHY power management bits */
 #define PWRM_BER_CONTROL	0x1
 #define PWRM_BANDWIDTH_CONTROL	0x2
@@ -605,11 +609,11 @@ int read_lcb_csr(struct hfi1_devdata *dd, u32 offset, u64 *data);
 int write_lcb_csr(struct hfi1_devdata *dd, u32 offset, u64 data);
 
 void __iomem *get_csr_addr(
-	struct hfi1_devdata *dd,
+	const struct hfi1_devdata *dd,
 	u32 offset);
 
 static inline void __iomem *get_kctxt_csr_addr(
-	struct hfi1_devdata *dd,
+	const struct hfi1_devdata *dd,
 	int ctxt,
 	u32 offset0)
 {
@@ -644,7 +648,6 @@ u64 create_pbc(struct hfi1_pportdata *ppd, u64 flags, int srate_mbs, u32 vl,
 #define NUM_PCIE_SERDES 16	/* number of PCIe serdes on the SBus */
 extern const u8 pcie_serdes_broadcast[];
 extern const u8 pcie_pcs_addrs[2][NUM_PCIE_SERDES];
-extern uint platform_config_load;
 
 /* SBus commands */
 #define RESET_SBUS_RECEIVER 0x20
@@ -704,6 +707,7 @@ int read_8051_data(struct hfi1_devdata *dd, u32 addr, u32 len, u64 *result);
 /* chip.c */
 void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor,
 		      u8 *ver_patch);
+int write_host_interface_version(struct hfi1_devdata *dd, u8 version);
 void read_guid(struct hfi1_devdata *dd);
 int wait_fm_ready(struct hfi1_devdata *dd, u32 mstimeout);
 void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason,
@@ -743,11 +747,10 @@ int is_ax(struct hfi1_devdata *dd);
 int is_bx(struct hfi1_devdata *dd);
 u32 read_physical_state(struct hfi1_devdata *dd);
 u32 chip_to_opa_pstate(struct hfi1_devdata *dd, u32 chip_pstate);
-u32 get_logical_state(struct hfi1_pportdata *ppd);
 const char *opa_lstate_name(u32 lstate);
 const char *opa_pstate_name(u32 pstate);
-u32 driver_physical_state(struct hfi1_pportdata *ppd);
-u32 driver_logical_state(struct hfi1_pportdata *ppd);
+u32 driver_pstate(struct hfi1_pportdata *ppd);
+u32 driver_lstate(struct hfi1_pportdata *ppd);
 
 int acquire_lcb_access(struct hfi1_devdata *dd, int sleep_ok);
 int release_lcb_access(struct hfi1_devdata *dd, int sleep_ok);
@@ -1347,21 +1350,21 @@ enum {
 u64 get_all_cpu_total(u64 __percpu *cntr);
 void hfi1_start_cleanup(struct hfi1_devdata *dd);
 void hfi1_clear_tids(struct hfi1_ctxtdata *rcd);
-struct ib_header *hfi1_get_msgheader(
-				struct hfi1_devdata *dd, __le32 *rhf_addr);
 void hfi1_init_ctxt(struct send_context *sc);
 void hfi1_put_tid(struct hfi1_devdata *dd, u32 index,
 		  u32 type, unsigned long pa, u16 order);
 void hfi1_quiet_serdes(struct hfi1_pportdata *ppd);
-void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op, int ctxt);
+void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
+		  struct hfi1_ctxtdata *rcd);
 u32 hfi1_read_cntrs(struct hfi1_devdata *dd, char **namep, u64 **cntrp);
 u32 hfi1_read_portcntrs(struct hfi1_pportdata *ppd, char **namep, u64 **cntrp);
-u8 hfi1_ibphys_portstate(struct hfi1_pportdata *ppd);
 int hfi1_get_ib_cfg(struct hfi1_pportdata *ppd, int which);
 int hfi1_set_ib_cfg(struct hfi1_pportdata *ppd, int which, u32 val);
-int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt, u16 jkey);
-int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, unsigned ctxt);
-int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, unsigned ctxt, u16 pkey);
+int hfi1_set_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd,
+		       u16 jkey);
+int hfi1_clear_ctxt_jkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt);
+int hfi1_set_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt,
+		       u16 pkey);
 int hfi1_clear_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt);
 void hfi1_read_link_quality(struct hfi1_devdata *dd, u8 *link_quality);
 void hfi1_init_vnic_rsm(struct hfi1_devdata *dd);
diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h
index 995d62c7f9a7..3e27794ec750 100644
--- a/drivers/infiniband/hw/hfi1/common.h
+++ b/drivers/infiniband/hw/hfi1/common.h
@@ -325,22 +325,15 @@ struct diag_pkt {
 #define HFI1_LRH_BTH 0x0002      /* 1. word of IB LRH - next header: BTH */
 
 /* misc. */
+#define SC15_PACKET 0xF
 #define SIZE_OF_CRC 1
+#define SIZE_OF_LT 1
 
 #define LIM_MGMT_P_KEY       0x7FFF
 #define FULL_MGMT_P_KEY      0xFFFF
 
 #define DEFAULT_P_KEY LIM_MGMT_P_KEY
 
-/**
- * 0xF8 - 4 bits of multicast range and 1 bit for collective range
- * Example: For 24 bit LID space,
- * Multicast range: 0xF00000 to 0xF7FFFF
- * Collective range: 0xF80000 to 0xFFFFFE
- */
-#define HFI1_MCAST_NR 0x4 /* Number of top bits set */
-#define HFI1_COLLECTIVE_NR 0x1 /* Number of bits after MCAST_NR */
-
 #define HFI1_PSM_IOC_BASE_SEQ 0x0
 
 static inline __u64 rhf_to_cpu(const __le32 *rbuf)
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index e9fa3c293e42..36ae1fd86502 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -1,4 +1,3 @@
-#ifdef CONFIG_DEBUG_FS
 /*
  * Copyright(c) 2015-2017 Intel Corporation.
  *
@@ -173,12 +172,15 @@ static int _opcode_stats_seq_show(struct seq_file *s, void *v)
 	u64 n_packets = 0, n_bytes = 0;
 	struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private;
 	struct hfi1_devdata *dd = dd_from_dev(ibd);
+	struct hfi1_ctxtdata *rcd;
 
 	for (j = 0; j < dd->first_dyn_alloc_ctxt; j++) {
-		if (!dd->rcd[j])
-			continue;
-		n_packets += dd->rcd[j]->opstats->stats[i].n_packets;
-		n_bytes += dd->rcd[j]->opstats->stats[i].n_bytes;
+		rcd = hfi1_rcd_get_by_index(dd, j);
+		if (rcd) {
+			n_packets += rcd->opstats->stats[i].n_packets;
+			n_bytes += rcd->opstats->stats[i].n_bytes;
+		}
+		hfi1_rcd_put(rcd);
 	}
 	if (!n_packets && !n_bytes)
 		return SEQ_SKIP;
@@ -231,6 +233,7 @@ static int _ctx_stats_seq_show(struct seq_file *s, void *v)
 	u64 n_packets = 0;
 	struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private;
 	struct hfi1_devdata *dd = dd_from_dev(ibd);
+	struct hfi1_ctxtdata *rcd;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(s, "Ctx:npkts\n");
@@ -240,11 +243,14 @@ static int _ctx_stats_seq_show(struct seq_file *s, void *v)
 	spos = v;
 	i = *spos;
 
-	if (!dd->rcd[i])
+	rcd = hfi1_rcd_get_by_index(dd, i);
+	if (!rcd)
 		return SEQ_SKIP;
 
-	for (j = 0; j < ARRAY_SIZE(dd->rcd[i]->opstats->stats); j++)
-		n_packets += dd->rcd[i]->opstats->stats[j].n_packets;
+	for (j = 0; j < ARRAY_SIZE(rcd->opstats->stats); j++)
+		n_packets += rcd->opstats->stats[j].n_packets;
+
+	hfi1_rcd_put(rcd);
 
 	if (!n_packets)
 		return SEQ_SKIP;
@@ -260,10 +266,10 @@ DEBUGFS_FILE_OPS(ctx_stats);
 static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
 	__acquires(RCU)
 {
-	struct qp_iter *iter;
+	struct rvt_qp_iter *iter;
 	loff_t n = *pos;
 
-	iter = qp_iter_init(s->private);
+	iter = rvt_qp_iter_init(s->private, 0, NULL);
 
 	/* stop calls rcu_read_unlock */
 	rcu_read_lock();
@@ -272,7 +278,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
 		return NULL;
 
 	do {
-		if (qp_iter_next(iter)) {
+		if (rvt_qp_iter_next(iter)) {
 			kfree(iter);
 			return NULL;
 		}
@@ -285,11 +291,11 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr,
 				loff_t *pos)
 	__must_hold(RCU)
 {
-	struct qp_iter *iter = iter_ptr;
+	struct rvt_qp_iter *iter = iter_ptr;
 
 	(*pos)++;
 
-	if (qp_iter_next(iter)) {
+	if (rvt_qp_iter_next(iter)) {
 		kfree(iter);
 		return NULL;
 	}
@@ -305,7 +311,7 @@ static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr)
 
 static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr)
 {
-	struct qp_iter *iter = iter_ptr;
+	struct rvt_qp_iter *iter = iter_ptr;
 
 	if (!iter)
 		return 0;
@@ -361,6 +367,52 @@ DEBUGFS_SEQ_FILE_OPS(sdes);
 DEBUGFS_SEQ_FILE_OPEN(sdes)
 DEBUGFS_FILE_OPS(sdes);
 
+static void *_rcds_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct hfi1_ibdev *ibd;
+	struct hfi1_devdata *dd;
+
+	ibd = (struct hfi1_ibdev *)s->private;
+	dd = dd_from_dev(ibd);
+	if (!dd->rcd || *pos >= dd->n_krcv_queues)
+		return NULL;
+	return pos;
+}
+
+static void *_rcds_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private;
+	struct hfi1_devdata *dd = dd_from_dev(ibd);
+
+	++*pos;
+	if (!dd->rcd || *pos >= dd->n_krcv_queues)
+		return NULL;
+	return pos;
+}
+
+static void _rcds_seq_stop(struct seq_file *s, void *v)
+{
+}
+
+static int _rcds_seq_show(struct seq_file *s, void *v)
+{
+	struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private;
+	struct hfi1_devdata *dd = dd_from_dev(ibd);
+	struct hfi1_ctxtdata *rcd;
+	loff_t *spos = v;
+	loff_t i = *spos;
+
+	rcd = hfi1_rcd_get_by_index(dd, i);
+	if (rcd)
+		seqfile_dump_rcd(s, rcd);
+	hfi1_rcd_put(rcd);
+	return 0;
+}
+
+DEBUGFS_SEQ_FILE_OPS(rcds);
+DEBUGFS_SEQ_FILE_OPEN(rcds)
+DEBUGFS_FILE_OPS(rcds);
+
 /* read the per-device counters */
 static ssize_t dev_counters_read(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)
@@ -1098,12 +1150,15 @@ static int _fault_stats_seq_show(struct seq_file *s, void *v)
 	u64 n_packets = 0, n_bytes = 0;
 	struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private;
 	struct hfi1_devdata *dd = dd_from_dev(ibd);
+	struct hfi1_ctxtdata *rcd;
 
 	for (j = 0; j < dd->first_dyn_alloc_ctxt; j++) {
-		if (!dd->rcd[j])
-			continue;
-		n_packets += dd->rcd[j]->opstats->stats[i].n_packets;
-		n_bytes += dd->rcd[j]->opstats->stats[i].n_bytes;
+		rcd = hfi1_rcd_get_by_index(dd, j);
+		if (rcd) {
+			n_packets += rcd->opstats->stats[i].n_packets;
+			n_bytes += rcd->opstats->stats[i].n_bytes;
+		}
+		hfi1_rcd_put(rcd);
 	}
 	if (!n_packets && !n_bytes)
 		return SEQ_SKIP;
@@ -1311,6 +1366,7 @@ void hfi1_dbg_ibdev_init(struct hfi1_ibdev *ibd)
 	DEBUGFS_SEQ_FILE_CREATE(ctx_stats, ibd->hfi1_ibdev_dbg, ibd);
 	DEBUGFS_SEQ_FILE_CREATE(qp_stats, ibd->hfi1_ibdev_dbg, ibd);
 	DEBUGFS_SEQ_FILE_CREATE(sdes, ibd->hfi1_ibdev_dbg, ibd);
+	DEBUGFS_SEQ_FILE_CREATE(rcds, ibd->hfi1_ibdev_dbg, ibd);
 	DEBUGFS_SEQ_FILE_CREATE(sdma_cpu_list, ibd->hfi1_ibdev_dbg, ibd);
 	/* dev counter files */
 	for (i = 0; i < ARRAY_SIZE(cntr_ops); i++)
@@ -1478,5 +1534,3 @@ void hfi1_dbg_exit(void)
 	debugfs_remove_recursive(hfi1_dbg_root);
 	hfi1_dbg_root = NULL;
 }
-
-#endif
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index a50870e455a3..7372cc00cb2d 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -96,7 +96,6 @@ MODULE_PARM_DESC(cap_mask, "Bit mask of enabled/disabled HW features");
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("Intel Omni-Path Architecture driver");
-MODULE_VERSION(HFI1_DRIVER_VERSION);
 
 /*
  * MAX_PKT_RCV is the max # if packets processed per receive interrupt.
@@ -196,7 +195,7 @@ int hfi1_count_active_units(void)
 
 	spin_lock_irqsave(&hfi1_devs_lock, flags);
 	list_for_each_entry(dd, &hfi1_dev_list, list) {
-		if (!(dd->flags & HFI1_PRESENT) || !dd->kregbase)
+		if (!(dd->flags & HFI1_PRESENT) || !dd->kregbase1)
 			continue;
 		for (pidx = 0; pidx < dd->num_pports; ++pidx) {
 			ppd = dd->pport + pidx;
@@ -224,6 +223,27 @@ static inline void *get_egrbuf(const struct hfi1_ctxtdata *rcd, u64 rhf,
 			(offset * RCV_BUF_BLOCK_SIZE));
 }
 
+static inline void *hfi1_get_header(struct hfi1_devdata *dd,
+				    __le32 *rhf_addr)
+{
+	u32 offset = rhf_hdrq_offset(rhf_to_cpu(rhf_addr));
+
+	return (void *)(rhf_addr - dd->rhf_offset + offset);
+}
+
+static inline struct ib_header *hfi1_get_msgheader(struct hfi1_devdata *dd,
+						   __le32 *rhf_addr)
+{
+	return (struct ib_header *)hfi1_get_header(dd, rhf_addr);
+}
+
+static inline struct hfi1_16b_header
+		*hfi1_get_16B_header(struct hfi1_devdata *dd,
+				     __le32 *rhf_addr)
+{
+	return (struct hfi1_16b_header *)hfi1_get_header(dd, rhf_addr);
+}
+
 /*
  * Validate and encode the a given RcvArray Buffer size.
  * The function will check whether the given size falls within
@@ -249,7 +269,7 @@ 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 = ib_get_lnh(rhdr);
+	u32 mlid_base;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_devdata *dd = ppd->dd;
 	struct rvt_dev_info *rdi = &dd->verbs_dev.rdi;
@@ -257,37 +277,47 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 	if (packet->rhf & (RHF_VCRC_ERR | RHF_ICRC_ERR))
 		return;
 
+	if (packet->etype == RHF_RCV_TYPE_BYPASS) {
+		goto drop;
+	} else {
+		u8 lnh = ib_get_lnh(rhdr);
+
+		mlid_base = be16_to_cpu(IB_MULTICAST_LID_BASE);
+		if (lnh == HFI1_LRH_BTH) {
+			packet->ohdr = &rhdr->u.oth;
+		} else if (lnh == HFI1_LRH_GRH) {
+			packet->ohdr = &rhdr->u.l.oth;
+			packet->grh = &rhdr->u.l.grh;
+		} else {
+			goto drop;
+		}
+	}
+
 	if (packet->rhf & RHF_TID_ERR) {
 		/* For TIDERR and RC QPs preemptively schedule a NAK */
-		struct ib_other_headers *ohdr = NULL;
 		u32 tlen = rhf_pkt_len(packet->rhf); /* in bytes */
-		u16 lid  = ib_get_dlid(rhdr);
+		u32 dlid = ib_get_dlid(rhdr);
 		u32 qp_num;
-		u32 rcv_flags = 0;
 
 		/* Sanity check packet */
 		if (tlen < 24)
 			goto drop;
 
 		/* Check for GRH */
-		if (lnh == HFI1_LRH_BTH) {
-			ohdr = &rhdr->u.oth;
-		} else if (lnh == HFI1_LRH_GRH) {
+		if (packet->grh) {
 			u32 vtf;
+			struct ib_grh *grh = packet->grh;
 
-			ohdr = &rhdr->u.l.oth;
-			if (rhdr->u.l.grh.next_hdr != IB_GRH_NEXT_HDR)
+			if (grh->next_hdr != IB_GRH_NEXT_HDR)
 				goto drop;
-			vtf = be32_to_cpu(rhdr->u.l.grh.version_tclass_flow);
+			vtf = be32_to_cpu(grh->version_tclass_flow);
 			if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION)
 				goto drop;
-			rcv_flags |= HFI1_HAS_GRH;
-		} else {
-			goto drop;
 		}
+
 		/* Get the destination QP number. */
-		qp_num = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK;
-		if (lid < be16_to_cpu(IB_MULTICAST_LID_BASE)) {
+		qp_num = ib_bth_get_qpn(packet->ohdr);
+		if (dlid < mlid_base) {
 			struct rvt_qp *qp;
 			unsigned long flags;
 
@@ -312,11 +342,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 
 			switch (qp->ibqp.qp_type) {
 			case IB_QPT_RC:
-				hfi1_rc_hdrerr(
-					rcd,
-					rhdr,
-					rcv_flags,
-					qp);
+				hfi1_rc_hdrerr(rcd, packet, qp);
 				break;
 			default:
 				/* For now don't handle any other QP types */
@@ -332,9 +358,8 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 	switch (rte) {
 	case RHF_RTE_ERROR_OP_CODE_ERR:
 	{
-		u32 opcode;
 		void *ebuf = NULL;
-		__be32 *bth = NULL;
+		u8 opcode;
 
 		if (rhf_use_egr_bfr(packet->rhf))
 			ebuf = packet->ebuf;
@@ -342,16 +367,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 		if (!ebuf)
 			goto drop; /* this should never happen */
 
-		if (lnh == HFI1_LRH_BTH)
-			bth = (__be32 *)ebuf;
-		else if (lnh == HFI1_LRH_GRH)
-			bth = (__be32 *)((char *)ebuf + sizeof(struct ib_grh));
-		else
-			goto drop;
-
-		opcode = be32_to_cpu(bth[0]) >> 24;
-		opcode &= 0xff;
-
+		opcode = ib_bth_get_opcode(packet->ohdr);
 		if (opcode == IB_OPCODE_CNP) {
 			/*
 			 * Only in pre-B0 h/w is the CNP_OPCODE handled
@@ -365,7 +381,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 			sc5 = hfi1_9B_get_sc5(rhdr, packet->rhf);
 			sl = ibp->sc_to_sl[sc5];
 
-			lqpn = be32_to_cpu(bth[1]) & RVT_QPN_MASK;
+			lqpn = ib_bth_get_qpn(packet->ohdr);
 			rcu_read_lock();
 			qp = rvt_lookup_qpn(rdi, &ibp->rvp, lqpn);
 			if (!qp) {
@@ -415,33 +431,39 @@ static inline void init_packet(struct hfi1_ctxtdata *rcd,
 	packet->rhf = rhf_to_cpu(packet->rhf_addr);
 	packet->rhqoff = rcd->head;
 	packet->numpkt = 0;
-	packet->rcv_flags = 0;
 }
 
 void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
 	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
-	struct ib_header *hdr = pkt->hdr;
 	struct ib_other_headers *ohdr = pkt->ohdr;
-	struct ib_grh *grh = NULL;
+	struct ib_grh *grh = pkt->grh;
 	u32 rqpn = 0, bth1;
-	u16 rlid, dlid = ib_get_dlid(hdr);
-	u8 sc, svc_type;
+	u16 pkey, rlid, dlid = ib_get_dlid(pkt->hdr);
+	u8 hdr_type, sc, svc_type;
 	bool is_mcast = false;
 
-	if (pkt->rcv_flags & HFI1_HAS_GRH)
-		grh = &hdr->u.l.grh;
+	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
+		is_mcast = hfi1_is_16B_mcast(dlid);
+		pkey = hfi1_16B_get_pkey(pkt->hdr);
+		sc = hfi1_16B_get_sc(pkt->hdr);
+		hdr_type = HFI1_PKT_TYPE_16B;
+	} else {
+		is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+			   (dlid != be16_to_cpu(IB_LID_PERMISSIVE));
+		pkey = ib_bth_get_pkey(ohdr);
+		sc = hfi1_9B_get_sc5(pkt->hdr, pkt->rhf);
+		hdr_type = HFI1_PKT_TYPE_9B;
+	}
 
 	switch (qp->ibqp.qp_type) {
 	case IB_QPT_SMI:
 	case IB_QPT_GSI:
 	case IB_QPT_UD:
-		rlid = ib_get_slid(hdr);
-		rqpn = be32_to_cpu(ohdr->u.ud.deth[1]) & RVT_QPN_MASK;
+		rlid = ib_get_slid(pkt->hdr);
+		rqpn = ib_get_sqpn(pkt->ohdr);
 		svc_type = IB_CC_SVCTYPE_UD;
-		is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
-			(dlid != be16_to_cpu(IB_LID_PERMISSIVE));
 		break;
 	case IB_QPT_UC:
 		rlid = rdma_ah_get_dlid(&qp->remote_ah_attr);
@@ -457,14 +479,11 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 		return;
 	}
 
-	sc = hfi1_9B_get_sc5(hdr, pkt->rhf);
-
 	bth1 = be32_to_cpu(ohdr->bth[1]);
-	if (do_cnp && (bth1 & IB_FECN_SMASK)) {
-		u16 pkey = (u16)be32_to_cpu(ohdr->bth[0]);
-
-		return_cnp(ibp, qp, rqpn, pkey, dlid, rlid, sc, grh);
-	}
+	/* Call appropriate CNP handler */
+	if (do_cnp && (bth1 & IB_FECN_SMASK))
+		hfi1_handle_cnp_tbl[hdr_type](ibp, qp, rqpn, pkey,
+					      dlid, rlid, sc, grh);
 
 	if (!is_mcast && (bth1 & IB_BECN_SMASK)) {
 		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
@@ -591,9 +610,10 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 
 		if (lnh == HFI1_LRH_BTH) {
 			packet->ohdr = &hdr->u.oth;
+			packet->grh = NULL;
 		} else if (lnh == HFI1_LRH_GRH) {
 			packet->ohdr = &hdr->u.l.oth;
-			packet->rcv_flags |= HFI1_HAS_GRH;
+			packet->grh = &hdr->u.l.grh;
 		} else {
 			goto next; /* just in case */
 		}
@@ -698,10 +718,8 @@ static inline int process_rcv_packet(struct hfi1_packet *packet, int thread)
 {
 	int ret;
 
-	packet->hdr = hfi1_get_msgheader(packet->rcd->dd,
-					 packet->rhf_addr);
-	packet->hlen = (u8 *)packet->rhf_addr - (u8 *)packet->hdr;
 	packet->etype = rhf_rcv_type(packet->rhf);
+
 	/* total length */
 	packet->tlen = rhf_pkt_len(packet->rhf); /* in bytes */
 	/* retrieve eager buffer details */
@@ -759,7 +777,7 @@ static inline void process_rcv_update(int last, struct hfi1_packet *packet)
 			       packet->etail, 0, 0);
 		packet->updegr = 0;
 	}
-	packet->rcv_flags = 0;
+	packet->grh = NULL;
 }
 
 static inline void finish_packet(struct hfi1_packet *packet)
@@ -837,9 +855,10 @@ bail:
 	return last;
 }
 
-static inline void set_nodma_rtail(struct hfi1_devdata *dd, u8 ctxt)
+static inline void set_nodma_rtail(struct hfi1_devdata *dd, u16 ctxt)
 {
-	int i;
+	struct hfi1_ctxtdata *rcd;
+	u16 i;
 
 	/*
 	 * For dynamically allocated kernel contexts (like vnic) switch
@@ -847,19 +866,28 @@ static inline void set_nodma_rtail(struct hfi1_devdata *dd, u8 ctxt)
 	 * interrupt handler for all statically allocated kernel contexts.
 	 */
 	if (ctxt >= dd->first_dyn_alloc_ctxt) {
-		dd->rcd[ctxt]->do_interrupt =
-			&handle_receive_interrupt_nodma_rtail;
+		rcd = hfi1_rcd_get_by_index(dd, ctxt);
+		if (rcd) {
+			rcd->do_interrupt =
+				&handle_receive_interrupt_nodma_rtail;
+			hfi1_rcd_put(rcd);
+		}
 		return;
 	}
 
-	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++)
-		dd->rcd[i]->do_interrupt =
-			&handle_receive_interrupt_nodma_rtail;
+	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++) {
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (rcd)
+			rcd->do_interrupt =
+				&handle_receive_interrupt_nodma_rtail;
+		hfi1_rcd_put(rcd);
+	}
 }
 
-static inline void set_dma_rtail(struct hfi1_devdata *dd, u8 ctxt)
+static inline void set_dma_rtail(struct hfi1_devdata *dd, u16 ctxt)
 {
-	int i;
+	struct hfi1_ctxtdata *rcd;
+	u16 i;
 
 	/*
 	 * For dynamically allocated kernel contexts (like vnic) switch
@@ -867,27 +895,39 @@ static inline void set_dma_rtail(struct hfi1_devdata *dd, u8 ctxt)
 	 * interrupt handler for all statically allocated kernel contexts.
 	 */
 	if (ctxt >= dd->first_dyn_alloc_ctxt) {
-		dd->rcd[ctxt]->do_interrupt =
-			&handle_receive_interrupt_dma_rtail;
+		rcd = hfi1_rcd_get_by_index(dd, ctxt);
+		if (rcd) {
+			rcd->do_interrupt =
+				&handle_receive_interrupt_dma_rtail;
+			hfi1_rcd_put(rcd);
+		}
 		return;
 	}
 
-	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++)
-		dd->rcd[i]->do_interrupt =
-			&handle_receive_interrupt_dma_rtail;
+	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++) {
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (rcd)
+			rcd->do_interrupt =
+				&handle_receive_interrupt_dma_rtail;
+		hfi1_rcd_put(rcd);
+	}
 }
 
 void set_all_slowpath(struct hfi1_devdata *dd)
 {
-	int i;
+	struct hfi1_ctxtdata *rcd;
+	u16 i;
 
 	/* HFI1_CTRL_CTXT must always use the slow path interrupt handler */
 	for (i = HFI1_CTRL_CTXT + 1; i < dd->num_rcv_contexts; i++) {
-		struct hfi1_ctxtdata *rcd = dd->rcd[i];
-
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (!rcd)
+			continue;
 		if ((i < dd->first_dyn_alloc_ctxt) ||
-		    (rcd && rcd->sc && (rcd->sc->type == SC_KERNEL)))
+		    (rcd->sc && (rcd->sc->type == SC_KERNEL))) {
 			rcd->do_interrupt = &handle_receive_interrupt;
+		}
+		hfi1_rcd_put(rcd);
 	}
 }
 
@@ -896,20 +936,30 @@ static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
 				      struct hfi1_devdata *dd)
 {
 	struct work_struct *lsaw = &rcd->ppd->linkstate_active_work;
-	struct ib_header *hdr = hfi1_get_msgheader(packet->rcd->dd,
-						   packet->rhf_addr);
 	u8 etype = rhf_rcv_type(packet->rhf);
+	u8 sc = SC15_PACKET;
+
+	if (etype == RHF_RCV_TYPE_IB) {
+		struct ib_header *hdr = hfi1_get_msgheader(packet->rcd->dd,
+							   packet->rhf_addr);
+		sc = hfi1_9B_get_sc5(hdr, packet->rhf);
+	} else if (etype == RHF_RCV_TYPE_BYPASS) {
+		struct hfi1_16b_header *hdr = hfi1_get_16B_header(
+						packet->rcd->dd,
+						packet->rhf_addr);
+		sc = hfi1_16B_get_sc(hdr);
+	}
+	if (sc != SC15_PACKET) {
+		int hwstate = driver_lstate(rcd->ppd);
 
-	if (etype == RHF_RCV_TYPE_IB &&
-	    hfi1_9B_get_sc5(hdr, packet->rhf) != 0xf) {
-		int hwstate = read_logical_state(dd);
-
-		if (hwstate != LSTATE_ACTIVE) {
-			dd_dev_info(dd, "Unexpected link state %d\n", hwstate);
+		if (hwstate != IB_PORT_ACTIVE) {
+			dd_dev_info(dd,
+				    "Unexpected link state %s\n",
+				    opa_lstate_name(hwstate));
 			return 0;
 		}
 
-		queue_work(rcd->ppd->hfi1_wq, lsaw);
+		queue_work(rcd->ppd->link_wq, lsaw);
 		return 1;
 	}
 	return 0;
@@ -1063,7 +1113,8 @@ void receive_interrupt_work(struct work_struct *work)
 	struct hfi1_pportdata *ppd = container_of(work, struct hfi1_pportdata,
 						  linkstate_active_work);
 	struct hfi1_devdata *dd = ppd->dd;
-	int i;
+	struct hfi1_ctxtdata *rcd;
+	u16 i;
 
 	/* Received non-SC15 packet implies neighbor_normal */
 	ppd->neighbor_normal = 1;
@@ -1073,8 +1124,12 @@ void receive_interrupt_work(struct work_struct *work)
 	 * Interrupt all statically allocated kernel contexts that could
 	 * have had an interrupt during auto activation.
 	 */
-	for (i = HFI1_CTRL_CTXT; i < dd->first_dyn_alloc_ctxt; i++)
-		force_recv_intr(dd->rcd[i]);
+	for (i = HFI1_CTRL_CTXT; i < dd->first_dyn_alloc_ctxt; i++) {
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (rcd)
+			force_recv_intr(rcd);
+		hfi1_rcd_put(rcd);
+	}
 }
 
 /*
@@ -1264,10 +1319,9 @@ void hfi1_start_led_override(struct hfi1_pportdata *ppd, unsigned int timeon,
  */
 int hfi1_reset_device(int unit)
 {
-	int ret, i;
+	int ret;
 	struct hfi1_devdata *dd = hfi1_lookup(unit);
 	struct hfi1_pportdata *ppd;
-	unsigned long flags;
 	int pidx;
 
 	if (!dd) {
@@ -1277,7 +1331,7 @@ int hfi1_reset_device(int unit)
 
 	dd_dev_info(dd, "Reset on unit %u requested\n", unit);
 
-	if (!dd->kregbase || !(dd->flags & HFI1_PRESENT)) {
+	if (!dd->kregbase1 || !(dd->flags & HFI1_PRESENT)) {
 		dd_dev_info(dd,
 			    "Invalid unit number %u or not initialized or not present\n",
 			    unit);
@@ -1285,17 +1339,15 @@ int hfi1_reset_device(int unit)
 		goto bail;
 	}
 
-	spin_lock_irqsave(&dd->uctxt_lock, flags);
+	/* If there are any user/vnic contexts, we cannot reset */
+	mutex_lock(&hfi1_mutex);
 	if (dd->rcd)
-		for (i = dd->first_dyn_alloc_ctxt;
-		     i < dd->num_rcv_contexts; i++) {
-			if (!dd->rcd[i])
-				continue;
-			spin_unlock_irqrestore(&dd->uctxt_lock, flags);
+		if (hfi1_stats.sps_ctxts) {
+			mutex_unlock(&hfi1_mutex);
 			ret = -EBUSY;
 			goto bail;
 		}
-	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
+	mutex_unlock(&hfi1_mutex);
 
 	for (pidx = 0; pidx < dd->num_pports; ++pidx) {
 		ppd = dd->pport + pidx;
@@ -1321,6 +1373,162 @@ bail:
 	return ret;
 }
 
+static inline void hfi1_setup_ib_header(struct hfi1_packet *packet)
+{
+	packet->hdr = (struct hfi1_ib_message_header *)
+			hfi1_get_msgheader(packet->rcd->dd,
+					   packet->rhf_addr);
+	packet->hlen = (u8 *)packet->rhf_addr - (u8 *)packet->hdr;
+}
+
+static int hfi1_bypass_ingress_pkt_check(struct hfi1_packet *packet)
+{
+	struct hfi1_pportdata *ppd = packet->rcd->ppd;
+
+	/* slid and dlid cannot be 0 */
+	if ((!packet->slid) || (!packet->dlid))
+		return -EINVAL;
+
+	/* Compare port lid with incoming packet dlid */
+	if ((!(hfi1_is_16B_mcast(packet->dlid))) &&
+	    (packet->dlid !=
+		opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B))) {
+		if (packet->dlid != ppd->lid)
+			return -EINVAL;
+	}
+
+	/* No multicast packets with SC15 */
+	if ((hfi1_is_16B_mcast(packet->dlid)) && (packet->sc == 0xF))
+		return -EINVAL;
+
+	/* Packets with permissive DLID always on SC15 */
+	if ((packet->dlid == opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE),
+					 16B)) &&
+	    (packet->sc != 0xF))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int hfi1_setup_9B_packet(struct hfi1_packet *packet)
+{
+	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
+	struct ib_header *hdr;
+	u8 lnh;
+
+	hfi1_setup_ib_header(packet);
+	hdr = packet->hdr;
+
+	lnh = ib_get_lnh(hdr);
+	if (lnh == HFI1_LRH_BTH) {
+		packet->ohdr = &hdr->u.oth;
+		packet->grh = NULL;
+	} else if (lnh == HFI1_LRH_GRH) {
+		u32 vtf;
+
+		packet->ohdr = &hdr->u.l.oth;
+		packet->grh = &hdr->u.l.grh;
+		if (packet->grh->next_hdr != IB_GRH_NEXT_HDR)
+			goto drop;
+		vtf = be32_to_cpu(packet->grh->version_tclass_flow);
+		if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION)
+			goto drop;
+	} else {
+		goto drop;
+	}
+
+	/* Query commonly used fields from packet header */
+	packet->payload = packet->ebuf;
+	packet->opcode = ib_bth_get_opcode(packet->ohdr);
+	packet->slid = ib_get_slid(hdr);
+	packet->dlid = ib_get_dlid(hdr);
+	if (unlikely((packet->dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+		     (packet->dlid != be16_to_cpu(IB_LID_PERMISSIVE))))
+		packet->dlid += opa_get_mcast_base(OPA_MCAST_NR) -
+				be16_to_cpu(IB_MULTICAST_LID_BASE);
+	packet->sl = ib_get_sl(hdr);
+	packet->sc = hfi1_9B_get_sc5(hdr, packet->rhf);
+	packet->pad = ib_bth_get_pad(packet->ohdr);
+	packet->extra_byte = 0;
+	packet->fecn = ib_bth_get_fecn(packet->ohdr);
+	packet->becn = ib_bth_get_becn(packet->ohdr);
+
+	return 0;
+drop:
+	ibp->rvp.n_pkt_drops++;
+	return -EINVAL;
+}
+
+static int hfi1_setup_bypass_packet(struct hfi1_packet *packet)
+{
+	/*
+	 * Bypass packets have a different header/payload split
+	 * compared to an IB packet.
+	 * Current split is set such that 16 bytes of the actual
+	 * header is in the header buffer and the remining is in
+	 * the eager buffer. We chose 16 since hfi1 driver only
+	 * supports 16B bypass packets and we will be able to
+	 * receive the entire LRH with such a split.
+	 */
+
+	struct hfi1_ctxtdata *rcd = packet->rcd;
+	struct hfi1_pportdata *ppd = rcd->ppd;
+	struct hfi1_ibport *ibp = &ppd->ibport_data;
+	u8 l4;
+	u8 grh_len;
+
+	packet->hdr = (struct hfi1_16b_header *)
+			hfi1_get_16B_header(packet->rcd->dd,
+					    packet->rhf_addr);
+	packet->hlen = (u8 *)packet->rhf_addr - (u8 *)packet->hdr;
+
+	l4 = hfi1_16B_get_l4(packet->hdr);
+	if (l4 == OPA_16B_L4_IB_LOCAL) {
+		grh_len = 0;
+		packet->ohdr = packet->ebuf;
+		packet->grh = NULL;
+	} else if (l4 == OPA_16B_L4_IB_GLOBAL) {
+		u32 vtf;
+
+		grh_len = sizeof(struct ib_grh);
+		packet->ohdr = packet->ebuf + grh_len;
+		packet->grh = packet->ebuf;
+		if (packet->grh->next_hdr != IB_GRH_NEXT_HDR)
+			goto drop;
+		vtf = be32_to_cpu(packet->grh->version_tclass_flow);
+		if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION)
+			goto drop;
+	} else {
+		goto drop;
+	}
+
+	/* Query commonly used fields from packet header */
+	packet->opcode = ib_bth_get_opcode(packet->ohdr);
+	packet->hlen = hdr_len_by_opcode[packet->opcode] + 8 + grh_len;
+	packet->payload = packet->ebuf + packet->hlen - (4 * sizeof(u32));
+	packet->slid = hfi1_16B_get_slid(packet->hdr);
+	packet->dlid = hfi1_16B_get_dlid(packet->hdr);
+	if (unlikely(hfi1_is_16B_mcast(packet->dlid)))
+		packet->dlid += opa_get_mcast_base(OPA_MCAST_NR) -
+				opa_get_lid(opa_get_mcast_base(OPA_MCAST_NR),
+					    16B);
+	packet->sc = hfi1_16B_get_sc(packet->hdr);
+	packet->sl = ibp->sc_to_sl[packet->sc];
+	packet->pad = hfi1_16B_bth_get_pad(packet->ohdr);
+	packet->extra_byte = SIZE_OF_LT;
+	packet->fecn = hfi1_16B_get_fecn(packet->hdr);
+	packet->becn = hfi1_16B_get_becn(packet->hdr);
+
+	if (hfi1_bypass_ingress_pkt_check(packet))
+		goto drop;
+
+	return 0;
+drop:
+	hfi1_cdbg(PKT, "%s: packet dropped\n", __func__);
+	ibp->rvp.n_pkt_drops++;
+	return -EINVAL;
+}
+
 void handle_eflags(struct hfi1_packet *packet)
 {
 	struct hfi1_ctxtdata *rcd = packet->rcd;
@@ -1351,6 +1559,9 @@ int process_receive_ib(struct hfi1_packet *packet)
 	if (unlikely(hfi1_dbg_fault_packet(packet)))
 		return RHF_RCV_CONTINUE;
 
+	if (hfi1_setup_9B_packet(packet))
+		return RHF_RCV_CONTINUE;
+
 	trace_hfi1_rcvhdr(packet->rcd->ppd->dd,
 			  packet->rcd->ctxt,
 			  rhf_err_flags(packet->rhf),
@@ -1380,8 +1591,8 @@ static inline bool hfi1_is_vnic_packet(struct hfi1_packet *packet)
 	if (packet->rcd->is_vnic)
 		return true;
 
-	if ((HFI1_GET_L2_TYPE(packet->ebuf) == OPA_VNIC_L2_TYPE) &&
-	    (HFI1_GET_L4_TYPE(packet->ebuf) == OPA_VNIC_L4_ETHR))
+	if ((hfi1_16B_get_l2(packet->ebuf) == OPA_16B_L2_TYPE) &&
+	    (hfi1_16B_get_l4(packet->ebuf) == OPA_16B_L4_ETHR))
 		return true;
 
 	return false;
@@ -1391,25 +1602,38 @@ int process_receive_bypass(struct hfi1_packet *packet)
 {
 	struct hfi1_devdata *dd = packet->rcd->dd;
 
-	if (unlikely(rhf_err_flags(packet->rhf))) {
-		handle_eflags(packet);
-	} else if (hfi1_is_vnic_packet(packet)) {
+	if (hfi1_is_vnic_packet(packet)) {
 		hfi1_vnic_bypass_rcv(packet);
 		return RHF_RCV_CONTINUE;
 	}
 
-	dd_dev_err(dd, "Unsupported bypass packet. Dropping\n");
-	incr_cntr64(&dd->sw_rcv_bypass_packet_errors);
-	if (!(dd->err_info_rcvport.status_and_code & OPA_EI_STATUS_SMASK)) {
-		u64 *flits = packet->ebuf;
+	if (hfi1_setup_bypass_packet(packet))
+		return RHF_RCV_CONTINUE;
+
+	if (unlikely(rhf_err_flags(packet->rhf))) {
+		handle_eflags(packet);
+		return RHF_RCV_CONTINUE;
+	}
 
-		if (flits && !(packet->rhf & RHF_LEN_ERR)) {
-			dd->err_info_rcvport.packet_flit1 = flits[0];
-			dd->err_info_rcvport.packet_flit2 =
-				packet->tlen > sizeof(flits[0]) ? flits[1] : 0;
+	if (hfi1_16B_get_l2(packet->hdr) == 0x2) {
+		hfi1_16B_rcv(packet);
+	} else {
+		dd_dev_err(dd,
+			   "Bypass packets other than 16B are not supported in normal operation. Dropping\n");
+		incr_cntr64(&dd->sw_rcv_bypass_packet_errors);
+		if (!(dd->err_info_rcvport.status_and_code &
+		      OPA_EI_STATUS_SMASK)) {
+			u64 *flits = packet->ebuf;
+
+			if (flits && !(packet->rhf & RHF_LEN_ERR)) {
+				dd->err_info_rcvport.packet_flit1 = flits[0];
+				dd->err_info_rcvport.packet_flit2 =
+					packet->tlen > sizeof(flits[0]) ?
+					flits[1] : 0;
+			}
+			dd->err_info_rcvport.status_and_code |=
+				(OPA_EI_STATUS_SMASK | BAD_L2_ERR);
 		}
-		dd->err_info_rcvport.status_and_code |=
-			(OPA_EI_STATUS_SMASK | BAD_L2_ERR);
 	}
 	return RHF_RCV_CONTINUE;
 }
@@ -1422,6 +1646,7 @@ int process_receive_error(struct hfi1_packet *packet)
 		 rhf_rcv_type_err(packet->rhf) == 3))
 		return RHF_RCV_CONTINUE;
 
+	hfi1_setup_ib_header(packet);
 	handle_eflags(packet);
 
 	if (unlikely(rhf_err_flags(packet->rhf)))
@@ -1435,6 +1660,8 @@ int kdeth_process_expected(struct hfi1_packet *packet)
 {
 	if (unlikely(hfi1_dbg_fault_packet(packet)))
 		return RHF_RCV_CONTINUE;
+
+	hfi1_setup_ib_header(packet);
 	if (unlikely(rhf_err_flags(packet->rhf)))
 		handle_eflags(packet);
 
@@ -1445,6 +1672,7 @@ int kdeth_process_expected(struct hfi1_packet *packet)
 
 int kdeth_process_eager(struct hfi1_packet *packet)
 {
+	hfi1_setup_ib_header(packet);
 	if (unlikely(rhf_err_flags(packet->rhf)))
 		handle_eflags(packet);
 	if (unlikely(hfi1_dbg_fault_packet(packet)))
@@ -1461,3 +1689,62 @@ int process_receive_invalid(struct hfi1_packet *packet)
 		   rhf_rcv_type(packet->rhf));
 	return RHF_RCV_CONTINUE;
 }
+
+void seqfile_dump_rcd(struct seq_file *s, struct hfi1_ctxtdata *rcd)
+{
+	struct hfi1_packet packet;
+	struct ps_mdata mdata;
+
+	seq_printf(s, "Rcd %u: RcvHdr cnt %u entsize %u %s head %llu tail %llu\n",
+		   rcd->ctxt, rcd->rcvhdrq_cnt, rcd->rcvhdrqentsize,
+		   HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ?
+		   "dma_rtail" : "nodma_rtail",
+		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_HEAD) &
+		   RCV_HDR_HEAD_HEAD_MASK,
+		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL));
+
+	init_packet(rcd, &packet);
+	init_ps_mdata(&mdata, &packet);
+
+	while (1) {
+		struct hfi1_devdata *dd = rcd->dd;
+		__le32 *rhf_addr = (__le32 *)rcd->rcvhdrq + mdata.ps_head +
+					 dd->rhf_offset;
+		struct ib_header *hdr;
+		u64 rhf = rhf_to_cpu(rhf_addr);
+		u32 etype = rhf_rcv_type(rhf), qpn;
+		u8 opcode;
+		u32 psn;
+		u8 lnh;
+
+		if (ps_done(&mdata, rhf, rcd))
+			break;
+
+		if (ps_skip(&mdata, rhf, rcd))
+			goto next;
+
+		if (etype > RHF_RCV_TYPE_IB)
+			goto next;
+
+		packet.hdr = hfi1_get_msgheader(dd, rhf_addr);
+		hdr = packet.hdr;
+
+		lnh = be16_to_cpu(hdr->lrh[0]) & 3;
+
+		if (lnh == HFI1_LRH_BTH)
+			packet.ohdr = &hdr->u.oth;
+		else if (lnh == HFI1_LRH_GRH)
+			packet.ohdr = &hdr->u.l.oth;
+		else
+			goto next; /* just in case */
+
+		opcode = (be32_to_cpu(packet.ohdr->bth[0]) >> 24);
+		qpn = be32_to_cpu(packet.ohdr->bth[1]) & RVT_QPN_MASK;
+		psn = mask_psn(be32_to_cpu(packet.ohdr->bth[2]));
+
+		seq_printf(s, "\tEnt %u: opcode 0x%x, qpn 0x%x, psn 0x%x\n",
+			   mdata.ps_head, opcode, qpn, psn);
+next:
+		update_ps_mdata(&mdata, rcd);
+	}
+}
diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c
index 26da124c88e2..d46b17107901 100644
--- a/drivers/infiniband/hw/hfi1/eprom.c
+++ b/drivers/infiniband/hw/hfi1/eprom.c
@@ -250,7 +250,6 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
 {
 	void *buffer;
 	void *p;
-	u32 length;
 	int ret;
 
 	buffer = kmalloc(P1_SIZE, GFP_KERNEL);
@@ -265,13 +264,13 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
 
 	/* scan for image magic that may trail the actual data */
 	p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
-	if (p)
-		length = p - buffer;
-	else
-		length = P1_SIZE;
+	if (!p) {
+		kfree(buffer);
+		return -ENOENT;
+	}
 
 	*data = buffer;
-	*size = length;
+	*size = p - buffer;
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/exp_rcv.c b/drivers/infiniband/hw/hfi1/exp_rcv.c
new file mode 100644
index 000000000000..0af91675acc6
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/exp_rcv.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright(c) 2017 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 "exp_rcv.h"
+#include "trace.h"
+
+/**
+ * exp_tid_group_init - initialize exp_tid_set
+ * @set - the set
+ */
+void hfi1_exp_tid_group_init(struct exp_tid_set *set)
+{
+	INIT_LIST_HEAD(&set->list);
+	set->count = 0;
+}
+
+/**
+ * alloc_ctxt_rcv_groups - initialize expected receive groups
+ * @rcd - the context to add the groupings to
+ */
+int hfi1_alloc_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd)
+{
+	struct hfi1_devdata *dd = rcd->dd;
+	u32 tidbase;
+	struct tid_group *grp;
+	int i;
+
+	tidbase = rcd->expected_base;
+	for (i = 0; i < rcd->expected_count /
+		     dd->rcv_entries.group_size; i++) {
+		grp = kzalloc(sizeof(*grp), GFP_KERNEL);
+		if (!grp)
+			goto bail;
+		grp->size = dd->rcv_entries.group_size;
+		grp->base = tidbase;
+		tid_group_add_tail(grp, &rcd->tid_group_list);
+		tidbase += dd->rcv_entries.group_size;
+	}
+
+	return 0;
+bail:
+	hfi1_free_ctxt_rcv_groups(rcd);
+	return -ENOMEM;
+}
+
+/**
+ * free_ctxt_rcv_groups - free  expected receive groups
+ * @rcd - the context to free
+ *
+ * The routine dismantles the expect receive linked
+ * list and clears any tids associated with the receive
+ * context.
+ *
+ * This should only be called for kernel contexts and the
+ * a base user context.
+ */
+void hfi1_free_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd)
+{
+	struct tid_group *grp, *gptr;
+
+	WARN_ON(!EXP_TID_SET_EMPTY(rcd->tid_full_list));
+	WARN_ON(!EXP_TID_SET_EMPTY(rcd->tid_used_list));
+
+	list_for_each_entry_safe(grp, gptr, &rcd->tid_group_list.list, list) {
+		tid_group_remove(grp, &rcd->tid_group_list);
+		kfree(grp);
+	}
+
+	hfi1_clear_tids(rcd);
+}
diff --git a/drivers/infiniband/hw/hfi1/exp_rcv.h b/drivers/infiniband/hw/hfi1/exp_rcv.h
new file mode 100644
index 000000000000..08719047628a
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/exp_rcv.h
@@ -0,0 +1,190 @@
+#ifndef _HFI1_EXP_RCV_H
+#define _HFI1_EXP_RCV_H
+/*
+ * Copyright(c) 2017 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 "hfi.h"
+
+#define EXP_TID_SET_EMPTY(set) (set.count == 0 && list_empty(&set.list))
+
+#define EXP_TID_TIDLEN_MASK   0x7FFULL
+#define EXP_TID_TIDLEN_SHIFT  0
+#define EXP_TID_TIDCTRL_MASK  0x3ULL
+#define EXP_TID_TIDCTRL_SHIFT 20
+#define EXP_TID_TIDIDX_MASK   0x3FFULL
+#define EXP_TID_TIDIDX_SHIFT  22
+#define EXP_TID_GET(tid, field)	\
+	(((tid) >> EXP_TID_TID##field##_SHIFT) & EXP_TID_TID##field##_MASK)
+
+#define EXP_TID_SET(field, value)			\
+	(((value) & EXP_TID_TID##field##_MASK) <<	\
+	 EXP_TID_TID##field##_SHIFT)
+#define EXP_TID_CLEAR(tid, field) ({					\
+		(tid) &= ~(EXP_TID_TID##field##_MASK <<			\
+			   EXP_TID_TID##field##_SHIFT);			\
+		})
+#define EXP_TID_RESET(tid, field, value) do {				\
+		EXP_TID_CLEAR(tid, field);				\
+		(tid) |= EXP_TID_SET(field, (value));			\
+	} while (0)
+
+/*
+ * Define fields in the KDETH header so we can update the header
+ * template.
+ */
+#define KDETH_OFFSET_SHIFT        0
+#define KDETH_OFFSET_MASK         0x7fff
+#define KDETH_OM_SHIFT            15
+#define KDETH_OM_MASK             0x1
+#define KDETH_TID_SHIFT           16
+#define KDETH_TID_MASK            0x3ff
+#define KDETH_TIDCTRL_SHIFT       26
+#define KDETH_TIDCTRL_MASK        0x3
+#define KDETH_INTR_SHIFT          28
+#define KDETH_INTR_MASK           0x1
+#define KDETH_SH_SHIFT            29
+#define KDETH_SH_MASK             0x1
+#define KDETH_KVER_SHIFT          30
+#define KDETH_KVER_MASK           0x3
+#define KDETH_JKEY_SHIFT          0x0
+#define KDETH_JKEY_MASK           0xff
+#define KDETH_HCRC_UPPER_SHIFT    16
+#define KDETH_HCRC_UPPER_MASK     0xff
+#define KDETH_HCRC_LOWER_SHIFT    24
+#define KDETH_HCRC_LOWER_MASK     0xff
+
+#define KDETH_GET(val, field)						\
+	(((le32_to_cpu((val))) >> KDETH_##field##_SHIFT) & KDETH_##field##_MASK)
+#define KDETH_SET(dw, field, val) do {					\
+		u32 dwval = le32_to_cpu(dw);				\
+		dwval &= ~(KDETH_##field##_MASK << KDETH_##field##_SHIFT); \
+		dwval |= (((val) & KDETH_##field##_MASK) << \
+			  KDETH_##field##_SHIFT);			\
+		dw = cpu_to_le32(dwval);				\
+	} while (0)
+
+#define KDETH_RESET(dw, field, val) ({ dw = 0; KDETH_SET(dw, field, val); })
+
+/* KDETH OM multipliers and switch over point */
+#define KDETH_OM_SMALL     4
+#define KDETH_OM_SMALL_SHIFT     2
+#define KDETH_OM_LARGE     64
+#define KDETH_OM_LARGE_SHIFT     6
+#define KDETH_OM_MAX_SIZE  (1 << ((KDETH_OM_LARGE / KDETH_OM_SMALL) + 1))
+
+struct tid_group {
+	struct list_head list;
+	u32 base;
+	u8 size;
+	u8 used;
+	u8 map;
+};
+
+/*
+ * Write an "empty" RcvArray entry.
+ * This function exists so the TID registaration code can use it
+ * to write to unused/unneeded entries and still take advantage
+ * of the WC performance improvements. The HFI will ignore this
+ * write to the RcvArray entry.
+ */
+static inline void rcv_array_wc_fill(struct hfi1_devdata *dd, u32 index)
+{
+	/*
+	 * Doing the WC fill writes only makes sense if the device is
+	 * present and the RcvArray has been mapped as WC memory.
+	 */
+	if ((dd->flags & HFI1_PRESENT) && dd->rcvarray_wc) {
+		writeq(0, dd->rcvarray_wc + (index * 8));
+		if ((index & 3) == 3)
+			flush_wc();
+	}
+}
+
+static inline void tid_group_add_tail(struct tid_group *grp,
+				      struct exp_tid_set *set)
+{
+	list_add_tail(&grp->list, &set->list);
+	set->count++;
+}
+
+static inline void tid_group_remove(struct tid_group *grp,
+				    struct exp_tid_set *set)
+{
+	list_del_init(&grp->list);
+	set->count--;
+}
+
+static inline void tid_group_move(struct tid_group *group,
+				  struct exp_tid_set *s1,
+				  struct exp_tid_set *s2)
+{
+	tid_group_remove(group, s1);
+	tid_group_add_tail(group, s2);
+}
+
+static inline struct tid_group *tid_group_pop(struct exp_tid_set *set)
+{
+	struct tid_group *grp =
+		list_first_entry(&set->list, struct tid_group, list);
+	list_del_init(&grp->list);
+	set->count--;
+	return grp;
+}
+
+static inline u32 rcventry2tidinfo(u32 rcventry)
+{
+	u32 pair = rcventry & ~0x1;
+
+	return EXP_TID_SET(IDX, pair >> 1) |
+		EXP_TID_SET(CTRL, 1 << (rcventry - pair));
+}
+
+int hfi1_alloc_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd);
+void hfi1_free_ctxt_rcv_groups(struct hfi1_ctxtdata *rcd);
+void hfi1_exp_tid_group_init(struct exp_tid_set *set);
+
+#endif /* _HFI1_EXP_RCV_H */
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 3158128d57e8..2bc89260235a 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -58,10 +58,10 @@
 #include "device.h"
 #include "common.h"
 #include "trace.h"
+#include "mmu_rb.h"
 #include "user_sdma.h"
 #include "user_exp_rcv.h"
 #include "aspm.h"
-#include "mmu_rb.h"
 
 #undef pr_fmt
 #define pr_fmt(fmt) DRIVER_NAME ": " fmt
@@ -79,21 +79,25 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma);
 
 static u64 kvirt_to_phys(void *addr);
 static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo);
-static int init_subctxts(struct hfi1_ctxtdata *uctxt,
-			 const struct hfi1_user_info *uinfo);
-static int init_user_ctxt(struct hfi1_filedata *fd);
+static void init_subctxts(struct hfi1_ctxtdata *uctxt,
+			  const struct hfi1_user_info *uinfo);
+static int init_user_ctxt(struct hfi1_filedata *fd,
+			  struct hfi1_ctxtdata *uctxt);
 static void user_init(struct hfi1_ctxtdata *uctxt);
 static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase,
 			 __u32 len);
 static int get_base_info(struct hfi1_filedata *fd, void __user *ubase,
 			 __u32 len);
-static int setup_base_ctxt(struct hfi1_filedata *fd);
+static int setup_base_ctxt(struct hfi1_filedata *fd,
+			   struct hfi1_ctxtdata *uctxt);
 static int setup_subctxt(struct hfi1_ctxtdata *uctxt);
 
 static int find_sub_ctxt(struct hfi1_filedata *fd,
 			 const struct hfi1_user_info *uinfo);
 static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd,
-			 struct hfi1_user_info *uinfo);
+			 struct hfi1_user_info *uinfo,
+			 struct hfi1_ctxtdata **cd);
+static void deallocate_ctxt(struct hfi1_ctxtdata *uctxt);
 static unsigned int poll_urgent(struct file *fp, struct poll_table_struct *pt);
 static unsigned int poll_next(struct file *fp, struct poll_table_struct *pt);
 static int user_event_ack(struct hfi1_ctxtdata *uctxt, u16 subctxt,
@@ -116,7 +120,7 @@ static const struct file_operations hfi1_file_ops = {
 	.llseek = noop_llseek,
 };
 
-static struct vm_operations_struct vm_ops = {
+static const struct vm_operations_struct vm_ops = {
 	.fault = vma_fault,
 };
 
@@ -181,7 +185,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 					       struct hfi1_devdata,
 					       user_cdev);
 
-	if (!((dd->flags & HFI1_PRESENT) && dd->kregbase))
+	if (!((dd->flags & HFI1_PRESENT) && dd->kregbase1))
 		return -EINVAL;
 
 	if (!atomic_inc_not_zero(&dd->user_refcount))
@@ -267,12 +271,14 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
 			/*
 			 * Copy the number of tidlist entries we used
 			 * and the length of the buffer we registered.
-			 * These fields are adjacent in the structure so
-			 * we can copy them at the same time.
 			 */
 			addr = arg + offsetof(struct hfi1_tid_info, tidcnt);
 			if (copy_to_user((void __user *)addr, &tinfo.tidcnt,
-					 sizeof(tinfo.tidcnt) +
+					 sizeof(tinfo.tidcnt)))
+				return -EFAULT;
+
+			addr = arg + offsetof(struct hfi1_tid_info, length);
+			if (copy_to_user((void __user *)addr, &tinfo.length,
 					 sizeof(tinfo.length)))
 				ret = -EFAULT;
 		}
@@ -388,8 +394,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
 
 			sc_disable(sc);
 			ret = sc_enable(sc);
-			hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_ENB,
-				     uctxt->ctxt);
+			hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_ENB, uctxt);
 		} else {
 			ret = sc_restart(sc);
 		}
@@ -425,8 +430,7 @@ static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 	if (!iter_is_iovec(from) || !dim)
 		return -EINVAL;
 
-	hfi1_cdbg(SDMA, "SDMA request from %u:%u (%lu)",
-		  fd->uctxt->ctxt, fd->subctxt, dim);
+	trace_hfi1_sdma_request(fd->dd, fd->uctxt->ctxt, fd->subctxt, dim);
 
 	if (atomic_read(&pq->n_reqs) == pq->n_max_reqs)
 		return -ENOSPC;
@@ -752,12 +756,11 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 	if (!uctxt)
 		goto done;
 
-	hfi1_cdbg(PROC, "freeing ctxt %u:%u", uctxt->ctxt, fdata->subctxt);
-	mutex_lock(&hfi1_mutex);
+	hfi1_cdbg(PROC, "closing ctxt %u:%u", uctxt->ctxt, fdata->subctxt);
 
 	flush_wc();
 	/* drain user sdma queue */
-	hfi1_user_sdma_free_queues(fdata);
+	hfi1_user_sdma_free_queues(fdata, uctxt);
 
 	/* release the cpu */
 	hfi1_put_proc_affinity(fdata->rec_cpu_num);
@@ -766,6 +769,13 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 	hfi1_user_exp_rcv_free(fdata);
 
 	/*
+	 * fdata->uctxt is used in the above cleanup.  It is not ready to be
+	 * removed until here.
+	 */
+	fdata->uctxt = NULL;
+	hfi1_rcd_put(uctxt);
+
+	/*
 	 * Clear any left over, unhandled events so the next process that
 	 * gets this context doesn't get confused.
 	 */
@@ -773,13 +783,14 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 			   HFI1_MAX_SHARED_CTXTS) + fdata->subctxt;
 	*ev = 0;
 
+	spin_lock_irqsave(&dd->uctxt_lock, flags);
 	__clear_bit(fdata->subctxt, uctxt->in_use_ctxts);
 	if (!bitmap_empty(uctxt->in_use_ctxts, HFI1_MAX_SHARED_CTXTS)) {
-		mutex_unlock(&hfi1_mutex);
+		spin_unlock_irqrestore(&dd->uctxt_lock, flags);
 		goto done;
 	}
+	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
 
-	spin_lock_irqsave(&dd->uctxt_lock, flags);
 	/*
 	 * Disable receive context and interrupt available, reset all
 	 * RcvCtxtCtrl bits to default values.
@@ -790,34 +801,24 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 		     HFI1_RCVCTRL_TAILUPD_DIS |
 		     HFI1_RCVCTRL_ONE_PKT_EGR_DIS |
 		     HFI1_RCVCTRL_NO_RHQ_DROP_DIS |
-		     HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt->ctxt);
+		     HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt);
 	/* Clear the context's J_KEY */
-	hfi1_clear_ctxt_jkey(dd, uctxt->ctxt);
+	hfi1_clear_ctxt_jkey(dd, uctxt);
 	/*
-	 * Reset context integrity checks to default.
-	 * (writes to CSRs probably belong in chip.c)
+	 * If a send context is allocated, reset context integrity
+	 * checks to default and disable the send context.
 	 */
-	write_kctxt_csr(dd, uctxt->sc->hw_context, SEND_CTXT_CHECK_ENABLE,
-			hfi1_pkt_default_send_ctxt_mask(dd, uctxt->sc->type));
-	sc_disable(uctxt->sc);
-	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
-
-	dd->rcd[uctxt->ctxt] = NULL;
+	if (uctxt->sc) {
+		set_pio_integrity(uctxt->sc);
+		sc_disable(uctxt->sc);
+	}
 
-	hfi1_user_exp_rcv_grp_free(uctxt);
+	hfi1_free_ctxt_rcv_groups(uctxt);
 	hfi1_clear_ctxt_pkey(dd, uctxt);
 
-	uctxt->rcvwait_to = 0;
-	uctxt->piowait_to = 0;
-	uctxt->rcvnowait = 0;
-	uctxt->pionowait = 0;
 	uctxt->event_flags = 0;
 
-	hfi1_stats.sps_ctxts--;
-	if (++dd->freectxts == dd->num_user_contexts)
-		aspm_enable_all(dd);
-	mutex_unlock(&hfi1_mutex);
-	hfi1_free_ctxtdata(dd, uctxt);
+	deallocate_ctxt(uctxt);
 done:
 	mmdrop(fdata->mm);
 	kobject_put(&dd->kobj);
@@ -845,135 +846,211 @@ static u64 kvirt_to_phys(void *addr)
 	return paddr;
 }
 
+/**
+ * complete_subctxt
+ * @fd: valid filedata pointer
+ *
+ * Sub-context info can only be set up after the base context
+ * has been completed.  This is indicated by the clearing of the
+ * HFI1_CTXT_BASE_UINIT bit.
+ *
+ * Wait for the bit to be cleared, and then complete the subcontext
+ * initialization.
+ *
+ */
+static int complete_subctxt(struct hfi1_filedata *fd)
+{
+	int ret;
+	unsigned long flags;
+
+	/*
+	 * sub-context info can only be set up after the base context
+	 * has been completed.
+	 */
+	ret = wait_event_interruptible(
+		fd->uctxt->wait,
+		!test_bit(HFI1_CTXT_BASE_UNINIT, &fd->uctxt->event_flags));
+
+	if (test_bit(HFI1_CTXT_BASE_FAILED, &fd->uctxt->event_flags))
+		ret = -ENOMEM;
+
+	/* Finish the sub-context init */
+	if (!ret) {
+		fd->rec_cpu_num = hfi1_get_proc_affinity(fd->uctxt->numa_id);
+		ret = init_user_ctxt(fd, fd->uctxt);
+	}
+
+	if (ret) {
+		hfi1_rcd_put(fd->uctxt);
+		fd->uctxt = NULL;
+		spin_lock_irqsave(&fd->dd->uctxt_lock, flags);
+		__clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts);
+		spin_unlock_irqrestore(&fd->dd->uctxt_lock, flags);
+	}
+
+	return ret;
+}
+
 static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo)
 {
 	int ret;
 	unsigned int swmajor, swminor;
+	struct hfi1_ctxtdata *uctxt = NULL;
 
 	swmajor = uinfo->userversion >> 16;
 	if (swmajor != HFI1_USER_SWMAJOR)
 		return -ENODEV;
 
+	if (uinfo->subctxt_cnt > HFI1_MAX_SHARED_CTXTS)
+		return -EINVAL;
+
 	swminor = uinfo->userversion & 0xffff;
 
+	/*
+	 * Acquire the mutex to protect against multiple creations of what
+	 * could be a shared base context.
+	 */
 	mutex_lock(&hfi1_mutex);
 	/*
-	 * Get a sub context if necessary.
+	 * Get a sub context if available  (fd->uctxt will be set).
 	 * ret < 0 error, 0 no context, 1 sub-context found
 	 */
-	ret = 0;
-	if (uinfo->subctxt_cnt) {
-		ret = find_sub_ctxt(fd, uinfo);
-		if (ret > 0)
-			fd->rec_cpu_num =
-				hfi1_get_proc_affinity(fd->uctxt->numa_id);
-	}
+	ret = find_sub_ctxt(fd, uinfo);
 
 	/*
-	 * Allocate a base context if context sharing is not required or we
-	 * couldn't find a sub context.
+	 * Allocate a base context if context sharing is not required or a
+	 * sub context wasn't found.
 	 */
 	if (!ret)
-		ret = allocate_ctxt(fd, fd->dd, uinfo);
+		ret = allocate_ctxt(fd, fd->dd, uinfo, &uctxt);
 
 	mutex_unlock(&hfi1_mutex);
 
-	/* Depending on the context type, do the appropriate init */
-	if (ret > 0) {
-		/*
-		 * sub-context info can only be set up after the base
-		 * context has been completed.
-		 */
-		ret = wait_event_interruptible(fd->uctxt->wait, !test_bit(
-					       HFI1_CTXT_BASE_UNINIT,
-					       &fd->uctxt->event_flags));
-		if (test_bit(HFI1_CTXT_BASE_FAILED, &fd->uctxt->event_flags)) {
-			clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts);
-			return -ENOMEM;
-		}
-		/* The only thing a sub context needs is the user_xxx stuff */
-		if (!ret)
-			ret = init_user_ctxt(fd);
-
-		if (ret)
-			clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts);
-	} else if (!ret) {
-		ret = setup_base_ctxt(fd);
-		if (fd->uctxt->subctxt_cnt) {
-			/* If there is an error, set the failed bit. */
-			if (ret)
-				set_bit(HFI1_CTXT_BASE_FAILED,
-					&fd->uctxt->event_flags);
+	/* Depending on the context type, finish the appropriate init */
+	switch (ret) {
+	case 0:
+		ret = setup_base_ctxt(fd, uctxt);
+		if (uctxt->subctxt_cnt) {
 			/*
-			 * Base context is done, notify anybody using a
-			 * sub-context that is waiting for this completion
+			 * Base context is done (successfully or not), notify
+			 * anybody using a sub-context that is waiting for
+			 * this completion.
 			 */
-			clear_bit(HFI1_CTXT_BASE_UNINIT,
-				  &fd->uctxt->event_flags);
-			wake_up(&fd->uctxt->wait);
+			clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
+			wake_up(&uctxt->wait);
 		}
+		break;
+	case 1:
+		ret = complete_subctxt(fd);
+		break;
+	default:
+		break;
 	}
 
 	return ret;
 }
 
-/*
- * The hfi1_mutex must be held when this function is called.  It is
- * necessary to ensure serialized access to the bitmask in_use_ctxts.
+/**
+ * match_ctxt
+ * @fd: valid filedata pointer
+ * @uinfo: user info to compare base context with
+ * @uctxt: context to compare uinfo to.
+ *
+ * Compare the given context with the given information to see if it
+ * can be used for a sub context.
  */
-static int find_sub_ctxt(struct hfi1_filedata *fd,
-			 const struct hfi1_user_info *uinfo)
+static int match_ctxt(struct hfi1_filedata *fd,
+		      const struct hfi1_user_info *uinfo,
+		      struct hfi1_ctxtdata *uctxt)
 {
-	int i;
 	struct hfi1_devdata *dd = fd->dd;
+	unsigned long flags;
 	u16 subctxt;
 
-	for (i = dd->first_dyn_alloc_ctxt; i < dd->num_rcv_contexts; i++) {
-		struct hfi1_ctxtdata *uctxt = dd->rcd[i];
+	/* Skip dynamically allocated kernel contexts */
+	if (uctxt->sc && (uctxt->sc->type == SC_KERNEL))
+		return 0;
 
-		/* Skip ctxts which are not yet open */
-		if (!uctxt ||
-		    bitmap_empty(uctxt->in_use_ctxts,
-				 HFI1_MAX_SHARED_CTXTS))
-			continue;
+	/* Skip ctxt if it doesn't match the requested one */
+	if (memcmp(uctxt->uuid, uinfo->uuid, sizeof(uctxt->uuid)) ||
+	    uctxt->jkey != generate_jkey(current_uid()) ||
+	    uctxt->subctxt_id != uinfo->subctxt_id ||
+	    uctxt->subctxt_cnt != uinfo->subctxt_cnt)
+		return 0;
 
-		/* Skip dynamically allocted kernel contexts */
-		if (uctxt->sc && (uctxt->sc->type == SC_KERNEL))
-			continue;
+	/* Verify the sharing process matches the base */
+	if (uctxt->userversion != uinfo->userversion)
+		return -EINVAL;
 
-		/* Skip ctxt if it doesn't match the requested one */
-		if (memcmp(uctxt->uuid, uinfo->uuid,
-			   sizeof(uctxt->uuid)) ||
-		    uctxt->jkey != generate_jkey(current_uid()) ||
-		    uctxt->subctxt_id != uinfo->subctxt_id ||
-		    uctxt->subctxt_cnt != uinfo->subctxt_cnt)
-			continue;
+	/* Find an unused sub context */
+	spin_lock_irqsave(&dd->uctxt_lock, flags);
+	if (bitmap_empty(uctxt->in_use_ctxts, HFI1_MAX_SHARED_CTXTS)) {
+		/* context is being closed, do not use */
+		spin_unlock_irqrestore(&dd->uctxt_lock, flags);
+		return 0;
+	}
 
-		/* Verify the sharing process matches the master */
-		if (uctxt->userversion != uinfo->userversion)
-			return -EINVAL;
+	subctxt = find_first_zero_bit(uctxt->in_use_ctxts,
+				      HFI1_MAX_SHARED_CTXTS);
+	if (subctxt >= uctxt->subctxt_cnt) {
+		spin_unlock_irqrestore(&dd->uctxt_lock, flags);
+		return -EBUSY;
+	}
 
-		/* Find an unused context */
-		subctxt = find_first_zero_bit(uctxt->in_use_ctxts,
-					      HFI1_MAX_SHARED_CTXTS);
-		if (subctxt >= uctxt->subctxt_cnt)
-			return -EBUSY;
+	fd->subctxt = subctxt;
+	__set_bit(fd->subctxt, uctxt->in_use_ctxts);
+	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
 
-		fd->uctxt = uctxt;
-		fd->subctxt = subctxt;
-		__set_bit(fd->subctxt, uctxt->in_use_ctxts);
+	fd->uctxt = uctxt;
+	hfi1_rcd_get(uctxt);
+
+	return 1;
+}
 
-		return 1;
+/**
+ * find_sub_ctxt
+ * @fd: valid filedata pointer
+ * @uinfo: matching info to use to find a possible context to share.
+ *
+ * The hfi1_mutex must be held when this function is called.  It is
+ * necessary to ensure serialized creation of shared contexts.
+ *
+ * Return:
+ *    0      No sub-context found
+ *    1      Subcontext found and allocated
+ *    errno  EINVAL (incorrect parameters)
+ *           EBUSY (all sub contexts in use)
+ */
+static int find_sub_ctxt(struct hfi1_filedata *fd,
+			 const struct hfi1_user_info *uinfo)
+{
+	struct hfi1_ctxtdata *uctxt;
+	struct hfi1_devdata *dd = fd->dd;
+	u16 i;
+	int ret;
+
+	if (!uinfo->subctxt_cnt)
+		return 0;
+
+	for (i = dd->first_dyn_alloc_ctxt; i < dd->num_rcv_contexts; i++) {
+		uctxt = hfi1_rcd_get_by_index(dd, i);
+		if (uctxt) {
+			ret = match_ctxt(fd, uinfo, uctxt);
+			hfi1_rcd_put(uctxt);
+			/* value of != 0 will return */
+			if (ret)
+				return ret;
+		}
 	}
 
 	return 0;
 }
 
 static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd,
-			 struct hfi1_user_info *uinfo)
+			 struct hfi1_user_info *uinfo,
+			 struct hfi1_ctxtdata **rcd)
 {
 	struct hfi1_ctxtdata *uctxt;
-	unsigned int ctxt;
 	int ret, numa;
 
 	if (dd->flags & HFI1_FROZEN) {
@@ -987,22 +1064,9 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd,
 		return -EIO;
 	}
 
-	/*
-	 * This check is sort of redundant to the next EBUSY error. It would
-	 * also indicate an inconsistancy in the driver if this value was
-	 * zero, but there were still contexts available.
-	 */
 	if (!dd->freectxts)
 		return -EBUSY;
 
-	for (ctxt = dd->first_dyn_alloc_ctxt;
-	     ctxt < dd->num_rcv_contexts; ctxt++)
-		if (!dd->rcd[ctxt])
-			break;
-
-	if (ctxt == dd->num_rcv_contexts)
-		return -EBUSY;
-
 	/*
 	 * If we don't have a NUMA node requested, preference is towards
 	 * device NUMA node.
@@ -1012,11 +1076,10 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd,
 		numa = cpu_to_node(fd->rec_cpu_num);
 	else
 		numa = numa_node_id();
-	uctxt = hfi1_create_ctxtdata(dd->pport, ctxt, numa);
-	if (!uctxt) {
-		dd_dev_err(dd,
-			   "Unable to allocate ctxtdata memory, failing open\n");
-		return -ENOMEM;
+	ret = hfi1_create_ctxtdata(dd->pport, numa, &uctxt);
+	if (ret < 0) {
+		dd_dev_err(dd, "user ctxtdata allocation failed\n");
+		return ret;
 	}
 	hfi1_cdbg(PROC, "[%u:%u] pid %u assigned to CPU %d (NUMA %u)",
 		  uctxt->ctxt, fd->subctxt, current->pid, fd->rec_cpu_num,
@@ -1025,8 +1088,7 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd,
 	/*
 	 * Allocate and enable a PIO send context.
 	 */
-	uctxt->sc = sc_alloc(dd, SC_USER, uctxt->rcvhdrqentsize,
-			     uctxt->dd->node);
+	uctxt->sc = sc_alloc(dd, SC_USER, uctxt->rcvhdrqentsize, dd->node);
 	if (!uctxt->sc) {
 		ret = -ENOMEM;
 		goto ctxdata_free;
@@ -1038,28 +1100,19 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd,
 		goto ctxdata_free;
 
 	/*
-	 * Setup sub context resources if the user-level has requested
+	 * Setup sub context information if the user-level has requested
 	 * sub contexts.
 	 * This has to be done here so the rest of the sub-contexts find the
-	 * proper master.
+	 * proper base context.
 	 */
-	if (uinfo->subctxt_cnt) {
-		ret = init_subctxts(uctxt, uinfo);
-		/*
-		 * On error, we don't need to disable and de-allocate the
-		 * send context because it will be done during file close
-		 */
-		if (ret)
-			goto ctxdata_free;
-	}
+	if (uinfo->subctxt_cnt)
+		init_subctxts(uctxt, uinfo);
 	uctxt->userversion = uinfo->userversion;
 	uctxt->flags = hfi1_cap_mask; /* save current flag state */
 	init_waitqueue_head(&uctxt->wait);
 	strlcpy(uctxt->comm, current->comm, sizeof(uctxt->comm));
 	memcpy(uctxt->uuid, uinfo->uuid, sizeof(uctxt->uuid));
 	uctxt->jkey = generate_jkey(current_uid());
-	INIT_LIST_HEAD(&uctxt->sdma_queues);
-	spin_lock_init(&uctxt->sdma_qlock);
 	hfi1_stats.sps_ctxts++;
 	/*
 	 * Disable ASPM when there are open user/PSM contexts to avoid
@@ -1067,31 +1120,33 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd,
 	 */
 	if (dd->freectxts-- == dd->num_user_contexts)
 		aspm_disable_all(dd);
-	fd->uctxt = uctxt;
+
+	*rcd = uctxt;
 
 	return 0;
 
 ctxdata_free:
-	dd->rcd[ctxt] = NULL;
-	hfi1_free_ctxtdata(dd, uctxt);
+	hfi1_free_ctxt(uctxt);
 	return ret;
 }
 
-static int init_subctxts(struct hfi1_ctxtdata *uctxt,
-			 const struct hfi1_user_info *uinfo)
+static void deallocate_ctxt(struct hfi1_ctxtdata *uctxt)
 {
-	u16 num_subctxts;
+	mutex_lock(&hfi1_mutex);
+	hfi1_stats.sps_ctxts--;
+	if (++uctxt->dd->freectxts == uctxt->dd->num_user_contexts)
+		aspm_enable_all(uctxt->dd);
+	mutex_unlock(&hfi1_mutex);
 
-	num_subctxts = uinfo->subctxt_cnt;
-	if (num_subctxts > HFI1_MAX_SHARED_CTXTS)
-		return -EINVAL;
+	hfi1_free_ctxt(uctxt);
+}
 
+static void init_subctxts(struct hfi1_ctxtdata *uctxt,
+			  const struct hfi1_user_info *uinfo)
+{
 	uctxt->subctxt_cnt = uinfo->subctxt_cnt;
 	uctxt->subctxt_id = uinfo->subctxt_id;
-	uctxt->redirect_seq_cnt = 1;
 	set_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
-
-	return 0;
 }
 
 static int setup_subctxt(struct hfi1_ctxtdata *uctxt)
@@ -1153,7 +1208,7 @@ static void user_init(struct hfi1_ctxtdata *uctxt)
 		clear_rcvhdrtail(uctxt);
 
 	/* Setup J_KEY before enabling the context */
-	hfi1_set_ctxt_jkey(uctxt->dd, uctxt->ctxt, uctxt->jkey);
+	hfi1_set_ctxt_jkey(uctxt->dd, uctxt, uctxt->jkey);
 
 	rcvctrl_ops = HFI1_RCVCTRL_CTXT_ENB;
 	if (HFI1_CAP_UGET_MASK(uctxt->flags, HDRSUPP))
@@ -1179,7 +1234,7 @@ static void user_init(struct hfi1_ctxtdata *uctxt)
 		rcvctrl_ops |= HFI1_RCVCTRL_TAILUPD_ENB;
 	else
 		rcvctrl_ops |= HFI1_RCVCTRL_TAILUPD_DIS;
-	hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt->ctxt);
+	hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt);
 }
 
 static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase,
@@ -1223,23 +1278,25 @@ static int get_ctxt_info(struct hfi1_filedata *fd, void __user *ubase,
 	return ret;
 }
 
-static int init_user_ctxt(struct hfi1_filedata *fd)
+static int init_user_ctxt(struct hfi1_filedata *fd,
+			  struct hfi1_ctxtdata *uctxt)
 {
-	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	int ret;
 
 	ret = hfi1_user_sdma_alloc_queues(uctxt, fd);
 	if (ret)
 		return ret;
 
-	ret = hfi1_user_exp_rcv_init(fd);
+	ret = hfi1_user_exp_rcv_init(fd, uctxt);
+	if (ret)
+		hfi1_user_sdma_free_queues(fd, uctxt);
 
 	return ret;
 }
 
-static int setup_base_ctxt(struct hfi1_filedata *fd)
+static int setup_base_ctxt(struct hfi1_filedata *fd,
+			   struct hfi1_ctxtdata *uctxt)
 {
-	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct hfi1_devdata *dd = uctxt->dd;
 	int ret = 0;
 
@@ -1260,20 +1317,27 @@ static int setup_base_ctxt(struct hfi1_filedata *fd)
 	if (ret)
 		goto setup_failed;
 
-	ret = hfi1_user_exp_rcv_grp_init(fd);
+	ret = hfi1_alloc_ctxt_rcv_groups(uctxt);
 	if (ret)
 		goto setup_failed;
 
-	ret = init_user_ctxt(fd);
+	ret = init_user_ctxt(fd, uctxt);
 	if (ret)
 		goto setup_failed;
 
 	user_init(uctxt);
 
+	/* Now that the context is set up, the fd can get a reference. */
+	fd->uctxt = uctxt;
+	hfi1_rcd_get(uctxt);
+
 	return 0;
 
 setup_failed:
-	hfi1_free_ctxtdata(dd, uctxt);
+	/* Set the failed bit so sub-context init can do the right thing */
+	set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
+	deallocate_ctxt(uctxt);
+
 	return ret;
 }
 
@@ -1390,7 +1454,7 @@ static unsigned int poll_next(struct file *fp,
 	spin_lock_irq(&dd->uctxt_lock);
 	if (hdrqempty(uctxt)) {
 		set_bit(HFI1_CTXT_WAITING_RCV, &uctxt->event_flags);
-		hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_ENB, uctxt->ctxt);
+		hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_ENB, uctxt);
 		pollflag = 0;
 	} else {
 		pollflag = POLLIN | POLLRDNORM;
@@ -1409,19 +1473,14 @@ int hfi1_set_uevent_bits(struct hfi1_pportdata *ppd, const int evtbit)
 {
 	struct hfi1_ctxtdata *uctxt;
 	struct hfi1_devdata *dd = ppd->dd;
-	unsigned ctxt;
-	int ret = 0;
-	unsigned long flags;
+	u16 ctxt;
 
-	if (!dd->events) {
-		ret = -EINVAL;
-		goto done;
-	}
+	if (!dd->events)
+		return -EINVAL;
 
-	spin_lock_irqsave(&dd->uctxt_lock, flags);
 	for (ctxt = dd->first_dyn_alloc_ctxt; ctxt < dd->num_rcv_contexts;
 	     ctxt++) {
-		uctxt = dd->rcd[ctxt];
+		uctxt = hfi1_rcd_get_by_index(dd, ctxt);
 		if (uctxt) {
 			unsigned long *evs = dd->events +
 				(uctxt->ctxt - dd->first_dyn_alloc_ctxt) *
@@ -1434,11 +1493,11 @@ int hfi1_set_uevent_bits(struct hfi1_pportdata *ppd, const int evtbit)
 			set_bit(evtbit, evs);
 			for (i = 1; i < uctxt->subctxt_cnt; i++)
 				set_bit(evtbit, evs + i);
+			hfi1_rcd_put(uctxt);
 		}
 	}
-	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
-done:
-	return ret;
+
+	return 0;
 }
 
 /**
@@ -1475,7 +1534,7 @@ static int manage_rcvq(struct hfi1_ctxtdata *uctxt, u16 subctxt,
 	} else {
 		rcvctrl_op = HFI1_RCVCTRL_CTXT_DIS;
 	}
-	hfi1_rcvctrl(dd, rcvctrl_op, uctxt->ctxt);
+	hfi1_rcvctrl(dd, rcvctrl_op, uctxt);
 	/* always; new head should be equal to new tail; see above */
 bail:
 	return 0;
@@ -1525,7 +1584,7 @@ static int set_ctxt_pkey(struct hfi1_ctxtdata *uctxt, u16 subctxt, u16 pkey)
 		}
 
 	if (intable)
-		ret = hfi1_set_ctxt_pkey(dd, uctxt->ctxt, pkey);
+		ret = hfi1_set_ctxt_pkey(dd, uctxt, pkey);
 done:
 	return ret;
 }
diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c
index 4042c11b2742..5aea8f47e670 100644
--- a/drivers/infiniband/hw/hfi1/firmware.c
+++ b/drivers/infiniband/hw/hfi1/firmware.c
@@ -64,30 +64,22 @@
 #define DEFAULT_FW_FABRIC_NAME "hfi1_fabric.fw"
 #define DEFAULT_FW_SBUS_NAME "hfi1_sbus.fw"
 #define DEFAULT_FW_PCIE_NAME "hfi1_pcie.fw"
-#define DEFAULT_PLATFORM_CONFIG_NAME "hfi1_platform.dat"
 #define ALT_FW_8051_NAME_ASIC "hfi1_dc8051_d.fw"
 #define ALT_FW_FABRIC_NAME "hfi1_fabric_d.fw"
 #define ALT_FW_SBUS_NAME "hfi1_sbus_d.fw"
 #define ALT_FW_PCIE_NAME "hfi1_pcie_d.fw"
+#define HOST_INTERFACE_VERSION 1
 
 static uint fw_8051_load = 1;
 static uint fw_fabric_serdes_load = 1;
 static uint fw_pcie_serdes_load = 1;
 static uint fw_sbus_load = 1;
 
-/*
- * Access required in platform.c
- * Maintains state of whether the platform config was fetched via the
- * fallback option
- */
-uint platform_config_load;
-
 /* Firmware file names get set in hfi1_firmware_init() based on the above */
 static char *fw_8051_name;
 static char *fw_fabric_serdes_name;
 static char *fw_sbus_name;
 static char *fw_pcie_serdes_name;
-static char *platform_config_name;
 
 #define SBUS_MAX_POLL_COUNT 100
 #define SBUS_COUNTER(reg, name) \
@@ -177,7 +169,6 @@ static struct firmware_details fw_8051;
 static struct firmware_details fw_fabric;
 static struct firmware_details fw_pcie;
 static struct firmware_details fw_sbus;
-static const struct firmware *platform_config;
 
 /* flags for turn_off_spicos() */
 #define SPICO_SBUS   0x1
@@ -615,6 +606,14 @@ retry:
 		fw_fabric_serdes_name = ALT_FW_FABRIC_NAME;
 		fw_sbus_name = ALT_FW_SBUS_NAME;
 		fw_pcie_serdes_name = ALT_FW_PCIE_NAME;
+
+		/*
+		 * Add a delay before obtaining and loading debug firmware.
+		 * Authorization will fail if the delay between firmware
+		 * authorization events is shorter than 50us. Add 100us to
+		 * make a delay time safe.
+		 */
+		usleep_range(100, 120);
 	}
 
 	if (fw_sbus_load) {
@@ -675,7 +674,6 @@ done:
 static int obtain_firmware(struct hfi1_devdata *dd)
 {
 	unsigned long timeout;
-	int err = 0;
 
 	mutex_lock(&fw_mutex);
 
@@ -699,38 +697,11 @@ static int obtain_firmware(struct hfi1_devdata *dd)
 	}
 	/* not in FW_TRY state */
 
-	if (fw_state == FW_FINAL) {
-		if (platform_config) {
-			dd->platform_config.data = platform_config->data;
-			dd->platform_config.size = platform_config->size;
-		}
-		goto done;	/* already acquired */
-	} else if (fw_state == FW_ERR) {
-		goto done;	/* already tried and failed */
-	}
-	/* fw_state is FW_EMPTY */
-
 	/* set fw_state to FW_TRY, FW_FINAL, or FW_ERR, and fw_err */
-	__obtain_firmware(dd);
-
-	if (platform_config_load) {
-		platform_config = NULL;
-		err = request_firmware(&platform_config, platform_config_name,
-				       &dd->pcidev->dev);
-		if (err) {
-			platform_config = NULL;
-			dd_dev_err(dd,
-				   "%s: No default platform config file found\n",
-				   __func__);
-			goto done;
-		}
-		dd->platform_config.data = platform_config->data;
-		dd->platform_config.size = platform_config->size;
-	}
+	if (fw_state == FW_EMPTY)
+		__obtain_firmware(dd);
 
-done:
 	mutex_unlock(&fw_mutex);
-
 	return fw_err;
 }
 
@@ -752,9 +723,6 @@ void dispose_firmware(void)
 	dispose_one_firmware(&fw_pcie);
 	dispose_one_firmware(&fw_sbus);
 
-	release_firmware(platform_config);
-	platform_config = NULL;
-
 	/* retain the error state, otherwise revert to empty */
 	if (fw_state != FW_ERR)
 		fw_state = FW_EMPTY;
@@ -1079,6 +1047,13 @@ static int load_8051_firmware(struct hfi1_devdata *dd,
 	dd_dev_info(dd, "8051 firmware version %d.%d.%d\n",
 		    (int)ver_major, (int)ver_minor, (int)ver_patch);
 	dd->dc8051_ver = dc8051_ver(ver_major, ver_minor, ver_patch);
+	ret = write_host_interface_version(dd, HOST_INTERFACE_VERSION);
+	if (ret != HCMD_SUCCESS) {
+		dd_dev_err(dd,
+			   "Failed to set host interface version, return 0x%x\n",
+			   ret);
+		return -EIO;
+	}
 
 	return 0;
 }
@@ -1709,10 +1684,8 @@ int hfi1_firmware_init(struct hfi1_devdata *dd)
 	}
 
 	/* no 8051 or QSFP on simulator */
-	if (dd->icode == ICODE_FUNCTIONAL_SIMULATOR) {
+	if (dd->icode == ICODE_FUNCTIONAL_SIMULATOR)
 		fw_8051_load = 0;
-		platform_config_load = 0;
-	}
 
 	if (!fw_8051_name) {
 		if (dd->icode == ICODE_RTL_SILICON)
@@ -1726,8 +1699,6 @@ int hfi1_firmware_init(struct hfi1_devdata *dd)
 		fw_sbus_name = DEFAULT_FW_SBUS_NAME;
 	if (!fw_pcie_serdes_name)
 		fw_pcie_serdes_name = DEFAULT_FW_PCIE_NAME;
-	if (!platform_config_name)
-		platform_config_name = DEFAULT_PLATFORM_CONFIG_NAME;
 
 	return obtain_firmware(dd);
 }
@@ -1773,6 +1744,7 @@ static int check_meta_version(struct hfi1_devdata *dd, u32 *system_table)
 int parse_platform_config(struct hfi1_devdata *dd)
 {
 	struct platform_config_cache *pcfgcache = &dd->pcfg_cache;
+	struct hfi1_pportdata *ppd = dd->pport;
 	u32 *ptr = NULL;
 	u32 header1 = 0, header2 = 0, magic_num = 0, crc = 0, file_length = 0;
 	u32 record_idx = 0, table_type = 0, table_length_dwords = 0;
@@ -1784,7 +1756,7 @@ int parse_platform_config(struct hfi1_devdata *dd)
 	 * scratch register bitmap, thus there is no platform config to parse.
 	 * Skip parsing in these situations.
 	 */
-	if (is_integrated(dd) && !platform_config_load)
+	if (ppd->config_from_scratch)
 		return 0;
 
 	if (!dd->platform_config.data) {
@@ -2073,13 +2045,14 @@ int get_platform_config_field(struct hfi1_devdata *dd,
 	int ret = 0, wlen = 0, seek = 0;
 	u32 field_len_bits = 0, field_start_bits = 0, *src_ptr = NULL;
 	struct platform_config_cache *pcfgcache = &dd->pcfg_cache;
+	struct hfi1_pportdata *ppd = dd->pport;
 
 	if (data)
 		memset(data, 0, len);
 	else
 		return -EINVAL;
 
-	if (is_integrated(dd) && !platform_config_load) {
+	if (ppd->config_from_scratch) {
 		/*
 		 * Use saved configuration from ppd for integrated platforms
 		 */
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 414a04a481c2..3ac9c307a285 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -66,9 +66,11 @@
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 #include <rdma/ib_hdrs.h>
+#include <rdma/opa_addr.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
 #include <rdma/rdma_vt.h>
+#include <rdma/opa_addr.h>
 
 #include "chip_registers.h"
 #include "common.h"
@@ -213,13 +215,11 @@ struct hfi1_ctxtdata {
 
 	/* dynamic receive available interrupt timeout */
 	u32 rcvavail_timeout;
-	/*
-	 * number of opens (including slave sub-contexts) on this instance
-	 * (ignoring forks, dup, etc. for now)
-	 */
-	int cnt;
+	/* Reference count the base context usage */
+	struct kref kref;
+
 	/* Device context index */
-	unsigned ctxt;
+	u16 ctxt;
 	/*
 	 * non-zero if ctxt can be shared, and defines the maximum number of
 	 * sub-contexts for this device context.
@@ -245,24 +245,10 @@ struct hfi1_ctxtdata {
 
 	/* lock protecting all Expected TID data */
 	struct mutex exp_lock;
-	/* number of pio bufs for this ctxt (all procs, if shared) */
-	u32 piocnt;
-	/* first pio buffer for this ctxt */
-	u32 pio_base;
-	/* chip offset of PIO buffers for this ctxt */
-	u32 piobufs;
 	/* per-context configuration flags */
 	unsigned long flags;
 	/* per-context event flags for fileops/intr communication */
 	unsigned long event_flags;
-	/* WAIT_RCV that timed out, no interrupt */
-	u32 rcvwait_to;
-	/* WAIT_PIO that timed out, no interrupt */
-	u32 piowait_to;
-	/* WAIT_RCV already happened, no wait */
-	u32 rcvnowait;
-	/* WAIT_PIO already happened, no wait */
-	u32 pionowait;
 	/* total number of polled urgent packets */
 	u32 urgent;
 	/* saved total number of polled urgent packets for poll edge trigger */
@@ -289,10 +275,8 @@ struct hfi1_ctxtdata {
 	u16 poll_type;
 	/* receive packet sequence counter */
 	u8 seq_cnt;
-	u8 redirect_seq_cnt;
 	/* ctxt rcvhdrq head offset */
 	u32 head;
-	u32 pkt_count;
 	/* QPs waiting for context processing */
 	struct list_head qp_wait_list;
 	/* interrupt handling */
@@ -301,15 +285,6 @@ struct hfi1_ctxtdata {
 	unsigned numa_id; /* numa node of this context */
 	/* verbs stats per CTX */
 	struct hfi1_opcode_stats_perctx *opstats;
-	/*
-	 * This is the kernel thread that will keep making
-	 * progress on the user sdma requests behind the scenes.
-	 * There is one per context (shared contexts use the master's).
-	 */
-	struct task_struct *progress;
-	struct list_head sdma_queues;
-	/* protect sdma queues */
-	spinlock_t sdma_qlock;
 
 	/* Is ASPM interrupt supported for this context */
 	bool aspm_intr_supported;
@@ -352,23 +327,150 @@ struct hfi1_ctxtdata {
 struct hfi1_packet {
 	void *ebuf;
 	void *hdr;
+	void *payload;
 	struct hfi1_ctxtdata *rcd;
 	__le32 *rhf_addr;
 	struct rvt_qp *qp;
 	struct ib_other_headers *ohdr;
+	struct ib_grh *grh;
 	u64 rhf;
 	u32 maxcnt;
 	u32 rhqoff;
+	u32 dlid;
+	u32 slid;
 	u16 tlen;
 	s16 etail;
 	u8 hlen;
 	u8 numpkt;
 	u8 rsize;
 	u8 updegr;
-	u8 rcv_flags;
 	u8 etype;
+	u8 extra_byte;
+	u8 pad;
+	u8 sc;
+	u8 sl;
+	u8 opcode;
+	bool becn;
+	bool fecn;
 };
 
+/* Packet types */
+#define HFI1_PKT_TYPE_9B  0
+#define HFI1_PKT_TYPE_16B 1
+
+/*
+ * OPA 16B Header
+ */
+#define OPA_16B_L4_MASK		0xFFull
+#define OPA_16B_SC_MASK		0x1F00000ull
+#define OPA_16B_SC_SHIFT	20
+#define OPA_16B_LID_MASK	0xFFFFFull
+#define OPA_16B_DLID_MASK	0xF000ull
+#define OPA_16B_DLID_SHIFT	20
+#define OPA_16B_DLID_HIGH_SHIFT	12
+#define OPA_16B_SLID_MASK	0xF00ull
+#define OPA_16B_SLID_SHIFT	20
+#define OPA_16B_SLID_HIGH_SHIFT	8
+#define OPA_16B_BECN_MASK       0x80000000ull
+#define OPA_16B_BECN_SHIFT      31
+#define OPA_16B_FECN_MASK       0x10000000ull
+#define OPA_16B_FECN_SHIFT      28
+#define OPA_16B_L2_MASK		0x60000000ull
+#define OPA_16B_L2_SHIFT	29
+#define OPA_16B_PKEY_MASK	0xFFFF0000ull
+#define OPA_16B_PKEY_SHIFT	16
+#define OPA_16B_LEN_MASK	0x7FF00000ull
+#define OPA_16B_LEN_SHIFT	20
+#define OPA_16B_RC_MASK		0xE000000ull
+#define OPA_16B_RC_SHIFT	25
+#define OPA_16B_AGE_MASK	0xFF0000ull
+#define OPA_16B_AGE_SHIFT	16
+#define OPA_16B_ENTROPY_MASK	0xFFFFull
+
+/*
+ * OPA 16B L2/L4 Encodings
+ */
+#define OPA_16B_L2_TYPE		0x02
+#define OPA_16B_L4_IB_LOCAL	0x09
+#define OPA_16B_L4_IB_GLOBAL	0x0A
+#define OPA_16B_L4_ETHR		OPA_VNIC_L4_ETHR
+
+static inline u8 hfi1_16B_get_l4(struct hfi1_16b_header *hdr)
+{
+	return (u8)(hdr->lrh[2] & OPA_16B_L4_MASK);
+}
+
+static inline u8 hfi1_16B_get_sc(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[1] & OPA_16B_SC_MASK) >> OPA_16B_SC_SHIFT);
+}
+
+static inline u32 hfi1_16B_get_dlid(struct hfi1_16b_header *hdr)
+{
+	return (u32)((hdr->lrh[1] & OPA_16B_LID_MASK) |
+		     (((hdr->lrh[2] & OPA_16B_DLID_MASK) >>
+		     OPA_16B_DLID_HIGH_SHIFT) << OPA_16B_DLID_SHIFT));
+}
+
+static inline u32 hfi1_16B_get_slid(struct hfi1_16b_header *hdr)
+{
+	return (u32)((hdr->lrh[0] & OPA_16B_LID_MASK) |
+		     (((hdr->lrh[2] & OPA_16B_SLID_MASK) >>
+		     OPA_16B_SLID_HIGH_SHIFT) << OPA_16B_SLID_SHIFT));
+}
+
+static inline u8 hfi1_16B_get_becn(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[0] & OPA_16B_BECN_MASK) >> OPA_16B_BECN_SHIFT);
+}
+
+static inline u8 hfi1_16B_get_fecn(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[1] & OPA_16B_FECN_MASK) >> OPA_16B_FECN_SHIFT);
+}
+
+static inline u8 hfi1_16B_get_l2(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[1] & OPA_16B_L2_MASK) >> OPA_16B_L2_SHIFT);
+}
+
+static inline u16 hfi1_16B_get_pkey(struct hfi1_16b_header *hdr)
+{
+	return (u16)((hdr->lrh[2] & OPA_16B_PKEY_MASK) >> OPA_16B_PKEY_SHIFT);
+}
+
+static inline u8 hfi1_16B_get_rc(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[1] & OPA_16B_RC_MASK) >> OPA_16B_RC_SHIFT);
+}
+
+static inline u8 hfi1_16B_get_age(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[3] & OPA_16B_AGE_MASK) >> OPA_16B_AGE_SHIFT);
+}
+
+static inline u16 hfi1_16B_get_len(struct hfi1_16b_header *hdr)
+{
+	return (u16)((hdr->lrh[0] & OPA_16B_LEN_MASK) >> OPA_16B_LEN_SHIFT);
+}
+
+static inline u16 hfi1_16B_get_entropy(struct hfi1_16b_header *hdr)
+{
+	return (u16)(hdr->lrh[3] & OPA_16B_ENTROPY_MASK);
+}
+
+#define OPA_16B_MAKE_QW(low_dw, high_dw) (((u64)(high_dw) << 32) | (low_dw))
+
+/*
+ * BTH
+ */
+#define OPA_16B_BTH_PAD_MASK	7
+static inline u8 hfi1_16B_bth_get_pad(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_PAD_SHIFT) &
+		   OPA_16B_BTH_PAD_MASK);
+}
+
 struct rvt_sge_state;
 
 /*
@@ -512,7 +614,7 @@ static inline void incr_cntr32(u32 *cntr)
 #define MAX_NAME_SIZE 64
 struct hfi1_msix_entry {
 	enum irq_type type;
-	struct msix_entry msix;
+	int irq;
 	void *arg;
 	char name[MAX_NAME_SIZE];
 	cpumask_t mask;
@@ -575,6 +677,9 @@ struct hfi1_pportdata {
 	u8  default_atten;
 	u8  max_power_class;
 
+	/* did we read platform config from scratch registers? */
+	bool config_from_scratch;
+
 	/* GUIDs for this interface, in host order, guids[0] is a port guid */
 	u64 guids[HFI1_GUIDS_PER_PORT];
 
@@ -593,6 +698,7 @@ struct hfi1_pportdata {
 	/* SendDMA related entries */
 
 	struct workqueue_struct *hfi1_wq;
+	struct workqueue_struct *link_wq;
 
 	/* move out of interrupt context */
 	struct work_struct link_vc_work;
@@ -607,8 +713,6 @@ struct hfi1_pportdata {
 	struct mutex hls_lock;
 	u32 host_link_state;
 
-	u32 lstate;	/* logical link state */
-
 	/* these are the "32 bit" regs */
 
 	u32 ibmtu; /* The MTU programmed for this unit */
@@ -619,7 +723,7 @@ struct hfi1_pportdata {
 	u32 ibmaxlen;
 	u32 current_egress_rate; /* units [10^6 bits/sec] */
 	/* LID programmed for this instance */
-	u16 lid;
+	u32 lid;
 	/* list of pkeys programmed; 0 if not set */
 	u16 pkeys[MAX_PKEY_VALUES];
 	u16 link_width_supported;
@@ -654,12 +758,12 @@ struct hfi1_pportdata {
 	u8 link_enabled;	/* link enabled? */
 	u8 linkinit_reason;
 	u8 local_tx_rate;	/* rate given to 8051 firmware */
-	u8 last_pstate;		/* info only */
 	u8 qsfp_retry_count;
 
 	/* placeholders for IB MAD packet settings */
 	u8 overrun_threshold;
 	u8 phy_error_threshold;
+	unsigned int is_link_down_queued;
 
 	/* Used to override LED behavior for things like maintenance beaconing*/
 	/*
@@ -756,6 +860,10 @@ struct hfi1_pportdata {
 typedef int (*rhf_rcv_function_ptr)(struct hfi1_packet *packet);
 
 typedef void (*opcode_handler)(struct hfi1_packet *packet);
+typedef void (*hfi1_make_req)(struct rvt_qp *qp,
+			      struct hfi1_pkt_state *ps,
+			      struct rvt_swqe *wqe);
+
 
 /* return values for the RHF receive functions */
 #define RHF_RCV_CONTINUE  0	/* keep going */
@@ -860,12 +968,15 @@ struct hfi1_devdata {
 	struct device *diag_device;
 	struct device *ui_device;
 
-	/* mem-mapped pointer to base of chip regs */
-	u8 __iomem *kregbase;
-	/* end of mem-mapped chip space excluding sendbuf and user regs */
-	u8 __iomem *kregend;
-	/* physical address of chip for io_remap, etc. */
+	/* first mapping up to RcvArray */
+	u8 __iomem *kregbase1;
 	resource_size_t physaddr;
+
+	/* second uncached mapping from RcvArray to pio send buffers */
+	u8 __iomem *kregbase2;
+	/* for detecting offset above kregbase2 address */
+	u32 base2_start;
+
 	/* Per VL data. Enough for all VLs but not all elements are set/used. */
 	struct per_vl_data vld[PER_VL_SEND_CONTEXTS];
 	/* send context data */
@@ -953,8 +1064,7 @@ struct hfi1_devdata {
 	u64 __iomem *egrtidbase;
 	spinlock_t sendctrl_lock; /* protect changes to SendCtrl */
 	spinlock_t rcvctrl_lock; /* protect changes to RcvCtrl */
-	/* around rcd and (user ctxts) ctxt_cnt use (intr vs free) */
-	spinlock_t uctxt_lock; /* rcd and user context changes */
+	spinlock_t uctxt_lock; /* protect rcd changes */
 	struct mutex dc8051_lock; /* exclusive access to 8051 */
 	struct workqueue_struct *update_cntr_wq;
 	struct work_struct update_cntr_work;
@@ -1229,9 +1339,10 @@ static inline bool hfi1_vnic_is_rsm_full(struct hfi1_devdata *dd, int spare)
 #define dc8051_ver_patch(a) ((a) & 0x0000ff)
 
 /* f_put_tid types */
-#define PT_EXPECTED 0
-#define PT_EAGER    1
-#define PT_INVALID  2
+#define PT_EXPECTED       0
+#define PT_EAGER          1
+#define PT_INVALID_FLUSH  2
+#define PT_INVALID        3
 
 struct tid_rb_node;
 struct mmu_rb_node;
@@ -1276,13 +1387,16 @@ void handle_user_interrupt(struct hfi1_ctxtdata *rcd);
 
 int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd);
 int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd);
-int hfi1_create_ctxts(struct hfi1_devdata *dd);
-struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
-					   int numa);
+int hfi1_create_kctxts(struct hfi1_devdata *dd);
+int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
+			 struct hfi1_ctxtdata **rcd);
+void hfi1_free_ctxt(struct hfi1_ctxtdata *rcd);
 void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 			 struct hfi1_devdata *dd, u8 hw_pidx, u8 port);
 void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd);
-
+int hfi1_rcd_put(struct hfi1_ctxtdata *rcd);
+void hfi1_rcd_get(struct hfi1_ctxtdata *rcd);
+struct hfi1_ctxtdata *hfi1_rcd_get_by_index(struct hfi1_devdata *dd, u16 ctxt);
 int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread);
 int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread);
 int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *rcd, int thread);
@@ -1292,6 +1406,13 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd);
 void hfi1_reset_vnic_msix_info(struct hfi1_ctxtdata *rcd);
 
 extern const struct pci_device_id hfi1_pci_tbl[];
+void hfi1_make_ud_req_9B(struct rvt_qp *qp,
+			 struct hfi1_pkt_state *ps,
+			 struct rvt_swqe *wqe);
+
+void hfi1_make_ud_req_16B(struct rvt_qp *qp,
+			  struct hfi1_pkt_state *ps,
+			  struct rvt_swqe *wqe);
 
 /* receive packet handler dispositions */
 #define RCV_PKT_OK      0x0 /* keep going */
@@ -1306,21 +1427,6 @@ static inline __le32 *get_rhf_addr(struct hfi1_ctxtdata *rcd)
 
 int hfi1_reset_device(int);
 
-/* return the driver's idea of the logical OPA port state */
-static inline u32 driver_lstate(struct hfi1_pportdata *ppd)
-{
-	/*
-	 * The driver does some processing from the time the logical
-	 * link state is at INIT to the time the SM can be notified
-	 * as such. Return IB_PORT_DOWN until the software state
-	 * is ready.
-	 */
-	if (ppd->lstate == IB_PORT_INIT && !(ppd->host_link_state & HLS_UP))
-		return IB_PORT_DOWN;
-	else
-		return ppd->lstate;
-}
-
 void receive_interrupt_work(struct work_struct *work);
 
 /* extract service channel from header and rhf */
@@ -1413,13 +1519,25 @@ static inline u32 egress_cycles(u32 len, u32 rate)
 }
 
 void set_link_ipg(struct hfi1_pportdata *ppd);
-void process_becn(struct hfi1_pportdata *ppd, u8 sl,  u16 rlid, u32 lqpn,
+void process_becn(struct hfi1_pportdata *ppd, u8 sl, u32 rlid, u32 lqpn,
 		  u32 rqpn, u8 svc_type);
 void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 		u32 pkey, u32 slid, u32 dlid, u8 sc5,
 		const struct ib_grh *old_grh);
+void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
+		    u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+		    u8 sc5, const struct ib_grh *old_grh);
+typedef void (*hfi1_handle_cnp)(struct hfi1_ibport *ibp, struct rvt_qp *qp,
+				u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+				u8 sc5, const struct ib_grh *old_grh);
+
+/* We support only two types - 9B and 16B for now */
+static const hfi1_handle_cnp hfi1_handle_cnp_tbl[2] = {
+	[HFI1_PKT_TYPE_9B] = &return_cnp,
+	[HFI1_PKT_TYPE_16B] = &return_cnp_16B
+};
 #define PKEY_CHECK_INVALID -1
-int egress_pkey_check(struct hfi1_pportdata *ppd, __be16 *lrh, __be32 *bth,
+int egress_pkey_check(struct hfi1_pportdata *ppd, u32 slid, u16 pkey,
 		      u8 sc5, int8_t s_pkey_index);
 
 #define PACKET_EGRESS_TIMEOUT 350
@@ -1522,9 +1640,9 @@ static void ingress_pkey_table_fail(struct hfi1_pportdata *ppd, u16 pkey,
  * by HW and rcv_pkey_check function should be called instead.
  */
 static inline int ingress_pkey_check(struct hfi1_pportdata *ppd, u16 pkey,
-				     u8 sc5, u8 idx, u16 slid)
+				     u8 sc5, u8 idx, u32 slid, bool force)
 {
-	if (!(ppd->part_enforce & HFI1_PART_ENFORCE_IN))
+	if (!(force) && !(ppd->part_enforce & HFI1_PART_ENFORCE_IN))
 		return 0;
 
 	/* If SC15, pkey[0:14] must be 0x7fff */
@@ -1658,12 +1776,22 @@ static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
 	struct ib_other_headers *ohdr = pkt->ohdr;
-	u32 bth1;
 
-	bth1 = be32_to_cpu(ohdr->bth[1]);
-	if (unlikely(bth1 & (IB_BECN_SMASK | IB_FECN_SMASK))) {
+	u32 bth1;
+	bool becn = false;
+	bool fecn = false;
+
+	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
+		fecn = hfi1_16B_get_fecn(pkt->hdr);
+		becn = hfi1_16B_get_becn(pkt->hdr);
+	} else {
+		bth1 = be32_to_cpu(ohdr->bth[1]);
+		fecn = bth1 & IB_FECN_SMASK;
+		becn = bth1 & IB_BECN_SMASK;
+	}
+	if (unlikely(fecn || becn)) {
 		hfi1_process_ecn_slowpath(qp, pkt, do_cnp);
-		return !!(bth1 & IB_FECN_SMASK);
+		return fecn;
 	}
 	return false;
 }
@@ -1829,10 +1957,9 @@ void hfi1_pcie_cleanup(struct pci_dev *pdev);
 int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev);
 void hfi1_pcie_ddcleanup(struct hfi1_devdata *);
 int pcie_speeds(struct hfi1_devdata *dd);
-void request_msix(struct hfi1_devdata *dd, u32 *nent,
-		  struct hfi1_msix_entry *entry);
-void hfi1_enable_intx(struct pci_dev *pdev);
-void restore_pci_variables(struct hfi1_devdata *dd);
+int request_msix(struct hfi1_devdata *dd, u32 msireq);
+int restore_pci_variables(struct hfi1_devdata *dd);
+int save_pci_variables(struct hfi1_devdata *dd);
 int do_pcie_gen3_transition(struct hfi1_devdata *dd);
 int parse_platform_config(struct hfi1_devdata *dd);
 int get_platform_config_field(struct hfi1_devdata *dd,
@@ -1860,6 +1987,7 @@ int process_receive_error(struct hfi1_packet *packet);
 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 seqfile_dump_rcd(struct seq_file *s, struct hfi1_ctxtdata *rcd);
 
 /* global module parameter variables */
 extern unsigned int hfi1_max_mtu;
@@ -1991,9 +2119,15 @@ static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd)
 #define dd_dev_emerg(dd, fmt, ...) \
 	dev_emerg(&(dd)->pcidev->dev, "%s: " fmt, \
 		  get_unit_name((dd)->unit), ##__VA_ARGS__)
+
 #define dd_dev_err(dd, fmt, ...) \
 	dev_err(&(dd)->pcidev->dev, "%s: " fmt, \
 			get_unit_name((dd)->unit), ##__VA_ARGS__)
+
+#define dd_dev_err_ratelimited(dd, fmt, ...) \
+	dev_err_ratelimited(&(dd)->pcidev->dev, "%s: " fmt, \
+			get_unit_name((dd)->unit), ##__VA_ARGS__)
+
 #define dd_dev_warn(dd, fmt, ...) \
 	dev_warn(&(dd)->pcidev->dev, "%s: " fmt, \
 			get_unit_name((dd)->unit), ##__VA_ARGS__)
@@ -2087,52 +2221,220 @@ int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
 #define DD_DEV_ENTRY(dd)       __string(dev, dev_name(&(dd)->pcidev->dev))
 #define DD_DEV_ASSIGN(dd)      __assign_str(dev, dev_name(&(dd)->pcidev->dev))
 
-#define packettype_name(etype) { RHF_RCV_TYPE_##etype, #etype }
-#define show_packettype(etype)                  \
-__print_symbolic(etype,                         \
-	packettype_name(EXPECTED),              \
-	packettype_name(EAGER),                 \
-	packettype_name(IB),                    \
-	packettype_name(ERROR),                 \
-	packettype_name(BYPASS))
-
-#define ib_opcode_name(opcode) { IB_OPCODE_##opcode, #opcode  }
-#define show_ib_opcode(opcode)                             \
-__print_symbolic(opcode,                                   \
-	ib_opcode_name(RC_SEND_FIRST),                     \
-	ib_opcode_name(RC_SEND_MIDDLE),                    \
-	ib_opcode_name(RC_SEND_LAST),                      \
-	ib_opcode_name(RC_SEND_LAST_WITH_IMMEDIATE),       \
-	ib_opcode_name(RC_SEND_ONLY),                      \
-	ib_opcode_name(RC_SEND_ONLY_WITH_IMMEDIATE),       \
-	ib_opcode_name(RC_RDMA_WRITE_FIRST),               \
-	ib_opcode_name(RC_RDMA_WRITE_MIDDLE),              \
-	ib_opcode_name(RC_RDMA_WRITE_LAST),                \
-	ib_opcode_name(RC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \
-	ib_opcode_name(RC_RDMA_WRITE_ONLY),                \
-	ib_opcode_name(RC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \
-	ib_opcode_name(RC_RDMA_READ_REQUEST),              \
-	ib_opcode_name(RC_RDMA_READ_RESPONSE_FIRST),       \
-	ib_opcode_name(RC_RDMA_READ_RESPONSE_MIDDLE),      \
-	ib_opcode_name(RC_RDMA_READ_RESPONSE_LAST),        \
-	ib_opcode_name(RC_RDMA_READ_RESPONSE_ONLY),        \
-	ib_opcode_name(RC_ACKNOWLEDGE),                    \
-	ib_opcode_name(RC_ATOMIC_ACKNOWLEDGE),             \
-	ib_opcode_name(RC_COMPARE_SWAP),                   \
-	ib_opcode_name(RC_FETCH_ADD),                      \
-	ib_opcode_name(UC_SEND_FIRST),                     \
-	ib_opcode_name(UC_SEND_MIDDLE),                    \
-	ib_opcode_name(UC_SEND_LAST),                      \
-	ib_opcode_name(UC_SEND_LAST_WITH_IMMEDIATE),       \
-	ib_opcode_name(UC_SEND_ONLY),                      \
-	ib_opcode_name(UC_SEND_ONLY_WITH_IMMEDIATE),       \
-	ib_opcode_name(UC_RDMA_WRITE_FIRST),               \
-	ib_opcode_name(UC_RDMA_WRITE_MIDDLE),              \
-	ib_opcode_name(UC_RDMA_WRITE_LAST),                \
-	ib_opcode_name(UC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \
-	ib_opcode_name(UC_RDMA_WRITE_ONLY),                \
-	ib_opcode_name(UC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \
-	ib_opcode_name(UD_SEND_ONLY),                      \
-	ib_opcode_name(UD_SEND_ONLY_WITH_IMMEDIATE),       \
-	ib_opcode_name(CNP))
+static inline void hfi1_update_ah_attr(struct ib_device *ibdev,
+				       struct rdma_ah_attr *attr)
+{
+	struct hfi1_pportdata *ppd;
+	struct hfi1_ibport *ibp;
+	u32 dlid = rdma_ah_get_dlid(attr);
+
+	/*
+	 * Kernel clients may not have setup GRH information
+	 * Set that here.
+	 */
+	ibp = to_iport(ibdev, rdma_ah_get_port_num(attr));
+	ppd = ppd_from_ibp(ibp);
+	if ((((dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) ||
+	      (ppd->lid >= be16_to_cpu(IB_MULTICAST_LID_BASE))) &&
+	    (dlid != be32_to_cpu(OPA_LID_PERMISSIVE)) &&
+	    (dlid != be16_to_cpu(IB_LID_PERMISSIVE)) &&
+	    (!(rdma_ah_get_ah_flags(attr) & IB_AH_GRH))) ||
+	    (rdma_ah_get_make_grd(attr))) {
+		rdma_ah_set_ah_flags(attr, IB_AH_GRH);
+		rdma_ah_set_interface_id(attr, OPA_MAKE_ID(dlid));
+		rdma_ah_set_subnet_prefix(attr, ibp->rvp.gid_prefix);
+	}
+}
+
+/*
+ * hfi1_check_mcast- Check if the given lid is
+ * in the OPA multicast range.
+ *
+ * The LID might either reside in ah.dlid or might be
+ * in the GRH of the address handle as DGID if extended
+ * addresses are in use.
+ */
+static inline bool hfi1_check_mcast(u32 lid)
+{
+	return ((lid >= opa_get_mcast_base(OPA_MCAST_NR)) &&
+		(lid != be32_to_cpu(OPA_LID_PERMISSIVE)));
+}
+
+#define opa_get_lid(lid, format)	\
+	__opa_get_lid(lid, OPA_PORT_PACKET_FORMAT_##format)
+
+/* Convert a lid to a specific lid space */
+static inline u32 __opa_get_lid(u32 lid, u8 format)
+{
+	bool is_mcast = hfi1_check_mcast(lid);
+
+	switch (format) {
+	case OPA_PORT_PACKET_FORMAT_8B:
+	case OPA_PORT_PACKET_FORMAT_10B:
+		if (is_mcast)
+			return (lid - opa_get_mcast_base(OPA_MCAST_NR) +
+				0xF0000);
+		return lid & 0xFFFFF;
+	case OPA_PORT_PACKET_FORMAT_16B:
+		if (is_mcast)
+			return (lid - opa_get_mcast_base(OPA_MCAST_NR) +
+				0xF00000);
+		return lid & 0xFFFFFF;
+	case OPA_PORT_PACKET_FORMAT_9B:
+		if (is_mcast)
+			return (lid -
+				opa_get_mcast_base(OPA_MCAST_NR) +
+				be16_to_cpu(IB_MULTICAST_LID_BASE));
+		else
+			return lid & 0xFFFF;
+	default:
+		return lid;
+	}
+}
+
+/* Return true if the given lid is the OPA 16B multicast range */
+static inline bool hfi1_is_16B_mcast(u32 lid)
+{
+	return ((lid >=
+		opa_get_lid(opa_get_mcast_base(OPA_MCAST_NR), 16B)) &&
+		(lid != opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B)));
+}
+
+static inline void hfi1_make_opa_lid(struct rdma_ah_attr *attr)
+{
+	const struct ib_global_route *grh = rdma_ah_read_grh(attr);
+	u32 dlid = rdma_ah_get_dlid(attr);
+
+	/* Modify ah_attr.dlid to be in the 32 bit LID space.
+	 * This is how the address will be laid out:
+	 * Assuming MCAST_NR to be 4,
+	 * 32 bit permissive LID = 0xFFFFFFFF
+	 * Multicast LID range = 0xFFFFFFFE to 0xF0000000
+	 * Unicast LID range = 0xEFFFFFFF to 1
+	 * Invalid LID = 0
+	 */
+	if (ib_is_opa_gid(&grh->dgid))
+		dlid = opa_get_lid_from_gid(&grh->dgid);
+	else if ((dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+		 (dlid != be16_to_cpu(IB_LID_PERMISSIVE)) &&
+		 (dlid != be32_to_cpu(OPA_LID_PERMISSIVE)))
+		dlid = dlid - be16_to_cpu(IB_MULTICAST_LID_BASE) +
+			opa_get_mcast_base(OPA_MCAST_NR);
+	else if (dlid == be16_to_cpu(IB_LID_PERMISSIVE))
+		dlid = be32_to_cpu(OPA_LID_PERMISSIVE);
+
+	rdma_ah_set_dlid(attr, dlid);
+}
+
+static inline u8 hfi1_get_packet_type(u32 lid)
+{
+	/* 9B if lid > 0xF0000000 */
+	if (lid >= opa_get_mcast_base(OPA_MCAST_NR))
+		return HFI1_PKT_TYPE_9B;
+
+	/* 16B if lid > 0xC000 */
+	if (lid >= opa_get_lid(opa_get_mcast_base(OPA_MCAST_NR), 9B))
+		return HFI1_PKT_TYPE_16B;
+
+	return HFI1_PKT_TYPE_9B;
+}
+
+static inline bool hfi1_get_hdr_type(u32 lid, struct rdma_ah_attr *attr)
+{
+	/*
+	 * If there was an incoming 16B packet with permissive
+	 * LIDs, OPA GIDs would have been programmed when those
+	 * packets were received. A 16B packet will have to
+	 * be sent in response to that packet. Return a 16B
+	 * header type if that's the case.
+	 */
+	if (rdma_ah_get_dlid(attr) == be32_to_cpu(OPA_LID_PERMISSIVE))
+		return (ib_is_opa_gid(&rdma_ah_read_grh(attr)->dgid)) ?
+			HFI1_PKT_TYPE_16B : HFI1_PKT_TYPE_9B;
+
+	/*
+	 * Return a 16B header type if either the the destination
+	 * or source lid is extended.
+	 */
+	if (hfi1_get_packet_type(rdma_ah_get_dlid(attr)) == HFI1_PKT_TYPE_16B)
+		return HFI1_PKT_TYPE_16B;
+
+	return hfi1_get_packet_type(lid);
+}
+
+static inline void hfi1_make_ext_grh(struct hfi1_packet *packet,
+				     struct ib_grh *grh, u32 slid,
+				     u32 dlid)
+{
+	struct hfi1_ibport *ibp = &packet->rcd->ppd->ibport_data;
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+
+	if (!ibp)
+		return;
+
+	grh->hop_limit = 1;
+	grh->sgid.global.subnet_prefix = ibp->rvp.gid_prefix;
+	if (slid == opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B))
+		grh->sgid.global.interface_id =
+			OPA_MAKE_ID(be32_to_cpu(OPA_LID_PERMISSIVE));
+	else
+		grh->sgid.global.interface_id = OPA_MAKE_ID(slid);
+
+	/*
+	 * Upper layers (like mad) may compare the dgid in the
+	 * wc that is obtained here with the sgid_index in
+	 * the wr. Since sgid_index in wr is always 0 for
+	 * extended lids, set the dgid here to the default
+	 * IB gid.
+	 */
+	grh->dgid.global.subnet_prefix = ibp->rvp.gid_prefix;
+	grh->dgid.global.interface_id =
+		cpu_to_be64(ppd->guids[HFI1_PORT_GUID_INDEX]);
+}
+
+static inline int hfi1_get_16b_padding(u32 hdr_size, u32 payload)
+{
+	return -(hdr_size + payload + (SIZE_OF_CRC << 2) +
+		     SIZE_OF_LT) & 0x7;
+}
+
+static inline void hfi1_make_ib_hdr(struct ib_header *hdr,
+				    u16 lrh0, u16 len,
+				    u16 dlid, u16 slid)
+{
+	hdr->lrh[0] = cpu_to_be16(lrh0);
+	hdr->lrh[1] = cpu_to_be16(dlid);
+	hdr->lrh[2] = cpu_to_be16(len);
+	hdr->lrh[3] = cpu_to_be16(slid);
+}
+
+static inline void hfi1_make_16b_hdr(struct hfi1_16b_header *hdr,
+				     u32 slid, u32 dlid,
+				     u16 len, u16 pkey,
+				     u8 becn, u8 fecn, u8 l4,
+				     u8 sc)
+{
+	u32 lrh0 = 0;
+	u32 lrh1 = 0x40000000;
+	u32 lrh2 = 0;
+	u32 lrh3 = 0;
+
+	lrh0 = (lrh0 & ~OPA_16B_BECN_MASK) | (becn << OPA_16B_BECN_SHIFT);
+	lrh0 = (lrh0 & ~OPA_16B_LEN_MASK) | (len << OPA_16B_LEN_SHIFT);
+	lrh0 = (lrh0 & ~OPA_16B_LID_MASK)  | (slid & OPA_16B_LID_MASK);
+	lrh1 = (lrh1 & ~OPA_16B_FECN_MASK) | (fecn << OPA_16B_FECN_SHIFT);
+	lrh1 = (lrh1 & ~OPA_16B_SC_MASK) | (sc << OPA_16B_SC_SHIFT);
+	lrh1 = (lrh1 & ~OPA_16B_LID_MASK) | (dlid & OPA_16B_LID_MASK);
+	lrh2 = (lrh2 & ~OPA_16B_SLID_MASK) |
+		((slid >> OPA_16B_SLID_SHIFT) << OPA_16B_SLID_HIGH_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_DLID_MASK) |
+		((dlid >> OPA_16B_DLID_SHIFT) << OPA_16B_DLID_HIGH_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | (pkey << OPA_16B_PKEY_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_L4_MASK) | l4;
+
+	hdr->lrh[0] = lrh0;
+	hdr->lrh[1] = lrh1;
+	hdr->lrh[2] = lrh2;
+	hdr->lrh[3] = lrh3;
+}
 #endif                          /* _HFI1_KERNEL_H */
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 4a11d4da4c92..fba77001c3a7 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -67,6 +67,7 @@
 #include "aspm.h"
 #include "affinity.h"
 #include "vnic.h"
+#include "exp_rcv.h"
 
 #undef pr_fmt
 #define pr_fmt(fmt) DRIVER_NAME ": " fmt
@@ -125,85 +126,198 @@ static struct idr hfi1_unit_table;
 u32 hfi1_cpulist_count;
 unsigned long *hfi1_cpulist;
 
-/*
- * Common code for creating the receive context array.
- */
-int hfi1_create_ctxts(struct hfi1_devdata *dd)
+static int hfi1_create_kctxt(struct hfi1_devdata *dd,
+			     struct hfi1_pportdata *ppd)
 {
-	unsigned i;
+	struct hfi1_ctxtdata *rcd;
 	int ret;
 
 	/* Control context has to be always 0 */
 	BUILD_BUG_ON(HFI1_CTRL_CTXT != 0);
 
+	ret = hfi1_create_ctxtdata(ppd, dd->node, &rcd);
+	if (ret < 0) {
+		dd_dev_err(dd, "Kernel receive context allocation failed\n");
+		return ret;
+	}
+
+	/*
+	 * Set up the kernel context flags here and now because they use
+	 * default values for all receive side memories.  User contexts will
+	 * be handled as they are created.
+	 */
+	rcd->flags = HFI1_CAP_KGET(MULTI_PKT_EGR) |
+		HFI1_CAP_KGET(NODROP_RHQ_FULL) |
+		HFI1_CAP_KGET(NODROP_EGR_FULL) |
+		HFI1_CAP_KGET(DMA_RTAIL);
+
+	/* Control context must use DMA_RTAIL */
+	if (rcd->ctxt == HFI1_CTRL_CTXT)
+		rcd->flags |= HFI1_CAP_DMA_RTAIL;
+	rcd->seq_cnt = 1;
+
+	rcd->sc = sc_alloc(dd, SC_ACK, rcd->rcvhdrqentsize, dd->node);
+	if (!rcd->sc) {
+		dd_dev_err(dd, "Kernel send context allocation failed\n");
+		return -ENOMEM;
+	}
+	hfi1_init_ctxt(rcd->sc);
+
+	return 0;
+}
+
+/*
+ * Create the receive context array and one or more kernel contexts
+ */
+int hfi1_create_kctxts(struct hfi1_devdata *dd)
+{
+	u16 i;
+	int ret;
+
 	dd->rcd = kzalloc_node(dd->num_rcv_contexts * sizeof(*dd->rcd),
 			       GFP_KERNEL, dd->node);
 	if (!dd->rcd)
-		goto nomem;
+		return -ENOMEM;
 
-	/* create one or more kernel contexts */
 	for (i = 0; i < dd->first_dyn_alloc_ctxt; ++i) {
-		struct hfi1_pportdata *ppd;
-		struct hfi1_ctxtdata *rcd;
+		ret = hfi1_create_kctxt(dd, dd->pport);
+		if (ret)
+			goto bail;
+	}
 
-		ppd = dd->pport + (i % dd->num_pports);
+	return 0;
+bail:
+	for (i = 0; dd->rcd && i < dd->first_dyn_alloc_ctxt; ++i)
+		hfi1_free_ctxt(dd->rcd[i]);
 
-		/* dd->rcd[i] gets assigned inside the callee */
-		rcd = hfi1_create_ctxtdata(ppd, i, dd->node);
-		if (!rcd) {
-			dd_dev_err(dd,
-				   "Unable to allocate kernel receive context, failing\n");
-			goto nomem;
-		}
-		/*
-		 * Set up the kernel context flags here and now because they
-		 * use default values for all receive side memories.  User
-		 * contexts will be handled as they are created.
-		 */
-		rcd->flags = HFI1_CAP_KGET(MULTI_PKT_EGR) |
-			HFI1_CAP_KGET(NODROP_RHQ_FULL) |
-			HFI1_CAP_KGET(NODROP_EGR_FULL) |
-			HFI1_CAP_KGET(DMA_RTAIL);
-
-		/* Control context must use DMA_RTAIL */
-		if (rcd->ctxt == HFI1_CTRL_CTXT)
-			rcd->flags |= HFI1_CAP_DMA_RTAIL;
-		rcd->seq_cnt = 1;
-
-		rcd->sc = sc_alloc(dd, SC_ACK, rcd->rcvhdrqentsize, dd->node);
-		if (!rcd->sc) {
-			dd_dev_err(dd,
-				   "Unable to allocate kernel send context, failing\n");
-			goto nomem;
-		}
+	/* All the contexts should be freed, free the array */
+	kfree(dd->rcd);
+	dd->rcd = NULL;
+	return ret;
+}
+
+/*
+ * Helper routines for the receive context reference count (rcd and uctxt).
+ */
+static void hfi1_rcd_init(struct hfi1_ctxtdata *rcd)
+{
+	kref_init(&rcd->kref);
+}
 
-		hfi1_init_ctxt(rcd->sc);
+/**
+ * hfi1_rcd_free - When reference is zero clean up.
+ * @kref: pointer to an initialized rcd data structure
+ *
+ */
+static void hfi1_rcd_free(struct kref *kref)
+{
+	unsigned long flags;
+	struct hfi1_ctxtdata *rcd =
+		container_of(kref, struct hfi1_ctxtdata, kref);
+
+	hfi1_free_ctxtdata(rcd->dd, rcd);
+
+	spin_lock_irqsave(&rcd->dd->uctxt_lock, flags);
+	rcd->dd->rcd[rcd->ctxt] = NULL;
+	spin_unlock_irqrestore(&rcd->dd->uctxt_lock, flags);
+
+	kfree(rcd);
+}
+
+/**
+ * hfi1_rcd_put - decrement reference for rcd
+ * @rcd: pointer to an initialized rcd data structure
+ *
+ * Use this to put a reference after the init.
+ */
+int hfi1_rcd_put(struct hfi1_ctxtdata *rcd)
+{
+	if (rcd)
+		return kref_put(&rcd->kref, hfi1_rcd_free);
+
+	return 0;
+}
+
+/**
+ * hfi1_rcd_get - increment reference for rcd
+ * @rcd: pointer to an initialized rcd data structure
+ *
+ * Use this to get a reference after the init.
+ */
+void hfi1_rcd_get(struct hfi1_ctxtdata *rcd)
+{
+	kref_get(&rcd->kref);
+}
+
+/**
+ * allocate_rcd_index - allocate an rcd index from the rcd array
+ * @dd: pointer to a valid devdata structure
+ * @rcd: rcd data structure to assign
+ * @index: pointer to index that is allocated
+ *
+ * Find an empty index in the rcd array, and assign the given rcd to it.
+ * If the array is full, we are EBUSY.
+ *
+ */
+static int allocate_rcd_index(struct hfi1_devdata *dd,
+			      struct hfi1_ctxtdata *rcd, u16 *index)
+{
+	unsigned long flags;
+	u16 ctxt;
+
+	spin_lock_irqsave(&dd->uctxt_lock, flags);
+	for (ctxt = 0; ctxt < dd->num_rcv_contexts; ctxt++)
+		if (!dd->rcd[ctxt])
+			break;
+
+	if (ctxt < dd->num_rcv_contexts) {
+		rcd->ctxt = ctxt;
+		dd->rcd[ctxt] = rcd;
+		hfi1_rcd_init(rcd);
 	}
+	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
 
-	/*
-	 * Initialize aspm, to be done after gen3 transition and setting up
-	 * contexts and before enabling interrupts
-	 */
-	aspm_init(dd);
+	if (ctxt >= dd->num_rcv_contexts)
+		return -EBUSY;
+
+	*index = ctxt;
 
 	return 0;
-nomem:
-	ret = -ENOMEM;
+}
 
-	if (dd->rcd) {
-		for (i = 0; i < dd->num_rcv_contexts; ++i)
-			hfi1_free_ctxtdata(dd, dd->rcd[i]);
+/**
+ * hfi1_rcd_get_by_index
+ * @dd: pointer to a valid devdata structure
+ * @ctxt: the index of an possilbe rcd
+ *
+ * We need to protect access to the rcd array.  If access is needed to
+ * one or more index, get the protecting spinlock and then increment the
+ * kref.
+ *
+ * The caller is responsible for making the _put().
+ *
+ */
+struct hfi1_ctxtdata *hfi1_rcd_get_by_index(struct hfi1_devdata *dd, u16 ctxt)
+{
+	unsigned long flags;
+	struct hfi1_ctxtdata *rcd = NULL;
+
+	spin_lock_irqsave(&dd->uctxt_lock, flags);
+	if (dd->rcd[ctxt]) {
+		rcd = dd->rcd[ctxt];
+		hfi1_rcd_get(rcd);
 	}
-	kfree(dd->rcd);
-	dd->rcd = NULL;
-	return ret;
+	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
+
+	return rcd;
 }
 
 /*
- * Common code for user and kernel context setup.
+ * Common code for user and kernel context create and setup.
+ * NOTE: the initial kref is done here (hf1_rcd_init()).
  */
-struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
-					   int numa)
+int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
+			 struct hfi1_ctxtdata **context)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	struct hfi1_ctxtdata *rcd;
@@ -217,20 +331,30 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 	rcd = kzalloc_node(sizeof(*rcd), GFP_KERNEL, numa);
 	if (rcd) {
 		u32 rcvtids, max_entries;
-
-		hfi1_cdbg(PROC, "setting up context %u\n", ctxt);
+		u16 ctxt;
+		int ret;
+
+		ret = allocate_rcd_index(dd, rcd, &ctxt);
+		if (ret) {
+			*context = NULL;
+			kfree(rcd);
+			return ret;
+		}
 
 		INIT_LIST_HEAD(&rcd->qp_wait_list);
+		hfi1_exp_tid_group_init(&rcd->tid_group_list);
+		hfi1_exp_tid_group_init(&rcd->tid_used_list);
+		hfi1_exp_tid_group_init(&rcd->tid_full_list);
 		rcd->ppd = ppd;
 		rcd->dd = dd;
 		__set_bit(0, rcd->in_use_ctxts);
-		rcd->ctxt = ctxt;
-		dd->rcd[ctxt] = rcd;
 		rcd->numa_id = numa;
 		rcd->rcv_array_groups = dd->rcv_entries.ngroups;
 
 		mutex_init(&rcd->exp_lock);
 
+		hfi1_cdbg(PROC, "setting up context %u\n", rcd->ctxt);
+
 		/*
 		 * Calculate the context's RcvArray entry starting point.
 		 * We do this here because we have to take into account all
@@ -328,14 +452,30 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 			if (!rcd->opstats)
 				goto bail;
 		}
+
+		*context = rcd;
+		return 0;
 	}
-	return rcd;
+
 bail:
-	dd->rcd[ctxt] = NULL;
-	kfree(rcd->egrbufs.rcvtids);
-	kfree(rcd->egrbufs.buffers);
-	kfree(rcd);
-	return NULL;
+	*context = NULL;
+	hfi1_free_ctxt(rcd);
+	return -ENOMEM;
+}
+
+/**
+ * hfi1_free_ctxt
+ * @rcd: pointer to an initialized rcd data structure
+ *
+ * This wrapper is the free function that matches hfi1_create_ctxtdata().
+ * When a context is done being used (kernel or user), this function is called
+ * for the "final" put to match the kref init from hf1i_create_ctxtdata().
+ * Other users of the context do a get/put sequence to make sure that the
+ * structure isn't removed while in use.
+ */
+void hfi1_free_ctxt(struct hfi1_ctxtdata *rcd)
+{
+	hfi1_rcd_put(rcd);
 }
 
 /*
@@ -483,7 +623,6 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 
 	ppd->pkeys[default_pkey_idx] = DEFAULT_P_KEY;
 	ppd->part_enforce |= HFI1_PART_ENFORCE_IN;
-	ppd->part_enforce |= HFI1_PART_ENFORCE_OUT;
 
 	if (loopback) {
 		hfi1_early_err(&pdev->dev,
@@ -559,16 +698,19 @@ static int loadtime_init(struct hfi1_devdata *dd)
 static int init_after_reset(struct hfi1_devdata *dd)
 {
 	int i;
-
+	struct hfi1_ctxtdata *rcd;
 	/*
 	 * Ensure chip does no sends or receives, tail updates, or
 	 * pioavail updates while we re-initialize.  This is mostly
 	 * for the driver data structures, not chip registers.
 	 */
-	for (i = 0; i < dd->num_rcv_contexts; i++)
+	for (i = 0; i < dd->num_rcv_contexts; i++) {
+		rcd = hfi1_rcd_get_by_index(dd, i);
 		hfi1_rcvctrl(dd, HFI1_RCVCTRL_CTXT_DIS |
-				  HFI1_RCVCTRL_INTRAVAIL_DIS |
-				  HFI1_RCVCTRL_TAILUPD_DIS, i);
+			     HFI1_RCVCTRL_INTRAVAIL_DIS |
+			     HFI1_RCVCTRL_TAILUPD_DIS, rcd);
+		hfi1_rcd_put(rcd);
+	}
 	pio_send_control(dd, PSC_GLOBAL_DISABLE);
 	for (i = 0; i < dd->num_send_contexts; i++)
 		sc_disable(dd->send_contexts[i].sc);
@@ -578,8 +720,9 @@ static int init_after_reset(struct hfi1_devdata *dd)
 
 static void enable_chip(struct hfi1_devdata *dd)
 {
+	struct hfi1_ctxtdata *rcd;
 	u32 rcvmask;
-	u32 i;
+	u16 i;
 
 	/* enable PIO send */
 	pio_send_control(dd, PSC_GLOBAL_ENABLE);
@@ -589,17 +732,21 @@ static void enable_chip(struct hfi1_devdata *dd)
 	 * Other ctxts done as user opens and initializes them.
 	 */
 	for (i = 0; i < dd->first_dyn_alloc_ctxt; ++i) {
+		rcd = hfi1_rcd_get_by_index(dd, i);
+		if (!rcd)
+			continue;
 		rcvmask = HFI1_RCVCTRL_CTXT_ENB | HFI1_RCVCTRL_INTRAVAIL_ENB;
-		rcvmask |= HFI1_CAP_KGET_MASK(dd->rcd[i]->flags, DMA_RTAIL) ?
+		rcvmask |= HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ?
 			HFI1_RCVCTRL_TAILUPD_ENB : HFI1_RCVCTRL_TAILUPD_DIS;
-		if (!HFI1_CAP_KGET_MASK(dd->rcd[i]->flags, MULTI_PKT_EGR))
+		if (!HFI1_CAP_KGET_MASK(rcd->flags, MULTI_PKT_EGR))
 			rcvmask |= HFI1_RCVCTRL_ONE_PKT_EGR_ENB;
-		if (HFI1_CAP_KGET_MASK(dd->rcd[i]->flags, NODROP_RHQ_FULL))
+		if (HFI1_CAP_KGET_MASK(rcd->flags, NODROP_RHQ_FULL))
 			rcvmask |= HFI1_RCVCTRL_NO_RHQ_DROP_ENB;
-		if (HFI1_CAP_KGET_MASK(dd->rcd[i]->flags, NODROP_EGR_FULL))
+		if (HFI1_CAP_KGET_MASK(rcd->flags, NODROP_EGR_FULL))
 			rcvmask |= HFI1_RCVCTRL_NO_EGR_DROP_ENB;
-		hfi1_rcvctrl(dd, rcvmask, i);
-		sc_enable(dd->rcd[i]->sc);
+		hfi1_rcvctrl(dd, rcvmask, rcd);
+		sc_enable(rcd->sc);
+		hfi1_rcd_put(rcd);
 	}
 }
 
@@ -624,6 +771,20 @@ static int create_workqueues(struct hfi1_devdata *dd)
 			if (!ppd->hfi1_wq)
 				goto wq_error;
 		}
+		if (!ppd->link_wq) {
+			/*
+			 * Make the link workqueue single-threaded to enforce
+			 * serialization.
+			 */
+			ppd->link_wq =
+				alloc_workqueue(
+				    "hfi_link_%d_%d",
+				    WQ_SYSFS | WQ_MEM_RECLAIM | WQ_UNBOUND,
+				    1, /* max_active */
+				    dd->unit, pidx);
+			if (!ppd->link_wq)
+				goto wq_error;
+		}
 	}
 	return 0;
 wq_error:
@@ -634,6 +795,10 @@ wq_error:
 			destroy_workqueue(ppd->hfi1_wq);
 			ppd->hfi1_wq = NULL;
 		}
+		if (ppd->link_wq) {
+			destroy_workqueue(ppd->link_wq);
+			ppd->link_wq = NULL;
+		}
 	}
 	return -ENOMEM;
 }
@@ -656,7 +821,8 @@ wq_error:
 int hfi1_init(struct hfi1_devdata *dd, int reinit)
 {
 	int ret = 0, pidx, lastfail = 0;
-	unsigned i, len;
+	unsigned long len;
+	u16 i;
 	struct hfi1_ctxtdata *rcd;
 	struct hfi1_pportdata *ppd;
 
@@ -725,7 +891,7 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 		 * existing, and re-allocate.
 		 * Need to re-create rest of ctxt 0 ctxtdata as well.
 		 */
-		rcd = dd->rcd[i];
+		rcd = hfi1_rcd_get_by_index(dd, i);
 		if (!rcd)
 			continue;
 
@@ -739,6 +905,7 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 				   "failed to allocate kernel ctxt's rcvhdrq and/or egr bufs\n");
 			ret = lastfail;
 		}
+		hfi1_rcd_put(rcd);
 	}
 
 	/* Allocate enough memory for user event notification. */
@@ -858,6 +1025,7 @@ static void stop_timers(struct hfi1_devdata *dd)
 static void shutdown_device(struct hfi1_devdata *dd)
 {
 	struct hfi1_pportdata *ppd;
+	struct hfi1_ctxtdata *rcd;
 	unsigned pidx;
 	int i;
 
@@ -876,12 +1044,15 @@ static void shutdown_device(struct hfi1_devdata *dd)
 
 	for (pidx = 0; pidx < dd->num_pports; ++pidx) {
 		ppd = dd->pport + pidx;
-		for (i = 0; i < dd->num_rcv_contexts; i++)
+		for (i = 0; i < dd->num_rcv_contexts; i++) {
+			rcd = hfi1_rcd_get_by_index(dd, i);
 			hfi1_rcvctrl(dd, HFI1_RCVCTRL_TAILUPD_DIS |
-					  HFI1_RCVCTRL_CTXT_DIS |
-					  HFI1_RCVCTRL_INTRAVAIL_DIS |
-					  HFI1_RCVCTRL_PKEY_DIS |
-					  HFI1_RCVCTRL_ONE_PKT_EGR_DIS, i);
+				     HFI1_RCVCTRL_CTXT_DIS |
+				     HFI1_RCVCTRL_INTRAVAIL_DIS |
+				     HFI1_RCVCTRL_PKEY_DIS |
+				     HFI1_RCVCTRL_ONE_PKT_EGR_DIS, rcd);
+			hfi1_rcd_put(rcd);
+		}
 		/*
 		 * Gracefully stop all sends allowing any in progress to
 		 * trickle out first.
@@ -917,6 +1088,10 @@ static void shutdown_device(struct hfi1_devdata *dd)
 			destroy_workqueue(ppd->hfi1_wq);
 			ppd->hfi1_wq = NULL;
 		}
+		if (ppd->link_wq) {
+			destroy_workqueue(ppd->link_wq);
+			ppd->link_wq = NULL;
+		}
 	}
 	sdma_exit(dd);
 }
@@ -927,14 +1102,11 @@ static void shutdown_device(struct hfi1_devdata *dd)
  * @rcd: the ctxtdata structure
  *
  * free up any allocated data for a context
- * This should not touch anything that would affect a simultaneous
- * re-allocation of context data, because it is called after hfi1_mutex
- * is released (and can be called from reinit as well).
  * It should never change any chip state, or global driver state.
  */
 void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 {
-	unsigned e;
+	u32 e;
 
 	if (!rcd)
 		return;
@@ -953,6 +1125,7 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 
 	/* all the RcvArray entries should have been cleared by now */
 	kfree(rcd->egrbufs.rcvtids);
+	rcd->egrbufs.rcvtids = NULL;
 
 	for (e = 0; e < rcd->egrbufs.alloced; e++) {
 		if (rcd->egrbufs.buffers[e].dma)
@@ -962,13 +1135,21 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 					  rcd->egrbufs.buffers[e].dma);
 	}
 	kfree(rcd->egrbufs.buffers);
+	rcd->egrbufs.alloced = 0;
+	rcd->egrbufs.buffers = NULL;
 
 	sc_free(rcd->sc);
+	rcd->sc = NULL;
+
 	vfree(rcd->subctxt_uregbase);
 	vfree(rcd->subctxt_rcvegrbuf);
 	vfree(rcd->subctxt_rcvhdr_base);
 	kfree(rcd->opstats);
-	kfree(rcd);
+
+	rcd->subctxt_uregbase = NULL;
+	rcd->subctxt_rcvegrbuf = NULL;
+	rcd->subctxt_rcvhdr_base = NULL;
+	rcd->opstats = NULL;
 }
 
 /*
@@ -1311,8 +1492,6 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
 {
 	int ctxt;
 	int pidx;
-	struct hfi1_ctxtdata **tmp;
-	unsigned long flags;
 
 	/* users can't do anything more with chip */
 	for (pidx = 0; pidx < dd->num_pports; ++pidx) {
@@ -1337,18 +1516,6 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
 
 	free_credit_return(dd);
 
-	/*
-	 * Free any resources still in use (usually just kernel contexts)
-	 * at unload; we do for ctxtcnt, because that's what we allocate.
-	 * We acquire lock to be really paranoid that rcd isn't being
-	 * accessed from some interrupt-related code (that should not happen,
-	 * but best to be sure).
-	 */
-	spin_lock_irqsave(&dd->uctxt_lock, flags);
-	tmp = dd->rcd;
-	dd->rcd = NULL;
-	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
-
 	if (dd->rcvhdrtail_dummy_kvaddr) {
 		dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
 				  (void *)dd->rcvhdrtail_dummy_kvaddr,
@@ -1356,16 +1523,22 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
 		dd->rcvhdrtail_dummy_kvaddr = NULL;
 	}
 
-	for (ctxt = 0; tmp && ctxt < dd->num_rcv_contexts; ctxt++) {
-		struct hfi1_ctxtdata *rcd = tmp[ctxt];
+	/*
+	 * Free any resources still in use (usually just kernel contexts)
+	 * at unload; we do for ctxtcnt, because that's what we allocate.
+	 */
+	for (ctxt = 0; dd->rcd && ctxt < dd->num_rcv_contexts; ctxt++) {
+		struct hfi1_ctxtdata *rcd = dd->rcd[ctxt];
 
-		tmp[ctxt] = NULL; /* debugging paranoia */
 		if (rcd) {
 			hfi1_clear_tids(rcd);
-			hfi1_free_ctxtdata(dd, rcd);
+			hfi1_free_ctxt(rcd);
 		}
 	}
-	kfree(tmp);
+
+	kfree(dd->rcd);
+	dd->rcd = NULL;
+
 	free_pio_map(dd);
 	/* must follow rcv context free - need to remove rcv's hooks */
 	for (ctxt = 0; ctxt < dd->num_send_contexts; ctxt++)
@@ -1532,6 +1705,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				destroy_workqueue(ppd->hfi1_wq);
 				ppd->hfi1_wq = NULL;
 			}
+			if (ppd->link_wq) {
+				destroy_workqueue(ppd->link_wq);
+				ppd->link_wq = NULL;
+			}
 		}
 		if (!j)
 			hfi1_device_remove(dd);
diff --git a/drivers/infiniband/hw/hfi1/intr.c b/drivers/infiniband/hw/hfi1/intr.c
index 04a5082d5ac5..96845dfed5c5 100644
--- a/drivers/infiniband/hw/hfi1/intr.c
+++ b/drivers/infiniband/hw/hfi1/intr.c
@@ -164,6 +164,7 @@ void handle_linkup_change(struct hfi1_devdata *dd, u32 linkup)
 		ppd->linkup = 0;
 
 		/* clear HW details of the previous connection */
+		ppd->actual_vls_operational = 0;
 		reset_link_credits(dd);
 
 		/* freeze after a link down to guarantee a clean egress */
@@ -196,7 +197,7 @@ void handle_user_interrupt(struct hfi1_ctxtdata *rcd)
 
 	if (test_and_clear_bit(HFI1_CTXT_WAITING_RCV, &rcd->event_flags)) {
 		wake_up_interruptible(&rcd->wait);
-		hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_DIS, rcd->ctxt);
+		hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_DIS, rcd);
 	} else if (test_and_clear_bit(HFI1_CTXT_WAITING_URG,
 							&rcd->event_flags)) {
 		rcd->urgent++;
diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h
index d9740ddea6f1..591697d85eed 100644
--- a/drivers/infiniband/hw/hfi1/iowait.h
+++ b/drivers/infiniband/hw/hfi1/iowait.h
@@ -106,7 +106,9 @@ struct iowait {
 		struct sdma_engine *sde,
 		struct iowait *wait,
 		struct sdma_txreq *tx,
-		unsigned seq);
+		uint seq,
+		bool pkts_sent
+		);
 	void (*wakeup)(struct iowait *wait, int reason);
 	void (*sdma_drained)(struct iowait *wait);
 	seqlock_t *lock;
@@ -118,6 +120,7 @@ struct iowait {
 	u32 count;
 	u32 tx_limit;
 	u32 tx_count;
+	u8 starved_cnt;
 };
 
 #define SDMA_AVAIL_REASON 0
@@ -143,7 +146,8 @@ static inline void iowait_init(
 		struct sdma_engine *sde,
 		struct iowait *wait,
 		struct sdma_txreq *tx,
-		unsigned seq),
+		uint seq,
+		bool pkts_sent),
 	void (*wakeup)(struct iowait *wait, int reason),
 	void (*sdma_drained)(struct iowait *wait))
 {
@@ -305,4 +309,66 @@ static inline struct sdma_txreq *iowait_get_txhead(struct iowait *wait)
 	return tx;
 }
 
+/**
+ * iowait_queue - Put the iowait on a wait queue
+ * @pkts_sent: have some packets been sent before queuing?
+ * @w: the iowait struct
+ * @wait_head: the wait queue
+ *
+ * This function is called to insert an iowait struct into a
+ * wait queue after a resource (eg, sdma decriptor or pio
+ * buffer) is run out.
+ */
+static inline void iowait_queue(bool pkts_sent, struct iowait *w,
+				struct list_head *wait_head)
+{
+	/*
+	 * To play fair, insert the iowait at the tail of the wait queue if it
+	 * has already sent some packets; Otherwise, put it at the head.
+	 */
+	if (pkts_sent) {
+		list_add_tail(&w->list, wait_head);
+		w->starved_cnt = 0;
+	} else {
+		list_add(&w->list, wait_head);
+		w->starved_cnt++;
+	}
+}
+
+/**
+ * iowait_starve_clear - clear the wait queue's starve count
+ * @pkts_sent: have some packets been sent?
+ * @w: the iowait struct
+ *
+ * This function is called to clear the starve count. If no
+ * packets have been sent, the starve count will not be cleared.
+ */
+static inline void iowait_starve_clear(bool pkts_sent, struct iowait *w)
+{
+	if (pkts_sent)
+		w->starved_cnt = 0;
+}
+
+/**
+ * iowait_starve_find_max - Find the maximum of the starve count
+ * @w: the iowait struct
+ * @max: a variable containing the max starve count
+ * @idx: the index of the current iowait in an array
+ * @max_idx: a variable containing the array index for the
+ *         iowait entry that has the max starve count
+ *
+ * This function is called to compare the starve count of a
+ * given iowait with the given max starve count. The max starve
+ * count and the index will be updated if the iowait's start
+ * count is larger.
+ */
+static inline void iowait_starve_find_max(struct iowait *w, u8 *max,
+					  uint idx, uint *max_idx)
+{
+	if (w->starved_cnt > *max) {
+		*max = w->starved_cnt;
+		*max_idx = idx;
+	}
+}
+
 #endif
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 5977673a52d4..f4c0ffc040cc 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -46,6 +46,7 @@
  */
 
 #include <linux/net.h>
+#include <rdma/opa_addr.h>
 #define OPA_NUM_PKEY_BLOCKS_PER_SMP (OPA_SMP_DR_DATA_SIZE \
 			/ (OPA_PARTITION_TABLE_BLK_SIZE * sizeof(u16)))
 
@@ -59,6 +60,24 @@
 #define OPA_LINK_WIDTH_RESET_OLD 0x0fff
 #define OPA_LINK_WIDTH_RESET 0xffff
 
+struct trap_node {
+	struct list_head list;
+	struct opa_mad_notice_attr data;
+	__be64 tid;
+	int len;
+	u32 retry;
+	u8 in_use;
+	u8 repress;
+};
+
+static int smp_length_check(u32 data_size, u32 request_len)
+{
+	if (unlikely(request_len < data_size))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int reply(struct ib_mad_hdr *smp)
 {
 	/*
@@ -89,28 +108,222 @@ void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port)
 	ib_dispatch_event(&event);
 }
 
-static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
+/*
+ * If the port is down, clean up all pending traps.  We need to be careful
+ * with the given trap, because it may be queued.
+ */
+static void cleanup_traps(struct hfi1_ibport *ibp, struct trap_node *trap)
+{
+	struct trap_node *node, *q;
+	unsigned long flags;
+	struct list_head trap_list;
+	int i;
+
+	for (i = 0; i < RVT_MAX_TRAP_LISTS; i++) {
+		spin_lock_irqsave(&ibp->rvp.lock, flags);
+		list_replace_init(&ibp->rvp.trap_lists[i].list, &trap_list);
+		ibp->rvp.trap_lists[i].list_len = 0;
+		spin_unlock_irqrestore(&ibp->rvp.lock, flags);
+
+		/*
+		 * Remove all items from the list, freeing all the non-given
+		 * traps.
+		 */
+		list_for_each_entry_safe(node, q, &trap_list, list) {
+			list_del(&node->list);
+			if (node != trap)
+				kfree(node);
+		}
+	}
+
+	/*
+	 * If this wasn't on one of the lists it would not be freed.  If it
+	 * was on the list, it is now safe to free.
+	 */
+	kfree(trap);
+}
+
+static struct trap_node *check_and_add_trap(struct hfi1_ibport *ibp,
+					    struct trap_node *trap)
+{
+	struct trap_node *node;
+	struct trap_list *trap_list;
+	unsigned long flags;
+	unsigned long timeout;
+	int found = 0;
+	unsigned int queue_id;
+	static int trap_count;
+
+	queue_id = trap->data.generic_type & 0x0F;
+	if (queue_id >= RVT_MAX_TRAP_LISTS) {
+		trap_count++;
+		pr_err_ratelimited("hfi1: Invalid trap 0x%0x dropped. Total dropped: %d\n",
+				   trap->data.generic_type, trap_count);
+		kfree(trap);
+		return NULL;
+	}
+
+	/*
+	 * Since the retry (handle timeout) does not remove a trap request
+	 * from the list, all we have to do is compare the node.
+	 */
+	spin_lock_irqsave(&ibp->rvp.lock, flags);
+	trap_list = &ibp->rvp.trap_lists[queue_id];
+
+	list_for_each_entry(node, &trap_list->list, list) {
+		if (node == trap) {
+			node->retry++;
+			found = 1;
+			break;
+		}
+	}
+
+	/* If it is not on the list, add it, limited to RVT-MAX_TRAP_LEN. */
+	if (!found) {
+		if (trap_list->list_len < RVT_MAX_TRAP_LEN) {
+			trap_list->list_len++;
+			list_add_tail(&trap->list, &trap_list->list);
+		} else {
+			pr_warn_ratelimited("hfi1: Maximum trap limit reached for 0x%0x traps\n",
+					    trap->data.generic_type);
+			kfree(trap);
+		}
+	}
+
+	/*
+	 * Next check to see if there is a timer pending.  If not, set it up
+	 * and get the first trap from the list.
+	 */
+	node = NULL;
+	if (!timer_pending(&ibp->rvp.trap_timer)) {
+		/*
+		 * o14-2
+		 * If the time out is set we have to wait until it expires
+		 * before the trap can be sent.
+		 * This should be > RVT_TRAP_TIMEOUT
+		 */
+		timeout = (RVT_TRAP_TIMEOUT *
+			   (1UL << ibp->rvp.subnet_timeout)) / 1000;
+		mod_timer(&ibp->rvp.trap_timer,
+			  jiffies + usecs_to_jiffies(timeout));
+		node = list_first_entry(&trap_list->list, struct trap_node,
+					list);
+		node->in_use = 1;
+	}
+	spin_unlock_irqrestore(&ibp->rvp.lock, flags);
+
+	return node;
+}
+
+static void subn_handle_opa_trap_repress(struct hfi1_ibport *ibp,
+					 struct opa_smp *smp)
+{
+	struct trap_list *trap_list;
+	struct trap_node *trap;
+	unsigned long flags;
+	int i;
+
+	if (smp->attr_id != IB_SMP_ATTR_NOTICE)
+		return;
+
+	spin_lock_irqsave(&ibp->rvp.lock, flags);
+	for (i = 0; i < RVT_MAX_TRAP_LISTS; i++) {
+		trap_list = &ibp->rvp.trap_lists[i];
+		trap = list_first_entry_or_null(&trap_list->list,
+						struct trap_node, list);
+		if (trap && trap->tid == smp->tid) {
+			if (trap->in_use) {
+				trap->repress = 1;
+			} else {
+				trap_list->list_len--;
+				list_del(&trap->list);
+				kfree(trap);
+			}
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&ibp->rvp.lock, flags);
+}
+
+static void hfi1_update_sm_ah_attr(struct hfi1_ibport *ibp,
+				   struct rdma_ah_attr *attr, u32 dlid)
+{
+	rdma_ah_set_dlid(attr, dlid);
+	rdma_ah_set_port_num(attr, ppd_from_ibp(ibp)->port);
+	if (dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) {
+		struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);
+
+		rdma_ah_set_ah_flags(attr, IB_AH_GRH);
+		grh->sgid_index = 0;
+		grh->hop_limit = 1;
+		grh->dgid.global.subnet_prefix =
+			ibp->rvp.gid_prefix;
+		grh->dgid.global.interface_id = OPA_MAKE_ID(dlid);
+	}
+}
+
+static int hfi1_modify_qp0_ah(struct hfi1_ibport *ibp,
+			      struct rvt_ah *ah, u32 dlid)
+{
+	struct rdma_ah_attr attr;
+	struct rvt_qp *qp0;
+	int ret = -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = ah->ibah.type;
+	hfi1_update_sm_ah_attr(ibp, &attr, dlid);
+	rcu_read_lock();
+	qp0 = rcu_dereference(ibp->rvp.qp[0]);
+	if (qp0)
+		ret = rdma_modify_ah(&ah->ibah, &attr);
+	rcu_read_unlock();
+	return ret;
+}
+
+static struct ib_ah *hfi1_create_qp0_ah(struct hfi1_ibport *ibp, u32 dlid)
+{
+	struct rdma_ah_attr attr;
+	struct ib_ah *ah = ERR_PTR(-EINVAL);
+	struct rvt_qp *qp0;
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	struct hfi1_devdata *dd = dd_from_ppd(ppd);
+	u8 port_num = ppd->port;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = rdma_ah_find_type(&dd->verbs_dev.rdi.ibdev, port_num);
+	hfi1_update_sm_ah_attr(ibp, &attr, dlid);
+	rcu_read_lock();
+	qp0 = rcu_dereference(ibp->rvp.qp[0]);
+	if (qp0)
+		ah = rdma_create_ah(qp0->ibqp.pd, &attr);
+	rcu_read_unlock();
+	return ah;
+}
+
+static void send_trap(struct hfi1_ibport *ibp, struct trap_node *trap)
 {
 	struct ib_mad_send_buf *send_buf;
 	struct ib_mad_agent *agent;
 	struct opa_smp *smp;
-	int ret;
 	unsigned long flags;
-	unsigned long timeout;
 	int pkey_idx;
 	u32 qpn = ppd_from_ibp(ibp)->sm_trap_qp;
 
 	agent = ibp->rvp.send_agent;
-	if (!agent)
+	if (!agent) {
+		cleanup_traps(ibp, trap);
 		return;
+	}
 
 	/* o14-3.2.1 */
-	if (ppd_from_ibp(ibp)->lstate != IB_PORT_ACTIVE)
+	if (driver_lstate(ppd_from_ibp(ibp)) != IB_PORT_ACTIVE) {
+		cleanup_traps(ibp, trap);
 		return;
+	}
 
-	/* o14-2 */
-	if (ibp->rvp.trap_timeout && time_before(jiffies,
-						 ibp->rvp.trap_timeout))
+	/* Add the trap to the list if necessary and see if we can send it */
+	trap = check_and_add_trap(ibp, trap);
+	if (!trap)
 		return;
 
 	pkey_idx = hfi1_lookup_pkey_idx(ibp, LIM_MGMT_P_KEY);
@@ -131,11 +344,21 @@ static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
 	smp->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
 	smp->class_version = OPA_SM_CLASS_VERSION;
 	smp->method = IB_MGMT_METHOD_TRAP;
-	ibp->rvp.tid++;
-	smp->tid = cpu_to_be64(ibp->rvp.tid);
+
+	/* Only update the transaction ID for new traps (o13-5). */
+	if (trap->tid == 0) {
+		ibp->rvp.tid++;
+		/* make sure that tid != 0 */
+		if (ibp->rvp.tid == 0)
+			ibp->rvp.tid++;
+		trap->tid = cpu_to_be64(ibp->rvp.tid);
+	}
+	smp->tid = trap->tid;
+
 	smp->attr_id = IB_SMP_ATTR_NOTICE;
 	/* o14-1: smp->mkey = 0; */
-	memcpy(smp->route.lid.data, data, len);
+
+	memcpy(smp->route.lid.data, &trap->data, trap->len);
 
 	spin_lock_irqsave(&ibp->rvp.lock, flags);
 	if (!ibp->rvp.sm_ah) {
@@ -144,65 +367,101 @@ static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
 
 			ah = hfi1_create_qp0_ah(ibp, ibp->rvp.sm_lid);
 			if (IS_ERR(ah)) {
-				ret = PTR_ERR(ah);
-			} else {
-				send_buf->ah = ah;
-				ibp->rvp.sm_ah = ibah_to_rvtah(ah);
-				ret = 0;
+				spin_unlock_irqrestore(&ibp->rvp.lock, flags);
+				return;
 			}
+			send_buf->ah = ah;
+			ibp->rvp.sm_ah = ibah_to_rvtah(ah);
 		} else {
-			ret = -EINVAL;
+			spin_unlock_irqrestore(&ibp->rvp.lock, flags);
+			return;
 		}
 	} else {
 		send_buf->ah = &ibp->rvp.sm_ah->ibah;
-		ret = 0;
 	}
+
+	/*
+	 * If the trap was repressed while things were getting set up, don't
+	 * bother sending it. This could happen for a retry.
+	 */
+	if (trap->repress) {
+		list_del(&trap->list);
+		spin_unlock_irqrestore(&ibp->rvp.lock, flags);
+		kfree(trap);
+		ib_free_send_mad(send_buf);
+		return;
+	}
+
+	trap->in_use = 0;
 	spin_unlock_irqrestore(&ibp->rvp.lock, flags);
 
-	if (!ret)
-		ret = ib_post_send_mad(send_buf, NULL);
-	if (!ret) {
-		/* 4.096 usec. */
-		timeout = (4096 * (1UL << ibp->rvp.subnet_timeout)) / 1000;
-		ibp->rvp.trap_timeout = jiffies + usecs_to_jiffies(timeout);
-	} else {
+	if (ib_post_send_mad(send_buf, NULL))
 		ib_free_send_mad(send_buf);
-		ibp->rvp.trap_timeout = 0;
+}
+
+void hfi1_handle_trap_timer(unsigned long data)
+{
+	struct hfi1_ibport *ibp = (struct hfi1_ibport *)data;
+	struct trap_node *trap = NULL;
+	unsigned long flags;
+	int i;
+
+	/* Find the trap with the highest priority */
+	spin_lock_irqsave(&ibp->rvp.lock, flags);
+	for (i = 0; !trap && i < RVT_MAX_TRAP_LISTS; i++) {
+		trap = list_first_entry_or_null(&ibp->rvp.trap_lists[i].list,
+						struct trap_node, list);
 	}
+	spin_unlock_irqrestore(&ibp->rvp.lock, flags);
+
+	if (trap)
+		send_trap(ibp, trap);
+}
+
+static struct trap_node *create_trap_node(u8 type, __be16 trap_num, u32 lid)
+{
+	struct trap_node *trap;
+
+	trap = kzalloc(sizeof(*trap), GFP_ATOMIC);
+	if (!trap)
+		return NULL;
+
+	INIT_LIST_HEAD(&trap->list);
+	trap->data.generic_type = type;
+	trap->data.prod_type_lsb = IB_NOTICE_PROD_CA;
+	trap->data.trap_num = trap_num;
+	trap->data.issuer_lid = cpu_to_be32(lid);
+
+	return trap;
 }
 
 /*
- * Send a bad [PQ]_Key trap (ch. 14.3.8).
+ * Send a bad P_Key trap (ch. 14.3.8).
  */
-void hfi1_bad_pqkey(struct hfi1_ibport *ibp, __be16 trap_num, u32 key, u32 sl,
-		    u32 qp1, u32 qp2, u16 lid1, u16 lid2)
+void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl,
+		   u32 qp1, u32 qp2, u32 lid1, u32 lid2)
 {
-	struct opa_mad_notice_attr data;
+	struct trap_node *trap;
 	u32 lid = ppd_from_ibp(ibp)->lid;
-	u32 _lid1 = lid1;
-	u32 _lid2 = lid2;
-
-	memset(&data, 0, sizeof(data));
 
-	if (trap_num == OPA_TRAP_BAD_P_KEY)
-		ibp->rvp.pkey_violations++;
-	else
-		ibp->rvp.qkey_violations++;
 	ibp->rvp.n_pkt_drops++;
+	ibp->rvp.pkey_violations++;
+
+	trap = create_trap_node(IB_NOTICE_TYPE_SECURITY, OPA_TRAP_BAD_P_KEY,
+				lid);
+	if (!trap)
+		return;
 
 	/* Send violation trap */
-	data.generic_type = IB_NOTICE_TYPE_SECURITY;
-	data.prod_type_lsb = IB_NOTICE_PROD_CA;
-	data.trap_num = trap_num;
-	data.issuer_lid = cpu_to_be32(lid);
-	data.ntc_257_258.lid1 = cpu_to_be32(_lid1);
-	data.ntc_257_258.lid2 = cpu_to_be32(_lid2);
-	data.ntc_257_258.key = cpu_to_be32(key);
-	data.ntc_257_258.sl = sl << 3;
-	data.ntc_257_258.qp1 = cpu_to_be32(qp1);
-	data.ntc_257_258.qp2 = cpu_to_be32(qp2);
-
-	send_trap(ibp, &data, sizeof(data));
+	trap->data.ntc_257_258.lid1 = cpu_to_be32(lid1);
+	trap->data.ntc_257_258.lid2 = cpu_to_be32(lid2);
+	trap->data.ntc_257_258.key = cpu_to_be32(key);
+	trap->data.ntc_257_258.sl = sl << 3;
+	trap->data.ntc_257_258.qp1 = cpu_to_be32(qp1);
+	trap->data.ntc_257_258.qp2 = cpu_to_be32(qp2);
+
+	trap->len = sizeof(trap->data);
+	send_trap(ibp, trap);
 }
 
 /*
@@ -211,34 +470,36 @@ void hfi1_bad_pqkey(struct hfi1_ibport *ibp, __be16 trap_num, u32 key, u32 sl,
 static void bad_mkey(struct hfi1_ibport *ibp, struct ib_mad_hdr *mad,
 		     __be64 mkey, __be32 dr_slid, u8 return_path[], u8 hop_cnt)
 {
-	struct opa_mad_notice_attr data;
+	struct trap_node *trap;
 	u32 lid = ppd_from_ibp(ibp)->lid;
 
-	memset(&data, 0, sizeof(data));
+	trap = create_trap_node(IB_NOTICE_TYPE_SECURITY, OPA_TRAP_BAD_M_KEY,
+				lid);
+	if (!trap)
+		return;
+
 	/* Send violation trap */
-	data.generic_type = IB_NOTICE_TYPE_SECURITY;
-	data.prod_type_lsb = IB_NOTICE_PROD_CA;
-	data.trap_num = OPA_TRAP_BAD_M_KEY;
-	data.issuer_lid = cpu_to_be32(lid);
-	data.ntc_256.lid = data.issuer_lid;
-	data.ntc_256.method = mad->method;
-	data.ntc_256.attr_id = mad->attr_id;
-	data.ntc_256.attr_mod = mad->attr_mod;
-	data.ntc_256.mkey = mkey;
+	trap->data.ntc_256.lid = trap->data.issuer_lid;
+	trap->data.ntc_256.method = mad->method;
+	trap->data.ntc_256.attr_id = mad->attr_id;
+	trap->data.ntc_256.attr_mod = mad->attr_mod;
+	trap->data.ntc_256.mkey = mkey;
 	if (mad->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
-		data.ntc_256.dr_slid = dr_slid;
-		data.ntc_256.dr_trunc_hop = IB_NOTICE_TRAP_DR_NOTICE;
-		if (hop_cnt > ARRAY_SIZE(data.ntc_256.dr_rtn_path)) {
-			data.ntc_256.dr_trunc_hop |=
+		trap->data.ntc_256.dr_slid = dr_slid;
+		trap->data.ntc_256.dr_trunc_hop = IB_NOTICE_TRAP_DR_NOTICE;
+		if (hop_cnt > ARRAY_SIZE(trap->data.ntc_256.dr_rtn_path)) {
+			trap->data.ntc_256.dr_trunc_hop |=
 				IB_NOTICE_TRAP_DR_TRUNC;
-			hop_cnt = ARRAY_SIZE(data.ntc_256.dr_rtn_path);
+			hop_cnt = ARRAY_SIZE(trap->data.ntc_256.dr_rtn_path);
 		}
-		data.ntc_256.dr_trunc_hop |= hop_cnt;
-		memcpy(data.ntc_256.dr_rtn_path, return_path,
+		trap->data.ntc_256.dr_trunc_hop |= hop_cnt;
+		memcpy(trap->data.ntc_256.dr_rtn_path, return_path,
 		       hop_cnt);
 	}
 
-	send_trap(ibp, &data, sizeof(data));
+	trap->len = sizeof(trap->data);
+
+	send_trap(ibp, trap);
 }
 
 /*
@@ -246,22 +507,24 @@ static void bad_mkey(struct hfi1_ibport *ibp, struct ib_mad_hdr *mad,
  */
 void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num)
 {
-	struct opa_mad_notice_attr data;
+	struct trap_node *trap;
 	struct hfi1_ibdev *verbs_dev = dev_from_rdi(rdi);
 	struct hfi1_devdata *dd = dd_from_dev(verbs_dev);
 	struct hfi1_ibport *ibp = &dd->pport[port_num - 1].ibport_data;
 	u32 lid = ppd_from_ibp(ibp)->lid;
 
-	memset(&data, 0, sizeof(data));
+	trap = create_trap_node(IB_NOTICE_TYPE_INFO,
+				OPA_TRAP_CHANGE_CAPABILITY,
+				lid);
+	if (!trap)
+		return;
 
-	data.generic_type = IB_NOTICE_TYPE_INFO;
-	data.prod_type_lsb = IB_NOTICE_PROD_CA;
-	data.trap_num = OPA_TRAP_CHANGE_CAPABILITY;
-	data.issuer_lid = cpu_to_be32(lid);
-	data.ntc_144.lid = data.issuer_lid;
-	data.ntc_144.new_cap_mask = cpu_to_be32(ibp->rvp.port_cap_flags);
+	trap->data.ntc_144.lid = trap->data.issuer_lid;
+	trap->data.ntc_144.new_cap_mask = cpu_to_be32(ibp->rvp.port_cap_flags);
+	trap->data.ntc_144.cap_mask3 = cpu_to_be16(ibp->rvp.port_cap3_flags);
 
-	send_trap(ibp, &data, sizeof(data));
+	trap->len = sizeof(trap->data);
+	send_trap(ibp, trap);
 }
 
 /*
@@ -269,19 +532,19 @@ void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num)
  */
 void hfi1_sys_guid_chg(struct hfi1_ibport *ibp)
 {
-	struct opa_mad_notice_attr data;
+	struct trap_node *trap;
 	u32 lid = ppd_from_ibp(ibp)->lid;
 
-	memset(&data, 0, sizeof(data));
+	trap = create_trap_node(IB_NOTICE_TYPE_INFO, OPA_TRAP_CHANGE_SYSGUID,
+				lid);
+	if (!trap)
+		return;
 
-	data.generic_type = IB_NOTICE_TYPE_INFO;
-	data.prod_type_lsb = IB_NOTICE_PROD_CA;
-	data.trap_num = OPA_TRAP_CHANGE_SYSGUID;
-	data.issuer_lid = cpu_to_be32(lid);
-	data.ntc_145.new_sys_guid = ib_hfi1_sys_image_guid;
-	data.ntc_145.lid = data.issuer_lid;
+	trap->data.ntc_145.new_sys_guid = ib_hfi1_sys_image_guid;
+	trap->data.ntc_145.lid = trap->data.issuer_lid;
 
-	send_trap(ibp, &data, sizeof(data));
+	trap->len = sizeof(trap->data);
+	send_trap(ibp, trap);
 }
 
 /*
@@ -289,29 +552,30 @@ void hfi1_sys_guid_chg(struct hfi1_ibport *ibp)
  */
 void hfi1_node_desc_chg(struct hfi1_ibport *ibp)
 {
-	struct opa_mad_notice_attr data;
+	struct trap_node *trap;
 	u32 lid = ppd_from_ibp(ibp)->lid;
 
-	memset(&data, 0, sizeof(data));
+	trap = create_trap_node(IB_NOTICE_TYPE_INFO,
+				OPA_TRAP_CHANGE_CAPABILITY,
+				lid);
+	if (!trap)
+		return;
 
-	data.generic_type = IB_NOTICE_TYPE_INFO;
-	data.prod_type_lsb = IB_NOTICE_PROD_CA;
-	data.trap_num = OPA_TRAP_CHANGE_CAPABILITY;
-	data.issuer_lid = cpu_to_be32(lid);
-	data.ntc_144.lid = data.issuer_lid;
-	data.ntc_144.change_flags =
+	trap->data.ntc_144.lid = trap->data.issuer_lid;
+	trap->data.ntc_144.change_flags =
 		cpu_to_be16(OPA_NOTICE_TRAP_NODE_DESC_CHG);
 
-	send_trap(ibp, &data, sizeof(data));
+	trap->len = sizeof(trap->data);
+	send_trap(ibp, trap);
 }
 
 static int __subn_get_opa_nodedesc(struct opa_smp *smp, u32 am,
 				   u8 *data, struct ib_device *ibdev,
-				   u8 port, u32 *resp_len)
+				   u8 port, u32 *resp_len, u32 max_len)
 {
 	struct opa_node_description *nd;
 
-	if (am) {
+	if (am || smp_length_check(sizeof(*nd), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -328,7 +592,7 @@ static int __subn_get_opa_nodedesc(struct opa_smp *smp, u32 am,
 
 static int __subn_get_opa_nodeinfo(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct opa_node_info *ni;
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
@@ -338,6 +602,7 @@ static int __subn_get_opa_nodeinfo(struct opa_smp *smp, u32 am, u8 *data,
 
 	/* GUID 0 is illegal */
 	if (am || pidx >= dd->num_pports || ibdev->node_guid == 0 ||
+	    smp_length_check(sizeof(*ni), max_len) ||
 	    get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
@@ -519,7 +784,7 @@ void read_ltp_rtt(struct hfi1_devdata *dd)
 
 static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	int i;
 	struct hfi1_devdata *dd;
@@ -535,7 +800,7 @@ static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	u32 buffer_units;
 	u64 tmp = 0;
 
-	if (num_ports != 1) {
+	if (num_ports != 1 || smp_length_check(sizeof(*pi), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -605,7 +870,7 @@ static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 		ppd->offline_disabled_reason;
 
 	pi->port_states.portphysstate_portstate =
-		(hfi1_ibphys_portstate(ppd) << 4) | state;
+		(driver_pstate(ppd) << 4) | state;
 
 	pi->mkeyprotect_lmc = (ibp->rvp.mkeyprot << 6) | ppd->lmc;
 
@@ -704,13 +969,9 @@ static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	buffer_units |= (dd->vl15_init << 11) & OPA_PI_MASK_BUF_UNIT_VL15_INIT;
 	pi->buffer_units = cpu_to_be32(buffer_units);
 
-	pi->opa_cap_mask = cpu_to_be16(OPA_CAP_MASK3_IsSharedSpaceSupported |
-				       OPA_CAP_MASK3_IsEthOnFabricSupported);
-	/* Driver does not support mcast/collective configuration */
-	pi->opa_cap_mask &=
-		cpu_to_be16(~OPA_CAP_MASK3_IsAddrRangeConfigSupported);
-	pi->collectivemask_multicastmask = ((HFI1_COLLECTIVE_NR & 0x7)
-					    << 3 | (HFI1_MCAST_NR & 0x7));
+	pi->opa_cap_mask = cpu_to_be16(ibp->rvp.port_cap3_flags);
+	pi->collectivemask_multicastmask = ((OPA_COLLECTIVE_NR & 0x7)
+					    << 3 | (OPA_MCAST_NR & 0x7));
 
 	/* HFI supports a replay buffer 128 LTPs in size */
 	pi->replay_depth.buffer = 0x80;
@@ -748,7 +1009,7 @@ static int get_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys)
 
 static int __subn_get_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data,
 				    struct ib_device *ibdev, u8 port,
-				    u32 *resp_len)
+				    u32 *resp_len, u32 max_len)
 {
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	u32 n_blocks_req = OPA_AM_NBLK(am);
@@ -771,6 +1032,11 @@ static int __subn_get_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data,
 
 	size = (n_blocks_req * OPA_PARTITION_TABLE_BLK_SIZE) * sizeof(u16);
 
+	if (smp_length_check(size, max_len)) {
+		smp->status |= IB_SMP_INVALID_FIELD;
+		return reply((struct ib_mad_hdr *)smp);
+	}
+
 	if (start_block + n_blocks_req > n_blocks_avail ||
 	    n_blocks_req > OPA_NUM_PKEY_BLOCKS_PER_SMP) {
 		pr_warn("OPA Get PKey AM Invalid : s 0x%x; req 0x%x; "
@@ -915,8 +1181,8 @@ static int physical_transition_allowed(int old, int new)
 static int port_states_transition_allowed(struct hfi1_pportdata *ppd,
 					  u32 logical_new, u32 physical_new)
 {
-	u32 physical_old = driver_physical_state(ppd);
-	u32 logical_old = driver_logical_state(ppd);
+	u32 physical_old = driver_pstate(ppd);
+	u32 logical_old = driver_lstate(ppd);
 	int ret, logical_allowed, physical_allowed;
 
 	ret = logical_transition_allowed(logical_old, logical_new);
@@ -1074,7 +1340,7 @@ static int set_port_states(struct hfi1_pportdata *ppd, struct opa_smp *smp,
  */
 static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct opa_port_info *pi = (struct opa_port_info *)data;
 	struct ib_event event;
@@ -1083,8 +1349,8 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	struct hfi1_ibport *ibp;
 	u8 clientrereg;
 	unsigned long flags;
-	u32 smlid, opa_lid; /* tmp vars to hold LID values */
-	u16 lid;
+	u32 smlid;
+	u32 lid;
 	u8 ls_old, ls_new, ps_new;
 	u8 vls;
 	u8 msl;
@@ -1095,27 +1361,26 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	int ret, i, invalid = 0, call_set_mtu = 0;
 	int call_link_downgrade_policy = 0;
 
-	if (num_ports != 1) {
+	if (num_ports != 1 ||
+	    smp_length_check(sizeof(*pi), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
-	opa_lid = be32_to_cpu(pi->lid);
-	if (opa_lid & 0xFFFF0000) {
-		pr_warn("OPA_PortInfo lid out of range: %X\n", opa_lid);
+	lid = be32_to_cpu(pi->lid);
+	if (lid & 0xFF000000) {
+		pr_warn("OPA_PortInfo lid out of range: %X\n", lid);
 		smp->status |= IB_SMP_INVALID_FIELD;
 		goto get_only;
 	}
 
-	lid = (u16)(opa_lid & 0x0000FFFF);
 
 	smlid = be32_to_cpu(pi->sm_lid);
-	if (smlid & 0xFFFF0000) {
+	if (smlid & 0xFF000000) {
 		pr_warn("OPA_PortInfo SM lid out of range: %X\n", smlid);
 		smp->status |= IB_SMP_INVALID_FIELD;
 		goto get_only;
 	}
-	smlid &= 0x0000FFFF;
 
 	clientrereg = (pi->clientrereg_subnettimeout &
 			OPA_PI_MASK_CLIENT_REREGISTER);
@@ -1130,12 +1395,16 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	ls_old = driver_lstate(ppd);
 
 	ibp->rvp.mkey = pi->mkey;
-	ibp->rvp.gid_prefix = pi->subnet_prefix;
+	if (ibp->rvp.gid_prefix != pi->subnet_prefix) {
+		ibp->rvp.gid_prefix = pi->subnet_prefix;
+		event.event = IB_EVENT_GID_CHANGE;
+		ib_dispatch_event(&event);
+	}
 	ibp->rvp.mkey_lease_period = be16_to_cpu(pi->mkey_lease_period);
 
 	/* Must be a valid unicast LID address. */
 	if ((lid == 0 && ls_old > IB_PORT_INIT) ||
-	    lid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) {
+	     (hfi1_is_16B_mcast(lid))) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		pr_warn("SubnSet(OPA_PortInfo) lid invalid 0x%x\n",
 			lid);
@@ -1148,6 +1417,16 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 		hfi1_set_lid(ppd, lid, pi->mkeyprotect_lmc & OPA_PI_MASK_LMC);
 		event.event = IB_EVENT_LID_CHANGE;
 		ib_dispatch_event(&event);
+
+		if (HFI1_PORT_GUID_INDEX + 1 < HFI1_GUIDS_PER_PORT) {
+			/* Manufacture GID from LID to support extended
+			 * addresses
+			 */
+			ppd->guids[HFI1_PORT_GUID_INDEX + 1] =
+				be64_to_cpu(OPA_MAKE_ID(lid));
+			event.event = IB_EVENT_GID_CHANGE;
+			ib_dispatch_event(&event);
+		}
 	}
 
 	msl = pi->smsl & OPA_PI_MASK_SMSL;
@@ -1158,7 +1437,7 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 
 	/* Must be a valid unicast LID address. */
 	if ((smlid == 0 && ls_old > IB_PORT_INIT) ||
-	    smlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) {
+	     (hfi1_is_16B_mcast(smlid))) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		pr_warn("SubnSet(OPA_PortInfo) smlid invalid 0x%x\n", smlid);
 	} else if (smlid != ibp->rvp.sm_lid || msl != ibp->rvp.sm_sl) {
@@ -1166,7 +1445,7 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 		spin_lock_irqsave(&ibp->rvp.lock, flags);
 		if (ibp->rvp.sm_ah) {
 			if (smlid != ibp->rvp.sm_lid)
-				rdma_ah_set_dlid(&ibp->rvp.sm_ah->attr, smlid);
+				hfi1_modify_qp0_ah(ibp, ibp->rvp.sm_ah, smlid);
 			if (msl != ibp->rvp.sm_sl)
 				rdma_ah_set_sl(&ibp->rvp.sm_ah->attr, msl);
 		}
@@ -1346,7 +1625,8 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	if (ret)
 		return ret;
 
-	ret = __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len);
+	ret = __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len,
+				      max_len);
 
 	/* restore re-reg bit per o14-12.2.1 */
 	pi->clientrereg_subnettimeout |= clientrereg;
@@ -1363,7 +1643,8 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	return ret;
 
 get_only:
-	return __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_portinfo(smp, am, data, ibdev, port, resp_len,
+				       max_len);
 }
 
 /**
@@ -1424,7 +1705,7 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys)
 
 static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data,
 				    struct ib_device *ibdev, u8 port,
-				    u32 *resp_len)
+				    u32 *resp_len, u32 max_len)
 {
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	u32 n_blocks_sent = OPA_AM_NBLK(am);
@@ -1434,6 +1715,7 @@ static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data,
 	int i;
 	u16 n_blocks_avail;
 	unsigned npkeys = hfi1_get_npkeys(dd);
+	u32 size = 0;
 
 	if (n_blocks_sent == 0) {
 		pr_warn("OPA Get PKey AM Invalid : P = %d; B = 0x%x; N = 0x%x\n",
@@ -1444,6 +1726,13 @@ static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data,
 
 	n_blocks_avail = (u16)(npkeys / OPA_PARTITION_TABLE_BLK_SIZE) + 1;
 
+	size = sizeof(u16) * (n_blocks_sent * OPA_PARTITION_TABLE_BLK_SIZE);
+
+	if (smp_length_check(size, max_len)) {
+		smp->status |= IB_SMP_INVALID_FIELD;
+		return reply((struct ib_mad_hdr *)smp);
+	}
+
 	if (start_block + n_blocks_sent > n_blocks_avail ||
 	    n_blocks_sent > OPA_NUM_PKEY_BLOCKS_PER_SMP) {
 		pr_warn("OPA Set PKey AM Invalid : s 0x%x; req 0x%x; avail 0x%x; blk/smp 0x%lx\n",
@@ -1461,7 +1750,8 @@ static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data,
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
-	return __subn_get_opa_pkeytable(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_pkeytable(smp, am, data, ibdev, port, resp_len,
+					max_len);
 }
 
 #define ILLEGAL_VL 12
@@ -1522,14 +1812,14 @@ static int get_sc2vlt_tables(struct hfi1_devdata *dd, void *data)
 
 static int __subn_get_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
 	u8 *p = data;
 	size_t size = ARRAY_SIZE(ibp->sl_to_sc); /* == 32 */
 	unsigned i;
 
-	if (am) {
+	if (am || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1545,14 +1835,15 @@ static int __subn_get_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_set_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
 	u8 *p = data;
+	size_t size = ARRAY_SIZE(ibp->sl_to_sc);
 	int i;
 	u8 sc;
 
-	if (am) {
+	if (am || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1567,19 +1858,20 @@ static int __subn_set_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data,
 		}
 	}
 
-	return __subn_get_opa_sl_to_sc(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_sl_to_sc(smp, am, data, ibdev, port, resp_len,
+				       max_len);
 }
 
 static int __subn_get_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
 	u8 *p = data;
 	size_t size = ARRAY_SIZE(ibp->sc_to_sl); /* == 32 */
 	unsigned i;
 
-	if (am) {
+	if (am || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1595,13 +1887,14 @@ static int __subn_get_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_set_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
+	size_t size = ARRAY_SIZE(ibp->sc_to_sl);
 	u8 *p = data;
 	int i;
 
-	if (am) {
+	if (am || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1609,19 +1902,20 @@ static int __subn_set_opa_sc_to_sl(struct opa_smp *smp, u32 am, u8 *data,
 	for (i = 0; i < ARRAY_SIZE(ibp->sc_to_sl); i++)
 		ibp->sc_to_sl[i] = *p++;
 
-	return __subn_get_opa_sc_to_sl(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_sc_to_sl(smp, am, data, ibdev, port, resp_len,
+				       max_len);
 }
 
 static int __subn_get_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data,
 				    struct ib_device *ibdev, u8 port,
-				    u32 *resp_len)
+				    u32 *resp_len, u32 max_len)
 {
 	u32 n_blocks = OPA_AM_NBLK(am);
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	void *vp = (void *)data;
 	size_t size = 4 * sizeof(u64);
 
-	if (n_blocks != 1) {
+	if (n_blocks != 1 || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1636,7 +1930,7 @@ static int __subn_get_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_set_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data,
 				    struct ib_device *ibdev, u8 port,
-				    u32 *resp_len)
+				    u32 *resp_len, u32 max_len)
 {
 	u32 n_blocks = OPA_AM_NBLK(am);
 	int async_update = OPA_AM_ASYNC(am);
@@ -1644,8 +1938,15 @@ static int __subn_set_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data,
 	void *vp = (void *)data;
 	struct hfi1_pportdata *ppd;
 	int lstate;
+	/*
+	 * set_sc2vlt_tables writes the information contained in *data
+	 * to four 64-bit registers SendSC2VLt[0-3]. We need to make
+	 * sure *max_len is not greater than the total size of the four
+	 * SendSC2VLt[0-3] registers.
+	 */
+	size_t size = 4 * sizeof(u64);
 
-	if (n_blocks != 1 || async_update) {
+	if (n_blocks != 1 || async_update || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1665,27 +1966,28 @@ static int __subn_set_opa_sc_to_vlt(struct opa_smp *smp, u32 am, u8 *data,
 
 	set_sc2vlt_tables(dd, vp);
 
-	return __subn_get_opa_sc_to_vlt(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_sc_to_vlt(smp, am, data, ibdev, port, resp_len,
+					max_len);
 }
 
 static int __subn_get_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data,
 				     struct ib_device *ibdev, u8 port,
-				     u32 *resp_len)
+				     u32 *resp_len, u32 max_len)
 {
 	u32 n_blocks = OPA_AM_NPORT(am);
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	struct hfi1_pportdata *ppd;
 	void *vp = (void *)data;
-	int size;
+	int size = sizeof(struct sc2vlnt);
 
-	if (n_blocks != 1) {
+	if (n_blocks != 1 || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
 	ppd = dd->pport + (port - 1);
 
-	size = fm_get_table(ppd, FM_TBL_SC2VLNT, vp);
+	fm_get_table(ppd, FM_TBL_SC2VLNT, vp);
 
 	if (resp_len)
 		*resp_len += size;
@@ -1695,15 +1997,16 @@ static int __subn_get_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_set_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data,
 				     struct ib_device *ibdev, u8 port,
-				     u32 *resp_len)
+				     u32 *resp_len, u32 max_len)
 {
 	u32 n_blocks = OPA_AM_NPORT(am);
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	struct hfi1_pportdata *ppd;
 	void *vp = (void *)data;
 	int lstate;
+	int size = sizeof(struct sc2vlnt);
 
-	if (n_blocks != 1) {
+	if (n_blocks != 1 || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1721,12 +2024,12 @@ static int __subn_set_opa_sc_to_vlnt(struct opa_smp *smp, u32 am, u8 *data,
 	fm_set_table(ppd, FM_TBL_SC2VLNT, vp);
 
 	return __subn_get_opa_sc_to_vlnt(smp, am, data, ibdev, port,
-					 resp_len);
+					 resp_len, max_len);
 }
 
 static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data,
 			      struct ib_device *ibdev, u8 port,
-			      u32 *resp_len)
+			      u32 *resp_len, u32 max_len)
 {
 	u32 nports = OPA_AM_NPORT(am);
 	u32 start_of_sm_config = OPA_AM_START_SM_CFG(am);
@@ -1735,7 +2038,7 @@ static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data,
 	struct hfi1_pportdata *ppd;
 	struct opa_port_state_info *psi = (struct opa_port_state_info *)data;
 
-	if (nports != 1) {
+	if (nports != 1 || smp_length_check(sizeof(*psi), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1755,7 +2058,7 @@ static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data,
 		ppd->offline_disabled_reason;
 
 	psi->port_states.portphysstate_portstate =
-		(hfi1_ibphys_portstate(ppd) << 4) | (lstate & 0xf);
+		(driver_pstate(ppd) << 4) | (lstate & 0xf);
 	psi->link_width_downgrade_tx_active =
 		cpu_to_be16(ppd->link_width_downgrade_tx_active);
 	psi->link_width_downgrade_rx_active =
@@ -1768,7 +2071,7 @@ static int __subn_get_opa_psi(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_set_opa_psi(struct opa_smp *smp, u32 am, u8 *data,
 			      struct ib_device *ibdev, u8 port,
-			      u32 *resp_len)
+			      u32 *resp_len, u32 max_len)
 {
 	u32 nports = OPA_AM_NPORT(am);
 	u32 start_of_sm_config = OPA_AM_START_SM_CFG(am);
@@ -1779,7 +2082,7 @@ static int __subn_set_opa_psi(struct opa_smp *smp, u32 am, u8 *data,
 	struct opa_port_state_info *psi = (struct opa_port_state_info *)data;
 	int ret, invalid = 0;
 
-	if (nports != 1) {
+	if (nports != 1 || smp_length_check(sizeof(*psi), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1809,19 +2112,21 @@ static int __subn_set_opa_psi(struct opa_smp *smp, u32 am, u8 *data,
 	if (invalid)
 		smp->status |= IB_SMP_INVALID_FIELD;
 
-	return __subn_get_opa_psi(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_psi(smp, am, data, ibdev, port, resp_len,
+				  max_len);
 }
 
 static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data,
 				     struct ib_device *ibdev, u8 port,
-				     u32 *resp_len)
+				     u32 *resp_len, u32 max_len)
 {
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	u32 addr = OPA_AM_CI_ADDR(am);
 	u32 len = OPA_AM_CI_LEN(am) + 1;
 	int ret;
 
-	if (dd->pport->port_type != PORT_TYPE_QSFP) {
+	if (dd->pport->port_type != PORT_TYPE_QSFP ||
+	    smp_length_check(len, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1864,21 +2169,22 @@ static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data,
 }
 
 static int __subn_get_opa_bct(struct opa_smp *smp, u32 am, u8 *data,
-			      struct ib_device *ibdev, u8 port, u32 *resp_len)
+			      struct ib_device *ibdev, u8 port, u32 *resp_len,
+			      u32 max_len)
 {
 	u32 num_ports = OPA_AM_NPORT(am);
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	struct hfi1_pportdata *ppd;
 	struct buffer_control *p = (struct buffer_control *)data;
-	int size;
+	int size = sizeof(struct buffer_control);
 
-	if (num_ports != 1) {
+	if (num_ports != 1 || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
 	ppd = dd->pport + (port - 1);
-	size = fm_get_table(ppd, FM_TBL_BUFFER_CONTROL, p);
+	fm_get_table(ppd, FM_TBL_BUFFER_CONTROL, p);
 	trace_bct_get(dd, p);
 	if (resp_len)
 		*resp_len += size;
@@ -1887,14 +2193,15 @@ static int __subn_get_opa_bct(struct opa_smp *smp, u32 am, u8 *data,
 }
 
 static int __subn_set_opa_bct(struct opa_smp *smp, u32 am, u8 *data,
-			      struct ib_device *ibdev, u8 port, u32 *resp_len)
+			      struct ib_device *ibdev, u8 port, u32 *resp_len,
+			      u32 max_len)
 {
 	u32 num_ports = OPA_AM_NPORT(am);
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	struct hfi1_pportdata *ppd;
 	struct buffer_control *p = (struct buffer_control *)data;
 
-	if (num_ports != 1) {
+	if (num_ports != 1 || smp_length_check(sizeof(*p), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1905,41 +2212,43 @@ static int __subn_set_opa_bct(struct opa_smp *smp, u32 am, u8 *data,
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
-	return __subn_get_opa_bct(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_bct(smp, am, data, ibdev, port, resp_len,
+				  max_len);
 }
 
 static int __subn_get_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data,
 				 struct ib_device *ibdev, u8 port,
-				 u32 *resp_len)
+				 u32 *resp_len, u32 max_len)
 {
 	struct hfi1_pportdata *ppd = ppd_from_ibp(to_iport(ibdev, port));
 	u32 num_ports = OPA_AM_NPORT(am);
 	u8 section = (am & 0x00ff0000) >> 16;
 	u8 *p = data;
-	int size = 0;
+	int size = 256;
 
-	if (num_ports != 1) {
+	if (num_ports != 1 || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
 	switch (section) {
 	case OPA_VLARB_LOW_ELEMENTS:
-		size = fm_get_table(ppd, FM_TBL_VL_LOW_ARB, p);
+		fm_get_table(ppd, FM_TBL_VL_LOW_ARB, p);
 		break;
 	case OPA_VLARB_HIGH_ELEMENTS:
-		size = fm_get_table(ppd, FM_TBL_VL_HIGH_ARB, p);
+		fm_get_table(ppd, FM_TBL_VL_HIGH_ARB, p);
 		break;
 	case OPA_VLARB_PREEMPT_ELEMENTS:
-		size = fm_get_table(ppd, FM_TBL_VL_PREEMPT_ELEMS, p);
+		fm_get_table(ppd, FM_TBL_VL_PREEMPT_ELEMS, p);
 		break;
 	case OPA_VLARB_PREEMPT_MATRIX:
-		size = fm_get_table(ppd, FM_TBL_VL_PREEMPT_MATRIX, p);
+		fm_get_table(ppd, FM_TBL_VL_PREEMPT_MATRIX, p);
 		break;
 	default:
 		pr_warn("OPA SubnGet(VL Arb) AM Invalid : 0x%x\n",
 			be32_to_cpu(smp->attr_mod));
 		smp->status |= IB_SMP_INVALID_FIELD;
+		size = 0;
 		break;
 	}
 
@@ -1951,14 +2260,15 @@ static int __subn_get_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_set_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data,
 				 struct ib_device *ibdev, u8 port,
-				 u32 *resp_len)
+				 u32 *resp_len, u32 max_len)
 {
 	struct hfi1_pportdata *ppd = ppd_from_ibp(to_iport(ibdev, port));
 	u32 num_ports = OPA_AM_NPORT(am);
 	u8 section = (am & 0x00ff0000) >> 16;
 	u8 *p = data;
+	int size = 256;
 
-	if (num_ports != 1) {
+	if (num_ports != 1 || smp_length_check(size, max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -1986,7 +2296,8 @@ static int __subn_set_opa_vl_arb(struct opa_smp *smp, u32 am, u8 *data,
 		break;
 	}
 
-	return __subn_get_opa_vl_arb(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_vl_arb(smp, am, data, ibdev, port, resp_len,
+				     max_len);
 }
 
 struct opa_pma_mad {
@@ -3282,13 +3593,18 @@ struct opa_congestion_info_attr {
 
 static int __subn_get_opa_cong_info(struct opa_smp *smp, u32 am, u8 *data,
 				    struct ib_device *ibdev, u8 port,
-				    u32 *resp_len)
+				    u32 *resp_len, u32 max_len)
 {
 	struct opa_congestion_info_attr *p =
 		(struct opa_congestion_info_attr *)data;
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 
+	if (smp_length_check(sizeof(*p), max_len)) {
+		smp->status |= IB_SMP_INVALID_FIELD;
+		return reply((struct ib_mad_hdr *)smp);
+	}
+
 	p->congestion_info = 0;
 	p->control_table_cap = ppd->cc_max_table_entries;
 	p->congestion_log_length = OPA_CONG_LOG_ELEMS;
@@ -3301,7 +3617,7 @@ static int __subn_get_opa_cong_info(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_get_opa_cong_setting(struct opa_smp *smp, u32 am,
 				       u8 *data, struct ib_device *ibdev,
-				       u8 port, u32 *resp_len)
+				       u8 port, u32 *resp_len, u32 max_len)
 {
 	int i;
 	struct opa_congestion_setting_attr *p =
@@ -3311,6 +3627,11 @@ static int __subn_get_opa_cong_setting(struct opa_smp *smp, u32 am,
 	struct opa_congestion_setting_entry_shadow *entries;
 	struct cc_state *cc_state;
 
+	if (smp_length_check(sizeof(*p), max_len)) {
+		smp->status |= IB_SMP_INVALID_FIELD;
+		return reply((struct ib_mad_hdr *)smp);
+	}
+
 	rcu_read_lock();
 
 	cc_state = get_cc_state(ppd);
@@ -3385,7 +3706,7 @@ static void apply_cc_state(struct hfi1_pportdata *ppd)
 
 static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
 				       struct ib_device *ibdev, u8 port,
-				       u32 *resp_len)
+				       u32 *resp_len, u32 max_len)
 {
 	struct opa_congestion_setting_attr *p =
 		(struct opa_congestion_setting_attr *)data;
@@ -3394,6 +3715,11 @@ static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
 	struct opa_congestion_setting_entry_shadow *entries;
 	int i;
 
+	if (smp_length_check(sizeof(*p), max_len)) {
+		smp->status |= IB_SMP_INVALID_FIELD;
+		return reply((struct ib_mad_hdr *)smp);
+	}
+
 	/*
 	 * Save details from packet into the ppd.  Hold the cc_state_lock so
 	 * our information is consistent with anyone trying to apply the state.
@@ -3415,12 +3741,12 @@ static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
 	apply_cc_state(ppd);
 
 	return __subn_get_opa_cong_setting(smp, am, data, ibdev, port,
-					   resp_len);
+					   resp_len, max_len);
 }
 
 static int __subn_get_opa_hfi1_cong_log(struct opa_smp *smp, u32 am,
 					u8 *data, struct ib_device *ibdev,
-					u8 port, u32 *resp_len)
+					u8 port, u32 *resp_len, u32 max_len)
 {
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
@@ -3428,7 +3754,7 @@ static int __subn_get_opa_hfi1_cong_log(struct opa_smp *smp, u32 am,
 	s64 ts;
 	int i;
 
-	if (am != 0) {
+	if (am || smp_length_check(sizeof(*cong_log), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -3486,7 +3812,7 @@ static int __subn_get_opa_hfi1_cong_log(struct opa_smp *smp, u32 am,
 
 static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct ib_cc_table_attr *cc_table_attr =
 		(struct ib_cc_table_attr *)data;
@@ -3498,9 +3824,10 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
 	int i, j;
 	u32 sentry, eentry;
 	struct cc_state *cc_state;
+	u32 size = sizeof(u16) * (IB_CCT_ENTRIES * n_blocks + 1);
 
 	/* sanity check n_blocks, start_block */
-	if (n_blocks == 0 ||
+	if (n_blocks == 0 || smp_length_check(size, max_len) ||
 	    start_block + n_blocks > ppd->cc_max_table_entries) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
@@ -3530,14 +3857,14 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
 	rcu_read_unlock();
 
 	if (resp_len)
-		*resp_len += sizeof(u16) * (IB_CCT_ENTRIES * n_blocks + 1);
+		*resp_len += size;
 
 	return reply((struct ib_mad_hdr *)smp);
 }
 
 static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct ib_cc_table_attr *p = (struct ib_cc_table_attr *)data;
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
@@ -3548,9 +3875,10 @@ static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
 	int i, j;
 	u32 sentry, eentry;
 	u16 ccti_limit;
+	u32 size = sizeof(u16) * (IB_CCT_ENTRIES * n_blocks + 1);
 
 	/* sanity check n_blocks, start_block */
-	if (n_blocks == 0 ||
+	if (n_blocks == 0 || smp_length_check(size, max_len) ||
 	    start_block + n_blocks > ppd->cc_max_table_entries) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
@@ -3581,7 +3909,8 @@ static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
 	/* now apply the information */
 	apply_cc_state(ppd);
 
-	return __subn_get_opa_cc_table(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_cc_table(smp, am, data, ibdev, port, resp_len,
+				       max_len);
 }
 
 struct opa_led_info {
@@ -3594,7 +3923,7 @@ struct opa_led_info {
 
 static int __subn_get_opa_led_info(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	struct hfi1_pportdata *ppd = dd->pport;
@@ -3602,7 +3931,7 @@ static int __subn_get_opa_led_info(struct opa_smp *smp, u32 am, u8 *data,
 	u32 nport = OPA_AM_NPORT(am);
 	u32 is_beaconing_active;
 
-	if (nport != 1) {
+	if (nport != 1 || smp_length_check(sizeof(*p), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -3624,14 +3953,14 @@ static int __subn_get_opa_led_info(struct opa_smp *smp, u32 am, u8 *data,
 
 static int __subn_set_opa_led_info(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
-				   u32 *resp_len)
+				   u32 *resp_len, u32 max_len)
 {
 	struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
 	struct opa_led_info *p = (struct opa_led_info *)data;
 	u32 nport = OPA_AM_NPORT(am);
 	int on = !!(be32_to_cpu(p->rsvd_led_mask) & OPA_LED_MASK);
 
-	if (nport != 1) {
+	if (nport != 1 || smp_length_check(sizeof(*p), max_len)) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
@@ -3641,12 +3970,13 @@ static int __subn_set_opa_led_info(struct opa_smp *smp, u32 am, u8 *data,
 	else
 		shutdown_led_override(dd->pport);
 
-	return __subn_get_opa_led_info(smp, am, data, ibdev, port, resp_len);
+	return __subn_get_opa_led_info(smp, am, data, ibdev, port, resp_len,
+				       max_len);
 }
 
 static int subn_get_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am,
 			    u8 *data, struct ib_device *ibdev, u8 port,
-			    u32 *resp_len)
+			    u32 *resp_len, u32 max_len)
 {
 	int ret;
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
@@ -3654,71 +3984,71 @@ static int subn_get_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am,
 	switch (attr_id) {
 	case IB_SMP_ATTR_NODE_DESC:
 		ret = __subn_get_opa_nodedesc(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_NODE_INFO:
 		ret = __subn_get_opa_nodeinfo(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_PORT_INFO:
 		ret = __subn_get_opa_portinfo(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_PKEY_TABLE:
 		ret = __subn_get_opa_pkeytable(smp, am, data, ibdev, port,
-					       resp_len);
+					       resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SL_TO_SC_MAP:
 		ret = __subn_get_opa_sl_to_sc(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SC_TO_SL_MAP:
 		ret = __subn_get_opa_sc_to_sl(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SC_TO_VLT_MAP:
 		ret = __subn_get_opa_sc_to_vlt(smp, am, data, ibdev, port,
-					       resp_len);
+					       resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SC_TO_VLNT_MAP:
 		ret = __subn_get_opa_sc_to_vlnt(smp, am, data, ibdev, port,
-						resp_len);
+						resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_PORT_STATE_INFO:
 		ret = __subn_get_opa_psi(smp, am, data, ibdev, port,
-					 resp_len);
+					 resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_BUFFER_CONTROL_TABLE:
 		ret = __subn_get_opa_bct(smp, am, data, ibdev, port,
-					 resp_len);
+					 resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_CABLE_INFO:
 		ret = __subn_get_opa_cable_info(smp, am, data, ibdev, port,
-						resp_len);
+						resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_VL_ARB_TABLE:
 		ret = __subn_get_opa_vl_arb(smp, am, data, ibdev, port,
-					    resp_len);
+					    resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_CONGESTION_INFO:
 		ret = __subn_get_opa_cong_info(smp, am, data, ibdev, port,
-					       resp_len);
+					       resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_HFI_CONGESTION_SETTING:
 		ret = __subn_get_opa_cong_setting(smp, am, data, ibdev,
-						  port, resp_len);
+						  port, resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_HFI_CONGESTION_LOG:
 		ret = __subn_get_opa_hfi1_cong_log(smp, am, data, ibdev,
-						   port, resp_len);
+						   port, resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_CONGESTION_CONTROL_TABLE:
 		ret = __subn_get_opa_cc_table(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_LED_INFO:
 		ret = __subn_get_opa_led_info(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_SM_INFO:
 		if (ibp->rvp.port_cap_flags & IB_PORT_SM_DISABLED)
@@ -3736,7 +4066,7 @@ static int subn_get_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am,
 
 static int subn_set_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am,
 			    u8 *data, struct ib_device *ibdev, u8 port,
-			    u32 *resp_len)
+			    u32 *resp_len, u32 max_len)
 {
 	int ret;
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
@@ -3744,51 +4074,51 @@ static int subn_set_opa_sma(__be16 attr_id, struct opa_smp *smp, u32 am,
 	switch (attr_id) {
 	case IB_SMP_ATTR_PORT_INFO:
 		ret = __subn_set_opa_portinfo(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_PKEY_TABLE:
 		ret = __subn_set_opa_pkeytable(smp, am, data, ibdev, port,
-					       resp_len);
+					       resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SL_TO_SC_MAP:
 		ret = __subn_set_opa_sl_to_sc(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SC_TO_SL_MAP:
 		ret = __subn_set_opa_sc_to_sl(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SC_TO_VLT_MAP:
 		ret = __subn_set_opa_sc_to_vlt(smp, am, data, ibdev, port,
-					       resp_len);
+					       resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_SC_TO_VLNT_MAP:
 		ret = __subn_set_opa_sc_to_vlnt(smp, am, data, ibdev, port,
-						resp_len);
+						resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_PORT_STATE_INFO:
 		ret = __subn_set_opa_psi(smp, am, data, ibdev, port,
-					 resp_len);
+					 resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_BUFFER_CONTROL_TABLE:
 		ret = __subn_set_opa_bct(smp, am, data, ibdev, port,
-					 resp_len);
+					 resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_VL_ARB_TABLE:
 		ret = __subn_set_opa_vl_arb(smp, am, data, ibdev, port,
-					    resp_len);
+					    resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_HFI_CONGESTION_SETTING:
 		ret = __subn_set_opa_cong_setting(smp, am, data, ibdev,
-						  port, resp_len);
+						  port, resp_len, max_len);
 		break;
 	case OPA_ATTRIB_ID_CONGESTION_CONTROL_TABLE:
 		ret = __subn_set_opa_cc_table(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_LED_INFO:
 		ret = __subn_set_opa_led_info(smp, am, data, ibdev, port,
-					      resp_len);
+					      resp_len, max_len);
 		break;
 	case IB_SMP_ATTR_SM_INFO:
 		if (ibp->rvp.port_cap_flags & IB_PORT_SM_DISABLED)
@@ -3844,7 +4174,10 @@ static int subn_get_opa_aggregate(struct opa_smp *smp,
 		memset(next_smp + sizeof(*agg), 0, agg_data_len);
 
 		(void)subn_get_opa_sma(agg->attr_id, smp, am, agg->data,
-					ibdev, port, NULL);
+				       ibdev, port, NULL, (u32)agg_data_len);
+
+		if (smp->status & IB_SMP_INVALID_FIELD)
+			break;
 		if (smp->status & ~IB_SMP_DIRECTION) {
 			set_aggr_error(agg);
 			return reply((struct ib_mad_hdr *)smp);
@@ -3887,7 +4220,9 @@ static int subn_set_opa_aggregate(struct opa_smp *smp,
 		}
 
 		(void)subn_set_opa_sma(agg->attr_id, smp, am, agg->data,
-					ibdev, port, NULL);
+				       ibdev, port, NULL, (u32)agg_data_len);
+		if (smp->status & IB_SMP_INVALID_FIELD)
+			break;
 		if (smp->status & ~IB_SMP_DIRECTION) {
 			set_aggr_error(agg);
 			return reply((struct ib_mad_hdr *)smp);
@@ -3958,7 +4293,7 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp,
 			       const struct ib_wc *in_wc)
 {
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	u16 slid = in_wc->slid;
+	u16 slid = ib_lid_cpu16(in_wc->slid);
 	u16 pkey;
 
 	if (in_wc->pkey_index >= ARRAY_SIZE(ppd->pkeys))
@@ -3997,12 +4332,13 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags,
 	struct opa_smp *smp = (struct opa_smp *)out_mad;
 	struct hfi1_ibport *ibp = to_iport(ibdev, port);
 	u8 *data;
-	u32 am;
+	u32 am, data_size;
 	__be16 attr_id;
 	int ret;
 
 	*out_mad = *in_mad;
 	data = opa_get_smp_data(smp);
+	data_size = (u32)opa_get_smp_data_size(smp);
 
 	am = be32_to_cpu(smp->attr_mod);
 	attr_id = smp->attr_id;
@@ -4046,7 +4382,8 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags,
 		default:
 			clear_opa_smp_data(smp);
 			ret = subn_get_opa_sma(attr_id, smp, am, data,
-					       ibdev, port, resp_len);
+					       ibdev, port, resp_len,
+					       data_size);
 			break;
 		case OPA_ATTRIB_ID_AGGREGATE:
 			ret = subn_get_opa_aggregate(smp, ibdev, port,
@@ -4058,7 +4395,8 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags,
 		switch (attr_id) {
 		default:
 			ret = subn_set_opa_sma(attr_id, smp, am, data,
-					       ibdev, port, resp_len);
+					       ibdev, port, resp_len,
+					       data_size);
 			break;
 		case OPA_ATTRIB_ID_AGGREGATE:
 			ret = subn_set_opa_aggregate(smp, ibdev, port,
@@ -4077,6 +4415,11 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags,
 		 */
 		ret = IB_MAD_RESULT_SUCCESS;
 		break;
+	case IB_MGMT_METHOD_TRAP_REPRESS:
+		subn_handle_opa_trap_repress(ibp, smp);
+		/* Always successful */
+		ret = IB_MAD_RESULT_SUCCESS;
+		break;
 	default:
 		smp->status |= IB_SMP_UNSUP_METHOD;
 		ret = reply((struct ib_mad_hdr *)smp);
diff --git a/drivers/infiniband/hw/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h
index 5aa3fd1be653..4c1245072093 100644
--- a/drivers/infiniband/hw/hfi1/mad.h
+++ b/drivers/infiniband/hw/hfi1/mad.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -115,7 +115,7 @@ struct opa_mad_notice_attr {
 			__be32	lid;		/* LID where change occurred */
 			__be32	new_cap_mask;	/* new capability mask */
 			__be16	reserved2;
-			__be16	cap_mask;
+			__be16	cap_mask3;
 			__be16	change_flags;	/* low 4 bits only */
 		} __packed ntc_144;
 
@@ -428,5 +428,6 @@ struct sc2vlnt {
 		    COUNTER_MASK(1, 4))
 
 void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port);
+void hfi1_handle_trap_timer(unsigned long data);
 
 #endif				/* _HFI1_MAD_H */
diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
index ccbf52c8ff6f..175002c046ed 100644
--- a/drivers/infiniband/hw/hfi1/mmu_rb.c
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 Intel Corporation.
+ * Copyright(c) 2016 - 2017 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.
@@ -54,7 +54,7 @@
 
 struct mmu_rb_handler {
 	struct mmu_notifier mn;
-	struct rb_root root;
+	struct rb_root_cached root;
 	void *ops_arg;
 	spinlock_t lock;        /* protect the RB tree */
 	struct mmu_rb_ops *ops;
@@ -67,8 +67,6 @@ struct mmu_rb_handler {
 
 static unsigned long mmu_node_start(struct mmu_rb_node *);
 static unsigned long mmu_node_last(struct mmu_rb_node *);
-static inline void mmu_notifier_page(struct mmu_notifier *, struct mm_struct *,
-				     unsigned long);
 static inline void mmu_notifier_range_start(struct mmu_notifier *,
 					    struct mm_struct *,
 					    unsigned long, unsigned long);
@@ -82,7 +80,6 @@ static void do_remove(struct mmu_rb_handler *handler,
 static void handle_remove(struct work_struct *work);
 
 static const struct mmu_notifier_ops mn_opts = {
-	.invalidate_page = mmu_notifier_page,
 	.invalidate_range_start = mmu_notifier_range_start,
 };
 
@@ -111,7 +108,7 @@ int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm,
 	if (!handlr)
 		return -ENOMEM;
 
-	handlr->root = RB_ROOT;
+	handlr->root = RB_ROOT_CACHED;
 	handlr->ops = ops;
 	handlr->ops_arg = ops_arg;
 	INIT_HLIST_NODE(&handlr->mn.hlist);
@@ -152,9 +149,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler)
 	INIT_LIST_HEAD(&del_list);
 
 	spin_lock_irqsave(&handler->lock, flags);
-	while ((node = rb_first(&handler->root))) {
+	while ((node = rb_first_cached(&handler->root))) {
 		rbnode = rb_entry(node, struct mmu_rb_node, node);
-		rb_erase(node, &handler->root);
+		rb_erase_cached(node, &handler->root);
 		/* move from LRU list to delete list */
 		list_move(&rbnode->list, &del_list);
 	}
@@ -172,9 +169,8 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler,
 	unsigned long flags;
 	int ret = 0;
 
+	trace_hfi1_mmu_rb_insert(mnode->addr, mnode->len);
 	spin_lock_irqsave(&handler->lock, flags);
-	hfi1_cdbg(MMU, "Inserting node addr 0x%llx, len %u", mnode->addr,
-		  mnode->len);
 	node = __mmu_rb_search(handler, mnode->addr, mnode->len);
 	if (node) {
 		ret = -EINVAL;
@@ -200,7 +196,7 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler,
 {
 	struct mmu_rb_node *node = NULL;
 
-	hfi1_cdbg(MMU, "Searching for addr 0x%llx, len %u", addr, len);
+	trace_hfi1_mmu_rb_search(addr, len);
 	if (!handler->ops->filter) {
 		node = __mmu_int_rb_iter_first(&handler->root, addr,
 					       (addr + len) - 1);
@@ -217,21 +213,27 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler,
 	return node;
 }
 
-struct mmu_rb_node *hfi1_mmu_rb_extract(struct mmu_rb_handler *handler,
-					unsigned long addr, unsigned long len)
+bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler,
+				     unsigned long addr, unsigned long len,
+				     struct mmu_rb_node **rb_node)
 {
 	struct mmu_rb_node *node;
 	unsigned long flags;
+	bool ret = false;
 
 	spin_lock_irqsave(&handler->lock, flags);
 	node = __mmu_rb_search(handler, addr, len);
 	if (node) {
+		if (node->addr == addr && node->len == len)
+			goto unlock;
 		__mmu_int_rb_remove(node, &handler->root);
 		list_del(&node->list); /* remove from LRU list */
+		ret = true;
 	}
+unlock:
 	spin_unlock_irqrestore(&handler->lock, flags);
-
-	return node;
+	*rb_node = node;
+	return ret;
 }
 
 void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg)
@@ -275,8 +277,7 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler,
 	unsigned long flags;
 
 	/* Validity of handler and node pointers has been checked by caller. */
-	hfi1_cdbg(MMU, "Removing node addr 0x%llx, len %u", node->addr,
-		  node->len);
+	trace_hfi1_mmu_rb_remove(node->addr, node->len);
 	spin_lock_irqsave(&handler->lock, flags);
 	__mmu_int_rb_remove(node, &handler->root);
 	list_del(&node->list); /* remove from LRU list */
@@ -285,12 +286,6 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler,
 	handler->ops->remove(handler->ops_arg, node);
 }
 
-static inline void mmu_notifier_page(struct mmu_notifier *mn,
-				     struct mm_struct *mm, unsigned long addr)
-{
-	mmu_notifier_mem_invalidate(mn, mm, addr, addr + PAGE_SIZE);
-}
-
 static inline void mmu_notifier_range_start(struct mmu_notifier *mn,
 					    struct mm_struct *mm,
 					    unsigned long start,
@@ -305,7 +300,7 @@ static void mmu_notifier_mem_invalidate(struct mmu_notifier *mn,
 {
 	struct mmu_rb_handler *handler =
 		container_of(mn, struct mmu_rb_handler, mn);
-	struct rb_root *root = &handler->root;
+	struct rb_root_cached *root = &handler->root;
 	struct mmu_rb_node *node, *ptr = NULL;
 	unsigned long flags;
 	bool added = false;
@@ -315,8 +310,7 @@ static void mmu_notifier_mem_invalidate(struct mmu_notifier *mn,
 	     node; node = ptr) {
 		/* Guard against node removal. */
 		ptr = __mmu_int_rb_iter_next(node, start, end - 1);
-		hfi1_cdbg(MMU, "Invalidating node addr 0x%llx, len %u",
-			  node->addr, node->len);
+		trace_hfi1_mmu_mem_invalidate(node->addr, node->len);
 		if (handler->ops->invalidate(handler->ops_arg, node)) {
 			__mmu_int_rb_remove(node, root);
 			/* move from LRU list to delete list */
diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h
index 754f6ebf13fb..f04cec1e99d1 100644
--- a/drivers/infiniband/hw/hfi1/mmu_rb.h
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.h
@@ -81,7 +81,8 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler,
 void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg);
 void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler,
 			struct mmu_rb_node *mnode);
-struct mmu_rb_node *hfi1_mmu_rb_extract(struct mmu_rb_handler *handler,
-					unsigned long addr, unsigned long len);
+bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler,
+				     unsigned long addr, unsigned long len,
+				     struct mmu_rb_node **rb_node);
 
 #endif /* _HFI1_MMU_RB_H */
diff --git a/drivers/infiniband/hw/hfi1/opa_compat.h b/drivers/infiniband/hw/hfi1/opa_compat.h
index 6ef3c1cbdcd7..774215b95df5 100644
--- a/drivers/infiniband/hw/hfi1/opa_compat.h
+++ b/drivers/infiniband/hw/hfi1/opa_compat.h
@@ -84,7 +84,8 @@ static inline u8 port_states_to_phys_state(struct opa_port_states *ps)
 /*
  * OPA port physical states
  * IB Volume 1, Table 146 PortInfo/IB Volume 2 Section 5.4.2(1) PortPhysState
- * values.
+ * values are the same in OmniPath Architecture. OPA leverages some of the same
+ * concepts as InfiniBand, but has a few other states as well.
  *
  * When writing, only values 0-3 are valid, other values are ignored.
  * When reading, 0 is reserved.
@@ -92,6 +93,8 @@ static inline u8 port_states_to_phys_state(struct opa_port_states *ps)
  * Returned by the ibphys_portstate() routine.
  */
 enum opa_port_phys_state {
+	/* Values 0-7 have the same meaning in OPA as in InfiniBand. */
+
 	IB_PORTPHYSSTATE_NOP = 0,
 	/* 1 is reserved */
 	IB_PORTPHYSSTATE_POLLING = 2,
@@ -101,9 +104,23 @@ enum opa_port_phys_state {
 	IB_PORTPHYSSTATE_LINK_ERROR_RECOVERY = 6,
 	IB_PORTPHYSSTATE_PHY_TEST = 7,
 	/* 8 is reserved */
+
+	/*
+	 * Offline: Port is quiet (transmitters disabled) due to lack of
+	 * physical media, unsupported media, or transition between link up
+	 * and next link up attempt
+	 */
 	OPA_PORTPHYSSTATE_OFFLINE = 9,
-	OPA_PORTPHYSSTATE_GANGED = 10,
+
+	/* 10 is reserved */
+
+	/*
+	 * Phy_Test: Specific test patterns are transmitted, and receiver BER
+	 * can be monitored. This facilitates signal integrity testing for the
+	 * physical layer of the port.
+	 */
 	OPA_PORTPHYSSTATE_TEST = 11,
+
 	OPA_PORTPHYSSTATE_MAX = 11,
 	/* values 12-15 are reserved/ignored */
 };
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 6a9f6f9819e1..82447b7cdda1 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -68,7 +68,7 @@
 /*
  * Code to adjust PCIe capabilities.
  */
-static void tune_pcie_caps(struct hfi1_devdata *);
+static int tune_pcie_caps(struct hfi1_devdata *);
 
 /*
  * Do all the common PCIe setup and initialization.
@@ -161,6 +161,7 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
 {
 	unsigned long len;
 	resource_size_t addr;
+	int ret = 0;
 
 	dd->pcidev = pdev;
 	pci_set_drvdata(pdev, dd);
@@ -179,47 +180,54 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
 		return -EINVAL;
 	}
 
-	dd->kregbase = ioremap_nocache(addr, TXE_PIO_SEND);
-	if (!dd->kregbase)
+	dd->kregbase1 = ioremap_nocache(addr, RCV_ARRAY);
+	if (!dd->kregbase1) {
+		dd_dev_err(dd, "UC mapping of kregbase1 failed\n");
 		return -ENOMEM;
+	}
+	dd_dev_info(dd, "UC base1: %p for %x\n", dd->kregbase1, RCV_ARRAY);
+	dd->chip_rcv_array_count = readq(dd->kregbase1 + RCV_ARRAY_CNT);
+	dd_dev_info(dd, "RcvArray count: %u\n", dd->chip_rcv_array_count);
+	dd->base2_start  = RCV_ARRAY + dd->chip_rcv_array_count * 8;
+
+	dd->kregbase2 = ioremap_nocache(
+		addr + dd->base2_start,
+		TXE_PIO_SEND - dd->base2_start);
+	if (!dd->kregbase2) {
+		dd_dev_err(dd, "UC mapping of kregbase2 failed\n");
+		goto nomem;
+	}
+	dd_dev_info(dd, "UC base2: %p for %x\n", dd->kregbase2,
+		    TXE_PIO_SEND - dd->base2_start);
 
 	dd->piobase = ioremap_wc(addr + TXE_PIO_SEND, TXE_PIO_SIZE);
 	if (!dd->piobase) {
-		iounmap(dd->kregbase);
-		return -ENOMEM;
+		dd_dev_err(dd, "WC mapping of send buffers failed\n");
+		goto nomem;
 	}
+	dd_dev_info(dd, "WC piobase: %p\n for %x", dd->piobase, TXE_PIO_SIZE);
 
-	dd->flags |= HFI1_PRESENT;	/* now register routines work */
-
-	dd->kregend = dd->kregbase + TXE_PIO_SEND;
 	dd->physaddr = addr;        /* used for io_remap, etc. */
 
 	/*
-	 * Re-map the chip's RcvArray as write-combining to allow us
+	 * Map the chip's RcvArray as write-combining to allow us
 	 * to write an entire cacheline worth of entries in one shot.
-	 * If this re-map fails, just continue - the RcvArray programming
-	 * function will handle both cases.
 	 */
-	dd->chip_rcv_array_count = read_csr(dd, RCV_ARRAY_CNT);
 	dd->rcvarray_wc = ioremap_wc(addr + RCV_ARRAY,
 				     dd->chip_rcv_array_count * 8);
-	dd_dev_info(dd, "WC Remapped RcvArray: %p\n", dd->rcvarray_wc);
-	/*
-	 * Save BARs and command to rewrite after device reset.
-	 */
-	pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0, &dd->pcibar0);
-	pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1, &dd->pcibar1);
-	pci_read_config_dword(dd->pcidev, PCI_ROM_ADDRESS, &dd->pci_rom);
-	pci_read_config_word(dd->pcidev, PCI_COMMAND, &dd->pci_command);
-	pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &dd->pcie_devctl);
-	pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL, &dd->pcie_lnkctl);
-	pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL2,
-				  &dd->pcie_devctl2);
-	pci_read_config_dword(dd->pcidev, PCI_CFG_MSIX0, &dd->pci_msix0);
-	pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, &dd->pci_lnkctl3);
-	pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2);
+	if (!dd->rcvarray_wc) {
+		dd_dev_err(dd, "WC mapping of receive array failed\n");
+		goto nomem;
+	}
+	dd_dev_info(dd, "WC RcvArray: %p for %x\n",
+		    dd->rcvarray_wc, dd->chip_rcv_array_count * 8);
 
+	dd->flags |= HFI1_PRESENT;	/* chip.c CSR routines now work */
 	return 0;
+nomem:
+	ret = -ENOMEM;
+	hfi1_pcie_ddcleanup(dd);
+	return ret;
 }
 
 /*
@@ -229,59 +237,19 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
  */
 void hfi1_pcie_ddcleanup(struct hfi1_devdata *dd)
 {
-	u64 __iomem *base = (void __iomem *)dd->kregbase;
-
 	dd->flags &= ~HFI1_PRESENT;
-	dd->kregbase = NULL;
-	iounmap(base);
+	if (dd->kregbase1)
+		iounmap(dd->kregbase1);
+	dd->kregbase1 = NULL;
+	if (dd->kregbase2)
+		iounmap(dd->kregbase2);
+	dd->kregbase2 = NULL;
 	if (dd->rcvarray_wc)
 		iounmap(dd->rcvarray_wc);
+	dd->rcvarray_wc = NULL;
 	if (dd->piobase)
 		iounmap(dd->piobase);
-}
-
-static void msix_setup(struct hfi1_devdata *dd, int pos, u32 *msixcnt,
-		       struct hfi1_msix_entry *hfi1_msix_entry)
-{
-	int ret;
-	int nvec = *msixcnt;
-	struct msix_entry *msix_entry;
-	int i;
-
-	/*
-	 * We can't pass hfi1_msix_entry array to msix_setup
-	 * so use a dummy msix_entry array and copy the allocated
-	 * irq back to the hfi1_msix_entry array.
-	 */
-	msix_entry = kmalloc_array(nvec, sizeof(*msix_entry), GFP_KERNEL);
-	if (!msix_entry) {
-		ret = -ENOMEM;
-		goto do_intx;
-	}
-
-	for (i = 0; i < nvec; i++)
-		msix_entry[i] = hfi1_msix_entry[i].msix;
-
-	ret = pci_enable_msix_range(dd->pcidev, msix_entry, 1, nvec);
-	if (ret < 0)
-		goto free_msix_entry;
-	nvec = ret;
-
-	for (i = 0; i < nvec; i++)
-		hfi1_msix_entry[i].msix = msix_entry[i];
-
-	kfree(msix_entry);
-	*msixcnt = nvec;
-	return;
-
-free_msix_entry:
-	kfree(msix_entry);
-
-do_intx:
-	dd_dev_err(dd, "pci_enable_msix_range %d vectors failed: %d, falling back to INTx\n",
-		   nvec, ret);
-	*msixcnt = 0;
-	hfi1_enable_intx(dd->pcidev);
+	dd->piobase = NULL;
 }
 
 /* return the PCIe link speed from the given link status */
@@ -314,8 +282,14 @@ static u32 extract_width(u16 linkstat)
 static void update_lbus_info(struct hfi1_devdata *dd)
 {
 	u16 linkstat;
+	int ret;
+
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat);
+	if (ret) {
+		dd_dev_err(dd, "Unable to read from PCI config\n");
+		return;
+	}
 
-	pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat);
 	dd->lbus_width = extract_width(linkstat);
 	dd->lbus_speed = extract_speed(linkstat);
 	snprintf(dd->lbus_info, sizeof(dd->lbus_info),
@@ -330,6 +304,7 @@ int pcie_speeds(struct hfi1_devdata *dd)
 {
 	u32 linkcap;
 	struct pci_dev *parent = dd->pcidev->bus->self;
+	int ret;
 
 	if (!pci_is_pcie(dd->pcidev)) {
 		dd_dev_err(dd, "Can't find PCI Express capability!\n");
@@ -339,7 +314,12 @@ int pcie_speeds(struct hfi1_devdata *dd)
 	/* find if our max speed is Gen3 and parent supports Gen3 speeds */
 	dd->link_gen3_capable = 1;
 
-	pcie_capability_read_dword(dd->pcidev, PCI_EXP_LNKCAP, &linkcap);
+	ret = pcie_capability_read_dword(dd->pcidev, PCI_EXP_LNKCAP, &linkcap);
+	if (ret) {
+		dd_dev_err(dd, "Unable to read from PCI config\n");
+		return ret;
+	}
+
 	if ((linkcap & PCI_EXP_LNKCAP_SLS) != GEN3_SPEED_VECTOR) {
 		dd_dev_info(dd,
 			    "This HFI is not Gen3 capable, max speed 0x%x, need 0x3\n",
@@ -364,49 +344,150 @@ int pcie_speeds(struct hfi1_devdata *dd)
 }
 
 /*
- * Returns in *nent:
- *	- actual number of interrupts allocated
+ * Returns:
+ *	- actual number of interrupts allocated or
  *	- 0 if fell back to INTx.
+ *      - error
  */
-void request_msix(struct hfi1_devdata *dd, u32 *nent,
-		  struct hfi1_msix_entry *entry)
+int request_msix(struct hfi1_devdata *dd, u32 msireq)
 {
-	int pos;
+	int nvec, ret;
 
-	pos = dd->pcidev->msix_cap;
-	if (*nent && pos) {
-		msix_setup(dd, pos, nent, entry);
-		/* did it, either MSI-X or INTx */
-	} else {
-		*nent = 0;
-		hfi1_enable_intx(dd->pcidev);
+	nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq,
+				     PCI_IRQ_MSIX | PCI_IRQ_LEGACY);
+	if (nvec < 0) {
+		dd_dev_err(dd, "pci_alloc_irq_vectors() failed: %d\n", nvec);
+		return nvec;
 	}
 
-	tune_pcie_caps(dd);
+	ret = tune_pcie_caps(dd);
+	if (ret) {
+		dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret);
+		pci_free_irq_vectors(dd->pcidev);
+		return ret;
+	}
+
+	/* check for legacy IRQ */
+	if (nvec == 1 && !dd->pcidev->msix_enabled)
+		return 0;
+
+	return nvec;
 }
 
-void hfi1_enable_intx(struct pci_dev *pdev)
+/* restore command and BARs after a reset has wiped them out */
+int restore_pci_variables(struct hfi1_devdata *dd)
 {
-	/* first, turn on INTx */
-	pci_intx(pdev, 1);
-	/* then turn off MSI-X */
-	pci_disable_msix(pdev);
+	int ret = 0;
+
+	ret = pci_write_config_word(dd->pcidev, PCI_COMMAND, dd->pci_command);
+	if (ret)
+		goto error;
+
+	ret = pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0,
+				     dd->pcibar0);
+	if (ret)
+		goto error;
+
+	ret = pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1,
+				     dd->pcibar1);
+	if (ret)
+		goto error;
+
+	ret = pci_write_config_dword(dd->pcidev, PCI_ROM_ADDRESS, dd->pci_rom);
+	if (ret)
+		goto error;
+
+	ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL,
+					 dd->pcie_devctl);
+	if (ret)
+		goto error;
+
+	ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL,
+					 dd->pcie_lnkctl);
+	if (ret)
+		goto error;
+
+	ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL2,
+					 dd->pcie_devctl2);
+	if (ret)
+		goto error;
+
+	ret = pci_write_config_dword(dd->pcidev, PCI_CFG_MSIX0, dd->pci_msix0);
+	if (ret)
+		goto error;
+
+	ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
+				     dd->pci_lnkctl3);
+	if (ret)
+		goto error;
+
+	ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2);
+	if (ret)
+		goto error;
+
+	return 0;
+
+error:
+	dd_dev_err(dd, "Unable to write to PCI config\n");
+	return ret;
 }
 
-/* restore command and BARs after a reset has wiped them out */
-void restore_pci_variables(struct hfi1_devdata *dd)
+/* Save BARs and command to rewrite after device reset */
+int save_pci_variables(struct hfi1_devdata *dd)
 {
-	pci_write_config_word(dd->pcidev, PCI_COMMAND, dd->pci_command);
-	pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0, dd->pcibar0);
-	pci_write_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1, dd->pcibar1);
-	pci_write_config_dword(dd->pcidev, PCI_ROM_ADDRESS, dd->pci_rom);
-	pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, dd->pcie_devctl);
-	pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL, dd->pcie_lnkctl);
-	pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL2,
-				   dd->pcie_devctl2);
-	pci_write_config_dword(dd->pcidev, PCI_CFG_MSIX0, dd->pci_msix0);
-	pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, dd->pci_lnkctl3);
-	pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2);
+	int ret = 0;
+
+	ret = pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0,
+				    &dd->pcibar0);
+	if (ret)
+		goto error;
+
+	ret = pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1,
+				    &dd->pcibar1);
+	if (ret)
+		goto error;
+
+	ret = pci_read_config_dword(dd->pcidev, PCI_ROM_ADDRESS, &dd->pci_rom);
+	if (ret)
+		goto error;
+
+	ret = pci_read_config_word(dd->pcidev, PCI_COMMAND, &dd->pci_command);
+	if (ret)
+		goto error;
+
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL,
+					&dd->pcie_devctl);
+	if (ret)
+		goto error;
+
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL,
+					&dd->pcie_lnkctl);
+	if (ret)
+		goto error;
+
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL2,
+					&dd->pcie_devctl2);
+	if (ret)
+		goto error;
+
+	ret = pci_read_config_dword(dd->pcidev, PCI_CFG_MSIX0, &dd->pci_msix0);
+	if (ret)
+		goto error;
+
+	ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
+				    &dd->pci_lnkctl3);
+	if (ret)
+		goto error;
+
+	ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2);
+	if (ret)
+		goto error;
+
+	return 0;
+
+error:
+	dd_dev_err(dd, "Unable to read from PCI config\n");
+	return ret;
 }
 
 /*
@@ -421,21 +502,33 @@ uint aspm_mode = ASPM_MODE_DISABLED;
 module_param_named(aspm, aspm_mode, uint, S_IRUGO);
 MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic");
 
-static void tune_pcie_caps(struct hfi1_devdata *dd)
+static int tune_pcie_caps(struct hfi1_devdata *dd)
 {
 	struct pci_dev *parent;
 	u16 rc_mpss, rc_mps, ep_mpss, ep_mps;
 	u16 rc_mrrs, ep_mrrs, max_mrrs, ectl;
+	int ret;
 
 	/*
 	 * Turn on extended tags in DevCtl in case the BIOS has turned it off
 	 * to improve WFR SDMA bandwidth
 	 */
-	pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl);
+	ret = pcie_capability_read_word(dd->pcidev,
+					PCI_EXP_DEVCTL, &ectl);
+	if (ret) {
+		dd_dev_err(dd, "Unable to read from PCI config\n");
+		return ret;
+	}
+
 	if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
 		dd_dev_info(dd, "Enabling PCIe extended tags\n");
 		ectl |= PCI_EXP_DEVCTL_EXT_TAG;
-		pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl);
+		ret = pcie_capability_write_word(dd->pcidev,
+						 PCI_EXP_DEVCTL, ectl);
+		if (ret) {
+			dd_dev_err(dd, "Unable to write to PCI config\n");
+			return ret;
+		}
 	}
 	/* Find out supported and configured values for parent (root) */
 	parent = dd->pcidev->bus->self;
@@ -444,14 +537,14 @@ static void tune_pcie_caps(struct hfi1_devdata *dd)
 	 * access to the upstream component.
 	 */
 	if (!parent)
-		return;
+		return -EINVAL;
 	if (!pci_is_root_bus(parent->bus)) {
 		dd_dev_info(dd, "Parent not root\n");
-		return;
+		return -EINVAL;
 	}
 
 	if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
-		return;
+		return -EINVAL;
 	rc_mpss = parent->pcie_mpss;
 	rc_mps = ffs(pcie_get_mps(parent)) - 8;
 	/* Find out supported and configured values for endpoint (us) */
@@ -497,6 +590,8 @@ static void tune_pcie_caps(struct hfi1_devdata *dd)
 		ep_mrrs = max_mrrs;
 		pcie_set_readrq(dd->pcidev, ep_mrrs);
 	}
+
+	return 0;
 }
 
 /* End of PCIe capability tuning */
@@ -728,6 +823,7 @@ static int load_eq_table(struct hfi1_devdata *dd, const u8 eq[11][3], u8 fs,
 	u32 violation;
 	u32 i;
 	u8 c_minus1, c0, c_plus1;
+	int ret;
 
 	for (i = 0; i < 11; i++) {
 		/* set index */
@@ -739,8 +835,14 @@ static int load_eq_table(struct hfi1_devdata *dd, const u8 eq[11][3], u8 fs,
 		pci_write_config_dword(pdev, PCIE_CFG_REG_PL102,
 				       eq_value(c_minus1, c0, c_plus1));
 		/* check if these coefficients violate EQ rules */
-		pci_read_config_dword(dd->pcidev, PCIE_CFG_REG_PL105,
-				      &violation);
+		ret = pci_read_config_dword(dd->pcidev,
+					    PCIE_CFG_REG_PL105, &violation);
+		if (ret) {
+			dd_dev_err(dd, "Unable to read from PCI config\n");
+			hit_error = 1;
+			break;
+		}
+
 		if (violation
 		    & PCIE_CFG_REG_PL105_GEN3_EQ_VIOLATE_COEF_RULES_SMASK){
 			if (hit_error == 0) {
@@ -1194,7 +1296,13 @@ retry:
 	 * that it is Gen3 capable earlier.
 	 */
 	dd_dev_info(dd, "%s: setting parent target link speed\n", __func__);
-	pcie_capability_read_word(parent, PCI_EXP_LNKCTL2, &lnkctl2);
+	ret = pcie_capability_read_word(parent, PCI_EXP_LNKCTL2, &lnkctl2);
+	if (ret) {
+		dd_dev_err(dd, "Unable to read from PCI config\n");
+		return_error = 1;
+		goto done;
+	}
+
 	dd_dev_info(dd, "%s: ..old link control2: 0x%x\n", __func__,
 		    (u32)lnkctl2);
 	/* only write to parent if target is not as high as ours */
@@ -1203,20 +1311,37 @@ retry:
 		lnkctl2 |= target_vector;
 		dd_dev_info(dd, "%s: ..new link control2: 0x%x\n", __func__,
 			    (u32)lnkctl2);
-		pcie_capability_write_word(parent, PCI_EXP_LNKCTL2, lnkctl2);
+		ret = pcie_capability_write_word(parent,
+						 PCI_EXP_LNKCTL2, lnkctl2);
+		if (ret) {
+			dd_dev_err(dd, "Unable to write to PCI config\n");
+			return_error = 1;
+			goto done;
+		}
 	} else {
 		dd_dev_info(dd, "%s: ..target speed is OK\n", __func__);
 	}
 
 	dd_dev_info(dd, "%s: setting target link speed\n", __func__);
-	pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL2, &lnkctl2);
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKCTL2, &lnkctl2);
+	if (ret) {
+		dd_dev_err(dd, "Unable to read from PCI config\n");
+		return_error = 1;
+		goto done;
+	}
+
 	dd_dev_info(dd, "%s: ..old link control2: 0x%x\n", __func__,
 		    (u32)lnkctl2);
 	lnkctl2 &= ~LNKCTL2_TARGET_LINK_SPEED_MASK;
 	lnkctl2 |= target_vector;
 	dd_dev_info(dd, "%s: ..new link control2: 0x%x\n", __func__,
 		    (u32)lnkctl2);
-	pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL2, lnkctl2);
+	ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_LNKCTL2, lnkctl2);
+	if (ret) {
+		dd_dev_err(dd, "Unable to write to PCI config\n");
+		return_error = 1;
+		goto done;
+	}
 
 	/* step 5h: arm gasket logic */
 	/* hold DC in reset across the SBR */
@@ -1266,7 +1391,14 @@ retry:
 
 	/* restore PCI space registers we know were reset */
 	dd_dev_info(dd, "%s: calling restore_pci_variables\n", __func__);
-	restore_pci_variables(dd);
+	ret = restore_pci_variables(dd);
+	if (ret) {
+		dd_dev_err(dd, "%s: Could not restore PCI variables\n",
+			   __func__);
+		return_error = 1;
+		goto done;
+	}
+
 	/* restore firmware control */
 	write_csr(dd, MISC_CFG_FW_CTRL, fw_ctrl);
 
@@ -1296,7 +1428,13 @@ retry:
 	setextled(dd, 0);
 
 	/* check for any per-lane errors */
-	pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE2, &reg32);
+	ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE2, &reg32);
+	if (ret) {
+		dd_dev_err(dd, "Unable to read from PCI config\n");
+		return_error = 1;
+		goto done;
+	}
+
 	dd_dev_info(dd, "%s: per-lane errors: 0x%x\n", __func__, reg32);
 
 	/* extract status, look for our HFI */
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index ed72b5aca139..7108a4b5e94c 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -1012,7 +1012,7 @@ static void sc_wait_for_packet_egress(struct send_context *sc, int pause)
 				   "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n",
 				   __func__, sc->sw_index,
 				   sc->hw_context, (u32)reg);
-			queue_work(dd->pport->hfi1_wq,
+			queue_work(dd->pport->link_wq,
 				   &dd->pport->link_bounce_work);
 			break;
 		}
@@ -1568,7 +1568,8 @@ static void sc_piobufavail(struct send_context *sc)
 	struct rvt_qp *qp;
 	struct hfi1_qp_priv *priv;
 	unsigned long flags;
-	unsigned i, n = 0;
+	uint i, n = 0, max_idx = 0;
+	u8 max_starved_cnt = 0;
 
 	if (dd->send_contexts[sc->sw_index].type != SC_KERNEL &&
 	    dd->send_contexts[sc->sw_index].type != SC_VL15)
@@ -1591,6 +1592,7 @@ static void sc_piobufavail(struct send_context *sc)
 		priv = qp->priv;
 		list_del_init(&priv->s_iowait.list);
 		priv->s_iowait.lock = NULL;
+		iowait_starve_find_max(wait, &max_starved_cnt, n, &max_idx);
 		/* refcount held until actual wake up */
 		qps[n++] = qp;
 	}
@@ -1605,9 +1607,14 @@ static void sc_piobufavail(struct send_context *sc)
 	}
 	write_sequnlock_irqrestore(&dev->iowait_lock, flags);
 
-	for (i = 0; i < n; i++)
-		hfi1_qp_wakeup(qps[i],
+	/* Wake up the most starved one first */
+	if (n)
+		hfi1_qp_wakeup(qps[max_idx],
 			       RVT_S_WAIT_PIO | RVT_S_WAIT_PIO_DRAIN);
+	for (i = 0; i < n; i++)
+		if (i != max_idx)
+			hfi1_qp_wakeup(qps[i],
+				       RVT_S_WAIT_PIO | RVT_S_WAIT_PIO_DRAIN);
 }
 
 /* translate a send credit update to a bit code of reasons */
diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index 838fe84e285a..a8af96d2b1b0 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -45,10 +45,14 @@
  *
  */
 
+#include <linux/firmware.h>
+
 #include "hfi.h"
 #include "efivar.h"
 #include "eprom.h"
 
+#define DEFAULT_PLATFORM_CONFIG_NAME "hfi1_platform.dat"
+
 static int validate_scratch_checksum(struct hfi1_devdata *dd)
 {
 	u64 checksum = 0, temp_scratch = 0;
@@ -58,8 +62,13 @@ static int validate_scratch_checksum(struct hfi1_devdata *dd)
 	version = (temp_scratch & BITMAP_VERSION_SMASK) >> BITMAP_VERSION_SHIFT;
 
 	/* Prevent power on default of all zeroes from passing checksum */
-	if (!version)
+	if (!version) {
+		dd_dev_err(dd, "%s: Config bitmap uninitialized\n", __func__);
+		dd_dev_err(dd,
+			   "%s: Please update your BIOS to support active channels\n",
+			   __func__);
 		return 0;
+	}
 
 	/*
 	 * ASIC scratch 0 only contains the checksum and bitmap version as
@@ -84,6 +93,8 @@ static int validate_scratch_checksum(struct hfi1_devdata *dd)
 
 	if (checksum + temp_scratch == 0xFFFF)
 		return 1;
+
+	dd_dev_err(dd, "%s: Configuration bitmap corrupted\n", __func__);
 	return 0;
 }
 
@@ -131,25 +142,22 @@ static void save_platform_config_fields(struct hfi1_devdata *dd)
 
 	ppd->max_power_class = (temp_scratch & QSFP_MAX_POWER_SMASK) >>
 				QSFP_MAX_POWER_SHIFT;
+
+	ppd->config_from_scratch = true;
 }
 
 void get_platform_config(struct hfi1_devdata *dd)
 {
 	int ret = 0;
-	unsigned long size = 0;
 	u8 *temp_platform_config = NULL;
 	u32 esize;
+	const struct firmware *platform_config_file = NULL;
 
 	if (is_integrated(dd)) {
 		if (validate_scratch_checksum(dd)) {
 			save_platform_config_fields(dd);
 			return;
 		}
-		dd_dev_err(dd, "%s: Config bitmap corrupted/uninitialized\n",
-			   __func__);
-		dd_dev_err(dd,
-			   "%s: Please update your BIOS to support active channels\n",
-			   __func__);
 	} else {
 		ret = eprom_read_platform_config(dd,
 						 (void **)&temp_platform_config,
@@ -160,36 +168,37 @@ void get_platform_config(struct hfi1_devdata *dd)
 			dd->platform_config.size = esize;
 			return;
 		}
-		/* fail, try EFI variable */
-
-		ret = read_hfi1_efi_var(dd, "configuration", &size,
-					(void **)&temp_platform_config);
-		if (!ret) {
-			dd->platform_config.data = temp_platform_config;
-			dd->platform_config.size = size;
-			return;
-		}
 	}
 	dd_dev_err(dd,
 		   "%s: Failed to get platform config, falling back to sub-optimal default file\n",
 		   __func__);
-	/* fall back to request firmware */
-	platform_config_load = 1;
-}
 
-void free_platform_config(struct hfi1_devdata *dd)
-{
-	if (!platform_config_load) {
-		/*
-		 * was loaded from EFI or the EPROM, release memory
-		 * allocated by read_efi_var/eprom_read_platform_config
-		 */
-		kfree(dd->platform_config.data);
+	ret = request_firmware(&platform_config_file,
+			       DEFAULT_PLATFORM_CONFIG_NAME,
+			       &dd->pcidev->dev);
+	if (ret) {
+		dd_dev_err(dd,
+			   "%s: No default platform config file found\n",
+			   __func__);
+		return;
 	}
+
 	/*
-	 * else do nothing, dispose_firmware will release
-	 * struct firmware platform_config on driver exit
+	 * Allocate separate memory block to store data and free firmware
+	 * structure. This allows free_platform_config to treat EPROM and
+	 * fallback configs in the same manner.
 	 */
+	dd->platform_config.data = kmemdup(platform_config_file->data,
+					   platform_config_file->size,
+					   GFP_KERNEL);
+	dd->platform_config.size = platform_config_file->size;
+	release_firmware(platform_config_file);
+}
+
+void free_platform_config(struct hfi1_devdata *dd)
+{
+	/* Release memory allocated for eprom or fallback file read. */
+	kfree(dd->platform_config.data);
 }
 
 void get_port_type(struct hfi1_pportdata *ppd)
@@ -242,7 +251,7 @@ static int qual_power(struct hfi1_pportdata *ppd)
 
 	if (ppd->offline_disabled_reason ==
 			HFI1_ODR_MASK(OPA_LINKDOWN_REASON_POWER_POLICY)) {
-		dd_dev_info(
+		dd_dev_err(
 			ppd->dd,
 			"%s: Port disabled due to system power restrictions\n",
 			__func__);
@@ -268,7 +277,7 @@ static int qual_bitrate(struct hfi1_pportdata *ppd)
 
 	if (ppd->offline_disabled_reason ==
 			HFI1_ODR_MASK(OPA_LINKDOWN_REASON_LINKSPEED_POLICY)) {
-		dd_dev_info(
+		dd_dev_err(
 			ppd->dd,
 			"%s: Cable failed bitrate check, disabling port\n",
 			__func__);
@@ -709,15 +718,15 @@ static void apply_tunings(
 		ret = load_8051_config(ppd->dd, DC_HOST_COMM_SETTINGS,
 				       GENERAL_CONFIG, config_data);
 		if (ret != HCMD_SUCCESS)
-			dd_dev_info(ppd->dd,
-				    "%s: Failed set ext device config params\n",
-				    __func__);
+			dd_dev_err(ppd->dd,
+				   "%s: Failed set ext device config params\n",
+				   __func__);
 	}
 
 	if (tx_preset_index == OPA_INVALID_INDEX) {
 		if (ppd->port_type == PORT_TYPE_QSFP && limiting_active)
-			dd_dev_info(ppd->dd, "%s: Invalid Tx preset index\n",
-				    __func__);
+			dd_dev_err(ppd->dd, "%s: Invalid Tx preset index\n",
+				   __func__);
 		return;
 	}
 
@@ -900,7 +909,7 @@ static int tune_qsfp(struct hfi1_pportdata *ppd,
 	case 0xD: /* fallthrough */
 	case 0xF:
 	default:
-		dd_dev_info(ppd->dd, "%s: Unknown/unsupported cable\n",
+		dd_dev_warn(ppd->dd, "%s: Unknown/unsupported cable\n",
 			    __func__);
 		break;
 	}
@@ -935,6 +944,21 @@ void tune_serdes(struct hfi1_pportdata *ppd)
 	if (loopback != LOOPBACK_NONE ||
 	    ppd->dd->icode == ICODE_FUNCTIONAL_SIMULATOR) {
 		ppd->driver_link_ready = 1;
+
+		if (qsfp_mod_present(ppd)) {
+			ret = acquire_chip_resource(ppd->dd,
+						    qsfp_resource(ppd->dd),
+						    QSFP_WAIT);
+			if (ret) {
+				dd_dev_err(ppd->dd, "%s: hfi%d: cannot lock i2c chain\n",
+					   __func__, (int)ppd->dd->hfi1_id);
+				goto bail;
+			}
+
+			refresh_qsfp_cache(ppd, &ppd->qsfp_info);
+			release_chip_resource(ppd->dd, qsfp_resource(ppd->dd));
+		}
+
 		return;
 	}
 
@@ -942,7 +966,7 @@ void tune_serdes(struct hfi1_pportdata *ppd)
 	case PORT_TYPE_DISCONNECTED:
 		ppd->offline_disabled_reason =
 			HFI1_ODR_MASK(OPA_LINKDOWN_REASON_DISCONNECTED);
-		dd_dev_info(dd, "%s: Port disconnected, disabling port\n",
+		dd_dev_warn(dd, "%s: Port disconnected, disabling port\n",
 			    __func__);
 		goto bail;
 	case PORT_TYPE_FIXED:
@@ -1027,7 +1051,7 @@ void tune_serdes(struct hfi1_pportdata *ppd)
 		}
 		break;
 	default:
-		dd_dev_info(ppd->dd, "%s: Unknown port type\n", __func__);
+		dd_dev_warn(ppd->dd, "%s: Unknown port type\n", __func__);
 		ppd->port_type = PORT_TYPE_UNKNOWN;
 		tuning_method = OPA_UNKNOWN_TUNING;
 		total_atten = 0;
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index 1a7af9f60c13..4b01ccd895b4 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -68,17 +68,12 @@ static int iowait_sleep(
 	struct sdma_engine *sde,
 	struct iowait *wait,
 	struct sdma_txreq *stx,
-	unsigned seq);
+	unsigned int seq,
+	bool pkts_sent);
 static void iowait_wakeup(struct iowait *wait, int reason);
 static void iowait_sdma_drained(struct iowait *wait);
 static void qp_pio_drain(struct rvt_qp *qp);
 
-static inline unsigned mk_qpn(struct rvt_qpn_table *qpt,
-			      struct rvt_qpn_map *map, unsigned off)
-{
-	return (map - qpt->map) * RVT_BITS_PER_PAGE + off;
-}
-
 const struct rvt_operation_params hfi1_post_parms[RVT_OPERATION_MAX] = {
 [IB_WR_RDMA_WRITE] = {
 	.length = sizeof(struct ib_rdma_wr),
@@ -237,6 +232,31 @@ int hfi1_check_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 	return 0;
 }
 
+/*
+ * qp_set_16b - Set the hdr_type based on whether the slid or the
+ * dlid in the connection is extended. Only applicable for RC and UC
+ * QPs. UD QPs determine this on the fly from the ah in the wqe
+ */
+static inline void qp_set_16b(struct rvt_qp *qp)
+{
+	struct hfi1_pportdata *ppd;
+	struct hfi1_ibport *ibp;
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	/* Update ah_attr to account for extended LIDs */
+	hfi1_update_ah_attr(qp->ibqp.device, &qp->remote_ah_attr);
+
+	/* Create 32 bit LIDs */
+	hfi1_make_opa_lid(&qp->remote_ah_attr);
+
+	if (!(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH))
+		return;
+
+	ibp = to_iport(qp->ibqp.device, qp->port_num);
+	ppd = ppd_from_ibp(ibp);
+	priv->hdr_type = hfi1_get_hdr_type(ppd->lid, &qp->remote_ah_attr);
+}
+
 void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		    int attr_mask, struct ib_udata *udata)
 {
@@ -247,6 +267,7 @@ void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		priv->s_sc = ah_to_sc(ibqp->device, &qp->remote_ah_attr);
 		priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
 		priv->s_sendcontext = qp_to_send_context(qp, priv->s_sc);
+		qp_set_16b(qp);
 	}
 
 	if (attr_mask & IB_QP_PATH_MIG_STATE &&
@@ -256,6 +277,7 @@ void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		priv->s_sc = ah_to_sc(ibqp->device, &qp->remote_ah_attr);
 		priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
 		priv->s_sendcontext = qp_to_send_context(qp, priv->s_sc);
+		qp_set_16b(qp);
 	}
 }
 
@@ -377,7 +399,8 @@ static int iowait_sleep(
 	struct sdma_engine *sde,
 	struct iowait *wait,
 	struct sdma_txreq *stx,
-	unsigned seq)
+	uint seq,
+	bool pkts_sent)
 {
 	struct verbs_txreq *tx = container_of(stx, struct verbs_txreq, txreq);
 	struct rvt_qp *qp;
@@ -408,7 +431,8 @@ static int iowait_sleep(
 
 			ibp->rvp.n_dmawait++;
 			qp->s_flags |= RVT_S_WAIT_DMA_DESC;
-			list_add_tail(&priv->s_iowait.list, &sde->dmawait);
+			iowait_queue(pkts_sent, &priv->s_iowait,
+				     &sde->dmawait);
 			priv->s_iowait.lock = &dev->iowait_lock;
 			trace_hfi1_qpsleep(qp, RVT_S_WAIT_DMA_DESC);
 			rvt_get_qp(qp);
@@ -506,82 +530,6 @@ struct send_context *qp_to_send_context(struct rvt_qp *qp, u8 sc5)
 					  sc5);
 }
 
-struct qp_iter {
-	struct hfi1_ibdev *dev;
-	struct rvt_qp *qp;
-	int specials;
-	int n;
-};
-
-struct qp_iter *qp_iter_init(struct hfi1_ibdev *dev)
-{
-	struct qp_iter *iter;
-
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (!iter)
-		return NULL;
-
-	iter->dev = dev;
-	iter->specials = dev->rdi.ibdev.phys_port_cnt * 2;
-
-	return iter;
-}
-
-int qp_iter_next(struct qp_iter *iter)
-{
-	struct hfi1_ibdev *dev = iter->dev;
-	int n = iter->n;
-	int ret = 1;
-	struct rvt_qp *pqp = iter->qp;
-	struct rvt_qp *qp;
-
-	/*
-	 * The approach is to consider the special qps
-	 * as an additional table entries before the
-	 * real hash table.  Since the qp code sets
-	 * the qp->next hash link to NULL, this works just fine.
-	 *
-	 * iter->specials is 2 * # ports
-	 *
-	 * n = 0..iter->specials is the special qp indices
-	 *
-	 * n = iter->specials..dev->rdi.qp_dev->qp_table_size+iter->specials are
-	 * the potential hash bucket entries
-	 *
-	 */
-	for (; n <  dev->rdi.qp_dev->qp_table_size + iter->specials; n++) {
-		if (pqp) {
-			qp = rcu_dereference(pqp->next);
-		} else {
-			if (n < iter->specials) {
-				struct hfi1_pportdata *ppd;
-				struct hfi1_ibport *ibp;
-				int pidx;
-
-				pidx = n % dev->rdi.ibdev.phys_port_cnt;
-				ppd = &dd_from_dev(dev)->pport[pidx];
-				ibp = &ppd->ibport_data;
-
-				if (!(n & 1))
-					qp = rcu_dereference(ibp->rvp.qp[0]);
-				else
-					qp = rcu_dereference(ibp->rvp.qp[1]);
-			} else {
-				qp = rcu_dereference(
-					dev->rdi.qp_dev->qp_table[
-						(n - iter->specials)]);
-			}
-		}
-		pqp = qp;
-		if (qp) {
-			iter->qp = qp;
-			iter->n = n;
-			return 0;
-		}
-	}
-	return ret;
-}
-
 static const char * const qp_type_str[] = {
 	"SMI", "GSI", "RC", "UC", "UD",
 };
@@ -595,19 +543,27 @@ static int qp_idle(struct rvt_qp *qp)
 		qp->s_tail == qp->s_head;
 }
 
-void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
+/**
+ * qp_iter_print - print the qp information to seq_file
+ * @s: the seq_file to emit the qp information on
+ * @iter: the iterator for the qp hash list
+ */
+void qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter)
 {
 	struct rvt_swqe *wqe;
 	struct rvt_qp *qp = iter->qp;
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct sdma_engine *sde;
 	struct send_context *send_context;
+	struct rvt_ack_entry *e = NULL;
 
 	sde = qp_to_sdma_engine(qp, priv->s_sc);
 	wqe = rvt_get_swqe_ptr(qp, qp->s_last);
 	send_context = qp_to_send_context(qp, priv->s_sc);
+	if (qp->s_ack_queue)
+		e = &qp->s_ack_queue[qp->s_tail_ack_queue];
 	seq_printf(s,
-		   "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",
+		   "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 S(%u %u %u %u %u %u %u) R(%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 OS %x %x E %x %x %x\n",
 		   iter->n,
 		   qp_idle(qp) ? "I" : "B",
 		   qp->ibqp.qp_num,
@@ -630,6 +586,10 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
 		   qp->s_last, qp->s_acked, qp->s_cur,
 		   qp->s_tail, qp->s_head, qp->s_size,
 		   qp->s_avail,
+		   /* ack_queue ring pointers, size */
+		   qp->s_tail_ack_queue, qp->r_head_ack_queue,
+		   rvt_max_atomic(&to_idev(qp->ibqp.device)->rdi),
+		   /* remote QP info  */
 		   qp->remote_qpn,
 		   rdma_ah_get_dlid(&qp->remote_ah_attr),
 		   rdma_ah_get_sl(&qp->remote_ah_attr),
@@ -644,7 +604,13 @@ void qp_iter_print(struct seq_file *s, struct qp_iter *iter)
 		   send_context ? send_context->sw_index : 0,
 		   ibcq_to_rvtcq(qp->ibqp.send_cq)->queue->head,
 		   ibcq_to_rvtcq(qp->ibqp.send_cq)->queue->tail,
-		   qp->pid);
+		   qp->pid,
+		   qp->s_state,
+		   qp->s_ack_state,
+		   /* ack queue information */
+		   e ? e->opcode : 0,
+		   e ? e->psn : 0,
+		   e ? e->lpsn : 0);
 }
 
 void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp)
@@ -750,6 +716,7 @@ void hfi1_migrate_qp(struct rvt_qp *qp)
 	qp->s_flags |= RVT_S_AHG_CLEAR;
 	priv->s_sc = ah_to_sc(qp->ibqp.device, &qp->remote_ah_attr);
 	priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
+	qp_set_16b(qp);
 
 	ev.device = qp->ibqp.device;
 	ev.element.qp = &qp->ibqp;
@@ -832,6 +799,45 @@ void notify_error_qp(struct rvt_qp *qp)
 }
 
 /**
+ * hfi1_qp_iter_cb - callback for iterator
+ * @qp - the qp
+ * @v - the sl in low bits of v
+ *
+ * This is called from the iterator callback to work
+ * on an individual qp.
+ */
+static void hfi1_qp_iter_cb(struct rvt_qp *qp, u64 v)
+{
+	int lastwqe;
+	struct ib_event ev;
+	struct hfi1_ibport *ibp =
+		to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	u8 sl = (u8)v;
+
+	if (qp->port_num != ppd->port ||
+	    (qp->ibqp.qp_type != IB_QPT_UC &&
+	     qp->ibqp.qp_type != IB_QPT_RC) ||
+	    rdma_ah_get_sl(&qp->remote_ah_attr) != sl ||
+	    !(ib_rvt_state_ops[qp->state] & RVT_POST_SEND_OK))
+		return;
+
+	spin_lock_irq(&qp->r_lock);
+	spin_lock(&qp->s_hlock);
+	spin_lock(&qp->s_lock);
+	lastwqe = rvt_error_qp(qp, IB_WC_WR_FLUSH_ERR);
+	spin_unlock(&qp->s_lock);
+	spin_unlock(&qp->s_hlock);
+	spin_unlock_irq(&qp->r_lock);
+	if (lastwqe) {
+		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);
+	}
+}
+
+/**
  * hfi1_error_port_qps - put a port's RC/UC qps into error state
  * @ibp: the ibport.
  * @sl: the service level.
@@ -842,44 +848,8 @@ void notify_error_qp(struct rvt_qp *qp)
  */
 void hfi1_error_port_qps(struct hfi1_ibport *ibp, u8 sl)
 {
-	struct rvt_qp *qp = NULL;
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct hfi1_ibdev *dev = &ppd->dd->verbs_dev;
-	int n;
-	int lastwqe;
-	struct ib_event ev;
-
-	rcu_read_lock();
-
-	/* Deal only with RC/UC qps that use the given SL. */
-	for (n = 0; n < dev->rdi.qp_dev->qp_table_size; n++) {
-		for (qp = rcu_dereference(dev->rdi.qp_dev->qp_table[n]); qp;
-			qp = rcu_dereference(qp->next)) {
-			if (qp->port_num == ppd->port &&
-			    (qp->ibqp.qp_type == IB_QPT_UC ||
-			     qp->ibqp.qp_type == IB_QPT_RC) &&
-			    rdma_ah_get_sl(&qp->remote_ah_attr) == sl &&
-			    (ib_rvt_state_ops[qp->state] &
-			     RVT_POST_SEND_OK)) {
-				spin_lock_irq(&qp->r_lock);
-				spin_lock(&qp->s_hlock);
-				spin_lock(&qp->s_lock);
-				lastwqe = rvt_error_qp(qp,
-						       IB_WC_WR_FLUSH_ERR);
-				spin_unlock(&qp->s_lock);
-				spin_unlock(&qp->s_hlock);
-				spin_unlock_irq(&qp->r_lock);
-				if (lastwqe) {
-					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);
-				}
-			}
-		}
-	}
 
-	rcu_read_unlock();
+	rvt_qp_iter(&dev->rdi, sl, hfi1_qp_iter_cb);
 }
diff --git a/drivers/infiniband/hw/hfi1/qp.h b/drivers/infiniband/hw/hfi1/qp.h
index 6fe542b6a927..c06d2f8348e0 100644
--- a/drivers/infiniband/hw/hfi1/qp.h
+++ b/drivers/infiniband/hw/hfi1/qp.h
@@ -1,7 +1,7 @@
 #ifndef _QP_H
 #define _QP_H
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -94,26 +94,7 @@ void hfi1_qp_wakeup(struct rvt_qp *qp, u32 flag);
 struct sdma_engine *qp_to_sdma_engine(struct rvt_qp *qp, u8 sc5);
 struct send_context *qp_to_send_context(struct rvt_qp *qp, u8 sc5);
 
-struct qp_iter;
-
-/**
- * qp_iter_init - initialize the iterator for the qp hash list
- * @dev: the hfi1_ibdev
- */
-struct qp_iter *qp_iter_init(struct hfi1_ibdev *dev);
-
-/**
- * qp_iter_next - Find the next qp in the hash list
- * @iter: the iterator for the qp hash list
- */
-int qp_iter_next(struct qp_iter *iter);
-
-/**
- * qp_iter_print - print the qp information to seq_file
- * @s: the seq_file to emit the qp information on
- * @iter: the iterator for the qp hash list
- */
-void qp_iter_print(struct seq_file *s, struct qp_iter *iter);
+void qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter);
 
 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 1080778a1f7c..e1cf0c08ca6f 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -100,8 +100,12 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp,
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
 		goto bail;
 
-	/* header size in 32-bit words LRH+BTH = (8+12)/4. */
-	hwords = 5;
+	if (priv->hdr_type == HFI1_PKT_TYPE_9B)
+		/* header size in 32-bit words LRH+BTH = (8+12)/4. */
+		hwords = 5;
+	else
+		/* header size in 32-bit words 16B LRH+BTH = (16+12)/4. */
+		hwords = 7;
 
 	switch (qp->s_ack_state) {
 	case OP(RDMA_READ_RESPONSE_LAST):
@@ -258,8 +262,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	struct ib_other_headers *ohdr;
 	struct rvt_sge_state *ss;
 	struct rvt_swqe *wqe;
-	/* header size in 32-bit words LRH+BTH = (8+12)/4. */
-	u32 hwords = 5;
+	u32 hwords;
 	u32 len;
 	u32 bth0 = 0;
 	u32 bth2;
@@ -273,9 +276,23 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	if (IS_ERR(ps->s_txreq))
 		goto bail_no_tx;
 
-	ohdr = &ps->s_txreq->phdr.hdr.u.oth;
-	if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)
-		ohdr = &ps->s_txreq->phdr.hdr.u.l.oth;
+	ps->s_txreq->phdr.hdr.hdr_type = priv->hdr_type;
+	if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
+		/* header size in 32-bit words LRH+BTH = (8+12)/4. */
+		hwords = 5;
+		if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)
+			ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
+		else
+			ohdr = &ps->s_txreq->phdr.hdr.ibh.u.oth;
+	} else {
+		/* header size in 32-bit words 16B LRH+BTH = (16+12)/4. */
+		hwords = 7;
+		if ((rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH) &&
+		    (hfi1_check_mcast(rdma_ah_get_dlid(&qp->remote_ah_attr))))
+			ohdr = &ps->s_txreq->phdr.hdr.opah.u.l.oth;
+		else
+			ohdr = &ps->s_txreq->phdr.hdr.opah.u.oth;
+	}
 
 	/* Sending responses has higher priority over sending requests. */
 	if ((qp->s_flags & RVT_S_RESP_PENDING) &&
@@ -425,7 +442,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		case IB_WR_RDMA_WRITE:
 			if (newreq && !(qp->s_flags & RVT_S_UNLIMITED_CREDIT))
 				qp->s_lsn++;
-			/* FALLTHROUGH */
+			goto no_flow_control;
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
@@ -433,6 +450,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
+no_flow_control:
 			put_ib_reth_vaddr(
 				wqe->rdma_wr.remote_addr,
 				&ohdr->u.rc.reth);
@@ -703,6 +721,154 @@ bail_no_tx:
 	return 0;
 }
 
+static inline void hfi1_make_bth_aeth(struct rvt_qp *qp,
+				      struct ib_other_headers *ohdr,
+				      u32 bth0, u32 bth1)
+{
+	if (qp->r_nak_state)
+		ohdr->u.aeth = cpu_to_be32((qp->r_msn & IB_MSN_MASK) |
+					    (qp->r_nak_state <<
+					     IB_AETH_CREDIT_SHIFT));
+	else
+		ohdr->u.aeth = rvt_compute_aeth(qp);
+
+	ohdr->bth[0] = cpu_to_be32(bth0);
+	ohdr->bth[1] = cpu_to_be32(bth1 | qp->remote_qpn);
+	ohdr->bth[2] = cpu_to_be32(mask_psn(qp->r_ack_psn));
+}
+
+static inline void hfi1_queue_rc_ack(struct rvt_qp *qp, bool is_fecn)
+{
+	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->s_lock, flags);
+	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
+		goto unlock;
+	this_cpu_inc(*ibp->rvp.rc_qacks);
+	qp->s_flags |= RVT_S_ACK_PENDING | RVT_S_RESP_PENDING;
+	qp->s_nak_state = qp->r_nak_state;
+	qp->s_ack_psn = qp->r_ack_psn;
+	if (is_fecn)
+		qp->s_flags |= RVT_S_ECN;
+
+	/* Schedule the send tasklet. */
+	hfi1_schedule_send(qp);
+unlock:
+	spin_unlock_irqrestore(&qp->s_lock, flags);
+}
+
+static inline void hfi1_make_rc_ack_9B(struct rvt_qp *qp,
+				       struct hfi1_opa_header *opa_hdr,
+				       u8 sc5, bool is_fecn,
+				       u64 *pbc_flags, u32 *hwords,
+				       u32 *nwords)
+{
+	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	struct ib_header *hdr = &opa_hdr->ibh;
+	struct ib_other_headers *ohdr;
+	u16 lrh0 = HFI1_LRH_BTH;
+	u16 pkey;
+	u32 bth0, bth1;
+
+	opa_hdr->hdr_type = HFI1_PKT_TYPE_9B;
+	ohdr = &hdr->u.oth;
+	/* header size in 32-bit words LRH+BTH+AETH = (8+12+4)/4 */
+	*hwords = 6;
+
+	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) {
+		*hwords += hfi1_make_grh(ibp, &hdr->u.l.grh,
+					 rdma_ah_read_grh(&qp->remote_ah_attr),
+					 *hwords - 2, SIZE_OF_CRC);
+		ohdr = &hdr->u.l.oth;
+		lrh0 = HFI1_LRH_GRH;
+	}
+	/* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */
+	*pbc_flags |= ((!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT);
+
+	/* read pkey_index w/o lock (its atomic) */
+	pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
+
+	lrh0 |= (sc5 & IB_SC_MASK) << IB_SC_SHIFT |
+		(rdma_ah_get_sl(&qp->remote_ah_attr) & IB_SL_MASK) <<
+			IB_SL_SHIFT;
+
+	hfi1_make_ib_hdr(hdr, lrh0, *hwords + SIZE_OF_CRC,
+			 opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr), 9B),
+			 ppd->lid | rdma_ah_get_path_bits(&qp->remote_ah_attr));
+
+	bth0 = pkey | (OP(ACKNOWLEDGE) << 24);
+	if (qp->s_mig_state == IB_MIG_MIGRATED)
+		bth0 |= IB_BTH_MIG_REQ;
+	bth1 = (!!is_fecn) << IB_BECN_SHIFT;
+	hfi1_make_bth_aeth(qp, ohdr, bth0, bth1);
+}
+
+static inline void hfi1_make_rc_ack_16B(struct rvt_qp *qp,
+					struct hfi1_opa_header *opa_hdr,
+					u8 sc5, bool is_fecn,
+					u64 *pbc_flags, u32 *hwords,
+					u32 *nwords)
+{
+	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	struct hfi1_16b_header *hdr = &opa_hdr->opah;
+	struct ib_other_headers *ohdr;
+	u32 bth0, bth1;
+	u16 len, pkey;
+	u8 becn = !!is_fecn;
+	u8 l4 = OPA_16B_L4_IB_LOCAL;
+	u8 extra_bytes;
+
+	opa_hdr->hdr_type = HFI1_PKT_TYPE_16B;
+	ohdr = &hdr->u.oth;
+	/* header size in 32-bit words 16B LRH+BTH+AETH = (16+12+4)/4 */
+	*hwords = 8;
+	extra_bytes = hfi1_get_16b_padding(*hwords << 2, 0);
+	*nwords = SIZE_OF_CRC + ((extra_bytes + SIZE_OF_LT) >> 2);
+
+	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH) &&
+	    hfi1_check_mcast(rdma_ah_get_dlid(&qp->remote_ah_attr))) {
+		*hwords += hfi1_make_grh(ibp, &hdr->u.l.grh,
+					 rdma_ah_read_grh(&qp->remote_ah_attr),
+					 *hwords - 4, *nwords);
+		ohdr = &hdr->u.l.oth;
+		l4 = OPA_16B_L4_IB_GLOBAL;
+	}
+	*pbc_flags |= PBC_PACKET_BYPASS | PBC_INSERT_BYPASS_ICRC;
+
+	/* read pkey_index w/o lock (its atomic) */
+	pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
+
+	/* Convert dwords to flits */
+	len = (*hwords + *nwords) >> 1;
+
+	hfi1_make_16b_hdr(hdr,
+			  ppd->lid | rdma_ah_get_path_bits(&qp->remote_ah_attr),
+			  opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr),
+				      16B),
+			  len, pkey, becn, 0, l4, sc5);
+
+	bth0 = pkey | (OP(ACKNOWLEDGE) << 24);
+	bth0 |= extra_bytes << 20;
+	if (qp->s_mig_state == IB_MIG_MIGRATED)
+		bth1 = OPA_BTH_MIG_REQ;
+	hfi1_make_bth_aeth(qp, ohdr, bth0, bth1);
+}
+
+typedef void (*hfi1_make_rc_ack)(struct rvt_qp *qp,
+				 struct hfi1_opa_header *opa_hdr,
+				 u8 sc5, bool is_fecn,
+				 u64 *pbc_flags, u32 *hwords,
+				 u32 *nwords);
+
+/* We support only two types - 9B and 16B for now */
+static const hfi1_make_rc_ack hfi1_make_rc_ack_tbl[2] = {
+	[HFI1_PKT_TYPE_9B] = &hfi1_make_rc_ack_9B,
+	[HFI1_PKT_TYPE_16B] = &hfi1_make_rc_ack_16B
+};
+
 /**
  * hfi1_send_rc_ack - Construct an ACK packet and send it
  * @qp: a pointer to the QP
@@ -711,83 +877,48 @@ bail_no_tx:
  * Note that RDMA reads and atomics are handled in the
  * send side QP state and send engine.
  */
-void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
-		      int is_fecn)
+void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd,
+		      struct rvt_qp *qp, bool is_fecn)
 {
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
+	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	u8 sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&qp->remote_ah_attr)];
 	u64 pbc, pbc_flags = 0;
-	u16 lrh0;
-	u16 sc5;
-	u32 bth0;
-	u32 hwords;
-	u32 vl, plen;
-	struct send_context *sc;
+	u32 hwords = 0;
+	u32 nwords = 0;
+	u32 plen;
 	struct pio_buf *pbuf;
-	struct ib_header hdr;
-	struct ib_other_headers *ohdr;
-	unsigned long flags;
+	struct hfi1_opa_header opa_hdr;
 
 	/* clear the defer count */
 	qp->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)
-		goto queue_ack;
+	if (qp->s_flags & RVT_S_RESP_PENDING) {
+		hfi1_queue_rc_ack(qp, is_fecn);
+		return;
+	}
 
 	/* Ensure s_rdma_ack_cnt changes are committed */
 	smp_read_barrier_depends();
-	if (qp->s_rdma_ack_cnt)
-		goto queue_ack;
-
-	/* Construct the header */
-	/* header size in 32-bit words LRH+BTH+AETH = (8+12+4)/4 */
-	hwords = 6;
-	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) {
-		hwords += hfi1_make_grh(ibp, &hdr.u.l.grh,
-					rdma_ah_read_grh(&qp->remote_ah_attr),
-					hwords, 0);
-		ohdr = &hdr.u.l.oth;
-		lrh0 = HFI1_LRH_GRH;
-	} else {
-		ohdr = &hdr.u.oth;
-		lrh0 = HFI1_LRH_BTH;
+	if (qp->s_rdma_ack_cnt) {
+		hfi1_queue_rc_ack(qp, is_fecn);
+		return;
 	}
-	/* read pkey_index w/o lock (its atomic) */
-	bth0 = hfi1_get_pkey(ibp, qp->s_pkey_index) | (OP(ACKNOWLEDGE) << 24);
-	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 & IB_MSN_MASK) |
-					    (qp->r_nak_state <<
-					     IB_AETH_CREDIT_SHIFT));
-	else
-		ohdr->u.aeth = rvt_compute_aeth(qp);
-	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&qp->remote_ah_attr)];
-	/* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */
-	pbc_flags |= ((!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT);
-	lrh0 |= (sc5 & 0xf) << 12 | (rdma_ah_get_sl(&qp->remote_ah_attr)
-				     & 0xf) << 4;
-	hdr.lrh[0] = cpu_to_be16(lrh0);
-	hdr.lrh[1] = cpu_to_be16(rdma_ah_get_dlid(&qp->remote_ah_attr));
-	hdr.lrh[2] = cpu_to_be16(hwords + SIZE_OF_CRC);
-	hdr.lrh[3] = cpu_to_be16(ppd->lid |
-				 rdma_ah_get_path_bits(&qp->remote_ah_attr));
-	ohdr->bth[0] = cpu_to_be32(bth0);
-	ohdr->bth[1] = cpu_to_be32(qp->remote_qpn);
-	ohdr->bth[1] |= cpu_to_be32((!!is_fecn) << IB_BECN_SHIFT);
-	ohdr->bth[2] = cpu_to_be32(mask_psn(qp->r_ack_psn));
 
 	/* Don't try to send ACKs if the link isn't ACTIVE */
 	if (driver_lstate(ppd) != IB_PORT_ACTIVE)
 		return;
 
-	sc = rcd->sc;
-	plen = 2 /* PBC */ + hwords;
-	vl = sc_to_vlt(ppd->dd, sc5);
-	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen);
+	/* Make the appropriate header */
+	hfi1_make_rc_ack_tbl[priv->hdr_type](qp, &opa_hdr, sc5, is_fecn,
+					     &pbc_flags, &hwords, &nwords);
 
-	pbuf = sc_buffer_alloc(sc, plen, NULL, NULL);
+	plen = 2 /* PBC */ + hwords + nwords;
+	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps,
+			 sc_to_vlt(ppd->dd, sc5), plen);
+	pbuf = sc_buffer_alloc(rcd->sc, plen, NULL, NULL);
 	if (!pbuf) {
 		/*
 		 * We have no room to send at the moment.  Pass
@@ -795,31 +926,18 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 		 * so that when enough buffer space becomes available,
 		 * the ACK is sent ahead of other outgoing packets.
 		 */
-		goto queue_ack;
+		hfi1_queue_rc_ack(qp, is_fecn);
+		return;
 	}
-
-	trace_ack_output_ibhdr(dd_from_ibdev(qp->ibqp.device), &hdr);
+	trace_ack_output_ibhdr(dd_from_ibdev(qp->ibqp.device),
+			       &opa_hdr, ib_is_sc5(sc5));
 
 	/* write the pbc and data */
-	ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc, &hdr, hwords);
-
+	ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc,
+				 (priv->hdr_type == HFI1_PKT_TYPE_9B ?
+				 (void *)&opa_hdr.ibh :
+				 (void *)&opa_hdr.opah), hwords);
 	return;
-
-queue_ack:
-	spin_lock_irqsave(&qp->s_lock, flags);
-	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
-		goto unlock;
-	this_cpu_inc(*ibp->rvp.rc_qacks);
-	qp->s_flags |= RVT_S_ACK_PENDING | RVT_S_RESP_PENDING;
-	qp->s_nak_state = qp->r_nak_state;
-	qp->s_ack_psn = qp->r_ack_psn;
-	if (is_fecn)
-		qp->s_flags |= RVT_S_ECN;
-
-	/* Schedule the send engine. */
-	hfi1_schedule_send(qp);
-unlock:
-	spin_unlock_irqrestore(&qp->s_lock, flags);
 }
 
 /**
@@ -984,10 +1102,13 @@ static void reset_sending_psn(struct rvt_qp *qp, u32 psn)
 /*
  * This should be called with the QP s_lock held and interrupts disabled.
  */
-void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
+void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah)
 {
 	struct ib_other_headers *ohdr;
+	struct hfi1_qp_priv *priv = qp->priv;
 	struct rvt_swqe *wqe;
+	struct ib_header *hdr = NULL;
+	struct hfi1_16b_header *hdr_16b = NULL;
 	u32 opcode;
 	u32 psn;
 
@@ -996,10 +1117,22 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 		return;
 
 	/* Find out where the BTH is */
-	if (ib_get_lnh(hdr) == HFI1_LRH_BTH)
-		ohdr = &hdr->u.oth;
-	else
-		ohdr = &hdr->u.l.oth;
+	if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
+		hdr = &opah->ibh;
+		if (ib_get_lnh(hdr) == HFI1_LRH_BTH)
+			ohdr = &hdr->u.oth;
+		else
+			ohdr = &hdr->u.l.oth;
+	} else {
+		u8 l4;
+
+		hdr_16b = &opah->opah;
+		l4  = hfi1_16B_get_l4(hdr_16b);
+		if (l4 == OPA_16B_L4_IB_LOCAL)
+			ohdr = &hdr_16b->u.oth;
+		else
+			ohdr = &hdr_16b->u.l.oth;
+	}
 
 	opcode = ib_bth_get_opcode(ohdr);
 	if (opcode >= OP(RDMA_READ_RESPONSE_FIRST) &&
@@ -1009,7 +1142,7 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 		return;
 	}
 
-	psn = be32_to_cpu(ohdr->bth[2]);
+	psn = ib_bth_get_psn(ohdr);
 	reset_sending_psn(qp, psn);
 
 	/*
@@ -1399,36 +1532,34 @@ static void rdma_seq_err(struct rvt_qp *qp, struct hfi1_ibport *ibp, u32 psn,
 
 /**
  * rc_rcv_resp - process an incoming RC response packet
- * @ibp: the port this packet came in on
- * @ohdr: the other headers for this packet
- * @data: the packet data
- * @tlen: the packet length
- * @qp: the QP for this packet
- * @opcode: the opcode for this packet
- * @psn: the packet sequence number for this packet
- * @hdrsize: the header length
- * @pmtu: the path MTU
+ * @packet: data packet information
  *
  * This is called from hfi1_rc_rcv() to process an incoming RC response
  * packet for the given QP.
  * Called at interrupt level.
  */
-static void rc_rcv_resp(struct hfi1_ibport *ibp,
-			struct ib_other_headers *ohdr,
-			void *data, u32 tlen, struct rvt_qp *qp,
-			u32 opcode, u32 psn, u32 hdrsize, u32 pmtu,
-			struct hfi1_ctxtdata *rcd)
+static void rc_rcv_resp(struct hfi1_packet *packet)
 {
+	struct hfi1_ctxtdata *rcd = packet->rcd;
+	void *data = packet->payload;
+	u32 tlen = packet->tlen;
+	struct rvt_qp *qp = packet->qp;
+	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct ib_other_headers *ohdr = packet->ohdr;
 	struct rvt_swqe *wqe;
 	enum ib_wc_status status;
 	unsigned long flags;
 	int diff;
-	u32 pad;
-	u32 aeth;
 	u64 val;
+	u32 aeth;
+	u32 psn = ib_bth_get_psn(packet->ohdr);
+	u32 pmtu = qp->pmtu;
+	u16 hdrsize = packet->hlen;
+	u8 opcode = packet->opcode;
+	u8 pad = packet->pad;
+	u8 extra_bytes = pad + packet->extra_byte + (SIZE_OF_CRC << 2);
 
 	spin_lock_irqsave(&qp->s_lock, flags);
-
 	trace_hfi1_ack(qp, psn);
 
 	/* Ignore invalid responses. */
@@ -1494,7 +1625,7 @@ static void rc_rcv_resp(struct hfi1_ibport *ibp,
 		if (unlikely(wqe->wr.opcode != IB_WR_RDMA_READ))
 			goto ack_op_err;
 read_middle:
-		if (unlikely(tlen != (hdrsize + pmtu + 4)))
+		if (unlikely(tlen != (hdrsize + pmtu + extra_bytes)))
 			goto ack_len_err;
 		if (unlikely(pmtu >= qp->s_rdma_read_len))
 			goto ack_len_err;
@@ -1526,13 +1657,11 @@ read_middle:
 		aeth = be32_to_cpu(ohdr->u.aeth);
 		if (!do_rc_ack(qp, aeth, psn, opcode, 0, rcd))
 			goto ack_done;
-		/* Get the number of bytes the message was padded by. */
-		pad = ib_bth_get_pad(ohdr);
 		/*
 		 * Check that the data size is >= 0 && <= pmtu.
 		 * Remember to account for ICRC (4).
 		 */
-		if (unlikely(tlen < (hdrsize + pad + 4)))
+		if (unlikely(tlen < (hdrsize + extra_bytes)))
 			goto ack_len_err;
 		/*
 		 * If this is a response to a resent RDMA read, we
@@ -1550,16 +1679,14 @@ read_middle:
 			goto ack_seq_err;
 		if (unlikely(wqe->wr.opcode != IB_WR_RDMA_READ))
 			goto ack_op_err;
-		/* Get the number of bytes the message was padded by. */
-		pad = ib_bth_get_pad(ohdr);
 		/*
 		 * Check that the data size is >= 1 && <= pmtu.
 		 * Remember to account for ICRC (4).
 		 */
-		if (unlikely(tlen <= (hdrsize + pad + 4)))
+		if (unlikely(tlen <= (hdrsize + extra_bytes)))
 			goto ack_len_err;
 read_last:
-		tlen -= hdrsize + pad + 4;
+		tlen -= hdrsize + extra_bytes;
 		if (unlikely(tlen != qp->s_rdma_read_len))
 			goto ack_len_err;
 		aeth = be32_to_cpu(ohdr->u.aeth);
@@ -1844,7 +1971,7 @@ static void log_cca_event(struct hfi1_pportdata *ppd, u8 sl, u32 rlid,
 	spin_unlock_irqrestore(&ppd->cc_log_lock, flags);
 }
 
-void process_becn(struct hfi1_pportdata *ppd, u8 sl, u16 rlid, u32 lqpn,
+void process_becn(struct hfi1_pportdata *ppd, u8 sl, u32 rlid, u32 lqpn,
 		  u32 rqpn, u8 svc_type)
 {
 	struct cca_timer *cca_timer;
@@ -1901,12 +2028,7 @@ void process_becn(struct hfi1_pportdata *ppd, u8 sl, u16 rlid, u32 lqpn,
 
 /**
  * hfi1_rc_rcv - process an incoming RC packet
- * @rcd: the context pointer
- * @hdr: the header of this packet
- * @rcv_flags: flags relevant to rcv processing
- * @data: the packet data
- * @tlen: the packet length
- * @qp: the QP for this packet
+ * @packet: data packet information
  *
  * This is called from qp_rcv() to process an incoming RC packet
  * for the given QP.
@@ -1915,17 +2037,16 @@ void process_becn(struct hfi1_pportdata *ppd, u8 sl, u16 rlid, u32 lqpn,
 void hfi1_rc_rcv(struct hfi1_packet *packet)
 {
 	struct hfi1_ctxtdata *rcd = packet->rcd;
-	struct ib_header *hdr = packet->hdr;
-	u32 rcv_flags = packet->rcv_flags;
-	void *data = packet->ebuf;
+	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct ib_other_headers *ohdr = packet->ohdr;
-	u32 bth0, opcode;
+	u32 bth0 = be32_to_cpu(ohdr->bth[0]);
+	u32 opcode = packet->opcode;
 	u32 hdrsize = packet->hlen;
-	u32 psn;
-	u32 pad;
+	u32 psn = ib_bth_get_psn(packet->ohdr);
+	u32 pad = packet->pad;
 	struct ib_wc wc;
 	u32 pmtu = qp->pmtu;
 	int diff;
@@ -1935,17 +2056,15 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	bool is_fecn = false;
 	bool copy_last = false;
 	u32 rkey;
+	u8 extra_bytes = pad + packet->extra_byte + (SIZE_OF_CRC << 2);
 
 	lockdep_assert_held(&qp->r_lock);
-	bth0 = be32_to_cpu(ohdr->bth[0]);
-	if (hfi1_ruc_check_hdr(ibp, hdr, rcv_flags & HFI1_HAS_GRH, qp, bth0))
+
+	if (hfi1_ruc_check_hdr(ibp, packet))
 		return;
 
 	is_fecn = process_ecn(qp, packet, false);
 
-	psn = be32_to_cpu(ohdr->bth[2]);
-	opcode = ib_bth_get_opcode(ohdr);
-
 	/*
 	 * Process responses (ACKs) before anything else.  Note that the
 	 * packet sequence number will be for something in the send work
@@ -1954,8 +2073,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	 */
 	if (opcode >= OP(RDMA_READ_RESPONSE_FIRST) &&
 	    opcode <= OP(ATOMIC_ACKNOWLEDGE)) {
-		rc_rcv_resp(ibp, ohdr, data, tlen, qp, opcode, psn,
-			    hdrsize, pmtu, rcd);
+		rc_rcv_resp(packet);
 		if (is_fecn)
 			goto send_ack;
 		return;
@@ -2022,7 +2140,12 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	case OP(RDMA_WRITE_MIDDLE):
 send_middle:
 		/* Check for invalid length PMTU or posted rwqe len. */
-		if (unlikely(tlen != (hdrsize + pmtu + 4)))
+		/*
+		 * There will be no padding for 9B packet but 16B packets
+		 * will come in with some padding since we always add
+		 * CRC and LT bytes which will need to be flit aligned
+		 */
+		if (unlikely(tlen != (hdrsize + pmtu + extra_bytes)))
 			goto nack_inv;
 		qp->r_rcv_len += pmtu;
 		if (unlikely(qp->r_rcv_len > qp->r_len))
@@ -2074,14 +2197,12 @@ no_immediate_data:
 		wc.wc_flags = 0;
 		wc.ex.imm_data = 0;
 send_last:
-		/* Get the number of bytes the message was padded by. */
-		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
-		if (unlikely(tlen < (hdrsize + pad + 4)))
+		if (unlikely(tlen < (hdrsize + extra_bytes)))
 			goto nack_inv;
-		/* Don't count the CRC. */
-		tlen -= (hdrsize + pad + 4);
+		/* Don't count the CRC(and padding and LT byte for 16B). */
+		tlen -= (hdrsize + extra_bytes);
 		wc.byte_len = tlen + qp->r_rcv_len;
 		if (unlikely(wc.byte_len > qp->r_len))
 			goto nack_inv;
@@ -2368,28 +2489,19 @@ send_ack:
 
 void hfi1_rc_hdrerr(
 	struct hfi1_ctxtdata *rcd,
-	struct ib_header *hdr,
-	u32 rcv_flags,
+	struct hfi1_packet *packet,
 	struct rvt_qp *qp)
 {
-	int has_grh = rcv_flags & HFI1_HAS_GRH;
-	struct ib_other_headers *ohdr;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	int diff;
 	u32 opcode;
-	u32 psn, bth0;
-
-	/* Check for GRH */
-	ohdr = &hdr->u.oth;
-	if (has_grh)
-		ohdr = &hdr->u.l.oth;
+	u32 psn;
 
-	bth0 = be32_to_cpu(ohdr->bth[0]);
-	if (hfi1_ruc_check_hdr(ibp, hdr, has_grh, qp, bth0))
+	if (hfi1_ruc_check_hdr(ibp, packet))
 		return;
 
-	psn = be32_to_cpu(ohdr->bth[2]);
-	opcode = ib_bth_get_opcode(ohdr);
+	psn = ib_bth_get_psn(packet->ohdr);
+	opcode = ib_bth_get_opcode(packet->ohdr);
 
 	/* Only deal with RDMA Writes for now */
 	if (opcode < IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST) {
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 3a17daba28a9..b3291f0fde9a 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -74,8 +74,10 @@ static int init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
 		if (wqe->sg_list[i].length == 0)
 			continue;
 		/* Check LKEY */
-		if (!rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
-				 &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE))
+		ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
+				  NULL, &wqe->sg_list[i],
+				  IB_ACCESS_LOCAL_WRITE);
+		if (unlikely(ret <= 0))
 			goto bad_lkey;
 		qp->r_len += wqe->sg_list[i].length;
 		j++;
@@ -214,100 +216,104 @@ static int gid_ok(union ib_gid *gid, __be64 gid_prefix, __be64 id)
  *
  * The s_lock will be acquired around the hfi1_migrate_qp() call.
  */
-int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct ib_header *hdr,
-		       int has_grh, struct rvt_qp *qp, u32 bth0)
+int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet)
 {
 	__be64 guid;
 	unsigned long flags;
+	struct rvt_qp *qp = packet->qp;
 	u8 sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&qp->remote_ah_attr)];
+	u32 dlid = packet->dlid;
+	u32 slid = packet->slid;
+	u32 sl = packet->sl;
+	int migrated;
+	u32 bth0, bth1;
+	u16 pkey;
+
+	bth0 = be32_to_cpu(packet->ohdr->bth[0]);
+	bth1 = be32_to_cpu(packet->ohdr->bth[1]);
+	if (packet->etype == RHF_RCV_TYPE_BYPASS) {
+		pkey = hfi1_16B_get_pkey(packet->hdr);
+		migrated = bth1 & OPA_BTH_MIG_REQ;
+	} else {
+		pkey = ib_bth_get_pkey(packet->ohdr);
+		migrated = bth0 & IB_BTH_MIG_REQ;
+	}
 
-	if (qp->s_mig_state == IB_MIG_ARMED && (bth0 & IB_BTH_MIG_REQ)) {
-		if (!has_grh) {
-			if (rdma_ah_get_ah_flags(&qp->alt_ah_attr) &
-			    IB_AH_GRH)
-				goto err;
+	if (qp->s_mig_state == IB_MIG_ARMED && migrated) {
+		if (!packet->grh) {
+			if ((rdma_ah_get_ah_flags(&qp->alt_ah_attr) &
+			     IB_AH_GRH) &&
+			    (packet->etype != RHF_RCV_TYPE_BYPASS))
+				return 1;
 		} else {
 			const struct ib_global_route *grh;
 
 			if (!(rdma_ah_get_ah_flags(&qp->alt_ah_attr) &
 			      IB_AH_GRH))
-				goto err;
+				return 1;
 			grh = rdma_ah_read_grh(&qp->alt_ah_attr);
 			guid = get_sguid(ibp, grh->sgid_index);
-			if (!gid_ok(&hdr->u.l.grh.dgid, ibp->rvp.gid_prefix,
+			if (!gid_ok(&packet->grh->dgid, ibp->rvp.gid_prefix,
 				    guid))
-				goto err;
+				return 1;
 			if (!gid_ok(
-				&hdr->u.l.grh.sgid,
+				&packet->grh->sgid,
 				grh->dgid.global.subnet_prefix,
 				grh->dgid.global.interface_id))
-				goto err;
+				return 1;
 		}
-		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, sc5,
-					    ib_get_slid(hdr)))) {
-			hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY,
-				       (u16)bth0,
-				       ib_get_sl(hdr),
-				       0, qp->ibqp.qp_num,
-				       ib_get_slid(hdr),
-				       ib_get_dlid(hdr));
-			goto err;
+		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), pkey,
+					    sc5, slid))) {
+			hfi1_bad_pkey(ibp, pkey, sl, 0, qp->ibqp.qp_num,
+				      slid, dlid);
+			return 1;
 		}
 		/* Validate the SLID. See Ch. 9.6.1.5 and 17.2.8 */
-		if (ib_get_slid(hdr) !=
-			rdma_ah_get_dlid(&qp->alt_ah_attr) ||
+		if (slid != rdma_ah_get_dlid(&qp->alt_ah_attr) ||
 		    ppd_from_ibp(ibp)->port !=
 			rdma_ah_get_port_num(&qp->alt_ah_attr))
-			goto err;
+			return 1;
 		spin_lock_irqsave(&qp->s_lock, flags);
 		hfi1_migrate_qp(qp);
 		spin_unlock_irqrestore(&qp->s_lock, flags);
 	} else {
-		if (!has_grh) {
-			if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) &
-						 IB_AH_GRH)
-				goto err;
+		if (!packet->grh) {
+			if ((rdma_ah_get_ah_flags(&qp->remote_ah_attr) &
+			     IB_AH_GRH) &&
+			    (packet->etype != RHF_RCV_TYPE_BYPASS))
+				return 1;
 		} else {
 			const struct ib_global_route *grh;
 
 			if (!(rdma_ah_get_ah_flags(&qp->remote_ah_attr) &
 						   IB_AH_GRH))
-				goto err;
+				return 1;
 			grh = rdma_ah_read_grh(&qp->remote_ah_attr);
 			guid = get_sguid(ibp, grh->sgid_index);
-			if (!gid_ok(&hdr->u.l.grh.dgid, ibp->rvp.gid_prefix,
+			if (!gid_ok(&packet->grh->dgid, ibp->rvp.gid_prefix,
 				    guid))
-				goto err;
+				return 1;
 			if (!gid_ok(
-			     &hdr->u.l.grh.sgid,
+			     &packet->grh->sgid,
 			     grh->dgid.global.subnet_prefix,
 			     grh->dgid.global.interface_id))
-				goto err;
+				return 1;
 		}
-		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, sc5,
-					    ib_get_slid(hdr)))) {
-			hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY,
-				       (u16)bth0,
-				       ib_get_sl(hdr),
-				       0, qp->ibqp.qp_num,
-				       ib_get_slid(hdr),
-				       ib_get_dlid(hdr));
-			goto err;
+		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), pkey,
+					    sc5, slid))) {
+			hfi1_bad_pkey(ibp, pkey, sl, 0, qp->ibqp.qp_num,
+				      slid, dlid);
+			return 1;
 		}
 		/* Validate the SLID. See Ch. 9.6.1.5 */
-		if (ib_get_slid(hdr) !=
-			rdma_ah_get_dlid(&qp->remote_ah_attr) ||
+		if ((slid != rdma_ah_get_dlid(&qp->remote_ah_attr)) ||
 		    ppd_from_ibp(ibp)->port != qp->port_num)
-			goto err;
-		if (qp->s_mig_state == IB_MIG_REARM &&
-		    !(bth0 & IB_BTH_MIG_REQ))
+			return 1;
+		if (qp->s_mig_state == IB_MIG_REARM && !migrated)
 			qp->s_mig_state = IB_MIG_ARMED;
 	}
 
 	return 0;
-
-err:
-	return 1;
 }
 
 /**
@@ -643,7 +649,7 @@ done:
  * @ibp: a pointer to the IB port
  * @hdr: a pointer to the GRH header being constructed
  * @grh: the global route address to send to
- * @hwords: the number of 32 bit words of header being sent
+ * @hwords: size of header after grh being sent in dwords
  * @nwords: the number of 32 bit words of data being sent
  *
  * Return the size of the header in 32 bit words.
@@ -655,7 +661,7 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
 		cpu_to_be32((IB_GRH_VERSION << IB_GRH_VERSION_SHIFT) |
 			    (grh->traffic_class << IB_GRH_TCLASS_SHIFT) |
 			    (grh->flow_label << IB_GRH_FLOW_SHIFT));
-	hdr->paylen = cpu_to_be16((hwords - 2 + nwords + SIZE_OF_CRC) << 2);
+	hdr->paylen = cpu_to_be16((hwords + nwords) << 2);
 	/* next_hdr is defined by C8-7 in ch. 8.4.1 */
 	hdr->next_hdr = IB_GRH_NEXT_HDR;
 	hdr->hop_limit = grh->hop_limit;
@@ -671,7 +677,8 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
 	return sizeof(struct ib_grh) / sizeof(u32);
 }
 
-#define BTH2_OFFSET (offsetof(struct hfi1_sdma_header, hdr.u.oth.bth[2]) / 4)
+#define BTH2_OFFSET (offsetof(struct hfi1_sdma_header, \
+			      hdr.ibh.u.oth.bth[2]) / 4)
 
 /**
  * build_ahg - create ahg in s_ahg
@@ -728,73 +735,186 @@ static inline void build_ahg(struct rvt_qp *qp, u32 npsn)
 	}
 }
 
-void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
-			  u32 bth0, u32 bth2, int middle,
-			  struct hfi1_pkt_state *ps)
+static inline void hfi1_make_ruc_bth(struct rvt_qp *qp,
+				     struct ib_other_headers *ohdr,
+				     u32 bth0, u32 bth1, u32 bth2)
+{
+	bth1 |= qp->remote_qpn;
+	ohdr->bth[0] = cpu_to_be32(bth0);
+	ohdr->bth[1] = cpu_to_be32(bth1);
+	ohdr->bth[2] = cpu_to_be32(bth2);
+}
+
+static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
+					    struct ib_other_headers *ohdr,
+					    u32 bth0, u32 bth2, int middle,
+					    struct hfi1_pkt_state *ps)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct hfi1_ibport *ibp = ps->ibp;
-	u16 lrh0;
-	u32 nwords;
-	u32 extra_bytes;
-	u32 bth1;
-
-	/* Construct the header. */
-	extra_bytes = -ps->s_txreq->s_cur_size & 3;
-	nwords = (ps->s_txreq->s_cur_size + extra_bytes) >> 2;
-	lrh0 = HFI1_LRH_BTH;
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	u32 bth1 = 0;
+	u32 slid;
+	u16 pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
+	u8 l4 = OPA_16B_L4_IB_LOCAL;
+	u8 extra_bytes = hfi1_get_16b_padding((qp->s_hdrwords << 2),
+				   ps->s_txreq->s_cur_size);
+	u32 nwords = SIZE_OF_CRC + ((ps->s_txreq->s_cur_size +
+				 extra_bytes + SIZE_OF_LT) >> 2);
+	u8 becn = 0;
+
+	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH) &&
+	    hfi1_check_mcast(rdma_ah_get_dlid(&qp->remote_ah_attr))) {
+		struct ib_grh *grh;
+		struct ib_global_route *grd =
+			rdma_ah_retrieve_grh(&qp->remote_ah_attr);
+		int hdrwords;
+
+		/*
+		 * Ensure OPA GIDs are transformed to IB gids
+		 * before creating the GRH.
+		 */
+		if (grd->sgid_index == OPA_GID_INDEX)
+			grd->sgid_index = 0;
+		grh = &ps->s_txreq->phdr.hdr.opah.u.l.grh;
+		l4 = OPA_16B_L4_IB_GLOBAL;
+		hdrwords = qp->s_hdrwords - 4;
+		qp->s_hdrwords += hfi1_make_grh(ibp, grh, grd,
+						hdrwords, nwords);
+		middle = 0;
+	}
+
+	if (qp->s_mig_state == IB_MIG_MIGRATED)
+		bth1 |= OPA_BTH_MIG_REQ;
+	else
+		middle = 0;
+
+	if (middle)
+		build_ahg(qp, bth2);
+	else
+		qp->s_flags &= ~RVT_S_AHG_VALID;
+
+	bth0 |= pkey;
+	bth0 |= extra_bytes << 20;
+	if (qp->s_flags & RVT_S_ECN) {
+		qp->s_flags &= ~RVT_S_ECN;
+		/* we recently received a FECN, so return a BECN */
+		becn = 1;
+	}
+	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
+
+	if (!ppd->lid)
+		slid = be32_to_cpu(OPA_LID_PERMISSIVE);
+	else
+		slid = ppd->lid |
+			(rdma_ah_get_path_bits(&qp->remote_ah_attr) &
+			((1 << ppd->lmc) - 1));
+
+	hfi1_make_16b_hdr(&ps->s_txreq->phdr.hdr.opah,
+			  slid,
+			  opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr),
+				      16B),
+			  (qp->s_hdrwords + nwords) >> 1,
+			  pkey, becn, 0, l4, priv->s_sc);
+}
+
+static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
+					   struct ib_other_headers *ohdr,
+					   u32 bth0, u32 bth2, int middle,
+					   struct hfi1_pkt_state *ps)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+	struct hfi1_ibport *ibp = ps->ibp;
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	u32 bth1 = 0;
+	u16 pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
+	u16 lrh0 = HFI1_LRH_BTH;
+	u16 slid;
+	u8 extra_bytes = -ps->s_txreq->s_cur_size & 3;
+	u32 nwords = SIZE_OF_CRC + ((ps->s_txreq->s_cur_size +
+					 extra_bytes) >> 2);
+
 	if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) {
+		struct ib_grh *grh = &ps->s_txreq->phdr.hdr.ibh.u.l.grh;
+		int hdrwords = qp->s_hdrwords - 2;
+
+		lrh0 = HFI1_LRH_GRH;
 		qp->s_hdrwords +=
-			hfi1_make_grh(ibp,
-				      &ps->s_txreq->phdr.hdr.u.l.grh,
+			hfi1_make_grh(ibp, grh,
 				      rdma_ah_read_grh(&qp->remote_ah_attr),
-				      qp->s_hdrwords, nwords);
-		lrh0 = HFI1_LRH_GRH;
+				      hdrwords, nwords);
 		middle = 0;
 	}
 	lrh0 |= (priv->s_sc & 0xf) << 12 |
 		(rdma_ah_get_sl(&qp->remote_ah_attr) & 0xf) << 4;
-	/*
-	 * reset s_ahg/AHG fields
-	 *
-	 * This insures that the ahgentry/ahgcount
-	 * are at a non-AHG default to protect
-	 * build_verbs_tx_desc() from using
-	 * an include ahgidx.
-	 *
-	 * build_ahg() will modify as appropriate
-	 * to use the AHG feature.
-	 */
-	priv->s_ahg->tx_flags = 0;
-	priv->s_ahg->ahgcount = 0;
-	priv->s_ahg->ahgidx = 0;
+
 	if (qp->s_mig_state == IB_MIG_MIGRATED)
 		bth0 |= IB_BTH_MIG_REQ;
 	else
 		middle = 0;
+
 	if (middle)
 		build_ahg(qp, bth2);
 	else
 		qp->s_flags &= ~RVT_S_AHG_VALID;
-	ps->s_txreq->phdr.hdr.lrh[0] = cpu_to_be16(lrh0);
-	ps->s_txreq->phdr.hdr.lrh[1] =
-		cpu_to_be16(rdma_ah_get_dlid(&qp->remote_ah_attr));
-	ps->s_txreq->phdr.hdr.lrh[2] =
-		cpu_to_be16(qp->s_hdrwords + nwords + SIZE_OF_CRC);
-	ps->s_txreq->phdr.hdr.lrh[3] =
-		cpu_to_be16(ppd_from_ibp(ibp)->lid |
-			    rdma_ah_get_path_bits(&qp->remote_ah_attr));
-	bth0 |= hfi1_get_pkey(ibp, qp->s_pkey_index);
+
+	bth0 |= pkey;
 	bth0 |= extra_bytes << 20;
-	ohdr->bth[0] = cpu_to_be32(bth0);
-	bth1 = qp->remote_qpn;
 	if (qp->s_flags & RVT_S_ECN) {
 		qp->s_flags &= ~RVT_S_ECN;
 		/* we recently received a FECN, so return a BECN */
 		bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
 	}
-	ohdr->bth[1] = cpu_to_be32(bth1);
-	ohdr->bth[2] = cpu_to_be32(bth2);
+	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
+
+	if (!ppd->lid)
+		slid = be16_to_cpu(IB_LID_PERMISSIVE);
+	else
+		slid = ppd->lid |
+			(rdma_ah_get_path_bits(&qp->remote_ah_attr) &
+			((1 << ppd->lmc) - 1));
+	hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
+			 lrh0,
+			 qp->s_hdrwords + nwords,
+			 opa_get_lid(rdma_ah_get_dlid(&qp->remote_ah_attr), 9B),
+			 ppd_from_ibp(ibp)->lid |
+				rdma_ah_get_path_bits(&qp->remote_ah_attr));
+}
+
+typedef void (*hfi1_make_ruc_hdr)(struct rvt_qp *qp,
+				  struct ib_other_headers *ohdr,
+				  u32 bth0, u32 bth2, int middle,
+				  struct hfi1_pkt_state *ps);
+
+/* We support only two types - 9B and 16B for now */
+static const hfi1_make_ruc_hdr hfi1_ruc_header_tbl[2] = {
+	[HFI1_PKT_TYPE_9B] = &hfi1_make_ruc_header_9B,
+	[HFI1_PKT_TYPE_16B] = &hfi1_make_ruc_header_16B
+};
+
+void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
+			  u32 bth0, u32 bth2, int middle,
+			  struct hfi1_pkt_state *ps)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	/*
+	 * reset s_ahg/AHG fields
+	 *
+	 * This insures that the ahgentry/ahgcount
+	 * are at a non-AHG default to protect
+	 * build_verbs_tx_desc() from using
+	 * an include ahgidx.
+	 *
+	 * build_ahg() will modify as appropriate
+	 * to use the AHG feature.
+	 */
+	priv->s_ahg->tx_flags = 0;
+	priv->s_ahg->ahgcount = 0;
+	priv->s_ahg->ahgidx = 0;
+
+	/* Make the appropriate header */
+	hfi1_ruc_header_tbl[priv->hdr_type](qp, ohdr, bth0, bth2, middle, ps);
 }
 
 /* when sending, force a reschedule every one of these periods */
@@ -816,6 +936,8 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 static bool schedule_send_yield(struct rvt_qp *qp,
 				struct hfi1_pkt_state *ps)
 {
+	ps->pkts_sent = true;
+
 	if (unlikely(time_after(jiffies, ps->timeout))) {
 		if (!ps->in_thread ||
 		    workqueue_congested(ps->cpu, ps->ppd->hfi1_wq)) {
@@ -912,6 +1034,7 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
 	ps.timeout = jiffies + ps.timeout_int;
 	ps.cpu = priv->s_sde ? priv->s_sde->cpu :
 			cpumask_first(cpumask_of_node(ps.ppd->dd->node));
+	ps.pkts_sent = false;
 
 	/* insure a pre-built packet is handled  */
 	ps.s_txreq = get_waiting_verbs_txreq(qp);
@@ -934,7 +1057,7 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
 			spin_lock_irqsave(&qp->s_lock, ps.flags);
 		}
 	} while (make_req(qp, &ps));
-
+	iowait_starve_clear(ps.pkts_sent, &priv->s_iowait);
 	spin_unlock_irqrestore(&qp->s_lock, ps.flags);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index bfd0d5187e9b..6781bcdb10b3 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -246,7 +246,7 @@ static void __sdma_process_event(
 	enum sdma_events event);
 static void dump_sdma_state(struct sdma_engine *sde);
 static void sdma_make_progress(struct sdma_engine *sde, u64 status);
-static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail);
+static void sdma_desc_avail(struct sdma_engine *sde, uint avail);
 static void sdma_flush_descq(struct sdma_engine *sde);
 
 /**
@@ -325,7 +325,7 @@ static void sdma_wait_for_packet_egress(struct sdma_engine *sde,
 			/* timed out - bounce the link */
 			dd_dev_err(dd, "%s: engine %u timeout waiting for packets to egress, remaining count %u, bouncing link\n",
 				   __func__, sde->this_idx, (u32)reg);
-			queue_work(dd->pport->hfi1_wq,
+			queue_work(dd->pport->link_wq,
 				   &dd->pport->link_bounce_work);
 			break;
 		}
@@ -1340,10 +1340,8 @@ static void sdma_clean(struct hfi1_devdata *dd, size_t num_engines)
  * @dd: hfi1_devdata
  * @port: port number (currently only zero)
  *
- * sdma_init initializes the specified number of engines.
- *
- * The code initializes each sde, its csrs.  Interrupts
- * are not required to be enabled.
+ * Initializes each sde and its csrs.
+ * Interrupts are not required to be enabled.
  *
  * Returns:
  * 0 - success, -errno on failure
@@ -1764,13 +1762,14 @@ retry:
  *
  * This is called with head_lock held.
  */
-static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail)
+static void sdma_desc_avail(struct sdma_engine *sde, uint avail)
 {
 	struct iowait *wait, *nw;
 	struct iowait *waits[SDMA_WAIT_BATCH_SIZE];
-	unsigned i, n = 0, seq;
+	uint i, n = 0, seq, max_idx = 0;
 	struct sdma_txreq *stx;
 	struct hfi1_ibdev *dev = &sde->dd->verbs_dev;
+	u8 max_starved_cnt = 0;
 
 #ifdef CONFIG_SDMA_VERBOSITY
 	dd_dev_err(sde->dd, "CONFIG SDMA(%u) %s:%d %s()\n", sde->this_idx,
@@ -1805,6 +1804,9 @@ static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail)
 				if (num_desc > avail)
 					break;
 				avail -= num_desc;
+				/* Find the most starved wait memeber */
+				iowait_starve_find_max(wait, &max_starved_cnt,
+						       n, &max_idx);
 				list_del_init(&wait->list);
 				waits[n++] = wait;
 			}
@@ -1813,8 +1815,13 @@ static void sdma_desc_avail(struct sdma_engine *sde, unsigned avail)
 		}
 	} while (read_seqretry(&dev->iowait_lock, seq));
 
+	/* Schedule the most starved one first */
+	if (n)
+		waits[max_idx]->wakeup(waits[max_idx], SDMA_AVAIL_REASON);
+
 	for (i = 0; i < n; i++)
-		waits[i]->wakeup(waits[i], SDMA_AVAIL_REASON);
+		if (i != max_idx)
+			waits[i]->wakeup(waits[i], SDMA_AVAIL_REASON);
 }
 
 /* head_lock must be held */
@@ -2351,7 +2358,8 @@ static inline u16 submit_tx(struct sdma_engine *sde, struct sdma_txreq *tx)
 static int sdma_check_progress(
 	struct sdma_engine *sde,
 	struct iowait *wait,
-	struct sdma_txreq *tx)
+	struct sdma_txreq *tx,
+	bool pkts_sent)
 {
 	int ret;
 
@@ -2364,7 +2372,7 @@ static int sdma_check_progress(
 
 		seq = raw_seqcount_begin(
 			(const seqcount_t *)&sde->head_lock.seqcount);
-		ret = wait->sleep(sde, wait, tx, seq);
+		ret = wait->sleep(sde, wait, tx, seq, pkts_sent);
 		if (ret == -EAGAIN)
 			sde->desc_avail = sdma_descq_freecnt(sde);
 	} else {
@@ -2378,6 +2386,7 @@ static int sdma_check_progress(
  * @sde: sdma engine to use
  * @wait: wait structure to use when full (may be NULL)
  * @tx: sdma_txreq to submit
+ * @pkts_sent: has any packet been sent yet?
  *
  * The call submits the tx into the ring.  If a iowait structure is non-NULL
  * the packet will be queued to the list in wait.
@@ -2389,7 +2398,8 @@ static int sdma_check_progress(
  */
 int sdma_send_txreq(struct sdma_engine *sde,
 		    struct iowait *wait,
-		    struct sdma_txreq *tx)
+		    struct sdma_txreq *tx,
+		    bool pkts_sent)
 {
 	int ret = 0;
 	u16 tail;
@@ -2431,7 +2441,7 @@ unlock_noconn:
 	ret = -ECOMM;
 	goto unlock;
 nodesc:
-	ret = sdma_check_progress(sde, wait, tx);
+	ret = sdma_check_progress(sde, wait, tx, pkts_sent);
 	if (ret == -EAGAIN) {
 		ret = 0;
 		goto retry;
@@ -2500,8 +2510,10 @@ retry:
 	}
 update_tail:
 	total_count = submit_count + flush_count;
-	if (wait)
+	if (wait) {
 		iowait_sdma_add(wait, total_count);
+		iowait_starve_clear(submit_count > 0, wait);
+	}
 	if (tail != INVALID_TAIL)
 		sdma_update_tail(sde, tail);
 	spin_unlock_irqrestore(&sde->tail_lock, flags);
@@ -2529,7 +2541,7 @@ unlock_noconn:
 	ret = -ECOMM;
 	goto update_tail;
 nodesc:
-	ret = sdma_check_progress(sde, wait, tx);
+	ret = sdma_check_progress(sde, wait, tx, submit_count > 0);
 	if (ret == -EAGAIN) {
 		ret = 0;
 		goto retry;
diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h
index 64f10b8b5db8..107011d8613b 100644
--- a/drivers/infiniband/hw/hfi1/sdma.h
+++ b/drivers/infiniband/hw/hfi1/sdma.h
@@ -852,7 +852,8 @@ struct iowait;
 
 int sdma_send_txreq(struct sdma_engine *sde,
 		    struct iowait *wait,
-		    struct sdma_txreq *tx);
+		    struct sdma_txreq *tx,
+		    bool pkts_sent);
 int sdma_send_txlist(struct sdma_engine *sde,
 		     struct iowait *wait,
 		     struct list_head *tx_list,
diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c
index 2f3bbcac1e34..6d2702ef34ac 100644
--- a/drivers/infiniband/hw/hfi1/sysfs.c
+++ b/drivers/infiniband/hw/hfi1/sysfs.c
@@ -95,7 +95,7 @@ static void port_release(struct kobject *kobj)
 	/* nothing to do since memory is freed by hfi1_free_devdata() */
 }
 
-static struct bin_attribute cc_table_bin_attr = {
+static const struct bin_attribute cc_table_bin_attr = {
 	.attr = {.name = "cc_table_bin", .mode = 0444},
 	.read = read_cc_table_bin,
 	.size = PAGE_SIZE,
@@ -137,7 +137,7 @@ static ssize_t read_cc_setting_bin(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute cc_setting_bin_attr = {
+static const struct bin_attribute cc_setting_bin_attr = {
 	.attr = {.name = "cc_settings_bin", .mode = 0444},
 	.read = read_cc_setting_bin,
 	.size = PAGE_SIZE,
diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c
index eafae487face..9938bb983ce6 100644
--- a/drivers/infiniband/hw/hfi1/trace.c
+++ b/drivers/infiniband/hw/hfi1/trace.c
@@ -47,7 +47,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-u8 ibhdr_exhdr_len(struct ib_header *hdr)
+static u8 __get_ib_hdr_len(struct ib_header *hdr)
 {
 	struct ib_other_headers *ohdr;
 	u8 opcode;
@@ -61,13 +61,69 @@ u8 ibhdr_exhdr_len(struct ib_header *hdr)
 	       0 : hdr_len_by_opcode[opcode] - (12 + 8);
 }
 
-#define IMM_PRN  "imm %d"
-#define RETH_PRN "reth vaddr 0x%.16llx rkey 0x%.8x dlen 0x%.8x"
-#define AETH_PRN "aeth syn 0x%.2x %s msn 0x%.8x"
-#define DETH_PRN "deth qkey 0x%.8x sqpn 0x%.6x"
-#define IETH_PRN "ieth rkey 0x%.8x"
-#define ATOMICACKETH_PRN "origdata %llx"
-#define ATOMICETH_PRN "vaddr 0x%llx rkey 0x%.8x sdata %llx cdata %llx"
+static u8 __get_16b_hdr_len(struct hfi1_16b_header *hdr)
+{
+	struct ib_other_headers *ohdr;
+	u8 opcode;
+
+	if (hfi1_16B_get_l4(hdr) == OPA_16B_L4_IB_LOCAL)
+		ohdr = &hdr->u.oth;
+	else
+		ohdr = &hdr->u.l.oth;
+	opcode = ib_bth_get_opcode(ohdr);
+	return hdr_len_by_opcode[opcode] == 0 ?
+	       0 : hdr_len_by_opcode[opcode] - (12 + 8 + 8);
+}
+
+u8 hfi1_trace_packet_hdr_len(struct hfi1_packet *packet)
+{
+	if (packet->etype != RHF_RCV_TYPE_BYPASS)
+		return __get_ib_hdr_len(packet->hdr);
+	else
+		return __get_16b_hdr_len(packet->hdr);
+}
+
+u8 hfi1_trace_opa_hdr_len(struct hfi1_opa_header *opa_hdr)
+{
+	if (!opa_hdr->hdr_type)
+		return __get_ib_hdr_len(&opa_hdr->ibh);
+	else
+		return __get_16b_hdr_len(&opa_hdr->opah);
+}
+
+const char *hfi1_trace_get_packet_str(struct hfi1_packet *packet)
+{
+	if (packet->etype != RHF_RCV_TYPE_BYPASS)
+		return "IB";
+
+	switch (hfi1_16B_get_l2(packet->hdr)) {
+	case 0:
+		return "0";
+	case 1:
+		return "1";
+	case 2:
+		return "16B";
+	case 3:
+		return "9B";
+	}
+	return "";
+}
+
+const char *hfi1_trace_get_packet_type_str(u8 l4)
+{
+	if (l4)
+		return "16B";
+	else
+		return "9B";
+}
+
+#define IMM_PRN  "imm:%d"
+#define RETH_PRN "reth vaddr:0x%.16llx rkey:0x%.8x dlen:0x%.8x"
+#define AETH_PRN "aeth syn:0x%.2x %s msn:0x%.8x"
+#define DETH_PRN "deth qkey:0x%.8x sqpn:0x%.6x"
+#define IETH_PRN "ieth rkey:0x%.8x"
+#define ATOMICACKETH_PRN "origdata:%llx"
+#define ATOMICETH_PRN "vaddr:0x%llx rkey:0x%.8x sdata:%llx cdata:%llx"
 
 #define OP(transport, op) IB_OPCODE_## transport ## _ ## op
 
@@ -84,6 +140,125 @@ static const char *parse_syndrome(u8 syndrome)
 	return "";
 }
 
+void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr,
+			     u8 *ack, u8 *becn, u8 *fecn, u8 *mig,
+			     u8 *se, u8 *pad, u8 *opcode, u8 *tver,
+			     u16 *pkey, u32 *psn, u32 *qpn)
+{
+	*ack = ib_bth_get_ackreq(ohdr);
+	*becn = ib_bth_get_becn(ohdr);
+	*fecn = ib_bth_get_fecn(ohdr);
+	*mig = ib_bth_get_migreq(ohdr);
+	*se = ib_bth_get_se(ohdr);
+	*pad = ib_bth_get_pad(ohdr);
+	*opcode = ib_bth_get_opcode(ohdr);
+	*tver = ib_bth_get_tver(ohdr);
+	*pkey = ib_bth_get_pkey(ohdr);
+	*psn = ib_bth_get_psn(ohdr);
+	*qpn = ib_bth_get_qpn(ohdr);
+}
+
+void hfi1_trace_parse_16b_bth(struct ib_other_headers *ohdr,
+			      u8 *ack, u8 *mig, u8 *opcode,
+			      u8 *pad, u8 *se, u8 *tver,
+			      u32 *psn, u32 *qpn)
+{
+	*ack = ib_bth_get_ackreq(ohdr);
+	*mig = ib_bth_get_migreq(ohdr);
+	*opcode = ib_bth_get_opcode(ohdr);
+	*pad = ib_bth_get_pad(ohdr);
+	*se = ib_bth_get_se(ohdr);
+	*tver = ib_bth_get_tver(ohdr);
+	*psn = ib_bth_get_psn(ohdr);
+	*qpn = ib_bth_get_qpn(ohdr);
+}
+
+void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5,
+			     u8 *lnh, u8 *lver, u8 *sl, u8 *sc,
+			     u16 *len, u32 *dlid, u32 *slid)
+{
+	*lnh = ib_get_lnh(hdr);
+	*lver = ib_get_lver(hdr);
+	*sl = ib_get_sl(hdr);
+	*sc = ib_get_sc(hdr) | (sc5 << 4);
+	*len = ib_get_len(hdr);
+	*dlid = ib_get_dlid(hdr);
+	*slid = ib_get_slid(hdr);
+}
+
+void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
+			      u8 *age, u8 *becn, u8 *fecn,
+			      u8 *l4, u8 *rc, u8 *sc,
+			      u16 *entropy, u16 *len, u16 *pkey,
+			      u32 *dlid, u32 *slid)
+{
+	*age = hfi1_16B_get_age(hdr);
+	*becn = hfi1_16B_get_becn(hdr);
+	*fecn = hfi1_16B_get_fecn(hdr);
+	*l4 = hfi1_16B_get_l4(hdr);
+	*rc = hfi1_16B_get_rc(hdr);
+	*sc = hfi1_16B_get_sc(hdr);
+	*entropy = hfi1_16B_get_entropy(hdr);
+	*len = hfi1_16B_get_len(hdr);
+	*pkey = hfi1_16B_get_pkey(hdr);
+	*dlid = hfi1_16B_get_dlid(hdr);
+	*slid = hfi1_16B_get_slid(hdr);
+}
+
+#define LRH_PRN "len:%d sc:%d dlid:0x%.4x slid:0x%.4x "
+#define LRH_9B_PRN "lnh:%d,%s lver:%d sl:%d"
+#define LRH_16B_PRN "age:%d becn:%d fecn:%d l4:%d " \
+		    "rc:%d sc:%d pkey:0x%.4x entropy:0x%.4x"
+const char *hfi1_trace_fmt_lrh(struct trace_seq *p, bool bypass,
+			       u8 age, u8 becn, u8 fecn, u8 l4,
+			       u8 lnh, const char *lnh_name, u8 lver,
+			       u8 rc, u8 sc, u8 sl, u16 entropy,
+			       u16 len, u16 pkey, u32 dlid, u32 slid)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+
+	trace_seq_printf(p, LRH_PRN, len, sc, dlid, slid);
+
+	if (bypass)
+		trace_seq_printf(p, LRH_16B_PRN,
+				 age, becn, fecn, l4, rc, sc, pkey, entropy);
+
+	else
+		trace_seq_printf(p, LRH_9B_PRN,
+				 lnh, lnh_name, lver, sl);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
+#define BTH_9B_PRN \
+	"op:0x%.2x,%s se:%d m:%d pad:%d tver:%d pkey:0x%.4x " \
+	"f:%d b:%d qpn:0x%.6x a:%d psn:0x%.8x"
+#define BTH_16B_PRN \
+	"op:0x%.2x,%s se:%d m:%d pad:%d tver:%d " \
+	"qpn:0x%.6x a:%d psn:0x%.8x"
+const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass,
+			       u8 ack, u8 becn, u8 fecn, u8 mig,
+			       u8 se, u8 pad, u8 opcode, const char *opname,
+			       u8 tver, u16 pkey, u32 psn, u32 qpn)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+
+	if (bypass)
+		trace_seq_printf(p, BTH_16B_PRN,
+				 opcode, opname,
+				 se, mig, pad, tver, qpn, ack, psn);
+
+	else
+		trace_seq_printf(p, BTH_9B_PRN,
+				 opcode, opname,
+				 se, mig, pad, tver, pkey, fecn, becn,
+				 qpn, ack, psn);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 const char *parse_everbs_hdrs(
 	struct trace_seq *p,
 	u8 opcode,
diff --git a/drivers/infiniband/hw/hfi1/trace.h b/drivers/infiniband/hw/hfi1/trace.h
index 92dc88f013c9..af50c0793450 100644
--- a/drivers/infiniband/hw/hfi1/trace.h
+++ b/drivers/infiniband/hw/hfi1/trace.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -51,3 +51,4 @@
 #include "trace_rc.h"
 #include "trace_rx.h"
 #include "trace_tx.h"
+#include "trace_mmu.h"
diff --git a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h
index 090f6b506953..6721f84dafa5 100644
--- a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h
+++ b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h
@@ -55,8 +55,79 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM hfi1_ibhdrs
 
+#define ib_opcode_name(opcode) { IB_OPCODE_##opcode, #opcode  }
+#define show_ib_opcode(opcode)                             \
+__print_symbolic(opcode,                                   \
+	ib_opcode_name(RC_SEND_FIRST),                     \
+	ib_opcode_name(RC_SEND_MIDDLE),                    \
+	ib_opcode_name(RC_SEND_LAST),                      \
+	ib_opcode_name(RC_SEND_LAST_WITH_IMMEDIATE),       \
+	ib_opcode_name(RC_SEND_ONLY),                      \
+	ib_opcode_name(RC_SEND_ONLY_WITH_IMMEDIATE),       \
+	ib_opcode_name(RC_RDMA_WRITE_FIRST),               \
+	ib_opcode_name(RC_RDMA_WRITE_MIDDLE),              \
+	ib_opcode_name(RC_RDMA_WRITE_LAST),                \
+	ib_opcode_name(RC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \
+	ib_opcode_name(RC_RDMA_WRITE_ONLY),                \
+	ib_opcode_name(RC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \
+	ib_opcode_name(RC_RDMA_READ_REQUEST),              \
+	ib_opcode_name(RC_RDMA_READ_RESPONSE_FIRST),       \
+	ib_opcode_name(RC_RDMA_READ_RESPONSE_MIDDLE),      \
+	ib_opcode_name(RC_RDMA_READ_RESPONSE_LAST),        \
+	ib_opcode_name(RC_RDMA_READ_RESPONSE_ONLY),        \
+	ib_opcode_name(RC_ACKNOWLEDGE),                    \
+	ib_opcode_name(RC_ATOMIC_ACKNOWLEDGE),             \
+	ib_opcode_name(RC_COMPARE_SWAP),                   \
+	ib_opcode_name(RC_FETCH_ADD),                      \
+	ib_opcode_name(UC_SEND_FIRST),                     \
+	ib_opcode_name(UC_SEND_MIDDLE),                    \
+	ib_opcode_name(UC_SEND_LAST),                      \
+	ib_opcode_name(UC_SEND_LAST_WITH_IMMEDIATE),       \
+	ib_opcode_name(UC_SEND_ONLY),                      \
+	ib_opcode_name(UC_SEND_ONLY_WITH_IMMEDIATE),       \
+	ib_opcode_name(UC_RDMA_WRITE_FIRST),               \
+	ib_opcode_name(UC_RDMA_WRITE_MIDDLE),              \
+	ib_opcode_name(UC_RDMA_WRITE_LAST),                \
+	ib_opcode_name(UC_RDMA_WRITE_LAST_WITH_IMMEDIATE), \
+	ib_opcode_name(UC_RDMA_WRITE_ONLY),                \
+	ib_opcode_name(UC_RDMA_WRITE_ONLY_WITH_IMMEDIATE), \
+	ib_opcode_name(UD_SEND_ONLY),                      \
+	ib_opcode_name(UD_SEND_ONLY_WITH_IMMEDIATE),       \
+	ib_opcode_name(CNP))
+
 u8 ibhdr_exhdr_len(struct ib_header *hdr);
 const char *parse_everbs_hdrs(struct trace_seq *p, u8 opcode, void *ehdrs);
+u8 hfi1_trace_opa_hdr_len(struct hfi1_opa_header *opah);
+u8 hfi1_trace_packet_hdr_len(struct hfi1_packet *packet);
+const char *hfi1_trace_get_packet_type_str(u8 l4);
+const char *hfi1_trace_get_packet_str(struct hfi1_packet *packet);
+void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr,
+			     u8 *ack, u8 *becn, u8 *fecn, u8 *mig,
+			     u8 *se, u8 *pad, u8 *opcode, u8 *tver,
+			     u16 *pkey, u32 *psn, u32 *qpn);
+void hfi1_trace_parse_9b_hdr(struct ib_header *hdr, bool sc5,
+			     u8 *lnh, u8 *lver, u8 *sl, u8 *sc,
+			     u16 *len, u32 *dlid, u32 *slid);
+void hfi1_trace_parse_16b_bth(struct ib_other_headers *ohdr,
+			      u8 *ack, u8 *mig, u8 *opcode,
+			      u8 *pad, u8 *se, u8 *tver,
+			      u32 *psn, u32 *qpn);
+void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
+			      u8 *age, u8 *becn, u8 *fecn,
+			      u8 *l4, u8 *rc, u8 *sc,
+			      u16 *entropy, u16 *len, u16 *pkey,
+			      u32 *dlid, u32 *slid);
+
+const char *hfi1_trace_fmt_lrh(struct trace_seq *p, bool bypass,
+			       u8 age, u8 becn, u8 fecn, u8 l4,
+			       u8 lnh, const char *lnh_name, u8 lver,
+			       u8 rc, u8 sc, u8 sl, u16 entropy,
+			       u16 len, u16 pkey, u32 dlid, u32 slid);
+
+const char *hfi1_trace_fmt_bth(struct trace_seq *p, bool bypass,
+			       u8 ack, u8 becn, u8 fecn, u8 mig,
+			       u8 se, u8 pad, u8 opcode, const char *opname,
+			       u8 tver, u16 pkey, u32 psn, u32 qpn);
 
 #define __parse_ib_ehdrs(op, ehdrs) parse_everbs_hdrs(p, op, ehdrs)
 
@@ -65,140 +136,303 @@ const char *parse_everbs_hdrs(struct trace_seq *p, u8 opcode, void *ehdrs);
 __print_symbolic(lrh,                    \
 	lrh_name(LRH_BTH),               \
 	lrh_name(LRH_GRH))
+#define PKT_ENTRY(pkt)	__string(ptype,  hfi1_trace_get_packet_str(packet))
+#define PKT_ASSIGN(pkt) __assign_str(ptype, hfi1_trace_get_packet_str(packet))
 
-#define LRH_PRN "vl %d lver %d sl %d lnh %d,%s dlid %.4x len %d slid %.4x"
-#define BTH_PRN \
-	"op 0x%.2x,%s se %d m %d pad %d tver %d pkey 0x%.4x " \
-	"f %d b %d qpn 0x%.6x a %d psn 0x%.8x"
-#define EHDR_PRN "%s"
-
-DECLARE_EVENT_CLASS(hfi1_ibhdr_template,
+DECLARE_EVENT_CLASS(hfi1_input_ibhdr_template,
 		    TP_PROTO(struct hfi1_devdata *dd,
-			     struct ib_header *hdr),
-		    TP_ARGS(dd, hdr),
+			     struct hfi1_packet *packet,
+			     bool sc5),
+		    TP_ARGS(dd, packet, sc5),
 		    TP_STRUCT__entry(
 			DD_DEV_ENTRY(dd)
-			/* LRH */
-			__field(u8, vl)
+			PKT_ENTRY(packet)
+			__field(bool, bypass)
+			__field(u8, ack)
+			__field(u8, age)
+			__field(u8, becn)
+			__field(u8, fecn)
+			__field(u8, l4)
+			__field(u8, lnh)
 			__field(u8, lver)
+			__field(u8, mig)
+			__field(u8, opcode)
+			__field(u8, pad)
+			__field(u8, rc)
+			__field(u8, sc)
+			__field(u8, se)
 			__field(u8, sl)
-			__field(u8, lnh)
-			__field(u16, dlid)
+			__field(u8, tver)
+			__field(u16, entropy)
 			__field(u16, len)
-			__field(u16, slid)
-			/* BTH */
+			__field(u16, pkey)
+			__field(u32, dlid)
+			__field(u32, psn)
+			__field(u32, qpn)
+			__field(u32, slid)
+			/* extended headers */
+			__dynamic_array(u8, ehdrs,
+					hfi1_trace_packet_hdr_len(packet))
+			),
+		    TP_fast_assign(
+			DD_DEV_ASSIGN(dd);
+			PKT_ASSIGN(packet);
+
+			if (packet->etype == RHF_RCV_TYPE_BYPASS) {
+				__entry->bypass = true;
+				hfi1_trace_parse_16b_hdr(packet->hdr,
+							 &__entry->age,
+							 &__entry->becn,
+							 &__entry->fecn,
+							 &__entry->l4,
+							 &__entry->rc,
+							 &__entry->sc,
+							 &__entry->entropy,
+							 &__entry->len,
+							 &__entry->pkey,
+							 &__entry->dlid,
+							 &__entry->slid);
+
+				  hfi1_trace_parse_16b_bth(packet->ohdr,
+							   &__entry->ack,
+							   &__entry->mig,
+							   &__entry->opcode,
+							   &__entry->pad,
+							   &__entry->se,
+							   &__entry->tver,
+							   &__entry->psn,
+							   &__entry->qpn);
+			} else {
+				__entry->bypass = false;
+				hfi1_trace_parse_9b_hdr(packet->hdr, sc5,
+							&__entry->lnh,
+							&__entry->lver,
+							&__entry->sl,
+							&__entry->sc,
+							&__entry->len,
+							&__entry->dlid,
+							&__entry->slid);
+
+				  hfi1_trace_parse_9b_bth(packet->ohdr,
+							  &__entry->ack,
+							  &__entry->becn,
+							  &__entry->fecn,
+							  &__entry->mig,
+							  &__entry->se,
+							  &__entry->pad,
+							  &__entry->opcode,
+							  &__entry->tver,
+							  &__entry->pkey,
+							  &__entry->psn,
+							  &__entry->qpn);
+				}
+				/* extended headers */
+				memcpy(__get_dynamic_array(ehdrs),
+				       &packet->ohdr->u,
+				       __get_dynamic_array_len(ehdrs));
+			 ),
+		    TP_printk("[%s] (%s) %s %s hlen:%d %s",
+			      __get_str(dev),
+			      __get_str(ptype),
+			      hfi1_trace_fmt_lrh(p,
+						 __entry->bypass,
+						 __entry->age,
+						 __entry->becn,
+						 __entry->fecn,
+						 __entry->l4,
+						 __entry->lnh,
+						 show_lnh(__entry->lnh),
+						 __entry->lver,
+						 __entry->rc,
+						 __entry->sc,
+						 __entry->sl,
+						 __entry->entropy,
+						 __entry->len,
+						 __entry->pkey,
+						 __entry->dlid,
+						 __entry->slid),
+			      hfi1_trace_fmt_bth(p,
+						 __entry->bypass,
+						 __entry->ack,
+						 __entry->becn,
+						 __entry->fecn,
+						 __entry->mig,
+						 __entry->se,
+						 __entry->pad,
+						 __entry->opcode,
+						 show_ib_opcode(__entry->opcode),
+						 __entry->tver,
+						 __entry->pkey,
+						 __entry->psn,
+						 __entry->qpn),
+			      /* extended headers */
+			      __get_dynamic_array_len(ehdrs),
+			      __parse_ib_ehdrs(
+					__entry->opcode,
+					(void *)__get_dynamic_array(ehdrs))
+			     )
+);
+
+DEFINE_EVENT(hfi1_input_ibhdr_template, input_ibhdr,
+	     TP_PROTO(struct hfi1_devdata *dd,
+		      struct hfi1_packet *packet, bool sc5),
+	     TP_ARGS(dd, packet, sc5));
+
+DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
+		    TP_PROTO(struct hfi1_devdata *dd,
+			     struct hfi1_opa_header *opah, bool sc5),
+		    TP_ARGS(dd, opah, sc5),
+		    TP_STRUCT__entry(
+			DD_DEV_ENTRY(dd)
+			__field(bool, bypass)
+			__field(u8, ack)
+			__field(u8, age)
+			__field(u8, becn)
+			__field(u8, fecn)
+			__field(u8, l4)
+			__field(u8, lnh)
+			__field(u8, lver)
+			__field(u8, mig)
 			__field(u8, opcode)
-			__field(u8, se)
-			__field(u8, m)
 			__field(u8, pad)
+			__field(u8, rc)
+			__field(u8, sc)
+			__field(u8, se)
+			__field(u8, sl)
 			__field(u8, tver)
+			__field(u16, entropy)
+			__field(u16, len)
 			__field(u16, pkey)
-			__field(u8, f)
-			__field(u8, b)
-			__field(u32, qpn)
-			__field(u8, a)
+			__field(u32, dlid)
 			__field(u32, psn)
+			__field(u32, qpn)
+			__field(u32, slid)
 			/* extended headers */
-			__dynamic_array(u8, ehdrs, ibhdr_exhdr_len(hdr))
+			__dynamic_array(u8, ehdrs,
+					hfi1_trace_opa_hdr_len(opah))
 			),
-		      TP_fast_assign(
+		    TP_fast_assign(
 			struct ib_other_headers *ohdr;
 
 			DD_DEV_ASSIGN(dd);
-			/* LRH */
-			__entry->vl =
-			(u8)(be16_to_cpu(hdr->lrh[0]) >> 12);
-			__entry->lver =
-			(u8)(be16_to_cpu(hdr->lrh[0]) >> 8) & 0xf;
-			__entry->sl =
-			(u8)(be16_to_cpu(hdr->lrh[0]) >> 4) & 0xf;
-			__entry->lnh =
-			(u8)(be16_to_cpu(hdr->lrh[0]) & 3);
-			__entry->dlid =
-			be16_to_cpu(hdr->lrh[1]);
-			/* allow for larger len */
-			__entry->len =
-			be16_to_cpu(hdr->lrh[2]);
-			__entry->slid =
-			be16_to_cpu(hdr->lrh[3]);
-			/* BTH */
-			if (__entry->lnh == HFI1_LRH_BTH)
-			ohdr = &hdr->u.oth;
-			else
-			ohdr = &hdr->u.l.oth;
-			__entry->opcode =
-			(be32_to_cpu(ohdr->bth[0]) >> 24) & 0xff;
-			__entry->se =
-			(be32_to_cpu(ohdr->bth[0]) >> 23) & 1;
-			__entry->m =
-			(be32_to_cpu(ohdr->bth[0]) >> 22) & 1;
-			__entry->pad =
-			(be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
-			__entry->tver =
-			(be32_to_cpu(ohdr->bth[0]) >> 16) & 0xf;
-			__entry->pkey =
-			be32_to_cpu(ohdr->bth[0]) & 0xffff;
-			__entry->f =
-			(be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) &
-			IB_FECN_MASK;
-			__entry->b =
-			(be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) &
-			IB_BECN_MASK;
-			__entry->qpn =
-			be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK;
-			__entry->a =
-			(be32_to_cpu(ohdr->bth[2]) >> 31) & 1;
-			/* allow for larger PSN */
-			__entry->psn =
-			be32_to_cpu(ohdr->bth[2]) & 0x7fffffff;
+
+			if (opah->hdr_type)  {
+				__entry->bypass = true;
+				hfi1_trace_parse_16b_hdr(&opah->opah,
+							 &__entry->age,
+							 &__entry->becn,
+							 &__entry->fecn,
+							 &__entry->l4,
+							 &__entry->rc,
+							 &__entry->sc,
+							 &__entry->entropy,
+							 &__entry->len,
+							 &__entry->pkey,
+							 &__entry->dlid,
+							 &__entry->slid);
+
+				if (entry->l4 == OPA_16B_L4_IB_LOCAL)
+					ohdr = &opah->opah.u.oth;
+				else
+					ohdr = &opah->opah.u.l.oth;
+				hfi1_trace_parse_16b_bth(ohdr,
+							 &__entry->ack,
+							 &__entry->mig,
+							 &__entry->opcode,
+							 &__entry->pad,
+							 &__entry->se,
+							 &__entry->tver,
+							 &__entry->psn,
+							 &__entry->qpn);
+			} else {
+				__entry->bypass = false;
+				hfi1_trace_parse_9b_hdr(&opah->ibh, sc5,
+							&__entry->lnh,
+							&__entry->lver,
+							&__entry->sl,
+							&__entry->sc,
+							&__entry->len,
+							&__entry->dlid,
+							&__entry->slid);
+				if (entry->lnh == HFI1_LRH_BTH)
+					ohdr = &opah->ibh.u.oth;
+				else
+					ohdr = &opah->ibh.u.l.oth;
+				hfi1_trace_parse_9b_bth(ohdr,
+							&__entry->ack,
+							&__entry->becn,
+							&__entry->fecn,
+							&__entry->mig,
+							&__entry->se,
+							&__entry->pad,
+							&__entry->opcode,
+							&__entry->tver,
+							&__entry->pkey,
+							&__entry->psn,
+							&__entry->qpn);
+			}
+
 			/* extended headers */
-			memcpy(__get_dynamic_array(ehdrs), &ohdr->u,
-			       ibhdr_exhdr_len(hdr));
-			),
-		TP_printk("[%s] " LRH_PRN " " BTH_PRN " " EHDR_PRN,
-			  __get_str(dev),
-			  /* LRH */
-			  __entry->vl,
-			  __entry->lver,
-			  __entry->sl,
-			  __entry->lnh, show_lnh(__entry->lnh),
-			  __entry->dlid,
-			  __entry->len,
-			  __entry->slid,
-			  /* BTH */
-			  __entry->opcode, show_ib_opcode(__entry->opcode),
-			  __entry->se,
-			  __entry->m,
-			  __entry->pad,
-			  __entry->tver,
-			  __entry->pkey,
-			  __entry->f,
-			  __entry->b,
-			  __entry->qpn,
-			  __entry->a,
-			  __entry->psn,
-			  /* extended headers */
-			  __parse_ib_ehdrs(
-				__entry->opcode,
-				(void *)__get_dynamic_array(ehdrs))
-			)
+			memcpy(__get_dynamic_array(ehdrs),
+			       &ohdr->u, __get_dynamic_array_len(ehdrs));
+		    ),
+		    TP_printk("[%s] (%s) %s %s hlen:%d %s",
+			      __get_str(dev),
+			      hfi1_trace_get_packet_type_str(__entry->l4),
+			      hfi1_trace_fmt_lrh(p,
+						 __entry->bypass,
+						 __entry->age,
+						 __entry->becn,
+						 __entry->fecn,
+						 __entry->l4,
+						 __entry->lnh,
+						 show_lnh(__entry->lnh),
+						 __entry->lver,
+						 __entry->rc,
+						 __entry->sc,
+						 __entry->sl,
+						 __entry->entropy,
+						 __entry->len,
+						 __entry->pkey,
+						 __entry->dlid,
+						 __entry->slid),
+			      hfi1_trace_fmt_bth(p,
+						 __entry->bypass,
+						 __entry->ack,
+						 __entry->becn,
+						 __entry->fecn,
+						 __entry->mig,
+						 __entry->se,
+						 __entry->pad,
+						 __entry->opcode,
+						 show_ib_opcode(__entry->opcode),
+						 __entry->tver,
+						 __entry->pkey,
+						 __entry->psn,
+						 __entry->qpn),
+			      /* extended headers */
+			      __get_dynamic_array_len(ehdrs),
+			      __parse_ib_ehdrs(
+					__entry->opcode,
+					(void *)__get_dynamic_array(ehdrs))
+			     )
 );
 
-DEFINE_EVENT(hfi1_ibhdr_template, input_ibhdr,
-	     TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr),
-	     TP_ARGS(dd, hdr));
+DEFINE_EVENT(hfi1_output_ibhdr_template, pio_output_ibhdr,
+	     TP_PROTO(struct hfi1_devdata *dd,
+		      struct hfi1_opa_header *opah, bool sc5),
+	     TP_ARGS(dd, opah, sc5));
 
-DEFINE_EVENT(hfi1_ibhdr_template, pio_output_ibhdr,
-	     TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr),
-	     TP_ARGS(dd, hdr));
+DEFINE_EVENT(hfi1_output_ibhdr_template, ack_output_ibhdr,
+	     TP_PROTO(struct hfi1_devdata *dd,
+		      struct hfi1_opa_header *opah, bool sc5),
+	     TP_ARGS(dd, opah, sc5));
 
-DEFINE_EVENT(hfi1_ibhdr_template, ack_output_ibhdr,
-	     TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr),
-	     TP_ARGS(dd, hdr));
+DEFINE_EVENT(hfi1_output_ibhdr_template, sdma_output_ibhdr,
+	     TP_PROTO(struct hfi1_devdata *dd,
+		      struct hfi1_opa_header *opah, bool sc5),
+	     TP_ARGS(dd, opah, sc5));
 
-DEFINE_EVENT(hfi1_ibhdr_template, sdma_output_ibhdr,
-	     TP_PROTO(struct hfi1_devdata *dd, struct ib_header *hdr),
-	     TP_ARGS(dd, hdr));
 
 #endif /* __HFI1_TRACE_IBHDRS_H */
 
diff --git a/drivers/infiniband/hw/hfi1/trace_misc.h b/drivers/infiniband/hw/hfi1/trace_misc.h
index deac77ddaeab..8db2253523ff 100644
--- a/drivers/infiniband/hw/hfi1/trace_misc.h
+++ b/drivers/infiniband/hw/hfi1/trace_misc.h
@@ -72,6 +72,26 @@ TRACE_EVENT(hfi1_interrupt,
 		      __entry->src)
 );
 
+DECLARE_EVENT_CLASS(
+	hfi1_csr_template,
+	TP_PROTO(void __iomem *addr, u64 value),
+	TP_ARGS(addr, value),
+	TP_STRUCT__entry(
+		__field(void __iomem *, addr)
+		__field(u64, value)
+	),
+	TP_fast_assign(
+		__entry->addr = addr;
+		__entry->value = value;
+	),
+	TP_printk("addr %p value %llx", __entry->addr, __entry->value)
+);
+
+DEFINE_EVENT(
+	hfi1_csr_template, hfi1_write_rcvarray,
+	TP_PROTO(void __iomem *addr, u64 value),
+	TP_ARGS(addr, value));
+
 #ifdef CONFIG_FAULT_INJECTION
 TRACE_EVENT(hfi1_fault_opcode,
 	    TP_PROTO(struct rvt_qp *qp, u8 opcode),
diff --git a/drivers/infiniband/hw/hfi1/trace_mmu.h b/drivers/infiniband/hw/hfi1/trace_mmu.h
new file mode 100644
index 000000000000..3b7abbc382c2
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/trace_mmu.h
@@ -0,0 +1,95 @@
+/*
+ * Copyright(c) 2017 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.
+ *
+ */
+#if !defined(__HFI1_TRACE_MMU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __HFI1_TRACE_MMU_H
+
+#include <linux/tracepoint.h>
+#include <linux/trace_seq.h>
+
+#include "hfi.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hfi1_mmu
+
+DECLARE_EVENT_CLASS(hfi1_mmu_rb_template,
+		    TP_PROTO(unsigned long addr, unsigned long len),
+		    TP_ARGS(addr, len),
+		    TP_STRUCT__entry(__field(unsigned long, addr)
+				     __field(unsigned long, len)
+			    ),
+		    TP_fast_assign(__entry->addr = addr;
+				   __entry->len = len;
+			    ),
+		    TP_printk("MMU node addr 0x%lx, len %lu",
+			      __entry->addr,
+			      __entry->len
+			    )
+);
+
+DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_rb_insert,
+	     TP_PROTO(unsigned long addr, unsigned long len),
+	     TP_ARGS(addr, len));
+
+DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_rb_search,
+	     TP_PROTO(unsigned long addr, unsigned long len),
+	     TP_ARGS(addr, len));
+
+DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_rb_remove,
+	     TP_PROTO(unsigned long addr, unsigned long len),
+	     TP_ARGS(addr, len));
+
+DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_mem_invalidate,
+	     TP_PROTO(unsigned long addr, unsigned long len),
+	     TP_ARGS(addr, len));
+
+#endif /* __HFI1_TRACE_RC_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_mmu
+#include <trace/define_trace.h>
diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h
index f77e59fb43fe..f9909d240dcc 100644
--- a/drivers/infiniband/hw/hfi1/trace_rx.h
+++ b/drivers/infiniband/hw/hfi1/trace_rx.h
@@ -52,9 +52,25 @@
 
 #include "hfi.h"
 
+#define tidtype_name(type) { PT_##type, #type }
+#define show_tidtype(type)                   \
+__print_symbolic(type,                       \
+	tidtype_name(EXPECTED),              \
+	tidtype_name(EAGER),                 \
+	tidtype_name(INVALID))               \
+
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM hfi1_rx
 
+#define packettype_name(etype) { RHF_RCV_TYPE_##etype, #etype }
+#define show_packettype(etype)                  \
+__print_symbolic(etype,                         \
+	packettype_name(EXPECTED),              \
+	packettype_name(EAGER),                 \
+	packettype_name(IB),                    \
+	packettype_name(ERROR),                 \
+	packettype_name(BYPASS))
+
 TRACE_EVENT(hfi1_rcvhdr,
 	    TP_PROTO(struct hfi1_devdata *dd,
 		     u32 ctxt,
@@ -98,24 +114,24 @@ TRACE_EVENT(hfi1_rcvhdr,
 );
 
 TRACE_EVENT(hfi1_receive_interrupt,
-	    TP_PROTO(struct hfi1_devdata *dd, u32 ctxt),
-	    TP_ARGS(dd, ctxt),
+	    TP_PROTO(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd),
+	    TP_ARGS(dd, rcd),
 	    TP_STRUCT__entry(DD_DEV_ENTRY(dd)
 			     __field(u32, ctxt)
 			     __field(u8, slow_path)
 			     __field(u8, dma_rtail)
 			     ),
 	    TP_fast_assign(DD_DEV_ASSIGN(dd);
-			__entry->ctxt = ctxt;
-			if (dd->rcd[ctxt]->do_interrupt ==
+			__entry->ctxt = rcd->ctxt;
+			if (rcd->do_interrupt ==
 			    &handle_receive_interrupt) {
 				__entry->slow_path = 1;
 				__entry->dma_rtail = 0xFF;
-			} else if (dd->rcd[ctxt]->do_interrupt ==
+			} else if (rcd->do_interrupt ==
 					&handle_receive_interrupt_dma_rtail){
 				__entry->dma_rtail = 1;
 				__entry->slow_path = 0;
-			} else if (dd->rcd[ctxt]->do_interrupt ==
+			} else if (rcd->do_interrupt ==
 					&handle_receive_interrupt_nodma_rtail) {
 				__entry->dma_rtail = 0;
 				__entry->slow_path = 0;
@@ -129,7 +145,8 @@ TRACE_EVENT(hfi1_receive_interrupt,
 		      )
 );
 
-TRACE_EVENT(hfi1_exp_tid_reg,
+DECLARE_EVENT_CLASS(
+	    hfi1_exp_tid_reg_unreg,
 	    TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr,
 		     u32 npages, unsigned long va, unsigned long pa,
 		     dma_addr_t dma),
@@ -163,38 +180,45 @@ TRACE_EVENT(hfi1_exp_tid_reg,
 		      )
 	);
 
-TRACE_EVENT(hfi1_exp_tid_unreg,
-	    TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages,
-		     unsigned long va, unsigned long pa, dma_addr_t dma),
-	    TP_ARGS(ctxt, subctxt, rarr, npages, va, pa, dma),
-	    TP_STRUCT__entry(
-			     __field(unsigned int, ctxt)
-			     __field(u16, subctxt)
-			     __field(u32, rarr)
-			     __field(u32, npages)
-			     __field(unsigned long, va)
-			     __field(unsigned long, pa)
-			     __field(dma_addr_t, dma)
-			     ),
-	    TP_fast_assign(
-			   __entry->ctxt = ctxt;
-			   __entry->subctxt = subctxt;
-			   __entry->rarr = rarr;
-			   __entry->npages = npages;
-			   __entry->va = va;
-			   __entry->pa = pa;
-			   __entry->dma = dma;
-			   ),
-	    TP_printk("[%u:%u] entry:%u, %u pages @ 0x%lx, va:0x%lx dma:0x%llx",
-		      __entry->ctxt,
-		      __entry->subctxt,
-		      __entry->rarr,
-		      __entry->npages,
-		      __entry->pa,
-		      __entry->va,
-		      __entry->dma
-		      )
-	);
+DEFINE_EVENT(
+	hfi1_exp_tid_reg_unreg, hfi1_exp_tid_unreg,
+	TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages,
+		 unsigned long va, unsigned long pa, dma_addr_t dma),
+	TP_ARGS(ctxt, subctxt, rarr, npages, va, pa, dma));
+
+DEFINE_EVENT(
+	hfi1_exp_tid_reg_unreg, hfi1_exp_tid_reg,
+	TP_PROTO(unsigned int ctxt, u16 subctxt, u32 rarr, u32 npages,
+		 unsigned long va, unsigned long pa, dma_addr_t dma),
+	TP_ARGS(ctxt, subctxt, rarr, npages, va, pa, dma));
+
+TRACE_EVENT(
+	hfi1_put_tid,
+	TP_PROTO(struct hfi1_devdata *dd,
+		 u32 index, u32 type, unsigned long pa, u16 order),
+	TP_ARGS(dd, index, type, pa, order),
+	TP_STRUCT__entry(
+		DD_DEV_ENTRY(dd)
+		__field(unsigned long, pa);
+		__field(u32, index);
+		__field(u32, type);
+		__field(u16, order);
+	),
+	TP_fast_assign(
+		DD_DEV_ASSIGN(dd);
+		__entry->pa = pa;
+		__entry->index = index;
+		__entry->type = type;
+		__entry->order = order;
+	),
+	TP_printk("[%s] type %s pa %lx index %u order %u",
+		  __get_str(dev),
+		  show_tidtype(__entry->type),
+		  __entry->pa,
+		  __entry->index,
+		  __entry->order
+	)
+);
 
 TRACE_EVENT(hfi1_exp_tid_inval,
 	    TP_PROTO(unsigned int ctxt, u16 subctxt, unsigned long va, u32 rarr,
diff --git a/drivers/infiniband/hw/hfi1/trace_tx.h b/drivers/infiniband/hw/hfi1/trace_tx.h
index c59809a7f121..c57af3b31fe1 100644
--- a/drivers/infiniband/hw/hfi1/trace_tx.h
+++ b/drivers/infiniband/hw/hfi1/trace_tx.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.
@@ -198,6 +198,140 @@ TRACE_EVENT(hfi1_sdma_engine_select,
 		      )
 );
 
+TRACE_EVENT(hfi1_sdma_user_free_queues,
+	    TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt),
+	    TP_ARGS(dd, ctxt, subctxt),
+	    TP_STRUCT__entry(DD_DEV_ENTRY(dd)
+			     __field(u16, ctxt)
+			     __field(u16, subctxt)
+			     ),
+	    TP_fast_assign(DD_DEV_ASSIGN(dd);
+			   __entry->ctxt = ctxt;
+			   __entry->subctxt = subctxt;
+			   ),
+	    TP_printk("[%s] SDMA [%u:%u] Freeing user SDMA queues",
+		      __get_str(dev),
+		      __entry->ctxt,
+		      __entry->subctxt
+		      )
+);
+
+TRACE_EVENT(hfi1_sdma_user_process_request,
+	    TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt,
+		     u16 comp_idx),
+	    TP_ARGS(dd, ctxt, subctxt, comp_idx),
+	    TP_STRUCT__entry(DD_DEV_ENTRY(dd)
+			     __field(u16, ctxt)
+			     __field(u16, subctxt)
+			     __field(u16, comp_idx)
+			     ),
+	    TP_fast_assign(DD_DEV_ASSIGN(dd);
+			   __entry->ctxt = ctxt;
+			   __entry->subctxt = subctxt;
+			   __entry->comp_idx = comp_idx;
+			   ),
+	    TP_printk("[%s] SDMA [%u:%u] Using req/comp entry: %u",
+		      __get_str(dev),
+		      __entry->ctxt,
+		      __entry->subctxt,
+		      __entry->comp_idx
+		      )
+);
+
+DECLARE_EVENT_CLASS(
+	hfi1_sdma_value_template,
+	TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt, u16 comp_idx,
+		 u32 value),
+	TP_ARGS(dd, ctxt, subctxt, comp_idx, value),
+	TP_STRUCT__entry(DD_DEV_ENTRY(dd)
+			 __field(u16, ctxt)
+			 __field(u16, subctxt)
+			 __field(u16, comp_idx)
+			 __field(u32, value)
+		),
+	TP_fast_assign(DD_DEV_ASSIGN(dd);
+		       __entry->ctxt = ctxt;
+		       __entry->subctxt = subctxt;
+		       __entry->comp_idx = comp_idx;
+		       __entry->value = value;
+		),
+	TP_printk("[%s] SDMA [%u:%u:%u] value: %u",
+		  __get_str(dev),
+		  __entry->ctxt,
+		  __entry->subctxt,
+		  __entry->comp_idx,
+		  __entry->value
+		)
+);
+
+DEFINE_EVENT(hfi1_sdma_value_template, hfi1_sdma_user_initial_tidoffset,
+	     TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt,
+		      u16 comp_idx, u32 tidoffset),
+	     TP_ARGS(dd, ctxt, subctxt, comp_idx, tidoffset));
+
+DEFINE_EVENT(hfi1_sdma_value_template, hfi1_sdma_user_data_length,
+	     TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt,
+		      u16 comp_idx, u32 data_len),
+	     TP_ARGS(dd, ctxt, subctxt, comp_idx, data_len));
+
+DEFINE_EVENT(hfi1_sdma_value_template, hfi1_sdma_user_compute_length,
+	     TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt,
+		      u16 comp_idx, u32 data_len),
+	     TP_ARGS(dd, ctxt, subctxt, comp_idx, data_len));
+
+TRACE_EVENT(hfi1_sdma_user_tid_info,
+	    TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt,
+		     u16 comp_idx, u32 tidoffset, u32 units, u8 shift),
+	    TP_ARGS(dd, ctxt, subctxt, comp_idx, tidoffset, units, shift),
+	    TP_STRUCT__entry(DD_DEV_ENTRY(dd)
+			     __field(u16, ctxt)
+			     __field(u16, subctxt)
+			     __field(u16, comp_idx)
+			     __field(u32, tidoffset)
+			     __field(u32, units)
+			     __field(u8, shift)
+			     ),
+	    TP_fast_assign(DD_DEV_ASSIGN(dd);
+			   __entry->ctxt = ctxt;
+			   __entry->subctxt = subctxt;
+			   __entry->comp_idx = comp_idx;
+			   __entry->tidoffset = tidoffset;
+			   __entry->units = units;
+			   __entry->shift = shift;
+			   ),
+	    TP_printk("[%s] SDMA [%u:%u:%u] TID offset %ubytes %uunits om %u",
+		      __get_str(dev),
+		      __entry->ctxt,
+		      __entry->subctxt,
+		      __entry->comp_idx,
+		      __entry->tidoffset,
+		      __entry->units,
+		      __entry->shift
+		      )
+);
+
+TRACE_EVENT(hfi1_sdma_request,
+	    TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u16 subctxt,
+		     unsigned long dim),
+	    TP_ARGS(dd, ctxt, subctxt, dim),
+	    TP_STRUCT__entry(DD_DEV_ENTRY(dd)
+			     __field(u16, ctxt)
+			     __field(u16, subctxt)
+			     __field(unsigned long, dim)
+			     ),
+	    TP_fast_assign(DD_DEV_ASSIGN(dd);
+			   __entry->ctxt = ctxt;
+			   __entry->subctxt = subctxt;
+			   __entry->dim = dim;
+			   ),
+	    TP_printk("[%s] SDMA from %u:%u (%lu)",
+		      __get_str(dev),
+		      __entry->ctxt,
+		      __entry->subctxt,
+		      __entry->dim
+		      )
+);
+
 DECLARE_EVENT_CLASS(hfi1_sdma_engine_class,
 		    TP_PROTO(struct sdma_engine *sde, u64 status),
 		    TP_ARGS(sde, status),
diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index 5da1e4546543..0b646173ca22 100644
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -65,7 +65,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct ib_other_headers *ohdr;
 	struct rvt_swqe *wqe;
-	u32 hwords = 5;
+	u32 hwords;
 	u32 bth0 = 0;
 	u32 len;
 	u32 pmtu = qp->pmtu;
@@ -93,9 +93,23 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		goto done_free_tx;
 	}
 
-	ohdr = &ps->s_txreq->phdr.hdr.u.oth;
-	if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)
-		ohdr = &ps->s_txreq->phdr.hdr.u.l.oth;
+	ps->s_txreq->phdr.hdr.hdr_type = priv->hdr_type;
+	if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
+		/* header size in 32-bit words LRH+BTH = (8+12)/4. */
+		hwords = 5;
+		if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)
+			ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
+		else
+			ohdr = &ps->s_txreq->phdr.hdr.ibh.u.oth;
+	} else {
+		/* header size in 32-bit words 16B LRH+BTH = (16+12)/4. */
+		hwords = 7;
+		if ((rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH) &&
+		    (hfi1_check_mcast(rdma_ah_get_dlid(&qp->remote_ah_attr))))
+			ohdr = &ps->s_txreq->phdr.hdr.opah.u.l.oth;
+		else
+			ohdr = &ps->s_txreq->phdr.hdr.opah.u.oth;
+	}
 
 	/* Get the next send request. */
 	wqe = rvt_get_swqe_ptr(qp, qp->s_cur);
@@ -297,31 +311,26 @@ bail_no_tx:
 void hfi1_uc_rcv(struct hfi1_packet *packet)
 {
 	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;
+	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
 	struct ib_other_headers *ohdr = packet->ohdr;
-	u32 bth0, opcode;
+	u32 opcode = packet->opcode;
 	u32 hdrsize = packet->hlen;
 	u32 psn;
-	u32 pad;
+	u32 pad = packet->pad;
 	struct ib_wc wc;
 	u32 pmtu = qp->pmtu;
 	struct ib_reth *reth;
-	int has_grh = rcv_flags & HFI1_HAS_GRH;
 	int ret;
+	u8 extra_bytes = pad + packet->extra_byte + (SIZE_OF_CRC << 2);
 
-	bth0 = be32_to_cpu(ohdr->bth[0]);
-	if (hfi1_ruc_check_hdr(ibp, hdr, has_grh, qp, bth0))
+	if (hfi1_ruc_check_hdr(ibp, packet))
 		return;
 
 	process_ecn(qp, packet, true);
 
-	psn = be32_to_cpu(ohdr->bth[2]);
-	opcode = ib_bth_get_opcode(ohdr);
-
+	psn = ib_bth_get_psn(ohdr);
 	/* Compare the PSN verses the expected PSN. */
 	if (unlikely(cmp_psn(psn, qp->r_psn) != 0)) {
 		/*
@@ -414,7 +423,12 @@ send_first:
 		/* FALLTHROUGH */
 	case OP(SEND_MIDDLE):
 		/* Check for invalid length PMTU or posted rwqe len. */
-		if (unlikely(tlen != (hdrsize + pmtu + 4)))
+		/*
+		 * There will be no padding for 9B packet but 16B packets
+		 * will come in with some padding since we always add
+		 * CRC and LT bytes which will need to be flit aligned
+		 */
+		if (unlikely(tlen != (hdrsize + pmtu + extra_bytes)))
 			goto rewind;
 		qp->r_rcv_len += pmtu;
 		if (unlikely(qp->r_rcv_len > qp->r_len))
@@ -432,14 +446,12 @@ no_immediate_data:
 		wc.ex.imm_data = 0;
 		wc.wc_flags = 0;
 send_last:
-		/* Get the number of bytes the message was padded by. */
-		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
-		if (unlikely(tlen < (hdrsize + pad + 4)))
+		if (unlikely(tlen < (hdrsize + extra_bytes)))
 			goto rewind;
 		/* Don't count the CRC. */
-		tlen -= (hdrsize + pad + 4);
+		tlen -= (hdrsize + extra_bytes);
 		wc.byte_len = tlen + qp->r_rcv_len;
 		if (unlikely(wc.byte_len > qp->r_len))
 			goto rewind;
@@ -527,14 +539,12 @@ rdma_first:
 rdma_last_imm:
 		wc.wc_flags = IB_WC_WITH_IMM;
 
-		/* Get the number of bytes the message was padded by. */
-		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
 		if (unlikely(tlen < (hdrsize + pad + 4)))
 			goto drop;
 		/* Don't count the CRC. */
-		tlen -= (hdrsize + pad + 4);
+		tlen -= (hdrsize + extra_bytes);
 		if (unlikely(tlen + qp->r_rcv_len != qp->r_len))
 			goto drop;
 		if (test_and_clear_bit(RVT_R_REWIND_SGE, &qp->r_aflags)) {
@@ -554,14 +564,12 @@ rdma_last_imm:
 
 	case OP(RDMA_WRITE_LAST):
 rdma_last:
-		/* Get the number of bytes the message was padded by. */
-		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
 		if (unlikely(tlen < (hdrsize + pad + 4)))
 			goto drop;
 		/* Don't count the CRC. */
-		tlen -= (hdrsize + pad + 4);
+		tlen -= (hdrsize + extra_bytes);
 		if (unlikely(tlen + qp->r_rcv_len != qp->r_len))
 			goto drop;
 		hfi1_copy_sge(&qp->r_sge, data, tlen, true, false);
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 6a4e95cefae5..2ba74fdd6f15 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -53,6 +53,12 @@
 #include "verbs_txreq.h"
 #include "qp.h"
 
+/* We support only two types - 9B and 16B for now */
+static const hfi1_make_req hfi1_make_ud_req_tbl[2] = {
+	[HFI1_PKT_TYPE_9B] = &hfi1_make_ud_req_9B,
+	[HFI1_PKT_TYPE_16B] = &hfi1_make_ud_req_16B
+};
+
 /**
  * ud_loopback - handle send on loopback QPs
  * @sqp: the sending QP
@@ -67,6 +73,7 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 {
 	struct hfi1_ibport *ibp = to_iport(sqp->ibqp.device, sqp->port_num);
 	struct hfi1_pportdata *ppd;
+	struct hfi1_qp_priv *priv = sqp->priv;
 	struct rvt_qp *qp;
 	struct rdma_ah_attr *ah_attr;
 	unsigned long flags;
@@ -102,18 +109,19 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 
 	if (qp->ibqp.qp_num > 1) {
 		u16 pkey;
-		u16 slid;
+		u32 slid;
 		u8 sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)];
 
 		pkey = hfi1_get_pkey(ibp, sqp->s_pkey_index);
 		slid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
 				   ((1 << ppd->lmc) - 1));
 		if (unlikely(ingress_pkey_check(ppd, pkey, sc5,
-						qp->s_pkey_index, slid))) {
-			hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY, pkey,
-				       rdma_ah_get_sl(ah_attr),
-				       sqp->ibqp.qp_num, qp->ibqp.qp_num,
-				       slid, rdma_ah_get_dlid(ah_attr));
+						qp->s_pkey_index,
+						slid, false))) {
+			hfi1_bad_pkey(ibp, pkey,
+				      rdma_ah_get_sl(ah_attr),
+				      sqp->ibqp.qp_num, qp->ibqp.qp_num,
+				      slid, rdma_ah_get_dlid(ah_attr));
 			goto drop;
 		}
 	}
@@ -128,18 +136,8 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 
 		qkey = (int)swqe->ud_wr.remote_qkey < 0 ?
 			sqp->qkey : swqe->ud_wr.remote_qkey;
-		if (unlikely(qkey != qp->qkey)) {
-			u16 lid;
-
-			lid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
-					  ((1 << ppd->lmc) - 1));
-			hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_Q_KEY, qkey,
-				       rdma_ah_get_sl(ah_attr),
-				       sqp->ibqp.qp_num, qp->ibqp.qp_num,
-				       lid,
-				       rdma_ah_get_dlid(ah_attr));
-			goto drop;
-		}
+		if (unlikely(qkey != qp->qkey))
+			goto drop; /* silently drop per IBTA spec */
 	}
 
 	/*
@@ -185,9 +183,33 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 
 	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
 		struct ib_grh grh;
-		const struct ib_global_route *grd = rdma_ah_read_grh(ah_attr);
+		struct ib_global_route grd = *(rdma_ah_read_grh(ah_attr));
+
+		/*
+		 * For loopback packets with extended LIDs, the
+		 * sgid_index in the GRH is 0 and the dgid is
+		 * OPA GID of the sender. While creating a response
+		 * to the loopback packet, IB core creates the new
+		 * sgid_index from the DGID and that will be the
+		 * OPA_GID_INDEX. The new dgid is from the sgid
+		 * index and that will be in the IB GID format.
+		 *
+		 * We now have a case where the sent packet had a
+		 * different sgid_index and dgid compared to the
+		 * one that was received in response.
+		 *
+		 * Fix this inconsistency.
+		 */
+		if (priv->hdr_type == HFI1_PKT_TYPE_16B) {
+			if (grd.sgid_index == 0)
+				grd.sgid_index = OPA_GID_INDEX;
+
+			if (ib_is_opa_gid(&grd.dgid))
+				grd.dgid.global.interface_id =
+				cpu_to_be64(ppd->guids[HFI1_PORT_GUID_INDEX]);
+		}
 
-		hfi1_make_grh(ibp, &grh, grd, 0, 0);
+		hfi1_make_grh(ibp, &grh, &grd, 0, 0);
 		hfi1_copy_sge(&qp->r_sge, &grh,
 			      sizeof(grh), true, false);
 		wc.wc_flags |= IB_WC_GRH;
@@ -244,7 +266,7 @@ static void ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 		wc.pkey_index = 0;
 	}
 	wc.slid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
-			      ((1 << ppd->lmc) - 1));
+				   ((1 << ppd->lmc) - 1));
 	/* Check for loopback when the port lid is not set */
 	if (wc.slid == 0 && sqp->ibqp.qp_type == IB_QPT_GSI)
 		wc.slid = be16_to_cpu(IB_LID_PERMISSIVE);
@@ -261,6 +283,183 @@ drop:
 	rcu_read_unlock();
 }
 
+static void hfi1_make_bth_deth(struct rvt_qp *qp, struct rvt_swqe *wqe,
+			       struct ib_other_headers *ohdr,
+			       u16 *pkey, u32 extra_bytes, bool bypass)
+{
+	u32 bth0;
+	struct hfi1_ibport *ibp;
+
+	ibp = to_iport(qp->ibqp.device, qp->port_num);
+	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM) {
+		ohdr->u.ud.imm_data = wqe->wr.ex.imm_data;
+		bth0 = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE << 24;
+	} else {
+		bth0 = IB_OPCODE_UD_SEND_ONLY << 24;
+	}
+
+	if (wqe->wr.send_flags & IB_SEND_SOLICITED)
+		bth0 |= IB_BTH_SOLICITED;
+	bth0 |= extra_bytes << 20;
+	if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_SMI)
+		*pkey = hfi1_get_pkey(ibp, wqe->ud_wr.pkey_index);
+	else
+		*pkey = hfi1_get_pkey(ibp, qp->s_pkey_index);
+	if (!bypass)
+		bth0 |= *pkey;
+	ohdr->bth[0] = cpu_to_be32(bth0);
+	ohdr->bth[1] = cpu_to_be32(wqe->ud_wr.remote_qpn);
+	ohdr->bth[2] = cpu_to_be32(mask_psn(wqe->psn));
+	/*
+	 * Qkeys with the high order bit set mean use the
+	 * qkey from the QP context instead of the WR (see 10.2.5).
+	 */
+	ohdr->u.ud.deth[0] = cpu_to_be32((int)wqe->ud_wr.remote_qkey < 0 ?
+					 qp->qkey : wqe->ud_wr.remote_qkey);
+	ohdr->u.ud.deth[1] = cpu_to_be32(qp->ibqp.qp_num);
+}
+
+void hfi1_make_ud_req_9B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
+			 struct rvt_swqe *wqe)
+{
+	u32 nwords, extra_bytes;
+	u16 len, slid, dlid, pkey;
+	u16 lrh0 = 0;
+	u8 sc5;
+	struct hfi1_qp_priv *priv = qp->priv;
+	struct ib_other_headers *ohdr;
+	struct rdma_ah_attr *ah_attr;
+	struct hfi1_pportdata *ppd;
+	struct hfi1_ibport *ibp;
+	struct ib_grh *grh;
+
+	ibp = to_iport(qp->ibqp.device, qp->port_num);
+	ppd = ppd_from_ibp(ibp);
+	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;
+
+	extra_bytes = -wqe->length & 3;
+	nwords = ((wqe->length + extra_bytes) >> 2) + SIZE_OF_CRC;
+	/* header size in dwords LRH+BTH+DETH = (8+12+8)/4. */
+	qp->s_hdrwords = 7;
+	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
+		qp->s_hdrwords++;
+
+	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
+		grh = &ps->s_txreq->phdr.hdr.ibh.u.l.grh;
+		qp->s_hdrwords += hfi1_make_grh(ibp, grh,
+						rdma_ah_read_grh(ah_attr),
+						qp->s_hdrwords - 2, nwords);
+		lrh0 = HFI1_LRH_GRH;
+		ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
+	} else {
+		lrh0 = HFI1_LRH_BTH;
+		ohdr = &ps->s_txreq->phdr.hdr.ibh.u.oth;
+	}
+
+	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)];
+	lrh0 |= (rdma_ah_get_sl(ah_attr) & 0xf) << 4;
+	if (qp->ibqp.qp_type == IB_QPT_SMI) {
+		lrh0 |= 0xF000; /* Set VL (see ch. 13.5.3.1) */
+		priv->s_sc = 0xf;
+	} else {
+		lrh0 |= (sc5 & 0xf) << 12;
+		priv->s_sc = sc5;
+	}
+
+	dlid = opa_get_lid(rdma_ah_get_dlid(ah_attr), 9B);
+	if (dlid == be16_to_cpu(IB_LID_PERMISSIVE)) {
+		slid = be16_to_cpu(IB_LID_PERMISSIVE);
+	} else {
+		u16 lid = (u16)ppd->lid;
+
+		if (lid) {
+			lid |= rdma_ah_get_path_bits(ah_attr) &
+				((1 << ppd->lmc) - 1);
+			slid = lid;
+		} else {
+			slid = be16_to_cpu(IB_LID_PERMISSIVE);
+		}
+	}
+	hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, false);
+	len = qp->s_hdrwords + nwords;
+
+	/* Setup the packet */
+	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_9B;
+	hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
+			 lrh0, len, dlid, slid);
+}
+
+void hfi1_make_ud_req_16B(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
+			  struct rvt_swqe *wqe)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+	struct ib_other_headers *ohdr;
+	struct rdma_ah_attr *ah_attr;
+	struct hfi1_pportdata *ppd;
+	struct hfi1_ibport *ibp;
+	u32 dlid, slid, nwords, extra_bytes;
+	u16 len, pkey;
+	u8 l4, sc5;
+
+	ibp = to_iport(qp->ibqp.device, qp->port_num);
+	ppd = ppd_from_ibp(ibp);
+	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;
+	/* header size in dwords 16B LRH+BTH+DETH = (16+12+8)/4. */
+	qp->s_hdrwords = 9;
+	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM)
+		qp->s_hdrwords++;
+
+	/* SW provides space for CRC and LT for bypass packets. */
+	extra_bytes = hfi1_get_16b_padding((qp->s_hdrwords << 2),
+					   wqe->length);
+	nwords = ((wqe->length + extra_bytes + SIZE_OF_LT) >> 2) + SIZE_OF_CRC;
+
+	if ((rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) &&
+	    hfi1_check_mcast(rdma_ah_get_dlid(ah_attr))) {
+		struct ib_grh *grh;
+		struct ib_global_route *grd = rdma_ah_retrieve_grh(ah_attr);
+		/*
+		 * Ensure OPA GIDs are transformed to IB gids
+		 * before creating the GRH.
+		 */
+		if (grd->sgid_index == OPA_GID_INDEX) {
+			dd_dev_warn(ppd->dd, "Bad sgid_index. sgid_index: %d\n",
+				    grd->sgid_index);
+			grd->sgid_index = 0;
+		}
+		grh = &ps->s_txreq->phdr.hdr.opah.u.l.grh;
+		qp->s_hdrwords += hfi1_make_grh(ibp, grh, grd,
+					qp->s_hdrwords - 4, nwords);
+		ohdr = &ps->s_txreq->phdr.hdr.opah.u.l.oth;
+		l4 = OPA_16B_L4_IB_GLOBAL;
+	} else {
+		ohdr = &ps->s_txreq->phdr.hdr.opah.u.oth;
+		l4 = OPA_16B_L4_IB_LOCAL;
+	}
+
+	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)];
+	if (qp->ibqp.qp_type == IB_QPT_SMI)
+		priv->s_sc = 0xf;
+	else
+		priv->s_sc = sc5;
+
+	dlid = opa_get_lid(rdma_ah_get_dlid(ah_attr), 16B);
+	if (!ppd->lid)
+		slid = be32_to_cpu(OPA_LID_PERMISSIVE);
+	else
+		slid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
+			   ((1 << ppd->lmc) - 1));
+
+	hfi1_make_bth_deth(qp, wqe, ohdr, &pkey, extra_bytes, true);
+	/* Convert dwords to flits */
+	len = (qp->s_hdrwords + nwords) >> 1;
+
+	/* Setup the packet */
+	ps->s_txreq->phdr.hdr.hdr_type = HFI1_PKT_TYPE_16B;
+	hfi1_make_16b_hdr(&ps->s_txreq->phdr.hdr.opah,
+			  slid, dlid, len, pkey, 0, 0, l4, priv->s_sc);
+}
+
 /**
  * hfi1_make_ud_req - construct a UD request packet
  * @qp: the QP
@@ -272,18 +471,12 @@ drop:
 int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 {
 	struct hfi1_qp_priv *priv = qp->priv;
-	struct ib_other_headers *ohdr;
 	struct rdma_ah_attr *ah_attr;
 	struct hfi1_pportdata *ppd;
 	struct hfi1_ibport *ibp;
 	struct rvt_swqe *wqe;
-	u32 nwords;
-	u32 extra_bytes;
-	u32 bth0;
-	u16 lrh0;
-	u16 lid;
 	int next_cur;
-	u8 sc5;
+	u32 lid;
 
 	ps->s_txreq = get_txreq(ps->dev, qp);
 	if (IS_ERR(ps->s_txreq))
@@ -320,13 +513,14 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	ibp = to_iport(qp->ibqp.device, qp->port_num);
 	ppd = ppd_from_ibp(ibp);
 	ah_attr = &ibah_to_rvtah(wqe->ud_wr.ah)->attr;
-	if (rdma_ah_get_dlid(ah_attr) < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
-	    rdma_ah_get_dlid(ah_attr) == be16_to_cpu(IB_LID_PERMISSIVE)) {
+	priv->hdr_type = hfi1_get_hdr_type(ppd->lid, ah_attr);
+	if ((!hfi1_check_mcast(rdma_ah_get_dlid(ah_attr))) ||
+	    (rdma_ah_get_dlid(ah_attr) == be32_to_cpu(OPA_LID_PERMISSIVE))) {
 		lid = rdma_ah_get_dlid(ah_attr) & ~((1 << ppd->lmc) - 1);
 		if (unlikely(!loopback &&
-			     (lid == ppd->lid ||
-			      (lid == be16_to_cpu(IB_LID_PERMISSIVE) &&
-			      qp->ibqp.qp_type == IB_QPT_GSI)))) {
+			     ((lid == ppd->lid) ||
+			      ((lid == be32_to_cpu(OPA_LID_PERMISSIVE)) &&
+			       (qp->ibqp.qp_type == IB_QPT_GSI))))) {
 			unsigned long tflags = ps->flags;
 			/*
 			 * If DMAs are in progress, we can't generate
@@ -350,11 +544,6 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	}
 
 	qp->s_cur = next_cur;
-	extra_bytes = -wqe->length & 3;
-	nwords = (wqe->length + extra_bytes) >> 2;
-
-	/* header size in 32-bit words LRH+BTH+DETH = (8+12+8)/4. */
-	qp->s_hdrwords = 7;
 	ps->s_txreq->s_cur_size = wqe->length;
 	ps->s_txreq->ss = &qp->s_sge;
 	qp->s_srate = rdma_ah_get_static_rate(ah_attr);
@@ -365,77 +554,12 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	qp->s_sge.num_sge = wqe->wr.num_sge;
 	qp->s_sge.total_len = wqe->length;
 
-	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
-		/* Header size in 32-bit words. */
-		qp->s_hdrwords += hfi1_make_grh(ibp,
-						&ps->s_txreq->phdr.hdr.u.l.grh,
-						rdma_ah_read_grh(ah_attr),
-						qp->s_hdrwords, nwords);
-		lrh0 = HFI1_LRH_GRH;
-		ohdr = &ps->s_txreq->phdr.hdr.u.l.oth;
-		/*
-		 * Don't worry about sending to locally attached multicast
-		 * QPs.  It is unspecified by the spec. what happens.
-		 */
-	} else {
-		/* Header size in 32-bit words. */
-		lrh0 = HFI1_LRH_BTH;
-		ohdr = &ps->s_txreq->phdr.hdr.u.oth;
-	}
-	if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM) {
-		qp->s_hdrwords++;
-		ohdr->u.ud.imm_data = wqe->wr.ex.imm_data;
-		bth0 = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE << 24;
-	} else {
-		bth0 = IB_OPCODE_UD_SEND_ONLY << 24;
-	}
-	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)];
-	lrh0 |= (rdma_ah_get_sl(ah_attr) & 0xf) << 4;
-	if (qp->ibqp.qp_type == IB_QPT_SMI) {
-		lrh0 |= 0xF000; /* Set VL (see ch. 13.5.3.1) */
-		priv->s_sc = 0xf;
-	} else {
-		lrh0 |= (sc5 & 0xf) << 12;
-		priv->s_sc = sc5;
-	}
+	/* Make the appropriate header */
+	hfi1_make_ud_req_tbl[priv->hdr_type](qp, ps, qp->s_wqe);
 	priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
 	ps->s_txreq->sde = priv->s_sde;
 	priv->s_sendcontext = qp_to_send_context(qp, priv->s_sc);
 	ps->s_txreq->psc = priv->s_sendcontext;
-	ps->s_txreq->phdr.hdr.lrh[0] = cpu_to_be16(lrh0);
-	ps->s_txreq->phdr.hdr.lrh[1] =
-		cpu_to_be16(rdma_ah_get_dlid(ah_attr));
-	ps->s_txreq->phdr.hdr.lrh[2] =
-		cpu_to_be16(qp->s_hdrwords + nwords + SIZE_OF_CRC);
-	if (rdma_ah_get_dlid(ah_attr) == be16_to_cpu(IB_LID_PERMISSIVE)) {
-		ps->s_txreq->phdr.hdr.lrh[3] = IB_LID_PERMISSIVE;
-	} else {
-		lid = ppd->lid;
-		if (lid) {
-			lid |= rdma_ah_get_path_bits(ah_attr) &
-				((1 << ppd->lmc) - 1);
-			ps->s_txreq->phdr.hdr.lrh[3] = cpu_to_be16(lid);
-		} else {
-			ps->s_txreq->phdr.hdr.lrh[3] = IB_LID_PERMISSIVE;
-		}
-	}
-	if (wqe->wr.send_flags & IB_SEND_SOLICITED)
-		bth0 |= IB_BTH_SOLICITED;
-	bth0 |= extra_bytes << 20;
-	if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_SMI)
-		bth0 |= hfi1_get_pkey(ibp, wqe->ud_wr.pkey_index);
-	else
-		bth0 |= hfi1_get_pkey(ibp, qp->s_pkey_index);
-	ohdr->bth[0] = cpu_to_be32(bth0);
-	ohdr->bth[1] = cpu_to_be32(wqe->ud_wr.remote_qpn);
-	ohdr->bth[2] = cpu_to_be32(mask_psn(wqe->psn));
-	/*
-	 * Qkeys with the high order bit set mean use the
-	 * qkey from the QP context instead of the WR (see 10.2.5).
-	 */
-	ohdr->u.ud.deth[0] = cpu_to_be32((int)wqe->ud_wr.remote_qkey < 0 ?
-					 qp->qkey : wqe->ud_wr.remote_qkey);
-	ohdr->u.ud.deth[1] = cpu_to_be32(qp->ibqp.qp_num);
 	/* disarm any ahg */
 	priv->s_ahg->ahgcount = 0;
 	priv->s_ahg->ahgidx = 0;
@@ -505,6 +629,64 @@ int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey)
 	return -1;
 }
 
+void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
+		    u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+		    u8 sc5, const struct ib_grh *old_grh)
+{
+	u64 pbc, pbc_flags = 0;
+	u32 bth0, plen, vl, hwords = 7;
+	u16 len;
+	u8 l4;
+	struct hfi1_16b_header hdr;
+	struct ib_other_headers *ohdr;
+	struct pio_buf *pbuf;
+	struct send_context *ctxt = qp_to_send_context(qp, sc5);
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+	u32 nwords;
+
+	/* Populate length */
+	nwords = ((hfi1_get_16b_padding(hwords << 2, 0) +
+		   SIZE_OF_LT) >> 2) + SIZE_OF_CRC;
+	if (old_grh) {
+		struct ib_grh *grh = &hdr.u.l.grh;
+
+		grh->version_tclass_flow = old_grh->version_tclass_flow;
+		grh->paylen = cpu_to_be16((hwords - 4 + nwords) << 2);
+		grh->hop_limit = 0xff;
+		grh->sgid = old_grh->dgid;
+		grh->dgid = old_grh->sgid;
+		ohdr = &hdr.u.l.oth;
+		l4 = OPA_16B_L4_IB_GLOBAL;
+		hwords += sizeof(struct ib_grh) / sizeof(u32);
+	} else {
+		ohdr = &hdr.u.oth;
+		l4 = OPA_16B_L4_IB_LOCAL;
+	}
+
+	/* BIT 16 to 19 is TVER. Bit 20 to 22 is pad cnt */
+	bth0 = (IB_OPCODE_CNP << 24) | (1 << 16) |
+	       (hfi1_get_16b_padding(hwords << 2, 0) << 20);
+	ohdr->bth[0] = cpu_to_be32(bth0);
+
+	ohdr->bth[1] = cpu_to_be32(remote_qpn);
+	ohdr->bth[2] = 0; /* PSN 0 */
+
+	/* Convert dwords to flits */
+	len = (hwords + nwords) >> 1;
+	hfi1_make_16b_hdr(&hdr, slid, dlid, len, pkey, 1, 0, l4, sc5);
+
+	plen = 2 /* PBC */ + hwords + nwords;
+	pbc_flags |= PBC_PACKET_BYPASS | PBC_INSERT_BYPASS_ICRC;
+	vl = sc_to_vlt(ppd->dd, sc5);
+	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen);
+	if (ctxt) {
+		pbuf = sc_buffer_alloc(ctxt, plen, NULL, NULL);
+		if (pbuf)
+			ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc,
+						 &hdr, hwords);
+	}
+}
+
 void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 		u32 pkey, u32 slid, u32 dlid, u8 sc5,
 		const struct ib_grh *old_grh)
@@ -543,13 +725,9 @@ void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 	ohdr->bth[1] = cpu_to_be32(remote_qpn | (1 << IB_BECN_SHIFT));
 	ohdr->bth[2] = 0; /* PSN 0 */
 
-	hdr.lrh[0] = cpu_to_be16(lrh0);
-	hdr.lrh[1] = cpu_to_be16(dlid);
-	hdr.lrh[2] = cpu_to_be16(hwords + SIZE_OF_CRC);
-	hdr.lrh[3] = cpu_to_be16(slid);
-
+	hfi1_make_ib_hdr(&hdr, lrh0, hwords + SIZE_OF_CRC, dlid, slid);
 	plen = 2 /* PBC */ + hwords;
-	pbc_flags |= (!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT;
+	pbc_flags |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
 	vl = sc_to_vlt(ppd->dd, sc5);
 	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen);
 	if (ctxt) {
@@ -668,37 +846,45 @@ static int opa_smp_check(struct hfi1_ibport *ibp, u16 pkey, u8 sc5,
 void hfi1_ud_rcv(struct hfi1_packet *packet)
 {
 	struct ib_other_headers *ohdr = packet->ohdr;
-	int opcode;
 	u32 hdrsize = packet->hlen;
 	struct ib_wc wc;
 	u32 qkey;
 	u32 src_qp;
-	u16 dlid, pkey;
+	u16 pkey;
 	int mgmt_pkey_idx = -1;
 	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;
-	void *data = packet->ebuf;
+	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
-	bool has_grh = rcv_flags & HFI1_HAS_GRH;
-	u8 sc5 = hfi1_9B_get_sc5(hdr, packet->rhf);
-	u32 bth1;
-	u8 sl_from_sc, sl;
-	u16 slid;
+	u8 sc5 = packet->sc;
+	u8 sl_from_sc;
+	u8 opcode = packet->opcode;
+	u8 sl = packet->sl;
+	u32 dlid = packet->dlid;
+	u32 slid = packet->slid;
 	u8 extra_bytes;
+	bool dlid_is_permissive;
+	bool slid_is_permissive;
 
-	qkey = be32_to_cpu(ohdr->u.ud.deth[0]);
-	src_qp = be32_to_cpu(ohdr->u.ud.deth[1]) & RVT_QPN_MASK;
-	dlid = ib_get_dlid(hdr);
-	bth1 = be32_to_cpu(ohdr->bth[1]);
-	slid = ib_get_slid(hdr);
-	pkey = ib_bth_get_pkey(ohdr);
-	opcode = ib_bth_get_opcode(ohdr);
-	sl = ib_get_sl(hdr);
-	extra_bytes = ib_bth_get_pad(ohdr);
-	extra_bytes += (SIZE_OF_CRC << 2);
+	extra_bytes = packet->pad + packet->extra_byte + (SIZE_OF_CRC << 2);
+	qkey = ib_get_qkey(ohdr);
+	src_qp = ib_get_sqpn(ohdr);
+
+	if (packet->etype == RHF_RCV_TYPE_BYPASS) {
+		u32 permissive_lid =
+			opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B);
+
+		pkey = hfi1_16B_get_pkey(packet->hdr);
+		dlid_is_permissive = (dlid == permissive_lid);
+		slid_is_permissive = (slid == permissive_lid);
+	} else {
+		hdr = packet->hdr;
+		pkey = ib_bth_get_pkey(ohdr);
+		dlid_is_permissive = (dlid == be16_to_cpu(IB_LID_PERMISSIVE));
+		slid_is_permissive = (slid == be16_to_cpu(IB_LID_PERMISSIVE));
+	}
 	sl_from_sc = ibp->sc_to_sl[sc5];
 
 	process_ecn(qp, packet, (opcode != IB_OPCODE_CNP));
@@ -716,8 +902,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	 * and the QKEY matches (see 9.6.1.4.1 and 9.6.1.5.1).
 	 */
 	if (qp->ibqp.qp_num) {
-		if (unlikely(hdr->lrh[1] == IB_LID_PERMISSIVE ||
-			     hdr->lrh[3] == IB_LID_PERMISSIVE))
+		if (unlikely(dlid_is_permissive || slid_is_permissive))
 			goto drop;
 		if (qp->ibqp.qp_num > 1) {
 			if (unlikely(rcv_pkey_check(ppd, pkey, sc5, slid))) {
@@ -727,10 +912,10 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 				 * for invalid pkeys is optional according to
 				 * IB spec (release 1.3, section 10.9.4)
 				 */
-				hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY,
-					       pkey, sl,
-					       src_qp, qp->ibqp.qp_num,
-					       slid, dlid);
+				hfi1_bad_pkey(ibp,
+					      pkey, sl,
+					      src_qp, qp->ibqp.qp_num,
+					      slid, dlid);
 				return;
 			}
 		} else {
@@ -739,12 +924,9 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 			if (mgmt_pkey_idx < 0)
 				goto drop;
 		}
-		if (unlikely(qkey != qp->qkey)) {
-			hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_Q_KEY, qkey, sl,
-				       src_qp, qp->ibqp.qp_num,
-				       slid, dlid);
+		if (unlikely(qkey != qp->qkey)) /* Silent drop */
 			return;
-		}
+
 		/* Drop invalid MAD packets (see 13.5.3.1). */
 		if (unlikely(qp->ibqp.qp_num == 1 &&
 			     (tlen > 2048 || (sc5 == 0xF))))
@@ -758,8 +940,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 
 		if (tlen > 2048)
 			goto drop;
-		if ((hdr->lrh[1] == IB_LID_PERMISSIVE ||
-		     hdr->lrh[3] == IB_LID_PERMISSIVE) &&
+		if ((dlid_is_permissive || slid_is_permissive) &&
 		    smp->mgmt_class != IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
 			goto drop;
 
@@ -811,8 +992,19 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 		qp->r_flags |= RVT_R_REUSE_SGE;
 		goto drop;
 	}
-	if (has_grh) {
-		hfi1_copy_sge(&qp->r_sge, &hdr->u.l.grh,
+	if (packet->grh) {
+		hfi1_copy_sge(&qp->r_sge, packet->grh,
+			      sizeof(struct ib_grh), true, false);
+		wc.wc_flags |= IB_WC_GRH;
+	} else if (packet->etype == RHF_RCV_TYPE_BYPASS) {
+		struct ib_grh grh;
+		/*
+		 * Assuming we only created 16B on the send side
+		 * if we want to use large LIDs, since GRH was stripped
+		 * out when creating 16B, add back the GRH here.
+		 */
+		hfi1_make_ext_grh(packet, &grh, slid, dlid);
+		hfi1_copy_sge(&qp->r_sge, &grh,
 			      sizeof(struct ib_grh), true, false);
 		wc.wc_flags |= IB_WC_GRH;
 	} else {
@@ -845,14 +1037,15 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	} else {
 		wc.pkey_index = 0;
 	}
-
+	if (slid_is_permissive)
+		slid = be32_to_cpu(OPA_LID_PERMISSIVE);
 	wc.slid = slid;
 	wc.sl = sl_from_sc;
 
 	/*
 	 * Save the LMC lower bits if the destination LID is a unicast LID.
 	 */
-	wc.dlid_path_bits = dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE) ? 0 :
+	wc.dlid_path_bits = hfi1_check_mcast(dlid) ? 0 :
 		dlid & ((1 << ppd_from_ibp(ibp)->lmc) - 1);
 	wc.port_num = qp->port_num;
 	/* Signal completion event if the solicited bit is set. */
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index a8f0aa4722f6..6f6c14df383e 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -47,58 +47,28 @@
 #include <asm/page.h>
 #include <linux/string.h>
 
+#include "mmu_rb.h"
 #include "user_exp_rcv.h"
 #include "trace.h"
-#include "mmu_rb.h"
-
-struct tid_group {
-	struct list_head list;
-	u32 base;
-	u8 size;
-	u8 used;
-	u8 map;
-};
-
-struct tid_rb_node {
-	struct mmu_rb_node mmu;
-	unsigned long phys;
-	struct tid_group *grp;
-	u32 rcventry;
-	dma_addr_t dma_addr;
-	bool freed;
-	unsigned npages;
-	struct page *pages[0];
-};
-
-struct tid_pageset {
-	u16 idx;
-	u16 count;
-};
-
-#define EXP_TID_SET_EMPTY(set) (set.count == 0 && list_empty(&set.list))
-
-#define num_user_pages(vaddr, len)				       \
-	(1 + (((((unsigned long)(vaddr) +			       \
-		 (unsigned long)(len) - 1) & PAGE_MASK) -	       \
-	       ((unsigned long)vaddr & PAGE_MASK)) >> PAGE_SHIFT))
 
 static void unlock_exp_tids(struct hfi1_ctxtdata *uctxt,
 			    struct exp_tid_set *set,
 			    struct hfi1_filedata *fd);
-static u32 find_phys_blocks(struct page **pages, unsigned npages,
-			    struct tid_pageset *list);
-static int set_rcvarray_entry(struct hfi1_filedata *fd, unsigned long vaddr,
+static u32 find_phys_blocks(struct tid_user_buf *tidbuf, unsigned int npages);
+static int set_rcvarray_entry(struct hfi1_filedata *fd,
+			      struct tid_user_buf *tbuf,
 			      u32 rcventry, struct tid_group *grp,
-			      struct page **pages, unsigned npages);
+			      u16 pageidx, unsigned int npages);
 static int tid_rb_insert(void *arg, struct mmu_rb_node *node);
 static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
 				    struct tid_rb_node *tnode);
 static void tid_rb_remove(void *arg, struct mmu_rb_node *node);
 static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode);
-static int program_rcvarray(struct hfi1_filedata *fd, unsigned long vaddr,
-			    struct tid_group *grp, struct tid_pageset *sets,
-			    unsigned start, u16 count, struct page **pages,
-			    u32 *tidlist, unsigned *tididx, unsigned *pmapped);
+static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *,
+			    struct tid_group *grp,
+			    unsigned int start, u16 count,
+			    u32 *tidlist, unsigned int *tididx,
+			    unsigned int *pmapped);
 static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
 			      struct tid_group **grp);
 static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node);
@@ -109,96 +79,14 @@ static struct mmu_rb_ops tid_rb_ops = {
 	.invalidate = tid_rb_invalidate
 };
 
-static inline u32 rcventry2tidinfo(u32 rcventry)
-{
-	u32 pair = rcventry & ~0x1;
-
-	return EXP_TID_SET(IDX, pair >> 1) |
-		EXP_TID_SET(CTRL, 1 << (rcventry - pair));
-}
-
-static inline void exp_tid_group_init(struct exp_tid_set *set)
-{
-	INIT_LIST_HEAD(&set->list);
-	set->count = 0;
-}
-
-static inline void tid_group_remove(struct tid_group *grp,
-				    struct exp_tid_set *set)
-{
-	list_del_init(&grp->list);
-	set->count--;
-}
-
-static inline void tid_group_add_tail(struct tid_group *grp,
-				      struct exp_tid_set *set)
-{
-	list_add_tail(&grp->list, &set->list);
-	set->count++;
-}
-
-static inline struct tid_group *tid_group_pop(struct exp_tid_set *set)
-{
-	struct tid_group *grp =
-		list_first_entry(&set->list, struct tid_group, list);
-	list_del_init(&grp->list);
-	set->count--;
-	return grp;
-}
-
-static inline void tid_group_move(struct tid_group *group,
-				  struct exp_tid_set *s1,
-				  struct exp_tid_set *s2)
-{
-	tid_group_remove(group, s1);
-	tid_group_add_tail(group, s2);
-}
-
-int hfi1_user_exp_rcv_grp_init(struct hfi1_filedata *fd)
-{
-	struct hfi1_ctxtdata *uctxt = fd->uctxt;
-	struct hfi1_devdata *dd = fd->dd;
-	u32 tidbase;
-	u32 i;
-	struct tid_group *grp, *gptr;
-
-	exp_tid_group_init(&uctxt->tid_group_list);
-	exp_tid_group_init(&uctxt->tid_used_list);
-	exp_tid_group_init(&uctxt->tid_full_list);
-
-	tidbase = uctxt->expected_base;
-	for (i = 0; i < uctxt->expected_count /
-		     dd->rcv_entries.group_size; i++) {
-		grp = kzalloc(sizeof(*grp), GFP_KERNEL);
-		if (!grp)
-			goto grp_failed;
-
-		grp->size = dd->rcv_entries.group_size;
-		grp->base = tidbase;
-		tid_group_add_tail(grp, &uctxt->tid_group_list);
-		tidbase += dd->rcv_entries.group_size;
-	}
-
-	return 0;
-
-grp_failed:
-	list_for_each_entry_safe(grp, gptr, &uctxt->tid_group_list.list,
-				 list) {
-		list_del_init(&grp->list);
-		kfree(grp);
-	}
-
-	return -ENOMEM;
-}
-
 /*
  * Initialize context and file private data needed for Expected
  * receive caching. This needs to be done after the context has
  * been configured with the eager/expected RcvEntry counts.
  */
-int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd)
+int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
+			   struct hfi1_ctxtdata *uctxt)
 {
-	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct hfi1_devdata *dd = uctxt->dd;
 	int ret = 0;
 
@@ -266,18 +154,6 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd)
 	return ret;
 }
 
-void hfi1_user_exp_rcv_grp_free(struct hfi1_ctxtdata *uctxt)
-{
-	struct tid_group *grp, *gptr;
-
-	list_for_each_entry_safe(grp, gptr, &uctxt->tid_group_list.list,
-				 list) {
-		list_del_init(&grp->list);
-		kfree(grp);
-	}
-	hfi1_clear_tids(uctxt);
-}
-
 void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd)
 {
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
@@ -302,21 +178,90 @@ void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd)
 	fd->entry_to_rb = NULL;
 }
 
-/*
- * Write an "empty" RcvArray entry.
- * This function exists so the TID registaration code can use it
- * to write to unused/unneeded entries and still take advantage
- * of the WC performance improvements. The HFI will ignore this
- * write to the RcvArray entry.
+/**
+ * Release pinned receive buffer pages.
+ *
+ * @mapped - true if the pages have been DMA mapped. false otherwise.
+ * @idx - Index of the first page to unpin.
+ * @npages - No of pages to unpin.
+ *
+ * If the pages have been DMA mapped (indicated by mapped parameter), their
+ * info will be passed via a struct tid_rb_node. If they haven't been mapped,
+ * their info will be passed via a struct tid_user_buf.
+ */
+static void unpin_rcv_pages(struct hfi1_filedata *fd,
+			    struct tid_user_buf *tidbuf,
+			    struct tid_rb_node *node,
+			    unsigned int idx,
+			    unsigned int npages,
+			    bool mapped)
+{
+	struct page **pages;
+	struct hfi1_devdata *dd = fd->uctxt->dd;
+
+	if (mapped) {
+		pci_unmap_single(dd->pcidev, node->dma_addr,
+				 node->mmu.len, PCI_DMA_FROMDEVICE);
+		pages = &node->pages[idx];
+	} else {
+		pages = &tidbuf->pages[idx];
+	}
+	hfi1_release_user_pages(fd->mm, pages, npages, mapped);
+	fd->tid_n_pinned -= npages;
+}
+
+/**
+ * Pin receive buffer pages.
  */
-static inline void rcv_array_wc_fill(struct hfi1_devdata *dd, u32 index)
+static int pin_rcv_pages(struct hfi1_filedata *fd, struct tid_user_buf *tidbuf)
 {
+	int pinned;
+	unsigned int npages;
+	unsigned long vaddr = tidbuf->vaddr;
+	struct page **pages = NULL;
+	struct hfi1_devdata *dd = fd->uctxt->dd;
+
+	/* Get the number of pages the user buffer spans */
+	npages = num_user_pages(vaddr, tidbuf->length);
+	if (!npages)
+		return -EINVAL;
+
+	if (npages > fd->uctxt->expected_count) {
+		dd_dev_err(dd, "Expected buffer too big\n");
+		return -EINVAL;
+	}
+
+	/* Verify that access is OK for the user buffer */
+	if (!access_ok(VERIFY_WRITE, (void __user *)vaddr,
+		       npages * PAGE_SIZE)) {
+		dd_dev_err(dd, "Fail vaddr %p, %u pages, !access_ok\n",
+			   (void *)vaddr, npages);
+		return -EFAULT;
+	}
+	/* Allocate the array of struct page pointers needed for pinning */
+	pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
 	/*
-	 * Doing the WC fill writes only makes sense if the device is
-	 * present and the RcvArray has been mapped as WC memory.
+	 * Pin all the pages of the user buffer. If we can't pin all the
+	 * pages, accept the amount pinned so far and program only that.
+	 * User space knows how to deal with partially programmed buffers.
 	 */
-	if ((dd->flags & HFI1_PRESENT) && dd->rcvarray_wc)
-		writeq(0, dd->rcvarray_wc + (index * 8));
+	if (!hfi1_can_pin_pages(dd, fd->mm, fd->tid_n_pinned, npages)) {
+		kfree(pages);
+		return -ENOMEM;
+	}
+
+	pinned = hfi1_acquire_user_pages(fd->mm, vaddr, npages, true, pages);
+	if (pinned <= 0) {
+		kfree(pages);
+		return pinned;
+	}
+	tidbuf->pages = pages;
+	tidbuf->npages = npages;
+	fd->tid_n_pinned += pinned;
+	return pinned;
 }
 
 /*
@@ -374,62 +319,33 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 	int ret = 0, need_group = 0, pinned;
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct hfi1_devdata *dd = uctxt->dd;
-	unsigned npages, ngroups, pageidx = 0, pageset_count, npagesets,
+	unsigned int ngroups, pageidx = 0, pageset_count,
 		tididx = 0, mapped, mapped_pages = 0;
-	unsigned long vaddr = tinfo->vaddr;
-	struct page **pages = NULL;
 	u32 *tidlist = NULL;
-	struct tid_pageset *pagesets = NULL;
+	struct tid_user_buf *tidbuf;
 
-	/* Get the number of pages the user buffer spans */
-	npages = num_user_pages(vaddr, tinfo->length);
-	if (!npages)
-		return -EINVAL;
-
-	if (npages > uctxt->expected_count) {
-		dd_dev_err(dd, "Expected buffer too big\n");
-		return -EINVAL;
-	}
-
-	/* Verify that access is OK for the user buffer */
-	if (!access_ok(VERIFY_WRITE, (void __user *)vaddr,
-		       npages * PAGE_SIZE)) {
-		dd_dev_err(dd, "Fail vaddr %p, %u pages, !access_ok\n",
-			   (void *)vaddr, npages);
-		return -EFAULT;
-	}
-
-	pagesets = kcalloc(uctxt->expected_count, sizeof(*pagesets),
-			   GFP_KERNEL);
-	if (!pagesets)
+	tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL);
+	if (!tidbuf)
 		return -ENOMEM;
 
-	/* Allocate the array of struct page pointers needed for pinning */
-	pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL);
-	if (!pages) {
-		ret = -ENOMEM;
-		goto bail;
-	}
-
-	/*
-	 * Pin all the pages of the user buffer. If we can't pin all the
-	 * pages, accept the amount pinned so far and program only that.
-	 * User space knows how to deal with partially programmed buffers.
-	 */
-	if (!hfi1_can_pin_pages(dd, fd->mm, fd->tid_n_pinned, npages)) {
-		ret = -ENOMEM;
-		goto bail;
+	tidbuf->vaddr = tinfo->vaddr;
+	tidbuf->length = tinfo->length;
+	tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets),
+				GFP_KERNEL);
+	if (!tidbuf->psets) {
+		kfree(tidbuf);
+		return -ENOMEM;
 	}
 
-	pinned = hfi1_acquire_user_pages(fd->mm, vaddr, npages, true, pages);
+	pinned = pin_rcv_pages(fd, tidbuf);
 	if (pinned <= 0) {
-		ret = pinned;
-		goto bail;
+		kfree(tidbuf->psets);
+		kfree(tidbuf);
+		return pinned;
 	}
-	fd->tid_n_pinned += npages;
 
 	/* Find sets of physically contiguous pages */
-	npagesets = find_phys_blocks(pages, pinned, pagesets);
+	tidbuf->n_psets = find_phys_blocks(tidbuf, pinned);
 
 	/*
 	 * We don't need to access this under a lock since tid_used is per
@@ -437,10 +353,10 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 	 * and hfi1_user_exp_rcv_setup() at the same time.
 	 */
 	spin_lock(&fd->tid_lock);
-	if (fd->tid_used + npagesets > fd->tid_limit)
+	if (fd->tid_used + tidbuf->n_psets > fd->tid_limit)
 		pageset_count = fd->tid_limit - fd->tid_used;
 	else
-		pageset_count = npagesets;
+		pageset_count = tidbuf->n_psets;
 	spin_unlock(&fd->tid_lock);
 
 	if (!pageset_count)
@@ -468,9 +384,9 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 		struct tid_group *grp =
 			tid_group_pop(&uctxt->tid_group_list);
 
-		ret = program_rcvarray(fd, vaddr, grp, pagesets,
+		ret = program_rcvarray(fd, tidbuf, grp,
 				       pageidx, dd->rcv_entries.group_size,
-				       pages, tidlist, &tididx, &mapped);
+				       tidlist, &tididx, &mapped);
 		/*
 		 * If there was a failure to program the RcvArray
 		 * entries for the entire group, reset the grp fields
@@ -514,8 +430,8 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 			unsigned use = min_t(unsigned, pageset_count - pageidx,
 					     grp->size - grp->used);
 
-			ret = program_rcvarray(fd, vaddr, grp, pagesets,
-					       pageidx, use, pages, tidlist,
+			ret = program_rcvarray(fd, tidbuf, grp,
+					       pageidx, use, tidlist,
 					       &tididx, &mapped);
 			if (ret < 0) {
 				hfi1_cdbg(TID,
@@ -575,16 +491,14 @@ nomem:
 	 * If not everything was mapped (due to insufficient RcvArray entries,
 	 * for example), unpin all unmapped pages so we can pin them nex time.
 	 */
-	if (mapped_pages != pinned) {
-		hfi1_release_user_pages(fd->mm, &pages[mapped_pages],
-					pinned - mapped_pages,
-					false);
-		fd->tid_n_pinned -= pinned - mapped_pages;
-	}
+	if (mapped_pages != pinned)
+		unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages,
+				(pinned - mapped_pages), false);
 bail:
-	kfree(pagesets);
-	kfree(pages);
+	kfree(tidbuf->psets);
 	kfree(tidlist);
+	kfree(tidbuf->pages);
+	kfree(tidbuf);
 	return ret > 0 ? 0 : ret;
 }
 
@@ -674,11 +588,12 @@ int hfi1_user_exp_rcv_invalid(struct hfi1_filedata *fd,
 	return ret;
 }
 
-static u32 find_phys_blocks(struct page **pages, unsigned npages,
-			    struct tid_pageset *list)
+static u32 find_phys_blocks(struct tid_user_buf *tidbuf, unsigned int npages)
 {
 	unsigned pagecount, pageidx, setcount = 0, i;
 	unsigned long pfn, this_pfn;
+	struct page **pages = tidbuf->pages;
+	struct tid_pageset *list = tidbuf->psets;
 
 	if (!npages)
 		return 0;
@@ -741,13 +656,13 @@ static u32 find_phys_blocks(struct page **pages, unsigned npages,
 /**
  * program_rcvarray() - program an RcvArray group with receive buffers
  * @fd: filedata pointer
- * @vaddr: starting user virtual address
+ * @tbuf: pointer to struct tid_user_buf that has the user buffer starting
+ *	  virtual address, buffer length, page pointers, pagesets (array of
+ *	  struct tid_pageset holding information on physically contiguous
+ *	  chunks from the user buffer), and other fields.
  * @grp: RcvArray group
- * @sets: array of struct tid_pageset holding information on physically
- *        contiguous chunks from the user buffer
  * @start: starting index into sets array
  * @count: number of struct tid_pageset's to program
- * @pages: an array of struct page * for the user buffer
  * @tidlist: the array of u32 elements when the information about the
  *           programmed RcvArray entries is to be encoded.
  * @tididx: starting offset into tidlist
@@ -765,11 +680,11 @@ static u32 find_phys_blocks(struct page **pages, unsigned npages,
  * -ENOMEM or -EFAULT on error from set_rcvarray_entry(), or
  * number of RcvArray entries programmed.
  */
-static int program_rcvarray(struct hfi1_filedata *fd, unsigned long vaddr,
+static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *tbuf,
 			    struct tid_group *grp,
-			    struct tid_pageset *sets,
-			    unsigned start, u16 count, struct page **pages,
-			    u32 *tidlist, unsigned *tididx, unsigned *pmapped)
+			    unsigned int start, u16 count,
+			    u32 *tidlist, unsigned int *tididx,
+			    unsigned int *pmapped)
 {
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct hfi1_devdata *dd = uctxt->dd;
@@ -808,11 +723,11 @@ static int program_rcvarray(struct hfi1_filedata *fd, unsigned long vaddr,
 		}
 
 		rcventry = grp->base + useidx;
-		npages = sets[setidx].count;
-		pageidx = sets[setidx].idx;
+		npages = tbuf->psets[setidx].count;
+		pageidx = tbuf->psets[setidx].idx;
 
-		ret = set_rcvarray_entry(fd, vaddr + (pageidx * PAGE_SIZE),
-					 rcventry, grp, pages + pageidx,
+		ret = set_rcvarray_entry(fd, tbuf,
+					 rcventry, grp, pageidx,
 					 npages);
 		if (ret)
 			return ret;
@@ -833,15 +748,17 @@ static int program_rcvarray(struct hfi1_filedata *fd, unsigned long vaddr,
 	return idx;
 }
 
-static int set_rcvarray_entry(struct hfi1_filedata *fd, unsigned long vaddr,
+static int set_rcvarray_entry(struct hfi1_filedata *fd,
+			      struct tid_user_buf *tbuf,
 			      u32 rcventry, struct tid_group *grp,
-			      struct page **pages, unsigned npages)
+			      u16 pageidx, unsigned int npages)
 {
 	int ret;
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct tid_rb_node *node;
 	struct hfi1_devdata *dd = uctxt->dd;
 	dma_addr_t phys;
+	struct page **pages = tbuf->pages + pageidx;
 
 	/*
 	 * Allocate the node first so we can handle a potential
@@ -862,7 +779,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd, unsigned long vaddr,
 		return -EFAULT;
 	}
 
-	node->mmu.addr = vaddr;
+	node->mmu.addr = tbuf->vaddr + (pageidx * PAGE_SIZE);
 	node->mmu.len = npages * PAGE_SIZE;
 	node->phys = page_to_phys(pages[0]);
 	node->npages = npages;
@@ -935,17 +852,13 @@ static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
 				 node->npages, node->mmu.addr, node->phys,
 				 node->dma_addr);
 
-	hfi1_put_tid(dd, node->rcventry, PT_INVALID, 0, 0);
 	/*
 	 * Make sure device has seen the write before we unpin the
 	 * pages.
 	 */
-	flush_wc();
+	hfi1_put_tid(dd, node->rcventry, PT_INVALID_FLUSH, 0, 0);
 
-	pci_unmap_single(dd->pcidev, node->dma_addr, node->mmu.len,
-			 PCI_DMA_FROMDEVICE);
-	hfi1_release_user_pages(fd->mm, node->pages, node->npages, true);
-	fd->tid_n_pinned -= node->npages;
+	unpin_rcv_pages(fd, NULL, node, 0, node->npages, true);
 
 	node->grp->used--;
 	node->grp->map &= ~(1 << (node->rcventry - node->grp->base));
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
index 5250c897298d..e383cc01a2bf 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
@@ -49,30 +49,44 @@
 
 #include "hfi.h"
 
-#define EXP_TID_TIDLEN_MASK   0x7FFULL
-#define EXP_TID_TIDLEN_SHIFT  0
-#define EXP_TID_TIDCTRL_MASK  0x3ULL
-#define EXP_TID_TIDCTRL_SHIFT 20
-#define EXP_TID_TIDIDX_MASK   0x3FFULL
-#define EXP_TID_TIDIDX_SHIFT  22
-#define EXP_TID_GET(tid, field)	\
-	(((tid) >> EXP_TID_TID##field##_SHIFT) & EXP_TID_TID##field##_MASK)
+#include "exp_rcv.h"
 
-#define EXP_TID_SET(field, value)			\
-	(((value) & EXP_TID_TID##field##_MASK) <<	\
-	 EXP_TID_TID##field##_SHIFT)
-#define EXP_TID_CLEAR(tid, field) ({					\
-		(tid) &= ~(EXP_TID_TID##field##_MASK <<			\
-			   EXP_TID_TID##field##_SHIFT);			\
-		})
-#define EXP_TID_RESET(tid, field, value) do {				\
-		EXP_TID_CLEAR(tid, field);				\
-		(tid) |= EXP_TID_SET(field, (value));			\
-	} while (0)
+struct tid_pageset {
+	u16 idx;
+	u16 count;
+};
 
-void hfi1_user_exp_rcv_grp_free(struct hfi1_ctxtdata *uctxt);
-int hfi1_user_exp_rcv_grp_init(struct hfi1_filedata *fd);
-int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd);
+struct tid_user_buf {
+	unsigned long vaddr;
+	unsigned long length;
+	unsigned int npages;
+	struct page **pages;
+	struct tid_pageset *psets;
+	unsigned int n_psets;
+};
+
+struct tid_rb_node {
+	struct mmu_rb_node mmu;
+	unsigned long phys;
+	struct tid_group *grp;
+	u32 rcventry;
+	dma_addr_t dma_addr;
+	bool freed;
+	unsigned int npages;
+	struct page *pages[0];
+};
+
+static inline int num_user_pages(unsigned long addr,
+				 unsigned long len)
+{
+	const unsigned long spage = addr & PAGE_MASK;
+	const unsigned long epage = (addr + len - 1) & PAGE_MASK;
+
+	return 1 + ((epage - spage) >> PAGE_SHIFT);
+}
+
+int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
+			   struct hfi1_ctxtdata *uctxt);
 void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd);
 int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 			    struct hfi1_tid_info *tinfo);
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index d55339f5d73b..c0c0e0445cbf 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -64,224 +64,20 @@
 
 #include "hfi.h"
 #include "sdma.h"
+#include "mmu_rb.h"
 #include "user_sdma.h"
 #include "verbs.h"  /* for the headers */
 #include "common.h" /* for struct hfi1_tid_info */
 #include "trace.h"
-#include "mmu_rb.h"
 
 static uint hfi1_sdma_comp_ring_size = 128;
 module_param_named(sdma_comp_size, hfi1_sdma_comp_ring_size, uint, S_IRUGO);
 MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 128");
 
-/* The maximum number of Data io vectors per message/request */
-#define MAX_VECTORS_PER_REQ 8
-/*
- * Maximum number of packet to send from each message/request
- * before moving to the next one.
- */
-#define MAX_PKTS_PER_QUEUE 16
-
-#define num_pages(x) (1 + ((((x) - 1) & PAGE_MASK) >> PAGE_SHIFT))
-
-#define req_opcode(x) \
-	(((x) >> HFI1_SDMA_REQ_OPCODE_SHIFT) & HFI1_SDMA_REQ_OPCODE_MASK)
-#define req_version(x) \
-	(((x) >> HFI1_SDMA_REQ_VERSION_SHIFT) & HFI1_SDMA_REQ_OPCODE_MASK)
-#define req_iovcnt(x) \
-	(((x) >> HFI1_SDMA_REQ_IOVCNT_SHIFT) & HFI1_SDMA_REQ_IOVCNT_MASK)
-
-/* Number of BTH.PSN bits used for sequence number in expected rcvs */
-#define BTH_SEQ_MASK 0x7ffull
-
-/*
- * Define fields in the KDETH header so we can update the header
- * template.
- */
-#define KDETH_OFFSET_SHIFT        0
-#define KDETH_OFFSET_MASK         0x7fff
-#define KDETH_OM_SHIFT            15
-#define KDETH_OM_MASK             0x1
-#define KDETH_TID_SHIFT           16
-#define KDETH_TID_MASK            0x3ff
-#define KDETH_TIDCTRL_SHIFT       26
-#define KDETH_TIDCTRL_MASK        0x3
-#define KDETH_INTR_SHIFT          28
-#define KDETH_INTR_MASK           0x1
-#define KDETH_SH_SHIFT            29
-#define KDETH_SH_MASK             0x1
-#define KDETH_HCRC_UPPER_SHIFT    16
-#define KDETH_HCRC_UPPER_MASK     0xff
-#define KDETH_HCRC_LOWER_SHIFT    24
-#define KDETH_HCRC_LOWER_MASK     0xff
-
-#define AHG_KDETH_INTR_SHIFT 12
-#define AHG_KDETH_SH_SHIFT   13
-
-#define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4)
-#define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff)
-
-#define KDETH_GET(val, field)						\
-	(((le32_to_cpu((val))) >> KDETH_##field##_SHIFT) & KDETH_##field##_MASK)
-#define KDETH_SET(dw, field, val) do {					\
-		u32 dwval = le32_to_cpu(dw);				\
-		dwval &= ~(KDETH_##field##_MASK << KDETH_##field##_SHIFT); \
-		dwval |= (((val) & KDETH_##field##_MASK) << \
-			  KDETH_##field##_SHIFT);			\
-		dw = cpu_to_le32(dwval);				\
-	} while (0)
-
-#define AHG_HEADER_SET(arr, idx, dw, bit, width, value)			\
-	do {								\
-		if ((idx) < ARRAY_SIZE((arr)))				\
-			(arr)[(idx++)] = sdma_build_ahg_descriptor(	\
-				(__force u16)(value), (dw), (bit),	\
-							(width));	\
-		else							\
-			return -ERANGE;					\
-	} while (0)
-
-/* KDETH OM multipliers and switch over point */
-#define KDETH_OM_SMALL     4
-#define KDETH_OM_SMALL_SHIFT     2
-#define KDETH_OM_LARGE     64
-#define KDETH_OM_LARGE_SHIFT     6
-#define KDETH_OM_MAX_SIZE  (1 << ((KDETH_OM_LARGE / KDETH_OM_SMALL) + 1))
-
-/* Tx request flag bits */
-#define TXREQ_FLAGS_REQ_ACK   BIT(0)      /* Set the ACK bit in the header */
-#define TXREQ_FLAGS_REQ_DISABLE_SH BIT(1) /* Disable header suppression */
-
-/* SDMA request flag bits */
-#define SDMA_REQ_FOR_THREAD 1
-#define SDMA_REQ_SEND_DONE  2
-#define SDMA_REQ_HAS_ERROR  3
-#define SDMA_REQ_DONE_ERROR 4
-
-#define SDMA_PKT_Q_INACTIVE BIT(0)
-#define SDMA_PKT_Q_ACTIVE   BIT(1)
-#define SDMA_PKT_Q_DEFERRED BIT(2)
-
-/*
- * Maximum retry attempts to submit a TX request
- * before putting the process to sleep.
- */
-#define MAX_DEFER_RETRY_COUNT 1
-
 static unsigned initial_pkt_count = 8;
 
-#define SDMA_IOWAIT_TIMEOUT 1000 /* in milliseconds */
-
-struct sdma_mmu_node;
-
-struct user_sdma_iovec {
-	struct list_head list;
-	struct iovec iov;
-	/* number of pages in this vector */
-	unsigned npages;
-	/* array of pinned pages for this vector */
-	struct page **pages;
-	/*
-	 * offset into the virtual address space of the vector at
-	 * which we last left off.
-	 */
-	u64 offset;
-	struct sdma_mmu_node *node;
-};
-
-struct sdma_mmu_node {
-	struct mmu_rb_node rb;
-	struct hfi1_user_sdma_pkt_q *pq;
-	atomic_t refcount;
-	struct page **pages;
-	unsigned npages;
-};
-
-/* evict operation argument */
-struct evict_data {
-	u32 cleared;	/* count evicted so far */
-	u32 target;	/* target count to evict */
-};
-
-struct user_sdma_request {
-	struct sdma_req_info info;
-	struct hfi1_user_sdma_pkt_q *pq;
-	struct hfi1_user_sdma_comp_q *cq;
-	/* This is the original header from user space */
-	struct hfi1_pkt_header hdr;
-	/*
-	 * Pointer to the SDMA engine for this request.
-	 * Since different request could be on different VLs,
-	 * each request will need it's own engine pointer.
-	 */
-	struct sdma_engine *sde;
-	s8 ahg_idx;
-	u32 ahg[9];
-	/*
-	 * KDETH.Offset (Eager) field
-	 * We need to remember the initial value so the headers
-	 * can be updated properly.
-	 */
-	u32 koffset;
-	/*
-	 * KDETH.OFFSET (TID) field
-	 * The offset can cover multiple packets, depending on the
-	 * size of the TID entry.
-	 */
-	u32 tidoffset;
-	/*
-	 * We copy the iovs for this request (based on
-	 * info.iovcnt). These are only the data vectors
-	 */
-	unsigned data_iovs;
-	/* total length of the data in the request */
-	u32 data_len;
-	/* progress index moving along the iovs array */
-	unsigned iov_idx;
-	struct user_sdma_iovec iovs[MAX_VECTORS_PER_REQ];
-	/* number of elements copied to the tids array */
-	u16 n_tids;
-	/* TID array values copied from the tid_iov vector */
-	u32 *tids;
-	u16 tididx;
-	u32 sent;
-	u64 seqnum;
-	u64 seqcomp;
-	u64 seqsubmitted;
-	struct list_head txps;
-	unsigned long flags;
-	/* status of the last txreq completed */
-	int status;
-};
-
-/*
- * A single txreq could span up to 3 physical pages when the MTU
- * is sufficiently large (> 4K). Each of the IOV pointers also
- * needs it's own set of flags so the vector has been handled
- * independently of each other.
- */
-struct user_sdma_txreq {
-	/* Packet header for the txreq */
-	struct hfi1_pkt_header hdr;
-	struct sdma_txreq txreq;
-	struct list_head list;
-	struct user_sdma_request *req;
-	u16 flags;
-	unsigned busycount;
-	u64 seqnum;
-};
-
-#define SDMA_DBG(req, fmt, ...)				     \
-	hfi1_cdbg(SDMA, "[%u:%u:%u:%u] " fmt, (req)->pq->dd->unit, \
-		 (req)->pq->ctxt, (req)->pq->subctxt, (req)->info.comp_idx, \
-		 ##__VA_ARGS__)
-#define SDMA_Q_DBG(pq, fmt, ...)			 \
-	hfi1_cdbg(SDMA, "[%u:%u:%u] " fmt, (pq)->dd->unit, (pq)->ctxt, \
-		 (pq)->subctxt, ##__VA_ARGS__)
-
 static int user_sdma_send_pkts(struct user_sdma_request *req,
 			       unsigned maxpkts);
-static int num_user_pages(const struct iovec *iov);
 static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status);
 static inline void pq_update(struct hfi1_user_sdma_pkt_q *pq);
 static void user_sdma_free_request(struct user_sdma_request *req, bool unpin);
@@ -307,7 +103,8 @@ static int defer_packet_queue(
 	struct sdma_engine *sde,
 	struct iowait *wait,
 	struct sdma_txreq *txreq,
-	unsigned int seq);
+	uint seq,
+	bool pkts_sent);
 static void activate_packet_queue(struct iowait *wait, int reason);
 static bool sdma_rb_filter(struct mmu_rb_node *node, unsigned long addr,
 			   unsigned long len);
@@ -329,7 +126,8 @@ static int defer_packet_queue(
 	struct sdma_engine *sde,
 	struct iowait *wait,
 	struct sdma_txreq *txreq,
-	unsigned seq)
+	uint seq,
+	bool pkts_sent)
 {
 	struct hfi1_user_sdma_pkt_q *pq =
 		container_of(wait, struct hfi1_user_sdma_pkt_q, busy);
@@ -349,7 +147,7 @@ static int defer_packet_queue(
 	xchg(&pq->state, SDMA_PKT_Q_DEFERRED);
 	write_seqlock(&dev->iowait_lock);
 	if (list_empty(&pq->busy.list))
-		list_add_tail(&pq->busy.list, &sde->dmawait);
+		iowait_queue(pkts_sent, &pq->busy, &sde->dmawait);
 	write_sequnlock(&dev->iowait_lock);
 	return -EBUSY;
 eagain:
@@ -364,13 +162,6 @@ static void activate_packet_queue(struct iowait *wait, int reason)
 	wake_up(&wait->wait_dma);
 };
 
-static void sdma_kmem_cache_ctor(void *obj)
-{
-	struct user_sdma_txreq *tx = obj;
-
-	memset(tx, 0, sizeof(*tx));
-}
-
 int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 				struct hfi1_filedata *fd)
 {
@@ -379,7 +170,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 	struct hfi1_devdata *dd;
 	struct hfi1_user_sdma_comp_q *cq;
 	struct hfi1_user_sdma_pkt_q *pq;
-	unsigned long flags;
 
 	if (!uctxt || !fd)
 		return -EBADF;
@@ -393,7 +183,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 	if (!pq)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&pq->list);
 	pq->dd = dd;
 	pq->ctxt = uctxt->ctxt;
 	pq->subctxt = fd->subctxt;
@@ -426,7 +215,7 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 					    sizeof(struct user_sdma_txreq),
 					    L1_CACHE_BYTES,
 					    SLAB_HWCACHE_ALIGN,
-					    sdma_kmem_cache_ctor);
+					    NULL);
 	if (!pq->txreq_cache) {
 		dd_dev_err(dd, "[%u] Failed to allocate TxReq cache\n",
 			   uctxt->ctxt);
@@ -454,10 +243,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 	fd->pq = pq;
 	fd->cq = cq;
 
-	spin_lock_irqsave(&uctxt->sdma_qlock, flags);
-	list_add(&pq->list, &uctxt->sdma_queues);
-	spin_unlock_irqrestore(&uctxt->sdma_qlock, flags);
-
 	return 0;
 
 pq_mmu_fail:
@@ -476,22 +261,17 @@ pq_reqs_nomem:
 	return ret;
 }
 
-int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd)
+int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
+			       struct hfi1_ctxtdata *uctxt)
 {
-	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct hfi1_user_sdma_pkt_q *pq;
-	unsigned long flags;
 
-	hfi1_cdbg(SDMA, "[%u:%u:%u] Freeing user SDMA queues", uctxt->dd->unit,
-		  uctxt->ctxt, fd->subctxt);
+	trace_hfi1_sdma_user_free_queues(uctxt->dd, uctxt->ctxt, fd->subctxt);
+
 	pq = fd->pq;
 	if (pq) {
 		if (pq->handler)
 			hfi1_mmu_rb_unregister(pq->handler);
-		spin_lock_irqsave(&uctxt->sdma_qlock, flags);
-		if (!list_empty(&pq->list))
-			list_del_init(&pq->list);
-		spin_unlock_irqrestore(&uctxt->sdma_qlock, flags);
 		iowait_sdma_drain(&pq->busy);
 		/* Wait until all requests have been freed. */
 		wait_event_interruptible(
@@ -546,6 +326,8 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 	struct sdma_req_info info;
 	struct user_sdma_request *req;
 	u8 opcode, sc, vl;
+	u16 pkey;
+	u32 slid;
 	int req_queued = 0;
 	u16 dlid;
 	u32 selector;
@@ -567,7 +349,6 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 
 	trace_hfi1_sdma_user_reqinfo(dd, uctxt->ctxt, fd->subctxt,
 				     (u16 *)&info);
-
 	if (info.comp_idx >= hfi1_sdma_comp_ring_size) {
 		hfi1_cdbg(SDMA,
 			  "[%u:%u:%u:%u] Invalid comp index",
@@ -604,15 +385,23 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 	/*
 	 * All safety checks have been done and this request has been claimed.
 	 */
-	hfi1_cdbg(SDMA, "[%u:%u:%u] Using req/comp entry %u\n", dd->unit,
-		  uctxt->ctxt, fd->subctxt, info.comp_idx);
+	trace_hfi1_sdma_user_process_request(dd, uctxt->ctxt, fd->subctxt,
+					     info.comp_idx);
 	req = pq->reqs + info.comp_idx;
-	memset(req, 0, sizeof(*req));
 	req->data_iovs = req_iovcnt(info.ctrl) - 1; /* subtract header vector */
+	req->data_len  = 0;
 	req->pq = pq;
 	req->cq = cq;
 	req->status = -1;
 	req->ahg_idx = -1;
+	req->iov_idx = 0;
+	req->sent = 0;
+	req->seqnum = 0;
+	req->seqcomp = 0;
+	req->seqsubmitted = 0;
+	req->tids = NULL;
+	req->done = 0;
+	req->has_error = 0;
 	INIT_LIST_HEAD(&req->txps);
 
 	memcpy(&req->info, &info, sizeof(info));
@@ -671,8 +460,9 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 	}
 
 	/* Checking P_KEY for requests from user-space */
-	if (egress_pkey_check(dd->pport, req->hdr.lrh, req->hdr.bth, sc,
-			      PKEY_CHECK_INVALID)) {
+	pkey = (u16)be32_to_cpu(req->hdr.bth[0]);
+	slid = be16_to_cpu(req->hdr.lrh[3]);
+	if (egress_pkey_check(dd->pport, slid, pkey, sc, PKEY_CHECK_INVALID)) {
 		ret = -EINVAL;
 		goto free_req;
 	}
@@ -696,24 +486,27 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 	req->tidoffset = KDETH_GET(req->hdr.kdeth.ver_tid_offset, OFFSET) *
 		(KDETH_GET(req->hdr.kdeth.ver_tid_offset, OM) ?
 		 KDETH_OM_LARGE : KDETH_OM_SMALL);
-	SDMA_DBG(req, "Initial TID offset %u", req->tidoffset);
+	trace_hfi1_sdma_user_initial_tidoffset(dd, uctxt->ctxt, fd->subctxt,
+					       info.comp_idx, req->tidoffset);
 	idx++;
 
 	/* Save all the IO vector structures */
 	for (i = 0; i < req->data_iovs; i++) {
+		req->iovs[i].offset = 0;
 		INIT_LIST_HEAD(&req->iovs[i].list);
 		memcpy(&req->iovs[i].iov,
 		       iovec + idx++,
 		       sizeof(req->iovs[i].iov));
 		ret = pin_vector_pages(req, &req->iovs[i]);
 		if (ret) {
+			req->data_iovs = i;
 			req->status = ret;
 			goto free_req;
 		}
 		req->data_len += req->iovs[i].iov.iov_len;
 	}
-	SDMA_DBG(req, "total data length %u", req->data_len);
-
+	trace_hfi1_sdma_user_data_length(dd, uctxt->ctxt, fd->subctxt,
+					 info.comp_idx, req->data_len);
 	if (pcount > req->info.npkts)
 		pcount = req->info.npkts;
 	/*
@@ -749,6 +542,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 		}
 		req->tids = tmp;
 		req->n_tids = ntids;
+		req->tididx = 0;
 		idx++;
 	}
 
@@ -791,12 +585,12 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 	 * request have been submitted to the SDMA engine. However, it
 	 * will not wait for send completions.
 	 */
-	while (!test_bit(SDMA_REQ_SEND_DONE, &req->flags)) {
+	while (req->seqsubmitted != req->info.npkts) {
 		ret = user_sdma_send_pkts(req, pcount);
 		if (ret < 0) {
 			if (ret != -EBUSY) {
 				req->status = ret;
-				set_bit(SDMA_REQ_DONE_ERROR, &req->flags);
+				WRITE_ONCE(req->has_error, 1);
 				if (ACCESS_ONCE(req->seqcomp) ==
 				    req->seqsubmitted - 1)
 					goto free_req;
@@ -867,7 +661,11 @@ static inline u32 compute_data_length(struct user_sdma_request *req,
 	} else {
 		len = min(req->data_len - req->sent, (u32)req->info.fragsize);
 	}
-	SDMA_DBG(req, "Data Length = %u", len);
+	trace_hfi1_sdma_user_compute_length(req->pq->dd,
+					    req->pq->ctxt,
+					    req->pq->subctxt,
+					    req->info.comp_idx,
+					    len);
 	return len;
 }
 
@@ -884,6 +682,84 @@ static inline u32 get_lrh_len(struct hfi1_pkt_header hdr, u32 len)
 	return ((sizeof(hdr) - sizeof(hdr.pbc)) + 4 + len);
 }
 
+static int user_sdma_txadd_ahg(struct user_sdma_request *req,
+			       struct user_sdma_txreq *tx,
+			       u32 datalen)
+{
+	int ret;
+	u16 pbclen = le16_to_cpu(req->hdr.pbc[0]);
+	u32 lrhlen = get_lrh_len(req->hdr, pad_len(datalen));
+	struct hfi1_user_sdma_pkt_q *pq = req->pq;
+
+	/*
+	 * Copy the request header into the tx header
+	 * because the HW needs a cacheline-aligned
+	 * address.
+	 * This copy can be optimized out if the hdr
+	 * member of user_sdma_request were also
+	 * cacheline aligned.
+	 */
+	memcpy(&tx->hdr, &req->hdr, sizeof(tx->hdr));
+	if (PBC2LRH(pbclen) != lrhlen) {
+		pbclen = (pbclen & 0xf000) | LRH2PBC(lrhlen);
+		tx->hdr.pbc[0] = cpu_to_le16(pbclen);
+	}
+	ret = check_header_template(req, &tx->hdr, lrhlen, datalen);
+	if (ret)
+		return ret;
+	ret = sdma_txinit_ahg(&tx->txreq, SDMA_TXREQ_F_AHG_COPY,
+			      sizeof(tx->hdr) + datalen, req->ahg_idx,
+			      0, NULL, 0, user_sdma_txreq_cb);
+	if (ret)
+		return ret;
+	ret = sdma_txadd_kvaddr(pq->dd, &tx->txreq, &tx->hdr, sizeof(tx->hdr));
+	if (ret)
+		sdma_txclean(pq->dd, &tx->txreq);
+	return ret;
+}
+
+static int user_sdma_txadd(struct user_sdma_request *req,
+			   struct user_sdma_txreq *tx,
+			   struct user_sdma_iovec *iovec, u32 datalen,
+			   u32 *queued_ptr, u32 *data_sent_ptr,
+			   u64 *iov_offset_ptr)
+{
+	int ret;
+	unsigned int pageidx, len;
+	unsigned long base, offset;
+	u64 iov_offset = *iov_offset_ptr;
+	u32 queued = *queued_ptr, data_sent = *data_sent_ptr;
+	struct hfi1_user_sdma_pkt_q *pq = req->pq;
+
+	base = (unsigned long)iovec->iov.iov_base;
+	offset = offset_in_page(base + iovec->offset + iov_offset);
+	pageidx = (((iovec->offset + iov_offset + base) - (base & PAGE_MASK)) >>
+		   PAGE_SHIFT);
+	len = offset + req->info.fragsize > PAGE_SIZE ?
+		PAGE_SIZE - offset : req->info.fragsize;
+	len = min((datalen - queued), len);
+	ret = sdma_txadd_page(pq->dd, &tx->txreq, iovec->pages[pageidx],
+			      offset, len);
+	if (ret) {
+		SDMA_DBG(req, "SDMA txreq add page failed %d\n", ret);
+		return ret;
+	}
+	iov_offset += len;
+	queued += len;
+	data_sent += len;
+	if (unlikely(queued < datalen && pageidx == iovec->npages &&
+		     req->iov_idx < req->data_iovs - 1)) {
+		iovec->offset += iov_offset;
+		iovec = &req->iovs[++req->iov_idx];
+		iov_offset = 0;
+	}
+
+	*queued_ptr = queued;
+	*data_sent_ptr = data_sent;
+	*iov_offset_ptr = iov_offset;
+	return ret;
+}
+
 static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 {
 	int ret = 0, count;
@@ -898,10 +774,8 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 	pq = req->pq;
 
 	/* If tx completion has reported an error, we are done. */
-	if (test_bit(SDMA_REQ_HAS_ERROR, &req->flags)) {
-		set_bit(SDMA_REQ_DONE_ERROR, &req->flags);
+	if (READ_ONCE(req->has_error))
 		return -EFAULT;
-	}
 
 	/*
 	 * Check if we might have sent the entire request already
@@ -924,10 +798,8 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 		 * with errors. If so, we are not going to process any
 		 * more packets from this request.
 		 */
-		if (test_bit(SDMA_REQ_HAS_ERROR, &req->flags)) {
-			set_bit(SDMA_REQ_DONE_ERROR, &req->flags);
+		if (READ_ONCE(req->has_error))
 			return -EFAULT;
-		}
 
 		tx = kmem_cache_alloc(pq->txreq_cache, GFP_KERNEL);
 		if (!tx)
@@ -984,39 +856,9 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 
 		if (req->ahg_idx >= 0) {
 			if (!req->seqnum) {
-				u16 pbclen = le16_to_cpu(req->hdr.pbc[0]);
-				u32 lrhlen = get_lrh_len(req->hdr,
-							 pad_len(datalen));
-				/*
-				 * Copy the request header into the tx header
-				 * because the HW needs a cacheline-aligned
-				 * address.
-				 * This copy can be optimized out if the hdr
-				 * member of user_sdma_request were also
-				 * cacheline aligned.
-				 */
-				memcpy(&tx->hdr, &req->hdr, sizeof(tx->hdr));
-				if (PBC2LRH(pbclen) != lrhlen) {
-					pbclen = (pbclen & 0xf000) |
-						LRH2PBC(lrhlen);
-					tx->hdr.pbc[0] = cpu_to_le16(pbclen);
-				}
-				ret = check_header_template(req, &tx->hdr,
-							    lrhlen, datalen);
+				ret = user_sdma_txadd_ahg(req, tx, datalen);
 				if (ret)
 					goto free_tx;
-				ret = sdma_txinit_ahg(&tx->txreq,
-						      SDMA_TXREQ_F_AHG_COPY,
-						      sizeof(tx->hdr) + datalen,
-						      req->ahg_idx, 0, NULL, 0,
-						      user_sdma_txreq_cb);
-				if (ret)
-					goto free_tx;
-				ret = sdma_txadd_kvaddr(pq->dd, &tx->txreq,
-							&tx->hdr,
-							sizeof(tx->hdr));
-				if (ret)
-					goto free_txreq;
 			} else {
 				int changes;
 
@@ -1024,11 +866,6 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 							       datalen);
 				if (changes < 0)
 					goto free_tx;
-				sdma_txinit_ahg(&tx->txreq,
-						SDMA_TXREQ_F_USE_AHG,
-						datalen, req->ahg_idx, changes,
-						req->ahg, sizeof(req->hdr),
-						user_sdma_txreq_cb);
 			}
 		} else {
 			ret = sdma_txinit(&tx->txreq, 0, sizeof(req->hdr) +
@@ -1052,35 +889,10 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 		 */
 		while (queued < datalen &&
 		       (req->sent + data_sent) < req->data_len) {
-			unsigned long base, offset;
-			unsigned pageidx, len;
-
-			base = (unsigned long)iovec->iov.iov_base;
-			offset = offset_in_page(base + iovec->offset +
-						iov_offset);
-			pageidx = (((iovec->offset + iov_offset +
-				     base) - (base & PAGE_MASK)) >> PAGE_SHIFT);
-			len = offset + req->info.fragsize > PAGE_SIZE ?
-				PAGE_SIZE - offset : req->info.fragsize;
-			len = min((datalen - queued), len);
-			ret = sdma_txadd_page(pq->dd, &tx->txreq,
-					      iovec->pages[pageidx],
-					      offset, len);
-			if (ret) {
-				SDMA_DBG(req, "SDMA txreq add page failed %d\n",
-					 ret);
+			ret = user_sdma_txadd(req, tx, iovec, datalen,
+					      &queued, &data_sent, &iov_offset);
+			if (ret)
 				goto free_txreq;
-			}
-			iov_offset += len;
-			queued += len;
-			data_sent += len;
-			if (unlikely(queued < datalen &&
-				     pageidx == iovec->npages &&
-				     req->iov_idx < req->data_iovs - 1)) {
-				iovec->offset += iov_offset;
-				iovec = &req->iovs[++req->iov_idx];
-				iov_offset = 0;
-			}
 		}
 		/*
 		 * The txreq was submitted successfully so we can update
@@ -1105,7 +917,7 @@ dosend:
 	ret = sdma_send_txlist(req->sde, &pq->busy, &req->txps, &count);
 	req->seqsubmitted += count;
 	if (req->seqsubmitted == req->info.npkts) {
-		set_bit(SDMA_REQ_SEND_DONE, &req->flags);
+		WRITE_ONCE(req->done, 1);
 		/*
 		 * The txreq has already been submitted to the HW queue
 		 * so we can free the AHG entry now. Corruption will not
@@ -1124,19 +936,6 @@ free_tx:
 	return ret;
 }
 
-/*
- * How many pages in this iovec element?
- */
-static inline int num_user_pages(const struct iovec *iov)
-{
-	const unsigned long addr  = (unsigned long)iov->iov_base;
-	const unsigned long len   = iov->iov_len;
-	const unsigned long spage = addr & PAGE_MASK;
-	const unsigned long epage = (addr + len - 1) & PAGE_MASK;
-
-	return 1 + ((epage - spage) >> PAGE_SHIFT);
-}
-
 static u32 sdma_cache_evict(struct hfi1_user_sdma_pkt_q *pq, u32 npages)
 {
 	struct evict_data evict_data;
@@ -1147,22 +946,82 @@ static u32 sdma_cache_evict(struct hfi1_user_sdma_pkt_q *pq, u32 npages)
 	return evict_data.cleared;
 }
 
+static int pin_sdma_pages(struct user_sdma_request *req,
+			  struct user_sdma_iovec *iovec,
+			  struct sdma_mmu_node *node,
+			  int npages)
+{
+	int pinned, cleared;
+	struct page **pages;
+	struct hfi1_user_sdma_pkt_q *pq = req->pq;
+
+	pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL);
+	if (!pages) {
+		SDMA_DBG(req, "Failed page array alloc");
+		return -ENOMEM;
+	}
+	memcpy(pages, node->pages, node->npages * sizeof(*pages));
+
+	npages -= node->npages;
+retry:
+	if (!hfi1_can_pin_pages(pq->dd, pq->mm,
+				atomic_read(&pq->n_locked), npages)) {
+		cleared = sdma_cache_evict(pq, npages);
+		if (cleared >= npages)
+			goto retry;
+	}
+	pinned = hfi1_acquire_user_pages(pq->mm,
+					 ((unsigned long)iovec->iov.iov_base +
+					 (node->npages * PAGE_SIZE)), npages, 0,
+					 pages + node->npages);
+	if (pinned < 0) {
+		kfree(pages);
+		return pinned;
+	}
+	if (pinned != npages) {
+		unpin_vector_pages(pq->mm, pages, node->npages, pinned);
+		return -EFAULT;
+	}
+	kfree(node->pages);
+	node->rb.len = iovec->iov.iov_len;
+	node->pages = pages;
+	atomic_add(pinned, &pq->n_locked);
+	return pinned;
+}
+
+static void unpin_sdma_pages(struct sdma_mmu_node *node)
+{
+	if (node->npages) {
+		unpin_vector_pages(node->pq->mm, node->pages, 0, node->npages);
+		atomic_sub(node->npages, &node->pq->n_locked);
+	}
+}
+
 static int pin_vector_pages(struct user_sdma_request *req,
 			    struct user_sdma_iovec *iovec)
 {
-	int ret = 0, pinned, npages, cleared;
-	struct page **pages;
+	int ret = 0, pinned, npages;
 	struct hfi1_user_sdma_pkt_q *pq = req->pq;
 	struct sdma_mmu_node *node = NULL;
 	struct mmu_rb_node *rb_node;
-
-	rb_node = hfi1_mmu_rb_extract(pq->handler,
-				      (unsigned long)iovec->iov.iov_base,
-				      iovec->iov.iov_len);
-	if (rb_node)
+	struct iovec *iov;
+	bool extracted;
+
+	extracted =
+		hfi1_mmu_rb_remove_unless_exact(pq->handler,
+						(unsigned long)
+						iovec->iov.iov_base,
+						iovec->iov.iov_len, &rb_node);
+	if (rb_node) {
 		node = container_of(rb_node, struct sdma_mmu_node, rb);
-	else
-		rb_node = NULL;
+		if (!extracted) {
+			atomic_inc(&node->refcount);
+			iovec->pages = node->pages;
+			iovec->npages = node->npages;
+			iovec->node = node;
+			return 0;
+		}
+	}
 
 	if (!node) {
 		node = kzalloc(sizeof(*node), GFP_KERNEL);
@@ -1174,46 +1033,16 @@ static int pin_vector_pages(struct user_sdma_request *req,
 		atomic_set(&node->refcount, 0);
 	}
 
-	npages = num_user_pages(&iovec->iov);
+	iov = &iovec->iov;
+	npages = num_user_pages((unsigned long)iov->iov_base, iov->iov_len);
 	if (node->npages < npages) {
-		pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL);
-		if (!pages) {
-			SDMA_DBG(req, "Failed page array alloc");
-			ret = -ENOMEM;
-			goto bail;
-		}
-		memcpy(pages, node->pages, node->npages * sizeof(*pages));
-
-		npages -= node->npages;
-
-retry:
-		if (!hfi1_can_pin_pages(pq->dd, pq->mm,
-					atomic_read(&pq->n_locked), npages)) {
-			cleared = sdma_cache_evict(pq, npages);
-			if (cleared >= npages)
-				goto retry;
-		}
-		pinned = hfi1_acquire_user_pages(pq->mm,
-			((unsigned long)iovec->iov.iov_base +
-			 (node->npages * PAGE_SIZE)), npages, 0,
-			pages + node->npages);
+		pinned = pin_sdma_pages(req, iovec, node, npages);
 		if (pinned < 0) {
-			kfree(pages);
 			ret = pinned;
 			goto bail;
 		}
-		if (pinned != npages) {
-			unpin_vector_pages(pq->mm, pages, node->npages,
-					   pinned);
-			ret = -EFAULT;
-			goto bail;
-		}
-		kfree(node->pages);
-		node->rb.len = iovec->iov.iov_len;
-		node->pages = pages;
 		node->npages += pinned;
 		npages = node->npages;
-		atomic_add(pinned, &pq->n_locked);
 	}
 	iovec->pages = node->pages;
 	iovec->npages = npages;
@@ -1221,14 +1050,12 @@ retry:
 
 	ret = hfi1_mmu_rb_insert(req->pq->handler, &node->rb);
 	if (ret) {
-		atomic_sub(node->npages, &pq->n_locked);
 		iovec->node = NULL;
 		goto bail;
 	}
 	return 0;
 bail:
-	if (rb_node)
-		unpin_vector_pages(pq->mm, node->pages, 0, node->npages);
+	unpin_sdma_pages(node);
 	kfree(node);
 	return ret;
 }
@@ -1408,9 +1235,10 @@ static int set_txreq_header(struct user_sdma_request *req,
 		 * Set the KDETH.OFFSET and KDETH.OM based on size of
 		 * transfer.
 		 */
-		SDMA_DBG(req, "TID offset %ubytes %uunits om%u",
-			 req->tidoffset, req->tidoffset >> omfactor,
-			 omfactor != KDETH_OM_SMALL_SHIFT);
+		trace_hfi1_sdma_user_tid_info(
+			pq->dd, pq->ctxt, pq->subctxt, req->info.comp_idx,
+			req->tidoffset, req->tidoffset >> omfactor,
+			omfactor != KDETH_OM_SMALL_SHIFT);
 		KDETH_SET(hdr->kdeth.ver_tid_offset, OFFSET,
 			  req->tidoffset >> omfactor);
 		KDETH_SET(hdr->kdeth.ver_tid_offset, OM,
@@ -1423,21 +1251,22 @@ done:
 }
 
 static int set_txreq_header_ahg(struct user_sdma_request *req,
-				struct user_sdma_txreq *tx, u32 len)
+				struct user_sdma_txreq *tx, u32 datalen)
 {
+	u32 ahg[AHG_KDETH_ARRAY_SIZE];
 	int diff = 0;
 	u8 omfactor; /* KDETH.OM */
 	struct hfi1_user_sdma_pkt_q *pq = req->pq;
 	struct hfi1_pkt_header *hdr = &req->hdr;
 	u16 pbclen = le16_to_cpu(hdr->pbc[0]);
-	u32 val32, tidval = 0, lrhlen = get_lrh_len(*hdr, pad_len(len));
+	u32 val32, tidval = 0, lrhlen = get_lrh_len(*hdr, pad_len(datalen));
 
 	if (PBC2LRH(pbclen) != lrhlen) {
 		/* PBC.PbcLengthDWs */
-		AHG_HEADER_SET(req->ahg, diff, 0, 0, 12,
+		AHG_HEADER_SET(ahg, diff, 0, 0, 12,
 			       cpu_to_le16(LRH2PBC(lrhlen)));
 		/* LRH.PktLen (we need the full 16 bits due to byte swap) */
-		AHG_HEADER_SET(req->ahg, diff, 3, 0, 16,
+		AHG_HEADER_SET(ahg, diff, 3, 0, 16,
 			       cpu_to_be16(lrhlen >> 2));
 	}
 
@@ -1449,13 +1278,12 @@ static int set_txreq_header_ahg(struct user_sdma_request *req,
 		(HFI1_CAP_IS_KSET(EXTENDED_PSN) ? 0x7fffffff : 0xffffff);
 	if (unlikely(tx->flags & TXREQ_FLAGS_REQ_ACK))
 		val32 |= 1UL << 31;
-	AHG_HEADER_SET(req->ahg, diff, 6, 0, 16, cpu_to_be16(val32 >> 16));
-	AHG_HEADER_SET(req->ahg, diff, 6, 16, 16, cpu_to_be16(val32 & 0xffff));
+	AHG_HEADER_SET(ahg, diff, 6, 0, 16, cpu_to_be16(val32 >> 16));
+	AHG_HEADER_SET(ahg, diff, 6, 16, 16, cpu_to_be16(val32 & 0xffff));
 	/* KDETH.Offset */
-	AHG_HEADER_SET(req->ahg, diff, 15, 0, 16,
+	AHG_HEADER_SET(ahg, diff, 15, 0, 16,
 		       cpu_to_le16(req->koffset & 0xffff));
-	AHG_HEADER_SET(req->ahg, diff, 15, 16, 16,
-		       cpu_to_le16(req->koffset >> 16));
+	AHG_HEADER_SET(ahg, diff, 15, 16, 16, cpu_to_le16(req->koffset >> 16));
 	if (req_opcode(req->info.ctrl) == EXPECTED) {
 		__le16 val;
 
@@ -1473,9 +1301,8 @@ static int set_txreq_header_ahg(struct user_sdma_request *req,
 			 * we have to check again.
 			 */
 			if (++req->tididx > req->n_tids - 1 ||
-			    !req->tids[req->tididx]) {
+			    !req->tids[req->tididx])
 				return -EINVAL;
-			}
 			tidval = req->tids[req->tididx];
 		}
 		omfactor = ((EXP_TID_GET(tidval, LEN) *
@@ -1483,7 +1310,7 @@ static int set_txreq_header_ahg(struct user_sdma_request *req,
 				 KDETH_OM_MAX_SIZE) ? KDETH_OM_LARGE_SHIFT :
 				 KDETH_OM_SMALL_SHIFT;
 		/* KDETH.OM and KDETH.OFFSET (TID) */
-		AHG_HEADER_SET(req->ahg, diff, 7, 0, 16,
+		AHG_HEADER_SET(ahg, diff, 7, 0, 16,
 			       ((!!(omfactor - KDETH_OM_SMALL_SHIFT)) << 15 |
 				((req->tidoffset >> omfactor)
 				 & 0x7fff)));
@@ -1503,12 +1330,20 @@ static int set_txreq_header_ahg(struct user_sdma_request *req,
 					     AHG_KDETH_INTR_SHIFT));
 		}
 
-		AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val);
+		AHG_HEADER_SET(ahg, diff, 7, 16, 14, val);
 	}
+	if (diff < 0)
+		return diff;
 
 	trace_hfi1_sdma_user_header_ahg(pq->dd, pq->ctxt, pq->subctxt,
 					req->info.comp_idx, req->sde->this_idx,
-					req->ahg_idx, req->ahg, diff, tidval);
+					req->ahg_idx, ahg, diff, tidval);
+	sdma_txinit_ahg(&tx->txreq,
+			SDMA_TXREQ_F_USE_AHG,
+			datalen, req->ahg_idx, diff,
+			ahg, sizeof(req->hdr),
+			user_sdma_txreq_cb);
+
 	return diff;
 }
 
@@ -1537,7 +1372,7 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status)
 	if (status != SDMA_TXREQ_S_OK) {
 		SDMA_DBG(req, "SDMA completion with error %d",
 			 status);
-		set_bit(SDMA_REQ_HAS_ERROR, &req->flags);
+		WRITE_ONCE(req->has_error, 1);
 	}
 
 	req->seqcomp = tx->seqnum;
@@ -1556,8 +1391,8 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status)
 		if (status != SDMA_TXREQ_S_OK)
 			req->status = status;
 		if (req->seqcomp == (ACCESS_ONCE(req->seqsubmitted) - 1) &&
-		    (test_bit(SDMA_REQ_SEND_DONE, &req->flags) ||
-		     test_bit(SDMA_REQ_DONE_ERROR, &req->flags))) {
+		    (READ_ONCE(req->done) ||
+		     READ_ONCE(req->has_error))) {
 			user_sdma_free_request(req, false);
 			pq_update(pq);
 			set_comp_state(pq, cq, idx, ERROR, req->status);
@@ -1611,8 +1446,6 @@ static inline void set_comp_state(struct hfi1_user_sdma_pkt_q *pq,
 				  u16 idx, enum hfi1_sdma_comp_state state,
 				  int ret)
 {
-	hfi1_cdbg(SDMA, "[%u:%u:%u:%u] Setting completion status %u %d",
-		  pq->dd->unit, pq->ctxt, pq->subctxt, idx, state, ret);
 	if (state == ERROR)
 		cq->comps[idx].errcode = -ret;
 	smp_wmb(); /* make sure errcode is visible first */
@@ -1667,10 +1500,7 @@ static void sdma_rb_remove(void *arg, struct mmu_rb_node *mnode)
 	struct sdma_mmu_node *node =
 		container_of(mnode, struct sdma_mmu_node, rb);
 
-	atomic_sub(node->npages, &node->pq->n_locked);
-
-	unpin_vector_pages(node->pq->mm, node->pages, 0, node->npages);
-
+	unpin_sdma_pages(node);
 	kfree(node);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h
index e5b10aefe212..9b8bb5634c0d 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.h
+++ b/drivers/infiniband/hw/hfi1/user_sdma.h
@@ -53,11 +53,68 @@
 #include "iowait.h"
 #include "user_exp_rcv.h"
 
+/* The maximum number of Data io vectors per message/request */
+#define MAX_VECTORS_PER_REQ 8
+/*
+ * Maximum number of packet to send from each message/request
+ * before moving to the next one.
+ */
+#define MAX_PKTS_PER_QUEUE 16
+
+#define num_pages(x) (1 + ((((x) - 1) & PAGE_MASK) >> PAGE_SHIFT))
+
+#define req_opcode(x) \
+	(((x) >> HFI1_SDMA_REQ_OPCODE_SHIFT) & HFI1_SDMA_REQ_OPCODE_MASK)
+#define req_version(x) \
+	(((x) >> HFI1_SDMA_REQ_VERSION_SHIFT) & HFI1_SDMA_REQ_OPCODE_MASK)
+#define req_iovcnt(x) \
+	(((x) >> HFI1_SDMA_REQ_IOVCNT_SHIFT) & HFI1_SDMA_REQ_IOVCNT_MASK)
+
+/* Number of BTH.PSN bits used for sequence number in expected rcvs */
+#define BTH_SEQ_MASK 0x7ffull
+
+#define AHG_KDETH_INTR_SHIFT 12
+#define AHG_KDETH_SH_SHIFT   13
+#define AHG_KDETH_ARRAY_SIZE  9
+
+#define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4)
+#define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff)
+
+#define AHG_HEADER_SET(arr, idx, dw, bit, width, value)			\
+	do {								\
+		if ((idx) < ARRAY_SIZE((arr)))				\
+			(arr)[(idx++)] = sdma_build_ahg_descriptor(	\
+				(__force u16)(value), (dw), (bit),	\
+							(width));	\
+		else							\
+			return -ERANGE;					\
+	} while (0)
+
+/* Tx request flag bits */
+#define TXREQ_FLAGS_REQ_ACK   BIT(0)      /* Set the ACK bit in the header */
+#define TXREQ_FLAGS_REQ_DISABLE_SH BIT(1) /* Disable header suppression */
+
+#define SDMA_PKT_Q_INACTIVE BIT(0)
+#define SDMA_PKT_Q_ACTIVE   BIT(1)
+#define SDMA_PKT_Q_DEFERRED BIT(2)
+
+/*
+ * Maximum retry attempts to submit a TX request
+ * before putting the process to sleep.
+ */
+#define MAX_DEFER_RETRY_COUNT 1
+
+#define SDMA_IOWAIT_TIMEOUT 1000 /* in milliseconds */
+
+#define SDMA_DBG(req, fmt, ...)				     \
+	hfi1_cdbg(SDMA, "[%u:%u:%u:%u] " fmt, (req)->pq->dd->unit, \
+		 (req)->pq->ctxt, (req)->pq->subctxt, (req)->info.comp_idx, \
+		 ##__VA_ARGS__)
+
 extern uint extended_psn;
 
 struct hfi1_user_sdma_pkt_q {
-	struct list_head list;
-	unsigned ctxt;
+	u16 ctxt;
 	u16 subctxt;
 	u16 n_max_reqs;
 	atomic_t n_reqs;
@@ -80,9 +137,115 @@ struct hfi1_user_sdma_comp_q {
 	struct hfi1_sdma_comp_entry *comps;
 };
 
+struct sdma_mmu_node {
+	struct mmu_rb_node rb;
+	struct hfi1_user_sdma_pkt_q *pq;
+	atomic_t refcount;
+	struct page **pages;
+	unsigned int npages;
+};
+
+struct user_sdma_iovec {
+	struct list_head list;
+	struct iovec iov;
+	/* number of pages in this vector */
+	unsigned int npages;
+	/* array of pinned pages for this vector */
+	struct page **pages;
+	/*
+	 * offset into the virtual address space of the vector at
+	 * which we last left off.
+	 */
+	u64 offset;
+	struct sdma_mmu_node *node;
+};
+
+/* evict operation argument */
+struct evict_data {
+	u32 cleared;	/* count evicted so far */
+	u32 target;	/* target count to evict */
+};
+
+struct user_sdma_request {
+	/* This is the original header from user space */
+	struct hfi1_pkt_header hdr;
+
+	/* Read mostly fields */
+	struct hfi1_user_sdma_pkt_q *pq ____cacheline_aligned_in_smp;
+	struct hfi1_user_sdma_comp_q *cq;
+	/*
+	 * Pointer to the SDMA engine for this request.
+	 * Since different request could be on different VLs,
+	 * each request will need it's own engine pointer.
+	 */
+	struct sdma_engine *sde;
+	struct sdma_req_info info;
+	/* TID array values copied from the tid_iov vector */
+	u32 *tids;
+	/* total length of the data in the request */
+	u32 data_len;
+	/* number of elements copied to the tids array */
+	u16 n_tids;
+	/*
+	 * We copy the iovs for this request (based on
+	 * info.iovcnt). These are only the data vectors
+	 */
+	u8 data_iovs;
+	s8 ahg_idx;
+
+	/* Writeable fields shared with interrupt */
+	u64 seqcomp ____cacheline_aligned_in_smp;
+	u64 seqsubmitted;
+	/* status of the last txreq completed */
+	int status;
+
+	/* Send side fields */
+	struct list_head txps ____cacheline_aligned_in_smp;
+	u64 seqnum;
+	/*
+	 * KDETH.OFFSET (TID) field
+	 * The offset can cover multiple packets, depending on the
+	 * size of the TID entry.
+	 */
+	u32 tidoffset;
+	/*
+	 * KDETH.Offset (Eager) field
+	 * We need to remember the initial value so the headers
+	 * can be updated properly.
+	 */
+	u32 koffset;
+	u32 sent;
+	/* TID index copied from the tid_iov vector */
+	u16 tididx;
+	/* progress index moving along the iovs array */
+	u8 iov_idx;
+	u8 done;
+	u8 has_error;
+
+	struct user_sdma_iovec iovs[MAX_VECTORS_PER_REQ];
+} ____cacheline_aligned_in_smp;
+
+/*
+ * A single txreq could span up to 3 physical pages when the MTU
+ * is sufficiently large (> 4K). Each of the IOV pointers also
+ * needs it's own set of flags so the vector has been handled
+ * independently of each other.
+ */
+struct user_sdma_txreq {
+	/* Packet header for the txreq */
+	struct hfi1_pkt_header hdr;
+	struct sdma_txreq txreq;
+	struct list_head list;
+	struct user_sdma_request *req;
+	u16 flags;
+	unsigned int busycount;
+	u64 seqnum;
+};
+
 int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 				struct hfi1_filedata *fd);
-int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd);
+int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
+			       struct hfi1_ctxtdata *uctxt);
 int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 				   struct iovec *iovec, unsigned long dim,
 				   unsigned long *count);
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 2d19f9bb434d..e232f3c608b4 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -53,6 +53,7 @@
 #include <linux/rculist.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <rdma/opa_addr.h>
 
 #include "hfi.h"
 #include "common.h"
@@ -508,13 +509,14 @@ again:
 /*
  * Make sure the QP is ready and able to accept the given opcode.
  */
-static inline opcode_handler qp_ok(int opcode, struct hfi1_packet *packet)
+static inline opcode_handler qp_ok(struct hfi1_packet *packet)
 {
 	if (!(ib_rvt_state_ops[packet->qp->state] & RVT_PROCESS_RECV_OK))
 		return NULL;
-	if (((opcode & RVT_OPCODE_QP_MASK) == packet->qp->allowed_ops) ||
-	    (opcode == IB_OPCODE_CNP))
-		return opcode_handler_tbl[opcode];
+	if (((packet->opcode & RVT_OPCODE_QP_MASK) ==
+	     packet->qp->allowed_ops) ||
+	    (packet->opcode == IB_OPCODE_CNP))
+		return opcode_handler_tbl[packet->opcode];
 
 	return NULL;
 }
@@ -548,69 +550,54 @@ static u64 hfi1_fault_tx(struct rvt_qp *qp, u8 opcode, u64 pbc)
 	return pbc;
 }
 
-/**
- * hfi1_ib_rcv - process an incoming packet
- * @packet: data packet information
- *
- * This is called to process an incoming packet at interrupt level.
- *
- * Tlen is the length of the header + data + CRC in bytes.
- */
-void hfi1_ib_rcv(struct hfi1_packet *packet)
+static int hfi1_do_pkey_check(struct hfi1_packet *packet)
 {
 	struct hfi1_ctxtdata *rcd = packet->rcd;
-	struct ib_header *hdr = packet->hdr;
-	u32 tlen = packet->tlen;
+	struct hfi1_pportdata *ppd = rcd->ppd;
+	struct hfi1_16b_header *hdr = packet->hdr;
+	u16 pkey;
+
+	/* Pkey check needed only for bypass packets */
+	if (packet->etype != RHF_RCV_TYPE_BYPASS)
+		return 0;
+
+	/* Perform pkey check */
+	pkey = hfi1_16B_get_pkey(hdr);
+	return ingress_pkey_check(ppd, pkey, packet->sc,
+				  packet->qp->s_pkey_index,
+				  packet->slid, true);
+}
+
+static inline void hfi1_handle_packet(struct hfi1_packet *packet,
+				      bool is_mcast)
+{
+	u32 qp_num;
+	struct hfi1_ctxtdata *rcd = packet->rcd;
 	struct hfi1_pportdata *ppd = rcd->ppd;
 	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;
-	u32 qp_num;
-	int lnh;
-	u8 opcode;
-	u16 lid;
-
-	/* Check for GRH */
-	lnh = ib_get_lnh(hdr);
-	if (lnh == HFI1_LRH_BTH) {
-		packet->ohdr = &hdr->u.oth;
-	} else if (lnh == HFI1_LRH_GRH) {
-		u32 vtf;
-
-		packet->ohdr = &hdr->u.l.oth;
-		if (hdr->u.l.grh.next_hdr != IB_GRH_NEXT_HDR)
-			goto drop;
-		vtf = be32_to_cpu(hdr->u.l.grh.version_tclass_flow);
-		if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION)
-			goto drop;
-		packet->rcv_flags |= HFI1_HAS_GRH;
-	} else {
-		goto drop;
-	}
-
-	trace_input_ibhdr(rcd->dd, hdr);
 
-	opcode = ib_bth_get_opcode(packet->ohdr);
-	inc_opstats(tlen, &rcd->opstats->stats[opcode]);
+	inc_opstats(packet->tlen, &rcd->opstats->stats[packet->opcode]);
 
-	/* Get the destination QP number. */
-	qp_num = be32_to_cpu(packet->ohdr->bth[1]) & RVT_QPN_MASK;
-	lid = ib_get_dlid(hdr);
-	if (unlikely((lid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
-		     (lid != be16_to_cpu(IB_LID_PERMISSIVE)))) {
+	if (unlikely(is_mcast)) {
 		struct rvt_mcast *mcast;
 		struct rvt_mcast_qp *p;
 
-		if (lnh != HFI1_LRH_GRH)
+		if (!packet->grh)
 			goto drop;
-		mcast = rvt_mcast_find(&ibp->rvp, &hdr->u.l.grh.dgid, lid);
+		mcast = rvt_mcast_find(&ibp->rvp,
+				       &packet->grh->dgid,
+				       opa_get_lid(packet->dlid, 9B));
 		if (!mcast)
 			goto drop;
 		list_for_each_entry_rcu(p, &mcast->qp_list, list) {
 			packet->qp = p->qp;
+			if (hfi1_do_pkey_check(packet))
+				goto drop;
 			spin_lock_irqsave(&packet->qp->r_lock, flags);
-			packet_handler = qp_ok(opcode, packet);
+			packet_handler = qp_ok(packet);
 			if (likely(packet_handler))
 				packet_handler(packet);
 			else
@@ -624,19 +611,22 @@ void hfi1_ib_rcv(struct hfi1_packet *packet)
 		if (atomic_dec_return(&mcast->refcount) <= 1)
 			wake_up(&mcast->wait);
 	} else {
+		/* Get the destination QP number. */
+		qp_num = ib_bth_get_qpn(packet->ohdr);
 		rcu_read_lock();
 		packet->qp = rvt_lookup_qpn(rdi, &ibp->rvp, qp_num);
-		if (!packet->qp) {
-			rcu_read_unlock();
-			goto drop;
-		}
-		if (unlikely(hfi1_dbg_fault_opcode(packet->qp, opcode,
-						   true))) {
-			rcu_read_unlock();
-			goto drop;
-		}
+		if (!packet->qp)
+			goto unlock_drop;
+
+		if (hfi1_do_pkey_check(packet))
+			goto unlock_drop;
+
+		if (unlikely(hfi1_dbg_fault_opcode(packet->qp, packet->opcode,
+						   true)))
+			goto unlock_drop;
+
 		spin_lock_irqsave(&packet->qp->r_lock, flags);
-		packet_handler = qp_ok(opcode, packet);
+		packet_handler = qp_ok(packet);
 		if (likely(packet_handler))
 			packet_handler(packet);
 		else
@@ -645,11 +635,34 @@ void hfi1_ib_rcv(struct hfi1_packet *packet)
 		rcu_read_unlock();
 	}
 	return;
-
+unlock_drop:
+	rcu_read_unlock();
 drop:
 	ibp->rvp.n_pkt_drops++;
 }
 
+/**
+ * hfi1_ib_rcv - process an incoming packet
+ * @packet: data packet information
+ *
+ * This is called to process an incoming packet at interrupt level.
+ */
+void hfi1_ib_rcv(struct hfi1_packet *packet)
+{
+	struct hfi1_ctxtdata *rcd = packet->rcd;
+
+	trace_input_ibhdr(rcd->dd, packet, !!(rhf_dc_info(packet->rhf)));
+	hfi1_handle_packet(packet, hfi1_check_mcast(packet->dlid));
+}
+
+void hfi1_16B_rcv(struct hfi1_packet *packet)
+{
+	struct hfi1_ctxtdata *rcd = packet->rcd;
+
+	trace_input_ibhdr(rcd->dd, packet, false);
+	hfi1_handle_packet(packet, hfi1_check_mcast(packet->dlid));
+}
+
 /*
  * This is called from a timer to check for QPs
  * which need kernel memory in order to send a packet.
@@ -696,7 +709,7 @@ static void verbs_sdma_complete(
 	if (tx->wqe) {
 		hfi1_send_complete(qp, tx->wqe, IB_WC_SUCCESS);
 	} else if (qp->ibqp.qp_type == IB_QPT_RC) {
-		struct ib_header *hdr;
+		struct hfi1_opa_header *hdr;
 
 		hdr = &tx->phdr.hdr;
 		hfi1_rc_send_complete(qp, hdr);
@@ -799,12 +812,27 @@ static int build_verbs_tx_desc(
 	int ret = 0;
 	struct hfi1_sdma_header *phdr = &tx->phdr;
 	u16 hdrbytes = tx->hdr_dwords << 2;
+	u32 *hdr;
+	u8 extra_bytes = 0;
+	static char trail_buf[12]; /* CRC = 4, LT = 1, Pad = 0 to 7 bytes */
 
+	if (tx->phdr.hdr.hdr_type) {
+		/*
+		 * hdrbytes accounts for PBC. Need to subtract 8 bytes
+		 * before calculating padding.
+		 */
+		extra_bytes = hfi1_get_16b_padding(hdrbytes - 8, length) +
+			      (SIZE_OF_CRC << 2) + SIZE_OF_LT;
+		hdr = (u32 *)&phdr->hdr.opah;
+	} else {
+		hdr = (u32 *)&phdr->hdr.ibh;
+	}
 	if (!ahg_info->ahgcount) {
 		ret = sdma_txinit_ahg(
 			&tx->txreq,
 			ahg_info->tx_flags,
-			hdrbytes + length,
+			hdrbytes + length +
+			extra_bytes,
 			ahg_info->ahgidx,
 			0,
 			NULL,
@@ -834,8 +862,17 @@ static int build_verbs_tx_desc(
 			goto bail_txadd;
 	}
 	/* add the ulp payload - if any. tx->ss can be NULL for acks */
-	if (tx->ss)
+	if (tx->ss) {
 		ret = build_verbs_ulp_payload(sde, length, tx);
+		if (ret)
+			goto bail_txadd;
+	}
+
+	/* add icrc, lt byte, and padding to flit */
+	if (extra_bytes != 0)
+		ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq,
+					trail_buf, extra_bytes);
+
 bail_txadd:
 	return ret;
 }
@@ -847,26 +884,42 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	struct hfi1_ahg_info *ahg_info = priv->s_ahg;
 	u32 hdrwords = qp->s_hdrwords;
 	u32 len = ps->s_txreq->s_cur_size;
-	u32 plen = hdrwords + ((len + 3) >> 2) + 2; /* includes pbc */
+	u32 plen;
 	struct hfi1_ibdev *dev = ps->dev;
 	struct hfi1_pportdata *ppd = ps->ppd;
 	struct verbs_txreq *tx;
 	u8 sc5 = priv->s_sc;
-
 	int ret;
+	u32 dwords;
+	bool bypass = false;
+
+	if (ps->s_txreq->phdr.hdr.hdr_type) {
+		u8 extra_bytes = hfi1_get_16b_padding((hdrwords << 2), len);
+
+		dwords = (len + extra_bytes + (SIZE_OF_CRC << 2) +
+			  SIZE_OF_LT) >> 2;
+		bypass = true;
+	} else {
+		dwords = (len + 3) >> 2;
+	}
+	plen = hdrwords + dwords + 2;
 
 	tx = ps->s_txreq;
 	if (!sdma_txreq_built(&tx->txreq)) {
 		if (likely(pbc == 0)) {
 			u32 vl = sc_to_vlt(dd_from_ibdev(qp->ibqp.device), sc5);
-			u8 opcode = get_opcode(&tx->phdr.hdr);
 
 			/* No vl15 here */
-			/* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */
-			pbc |= (!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT;
+			/* set PBC_DC_INFO bit (aka SC[4]) in pbc */
+			if (ps->s_txreq->phdr.hdr.hdr_type)
+				pbc |= PBC_PACKET_BYPASS |
+				       PBC_INSERT_BYPASS_ICRC;
+			else
+				pbc |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
 
-			if (unlikely(hfi1_dbg_fault_opcode(qp, opcode, false)))
-				pbc = hfi1_fault_tx(qp, opcode, pbc);
+			if (unlikely(hfi1_dbg_fault_opcode(qp, ps->opcode,
+							   false)))
+				pbc = hfi1_fault_tx(qp, ps->opcode, pbc);
 			pbc = create_pbc(ppd,
 					 pbc,
 					 qp->srate_mbps,
@@ -878,14 +931,15 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		if (unlikely(ret))
 			goto bail_build;
 	}
-	ret =  sdma_send_txreq(tx->sde, &priv->s_iowait, &tx->txreq);
+	ret =  sdma_send_txreq(tx->sde, &priv->s_iowait, &tx->txreq,
+			       ps->pkts_sent);
 	if (unlikely(ret < 0)) {
 		if (ret == -ECOMM)
 			goto bail_ecomm;
 		return ret;
 	}
 	trace_sdma_output_ibhdr(dd_from_ibdev(qp->ibqp.device),
-				&ps->s_txreq->phdr.hdr);
+				&ps->s_txreq->phdr.hdr, ib_is_sc5(sc5));
 	return ret;
 
 bail_ecomm:
@@ -935,7 +989,8 @@ static int pio_wait(struct rvt_qp *qp,
 			dev->n_piodrain += !!(flag & RVT_S_WAIT_PIO_DRAIN);
 			qp->s_flags |= flag;
 			was_empty = list_empty(&sc->piowait);
-			list_add_tail(&priv->s_iowait.list, &sc->piowait);
+			iowait_queue(ps->pkts_sent, &priv->s_iowait,
+				     &sc->piowait);
 			priv->s_iowait.lock = &dev->iowait_lock;
 			trace_hfi1_qpsleep(qp, RVT_S_WAIT_PIO);
 			rvt_get_qp(qp);
@@ -967,10 +1022,10 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	u32 hdrwords = qp->s_hdrwords;
 	struct rvt_sge_state *ss = ps->s_txreq->ss;
 	u32 len = ps->s_txreq->s_cur_size;
-	u32 dwords = (len + 3) >> 2;
-	u32 plen = hdrwords + dwords + 2; /* includes pbc */
+	u32 dwords;
+	u32 plen;
 	struct hfi1_pportdata *ppd = ps->ppd;
-	u32 *hdr = (u32 *)&ps->s_txreq->phdr.hdr;
+	u32 *hdr;
 	u8 sc5;
 	unsigned long flags = 0;
 	struct send_context *sc;
@@ -978,6 +1033,23 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 	int wc_status = IB_WC_SUCCESS;
 	int ret = 0;
 	pio_release_cb cb = NULL;
+	u32 lrh0_16b;
+	bool bypass = false;
+	u8 extra_bytes = 0;
+
+	if (ps->s_txreq->phdr.hdr.hdr_type) {
+		u8 pad_size = hfi1_get_16b_padding((hdrwords << 2), len);
+
+		extra_bytes = pad_size + (SIZE_OF_CRC << 2) + SIZE_OF_LT;
+		dwords = (len + extra_bytes) >> 2;
+		hdr = (u32 *)&ps->s_txreq->phdr.hdr.opah;
+		lrh0_16b = ps->s_txreq->phdr.hdr.opah.lrh[0];
+		bypass = true;
+	} else {
+		dwords = (len + 3) >> 2;
+		hdr = (u32 *)&ps->s_txreq->phdr.hdr.ibh;
+	}
+	plen = hdrwords + dwords + 2;
 
 	/* only RC/UC use complete */
 	switch (qp->ibqp.qp_type) {
@@ -995,13 +1067,14 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 
 	if (likely(pbc == 0)) {
 		u8 vl = sc_to_vlt(dd_from_ibdev(qp->ibqp.device), sc5);
-		struct verbs_txreq *tx = ps->s_txreq;
-		u8 opcode = get_opcode(&tx->phdr.hdr);
 
-		/* set PBC_DC_INFO bit (aka SC[4]) in pbc_flags */
-		pbc |= (!!(sc5 & 0x10)) << PBC_DC_INFO_SHIFT;
-		if (unlikely(hfi1_dbg_fault_opcode(qp, opcode, false)))
-			pbc = hfi1_fault_tx(qp, opcode, pbc);
+		/* set PBC_DC_INFO bit (aka SC[4]) in pbc */
+		if (ps->s_txreq->phdr.hdr.hdr_type)
+			pbc |= PBC_PACKET_BYPASS | PBC_INSERT_BYPASS_ICRC;
+		else
+			pbc |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
+		if (unlikely(hfi1_dbg_fault_opcode(qp, ps->opcode, false)))
+			pbc = hfi1_fault_tx(qp, ps->opcode, pbc);
 		pbc = create_pbc(ppd, pbc, qp->srate_mbps, vl, plen);
 	}
 	if (cb)
@@ -1038,11 +1111,12 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		}
 	}
 
-	if (len == 0) {
+	if (dwords == 0) {
 		pio_copy(ppd->dd, pbuf, pbc, hdr, hdrwords);
 	} else {
+		seg_pio_copy_start(pbuf, pbc,
+				   hdr, hdrwords * 4);
 		if (ss) {
-			seg_pio_copy_start(pbuf, pbc, hdr, hdrwords * 4);
 			while (len) {
 				void *addr = ss->sge.vaddr;
 				u32 slen = ss->sge.length;
@@ -1053,12 +1127,24 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 				seg_pio_copy_mid(pbuf, addr, slen);
 				len -= slen;
 			}
-			seg_pio_copy_end(pbuf);
 		}
+		/*
+		 * Bypass packet will need to copy additional
+		 * bytes to accommodate for CRC and LT bytes
+		 */
+		if (extra_bytes) {
+			u8 *empty_buf;
+
+			empty_buf = kcalloc(extra_bytes, sizeof(u8),
+					    GFP_KERNEL);
+			seg_pio_copy_mid(pbuf, empty_buf, extra_bytes);
+			kfree(empty_buf);
+		}
+		seg_pio_copy_end(pbuf);
 	}
 
 	trace_pio_output_ibhdr(dd_from_ibdev(qp->ibqp.device),
-			       &ps->s_txreq->phdr.hdr);
+			       &ps->s_txreq->phdr.hdr, ib_is_sc5(sc5));
 
 pio_bail:
 	if (qp->s_wqe) {
@@ -1104,10 +1190,10 @@ static inline int egress_pkey_matches_entry(u16 pkey, u16 ent)
 
 /**
  * egress_pkey_check - check P_KEY of a packet
- * @ppd:    Physical IB port data
- * @lrh: Local route header
- * @bth: Base transport header
- * @sc5:    SC for packet
+ * @ppd:  Physical IB port data
+ * @slid: SLID for packet
+ * @bkey: PKEY for header
+ * @sc5:  SC for packet
  * @s_pkey_index: It will be used for look up optimization for kernel contexts
  * only. If it is negative value, then it means user contexts is calling this
  * function.
@@ -1116,19 +1202,16 @@ static inline int egress_pkey_matches_entry(u16 pkey, u16 ent)
  *
  * Return: 0 on success, otherwise, 1
  */
-int egress_pkey_check(struct hfi1_pportdata *ppd, __be16 *lrh, __be32 *bth,
+int egress_pkey_check(struct hfi1_pportdata *ppd, u32 slid, u16 pkey,
 		      u8 sc5, int8_t s_pkey_index)
 {
 	struct hfi1_devdata *dd;
 	int i;
-	u16 pkey;
 	int is_user_ctxt_mechanism = (s_pkey_index < 0);
 
 	if (!(ppd->part_enforce & HFI1_PART_ENFORCE_OUT))
 		return 0;
 
-	pkey = (u16)be32_to_cpu(bth[0]);
-
 	/* If SC15, pkey[0:14] must be 0x7fff */
 	if ((sc5 == 0xf) && ((pkey & PKEY_LOW_15_MASK) != PKEY_LOW_15_MASK))
 		goto bad;
@@ -1161,8 +1244,6 @@ bad:
 		dd = ppd->dd;
 		if (!(dd->err_info_xmit_constraint.status &
 		      OPA_EI_STATUS_SMASK)) {
-			u16 slid = be16_to_cpu(lrh[3]);
-
 			dd->err_info_xmit_constraint.status |=
 				OPA_EI_STATUS_SMASK;
 			dd->err_info_xmit_constraint.slid = slid;
@@ -1179,11 +1260,11 @@ bad:
  * and size
  */
 static inline send_routine get_send_routine(struct rvt_qp *qp,
-					    struct verbs_txreq *tx)
+					    struct hfi1_pkt_state *ps)
 {
 	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
 	struct hfi1_qp_priv *priv = qp->priv;
-	struct ib_header *h = &tx->phdr.hdr;
+	struct verbs_txreq *tx = ps->s_txreq;
 
 	if (unlikely(!(dd->flags & HFI1_HAS_SEND_DMA)))
 		return dd->process_pio_send;
@@ -1195,11 +1276,9 @@ static inline send_routine get_send_routine(struct rvt_qp *qp,
 		break;
 	case IB_QPT_UC:
 	case IB_QPT_RC: {
-		u8 op = get_opcode(h);
-
 		if (piothreshold &&
 		    tx->s_cur_size <= min(piothreshold, qp->pmtu) &&
-		    (BIT(op & OPMASK) & pio_opmask[op >> 5]) &&
+		    (BIT(ps->opcode & OPMASK) & pio_opmask[ps->opcode >> 5]) &&
 		    iowait_sdma_pending(&priv->s_iowait) == 0 &&
 		    !sdma_txreq_built(&tx->txreq))
 			return dd->process_pio_send;
@@ -1224,25 +1303,38 @@ int hfi1_verbs_send(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
 	struct hfi1_qp_priv *priv = qp->priv;
 	struct ib_other_headers *ohdr;
-	struct ib_header *hdr;
 	send_routine sr;
 	int ret;
-	u8 lnh;
+	u16 pkey;
+	u32 slid;
 
-	hdr = &ps->s_txreq->phdr.hdr;
 	/* locate the pkey within the headers */
-	lnh = ib_get_lnh(hdr);
-	if (lnh == HFI1_LRH_GRH)
-		ohdr = &hdr->u.l.oth;
-	else
-		ohdr = &hdr->u.oth;
-
-	sr = get_send_routine(qp, ps->s_txreq);
-	ret = egress_pkey_check(dd->pport,
-				hdr->lrh,
-				ohdr->bth,
-				priv->s_sc,
-				qp->s_pkey_index);
+	if (ps->s_txreq->phdr.hdr.hdr_type) {
+		struct hfi1_16b_header *hdr = &ps->s_txreq->phdr.hdr.opah;
+		u8 l4 = hfi1_16B_get_l4(hdr);
+
+		if (l4 == OPA_16B_L4_IB_GLOBAL)
+			ohdr = &hdr->u.l.oth;
+		else
+			ohdr = &hdr->u.oth;
+		slid = hfi1_16B_get_slid(hdr);
+		pkey = hfi1_16B_get_pkey(hdr);
+	} else {
+		struct ib_header *hdr = &ps->s_txreq->phdr.hdr.ibh;
+		u8 lnh = ib_get_lnh(hdr);
+
+		if (lnh == HFI1_LRH_GRH)
+			ohdr = &hdr->u.l.oth;
+		else
+			ohdr = &hdr->u.oth;
+		slid = ib_get_slid(hdr);
+		pkey = ib_bth_get_pkey(ohdr);
+	}
+
+	ps->opcode = ib_bth_get_opcode(ohdr);
+	sr = get_send_routine(qp, ps);
+	ret = egress_pkey_check(dd->pport, slid, pkey,
+				priv->s_sc, qp->s_pkey_index);
 	if (unlikely(ret)) {
 		/*
 		 * The value we are returning here does not get propagated to
@@ -1361,14 +1453,14 @@ static int query_port(struct rvt_dev_info *rdi, u8 port_num,
 	struct hfi1_ibdev *verbs_dev = dev_from_rdi(rdi);
 	struct hfi1_devdata *dd = dd_from_dev(verbs_dev);
 	struct hfi1_pportdata *ppd = &dd->pport[port_num - 1];
-	u16 lid = ppd->lid;
+	u32 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 */
 	props->state = driver_lstate(ppd);
-	props->phys_state = hfi1_ibphys_portstate(ppd);
+	props->phys_state = driver_pstate(ppd);
 	props->gid_tbl_len = HFI1_GUIDS_PER_PORT;
 	props->active_width = (u8)opa_width_to_ib(ppd->link_width_active);
 	/* see rate_show() in ib core/sysfs.c */
@@ -1388,6 +1480,15 @@ static int query_port(struct rvt_dev_info *rdi, u8 port_num,
 	props->active_mtu = !valid_ib_mtu(ppd->ibmtu) ? props->max_mtu :
 		mtu_to_enum(ppd->ibmtu, IB_MTU_2048);
 
+	/*
+	 * sm_lid of 0xFFFF needs special handling so that it can
+	 * be differentiated from a permissve LID of 0xFFFF.
+	 * We set the grh_required flag here so the SA can program
+	 * the DGID in the address handle appropriately
+	 */
+	if (props->sm_lid == be16_to_cpu(IB_LID_PERMISSIVE))
+		props->grh_required = true;
+
 	return 0;
 }
 
@@ -1473,6 +1574,10 @@ static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr)
 	struct hfi1_devdata *dd;
 	u8 sc5;
 
+	if (hfi1_check_mcast(rdma_ah_get_dlid(ah_attr)) &&
+	    !(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH))
+		return -EINVAL;
+
 	/* test the mapping for validity */
 	ibp = to_iport(ibdev, rdma_ah_get_port_num(ah_attr));
 	ppd = ppd_from_ibp(ibp);
@@ -1491,6 +1596,7 @@ static void hfi1_notify_new_ah(struct ib_device *ibdev,
 	struct hfi1_pportdata *ppd;
 	struct hfi1_devdata *dd;
 	u8 sc5;
+	struct rdma_ah_attr *attr = &ah->attr;
 
 	/*
 	 * Do not trust reading anything from rvt_ah at this point as it is not
@@ -1500,33 +1606,14 @@ static void hfi1_notify_new_ah(struct ib_device *ibdev,
 	ibp = to_iport(ibdev, rdma_ah_get_port_num(ah_attr));
 	ppd = ppd_from_ibp(ibp);
 	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&ah->attr)];
+	hfi1_update_ah_attr(ibdev, attr);
+	hfi1_make_opa_lid(attr);
 	dd = dd_from_ppd(ppd);
 	ah->vl = sc_to_vlt(dd, sc5);
 	if (ah->vl < num_vls || ah->vl == 15)
 		ah->log_pmtu = ilog2(dd->vld[ah->vl].mtu);
 }
 
-struct ib_ah *hfi1_create_qp0_ah(struct hfi1_ibport *ibp, u16 dlid)
-{
-	struct rdma_ah_attr attr;
-	struct ib_ah *ah = ERR_PTR(-EINVAL);
-	struct rvt_qp *qp0;
-	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	struct hfi1_devdata *dd = dd_from_ppd(ppd);
-	u8 port_num = ppd->port;
-
-	memset(&attr, 0, sizeof(attr));
-	attr.type = rdma_ah_find_type(&dd->verbs_dev.rdi.ibdev, port_num);
-	rdma_ah_set_dlid(&attr, dlid);
-	rdma_ah_set_port_num(&attr, ppd_from_ibp(ibp)->port);
-	rcu_read_lock();
-	qp0 = rcu_dereference(ibp->rvp.qp[0]);
-	if (qp0)
-		ah = rdma_create_ah(qp0->ibqp.pd, &attr);
-	rcu_read_unlock();
-	return ah;
-}
-
 /**
  * hfi1_get_npkeys - return the size of the PKEY table for context 0
  * @dd: the hfi1_ib device
@@ -1547,13 +1634,22 @@ static void init_ibport(struct hfi1_pportdata *ppd)
 		ibp->sc_to_sl[i] = i;
 	}
 
+	for (i = 0; i < RVT_MAX_TRAP_LISTS ; i++)
+		INIT_LIST_HEAD(&ibp->rvp.trap_lists[i].list);
+	setup_timer(&ibp->rvp.trap_timer, hfi1_handle_trap_timer,
+		    (unsigned long)ibp);
+
 	spin_lock_init(&ibp->rvp.lock);
 	/* Set the prefix to the default value (see ch. 4.1.1) */
 	ibp->rvp.gid_prefix = IB_DEFAULT_GID_PREFIX;
 	ibp->rvp.sm_lid = 0;
-	/* Below should only set bits defined in OPA PortInfo.CapabilityMask */
+	/*
+	 * Below should only set bits defined in OPA PortInfo.CapabilityMask
+	 * and PortInfo.CapabilityMask3
+	 */
 	ibp->rvp.port_cap_flags = IB_PORT_AUTO_MIGR_SUP |
 		IB_PORT_CAP_MASK_NOTICE_SUP;
+	ibp->rvp.port_cap3_flags = OPA_CAP_MASK3_IsSharedSpaceSupported;
 	ibp->rvp.pma_counter_select[0] = IB_PMA_PORT_XMIT_DATA;
 	ibp->rvp.pma_counter_select[1] = IB_PMA_PORT_RCV_DATA;
 	ibp->rvp.pma_counter_select[2] = IB_PMA_PORT_XMIT_PKTS;
@@ -1564,14 +1660,13 @@ static void init_ibport(struct hfi1_pportdata *ppd)
 	RCU_INIT_POINTER(ibp->rvp.qp[1], NULL);
 }
 
-static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str,
-				size_t str_len)
+static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
 	struct hfi1_ibdev *dev = dev_from_rdi(rdi);
 	u32 ver = dd_from_dev(dev)->dc8051_ver;
 
-	snprintf(str, str_len, "%u.%u.%u", dc8051_ver_maj(ver),
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u", dc8051_ver_maj(ver),
 		 dc8051_ver_min(ver), dc8051_ver_patch(ver));
 }
 
@@ -1816,7 +1911,8 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	dd->verbs_dev.rdi.dparms.psn_mask = PSN_MASK;
 	dd->verbs_dev.rdi.dparms.psn_shift = PSN_SHIFT;
 	dd->verbs_dev.rdi.dparms.psn_modify_mask = PSN_MODIFY_MASK;
-	dd->verbs_dev.rdi.dparms.core_cap_flags = RDMA_CORE_PORT_INTEL_OPA;
+	dd->verbs_dev.rdi.dparms.core_cap_flags = RDMA_CORE_PORT_INTEL_OPA |
+						RDMA_CORE_CAP_OPA_AH;
 	dd->verbs_dev.rdi.dparms.max_mad_size = OPA_MGMT_MAD_SIZE;
 
 	dd->verbs_dev.rdi.driver_f.qp_priv_alloc = qp_priv_alloc;
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index cd635d0c1d3b..87d1285a3340 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -95,6 +95,7 @@ struct hfi1_packet;
 #define HFI1_VENDOR_IPG		cpu_to_be16(0xFFA0)
 
 #define IB_DEFAULT_GID_PREFIX	cpu_to_be64(0xfe80000000000000ULL)
+#define OPA_BTH_MIG_REQ		BIT(31)
 
 #define RC_OP(x) IB_OPCODE_RC_##x
 #define UC_OP(x) IB_OPCODE_UC_##x
@@ -104,6 +105,25 @@ enum {
 	HFI1_HAS_GRH = (1 << 0),
 };
 
+struct hfi1_16b_header {
+	u32 lrh[4];
+	union {
+		struct {
+			struct ib_grh grh;
+			struct ib_other_headers oth;
+		} l;
+		struct ib_other_headers oth;
+	} u;
+} __packed;
+
+struct hfi1_opa_header {
+	union {
+		struct ib_header ibh; /* 9B header */
+		struct hfi1_16b_header opah; /* 16B header */
+	};
+	u8 hdr_type; /* 9B or 16B */
+} __packed;
+
 struct hfi1_ahg_info {
 	u32 ahgdesc[2];
 	u16 tx_flags;
@@ -113,7 +133,7 @@ struct hfi1_ahg_info {
 
 struct hfi1_sdma_header {
 	__le64 pbc;
-	struct ib_header hdr;
+	struct hfi1_opa_header hdr;
 } __packed;
 
 /*
@@ -127,6 +147,7 @@ struct hfi1_qp_priv {
 	u8 s_sc;		                  /* SC[0..4] for next packet */
 	struct iowait s_iowait;
 	struct rvt_qp *owner;
+	u8 hdr_type; /* 9B or 16B */
 };
 
 /*
@@ -142,7 +163,9 @@ struct hfi1_pkt_state {
 	unsigned long timeout;
 	unsigned long timeout_int;
 	int cpu;
+	u8 opcode;
 	bool in_thread;
+	bool pkts_sent;
 };
 
 #define HFI1_PSN_CREDIT  16
@@ -236,8 +259,8 @@ static inline int hfi1_send_ok(struct rvt_qp *qp)
 /*
  * This must be called with s_lock held.
  */
-void hfi1_bad_pqkey(struct hfi1_ibport *ibp, __be16 trap_num, u32 key, u32 sl,
-		    u32 qp1, u32 qp2, u16 lid1, u16 lid2);
+void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl,
+		   u32 qp1, u32 qp2, u32 lid1, u32 lid2);
 void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num);
 void hfi1_sys_guid_chg(struct hfi1_ibport *ibp);
 void hfi1_node_desc_chg(struct hfi1_ibport *ibp);
@@ -257,13 +280,8 @@ int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
  * necessarily be at least one bit less than
  * the container holding the PSN.
  */
-#ifndef CONFIG_HFI1_VERBS_31BIT_PSN
-#define PSN_MASK 0xFFFFFF
-#define PSN_SHIFT 8
-#else
 #define PSN_MASK 0x7FFFFFFF
 #define PSN_SHIFT 1
-#endif
 #define PSN_MODIFY_MASK 0xFFFFFF
 
 /*
@@ -307,15 +325,12 @@ void hfi1_rc_rcv(struct hfi1_packet *packet);
 
 void hfi1_rc_hdrerr(
 	struct hfi1_ctxtdata *rcd,
-	struct ib_header *hdr,
-	u32 rcv_flags,
+	struct hfi1_packet *packet,
 	struct rvt_qp *qp);
 
 u8 ah_to_sc(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr);
 
-struct ib_ah *hfi1_create_qp0_ah(struct hfi1_ibport *ibp, u16 dlid);
-
-void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr);
+void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah);
 
 void hfi1_ud_rcv(struct hfi1_packet *packet);
 
@@ -336,18 +351,7 @@ int hfi1_check_send_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe);
 extern const u32 rc_only_opcode;
 extern const u32 uc_only_opcode;
 
-static inline u8 get_opcode(struct ib_header *h)
-{
-	u16 lnh = be16_to_cpu(h->lrh[0]) & 3;
-
-	if (lnh == IB_LNH_IBA_LOCAL)
-		return be32_to_cpu(h->u.oth.bth[0]) >> 24;
-	else
-		return be32_to_cpu(h->u.l.oth.bth[0]) >> 24;
-}
-
-int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct ib_header *hdr,
-		       int has_grh, struct rvt_qp *qp, u32 bth0);
+int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet);
 
 u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
 		  const struct ib_global_route *grh, u32 hwords, u32 nwords);
@@ -365,7 +369,8 @@ void hfi1_do_send(struct rvt_qp *qp, bool in_thread);
 void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 			enum ib_wc_status status);
 
-void hfi1_send_rc_ack(struct hfi1_ctxtdata *, struct rvt_qp *qp, int is_fecn);
+void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
+		      bool is_fecn);
 
 int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps);
 
@@ -379,6 +384,8 @@ void hfi1_unregister_ib_device(struct hfi1_devdata *);
 
 void hfi1_ib_rcv(struct hfi1_packet *packet);
 
+void hfi1_16B_rcv(struct hfi1_packet *packet);
+
 unsigned hfi1_get_npkeys(struct hfi1_devdata *);
 
 int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c
index 5d23172c470f..873e48ea923f 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.c
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 Intel Corporation.
+ * Copyright(c) 2016 - 2017 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.
@@ -119,13 +119,6 @@ out:
 	return tx;
 }
 
-static void verbs_txreq_kmem_cache_ctor(void *obj)
-{
-	struct verbs_txreq *tx = (struct verbs_txreq *)obj;
-
-	memset(tx, 0, sizeof(*tx));
-}
-
 int verbs_txreq_init(struct hfi1_ibdev *dev)
 {
 	char buf[TXREQ_LEN];
@@ -135,7 +128,7 @@ int verbs_txreq_init(struct hfi1_ibdev *dev)
 	dev->verbs_txreq_cache = kmem_cache_create(buf,
 						   sizeof(struct verbs_txreq),
 						   0, SLAB_HWCACHE_ALIGN,
-						   verbs_txreq_kmem_cache_ctor);
+						   NULL);
 	if (!dev->verbs_txreq_cache)
 		return -ENOMEM;
 	return 0;
diff --git a/drivers/infiniband/hw/hfi1/vnic.h b/drivers/infiniband/hw/hfi1/vnic.h
index 4a621cde4abb..5ae781514e32 100644
--- a/drivers/infiniband/hw/hfi1/vnic.h
+++ b/drivers/infiniband/hw/hfi1/vnic.h
@@ -54,21 +54,6 @@
 #define HFI1_VNIC_MAX_TXQ     16
 #define HFI1_VNIC_MAX_PAD     12
 
-/* L2 header definitions */
-#define HFI1_L2_TYPE_OFFSET     0x7
-#define HFI1_L2_TYPE_SHFT       0x5
-#define HFI1_L2_TYPE_MASK       0x3
-
-#define HFI1_GET_L2_TYPE(hdr)                                            \
-	((*((u8 *)(hdr) + HFI1_L2_TYPE_OFFSET) >> HFI1_L2_TYPE_SHFT) &   \
-	 HFI1_L2_TYPE_MASK)
-
-/* L4 type definitions */
-#define HFI1_L4_TYPE_OFFSET 8
-
-#define HFI1_GET_L4_TYPE(data)   \
-	(*((u8 *)(data) + HFI1_L4_TYPE_OFFSET))
-
 /* L4 header definitions */
 #define HFI1_VNIC_L4_HDR_OFFSET  OPA_VNIC_L2_HDR_LEN
 
@@ -103,6 +88,7 @@ struct hfi1_vnic_sdma {
 	struct sdma_txreq stx;
 	unsigned int state;
 	u8 q_idx;
+	bool pkts_sent;
 };
 
 /**
diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index 339f0cdd56d6..f419cbb05928 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -95,7 +95,7 @@ static int setup_vnic_ctxt(struct hfi1_devdata *dd, struct hfi1_ctxtdata *uctxt)
 	if (HFI1_CAP_KGET_MASK(uctxt->flags, DMA_RTAIL))
 		rcvctrl_ops |= HFI1_RCVCTRL_TAILUPD_ENB;
 
-	hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt->ctxt);
+	hfi1_rcvctrl(uctxt->dd, rcvctrl_ops, uctxt);
 
 	uctxt->is_vnic = true;
 done:
@@ -106,22 +106,13 @@ static int allocate_vnic_ctxt(struct hfi1_devdata *dd,
 			      struct hfi1_ctxtdata **vnic_ctxt)
 {
 	struct hfi1_ctxtdata *uctxt;
-	unsigned int ctxt;
 	int ret;
 
 	if (dd->flags & HFI1_FROZEN)
 		return -EIO;
 
-	for (ctxt = dd->first_dyn_alloc_ctxt;
-	     ctxt < dd->num_rcv_contexts; ctxt++)
-		if (!dd->rcd[ctxt])
-			break;
-
-	if (ctxt == dd->num_rcv_contexts)
-		return -EBUSY;
-
-	uctxt = hfi1_create_ctxtdata(dd->pport, ctxt, dd->node);
-	if (!uctxt) {
+	ret = hfi1_create_ctxtdata(dd->pport, dd->node, &uctxt);
+	if (ret < 0) {
 		dd_dev_err(dd, "Unable to create ctxtdata, failing open\n");
 		return -ENOMEM;
 	}
@@ -155,12 +146,7 @@ static int allocate_vnic_ctxt(struct hfi1_devdata *dd,
 
 	return ret;
 bail:
-	/*
-	 * hfi1_free_ctxtdata() also releases send_context
-	 * structure if uctxt->sc is not null
-	 */
-	dd->rcd[uctxt->ctxt] = NULL;
-	hfi1_free_ctxtdata(dd, uctxt);
+	hfi1_free_ctxt(uctxt);
 	dd_dev_dbg(dd, "vnic allocation failed. rc %d\n", ret);
 	return ret;
 }
@@ -168,15 +154,12 @@ bail:
 static void deallocate_vnic_ctxt(struct hfi1_devdata *dd,
 				 struct hfi1_ctxtdata *uctxt)
 {
-	unsigned long flags;
-
 	dd_dev_dbg(dd, "closing vnic context %d\n", uctxt->ctxt);
 	flush_wc();
 
 	if (dd->num_msix_entries)
 		hfi1_reset_vnic_msix_info(uctxt);
 
-	spin_lock_irqsave(&dd->uctxt_lock, flags);
 	/*
 	 * Disable receive context and interrupt available, reset all
 	 * RcvCtxtCtrl bits to default values.
@@ -186,7 +169,7 @@ static void deallocate_vnic_ctxt(struct hfi1_devdata *dd,
 		     HFI1_RCVCTRL_INTRAVAIL_DIS |
 		     HFI1_RCVCTRL_ONE_PKT_EGR_DIS |
 		     HFI1_RCVCTRL_NO_RHQ_DROP_DIS |
-		     HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt->ctxt);
+		     HFI1_RCVCTRL_NO_EGR_DROP_DIS, uctxt);
 	/*
 	 * VNIC contexts are allocated from user context pool.
 	 * Release them back to user context pool.
@@ -199,16 +182,15 @@ static void deallocate_vnic_ctxt(struct hfi1_devdata *dd,
 	sc_disable(uctxt->sc);
 
 	dd->send_contexts[uctxt->sc->sw_index].type = SC_USER;
-	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
 
-	dd->rcd[uctxt->ctxt] = NULL;
 	uctxt->event_flags = 0;
 
 	hfi1_clear_tids(uctxt);
 	hfi1_clear_ctxt_pkey(dd, uctxt);
 
 	hfi1_stats.sps_ctxts--;
-	hfi1_free_ctxtdata(dd, uctxt);
+
+	hfi1_free_ctxt(uctxt);
 }
 
 void hfi1_vnic_setup(struct hfi1_devdata *dd)
@@ -582,8 +564,8 @@ void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet)
 	int l4_type, vesw_id = -1;
 	u8 q_idx;
 
-	l4_type = HFI1_GET_L4_TYPE(packet->ebuf);
-	if (likely(l4_type == OPA_VNIC_L4_ETHR)) {
+	l4_type = hfi1_16B_get_l4(packet->ebuf);
+	if (likely(l4_type == OPA_16B_L4_ETHR)) {
 		vesw_id = HFI1_VNIC_GET_VESWID(packet->ebuf);
 		vinfo = idr_find(&dd->vnic.vesw_idr, vesw_id);
 
@@ -751,6 +733,7 @@ static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo)
 		rc = hfi1_vnic_allot_ctxt(dd, &dd->vnic.ctxt[i]);
 		if (rc)
 			break;
+		hfi1_rcd_get(dd->vnic.ctxt[i]);
 		dd->vnic.ctxt[i]->vnic_q_idx = i;
 	}
 
@@ -762,6 +745,7 @@ static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo)
 		 */
 		while (i-- > dd->vnic.num_ctxt) {
 			deallocate_vnic_ctxt(dd, dd->vnic.ctxt[i]);
+			hfi1_rcd_put(dd->vnic.ctxt[i]);
 			dd->vnic.ctxt[i] = NULL;
 		}
 		goto alloc_fail;
@@ -791,6 +775,7 @@ static void hfi1_vnic_deinit(struct hfi1_vnic_vport_info *vinfo)
 	if (--dd->vnic.num_vports == 0) {
 		for (i = 0; i < dd->vnic.num_ctxt; i++) {
 			deallocate_vnic_ctxt(dd, dd->vnic.ctxt[i]);
+			hfi1_rcd_put(dd->vnic.ctxt[i]);
 			dd->vnic.ctxt[i] = NULL;
 		}
 		hfi1_deinit_vnic_rsm(dd);
diff --git a/drivers/infiniband/hw/hfi1/vnic_sdma.c b/drivers/infiniband/hw/hfi1/vnic_sdma.c
index 51a817d3aa14..c3c96c5869ed 100644
--- a/drivers/infiniband/hw/hfi1/vnic_sdma.c
+++ b/drivers/infiniband/hw/hfi1/vnic_sdma.c
@@ -198,11 +198,16 @@ int hfi1_vnic_send_dma(struct hfi1_devdata *dd, u8 q_idx,
 		goto free_desc;
 	tx->retry_count = 0;
 
-	ret = sdma_send_txreq(sde, &vnic_sdma->wait, &tx->txreq);
+	ret = sdma_send_txreq(sde, &vnic_sdma->wait, &tx->txreq,
+			      vnic_sdma->pkts_sent);
 	/* When -ECOMM, sdma callback will be called with ABORT status */
 	if (unlikely(ret && unlikely(ret != -ECOMM)))
 		goto free_desc;
 
+	if (!ret) {
+		vnic_sdma->pkts_sent = true;
+		iowait_starve_clear(vnic_sdma->pkts_sent, &vnic_sdma->wait);
+	}
 	return ret;
 
 free_desc:
@@ -211,6 +216,8 @@ free_desc:
 tx_err:
 	if (ret != -EBUSY)
 		dev_kfree_skb_any(skb);
+	else
+		vnic_sdma->pkts_sent = false;
 	return ret;
 }
 
@@ -225,7 +232,8 @@ tx_err:
 static int hfi1_vnic_sdma_sleep(struct sdma_engine *sde,
 				struct iowait *wait,
 				struct sdma_txreq *txreq,
-				unsigned int seq)
+				uint seq,
+				bool pkts_sent)
 {
 	struct hfi1_vnic_sdma *vnic_sdma =
 		container_of(wait, struct hfi1_vnic_sdma, wait);
@@ -239,7 +247,7 @@ static int hfi1_vnic_sdma_sleep(struct sdma_engine *sde,
 	vnic_sdma->state = HFI1_VNIC_SDMA_Q_DEFERRED;
 	write_seqlock(&dev->iowait_lock);
 	if (list_empty(&vnic_sdma->wait.list))
-		list_add_tail(&vnic_sdma->wait.list, &sde->dmawait);
+		iowait_queue(pkts_sent, wait, &sde->dmawait);
 	write_sequnlock(&dev->iowait_lock);
 	return -EBUSY;
 }
@@ -295,22 +303,15 @@ void hfi1_vnic_sdma_init(struct hfi1_vnic_vport_info *vinfo)
 	}
 }
 
-static void hfi1_vnic_txreq_kmem_cache_ctor(void *obj)
-{
-	struct vnic_txreq *tx = (struct vnic_txreq *)obj;
-
-	memset(tx, 0, sizeof(*tx));
-}
-
 int hfi1_vnic_txreq_init(struct hfi1_devdata *dd)
 {
 	char buf[HFI1_VNIC_TXREQ_NAME_LEN];
 
 	snprintf(buf, sizeof(buf), "hfi1_%u_vnic_txreq_cache", dd->unit);
 	dd->vnic.txreq_cache = kmem_cache_create(buf,
-					  sizeof(struct vnic_txreq),
-					  0, SLAB_HWCACHE_ALIGN,
-					  hfi1_vnic_txreq_kmem_cache_ctor);
+						 sizeof(struct vnic_txreq),
+						 0, SLAB_HWCACHE_ALIGN,
+						 NULL);
 	if (!dd->vnic.txreq_cache)
 		return -ENOMEM;
 	return 0;
diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig
index e1a6e055cd60..61c93bbd230d 100644
--- a/drivers/infiniband/hw/hns/Kconfig
+++ b/drivers/infiniband/hw/hns/Kconfig
@@ -1,7 +1,7 @@
 config INFINIBAND_HNS
 	tristate "HNS RoCE Driver"
 	depends on NET_VENDOR_HISILICON
-	depends on ARM64 && HNS && HNS_DSAF && HNS_ENET
+	depends on (ARM64 || (COMPILE_TEST && 64BIT)) && HNS && HNS_DSAF && HNS_ENET
 	---help---
 	  This is a RoCE/RDMA driver for the Hisilicon RoCE engine. The engine
 	  is used in Hisilicon Hi1610 and more further ICT SoC.
diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
index f78a733a63ec..d545302b8ef8 100644
--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
+++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
@@ -64,8 +64,10 @@ struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd,
 	} else {
 		u8 *dmac = rdma_ah_retrieve_dmac(ah_attr);
 
-		if (!dmac)
+		if (!dmac) {
+			kfree(ah);
 			return ERR_PTR(-EINVAL);
+		}
 		memcpy(ah->av.mac, dmac, ETH_ALEN);
 	}
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index 605962f2828c..e1b433cdd5e2 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/platform_device.h>
+#include <linux/vmalloc.h>
 #include "hns_roce_device.h"
 
 int hns_roce_bitmap_alloc(struct hns_roce_bitmap *bitmap, unsigned long *obj)
diff --git a/drivers/infiniband/hw/hns/hns_roce_eq.c b/drivers/infiniband/hw/hns/hns_roce_eq.c
index 50f864935a0e..b0f43735de1a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_eq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_eq.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/platform_device.h>
+#include <linux/interrupt.h>
 #include "hns_roce_common.h"
 #include "hns_roce_device.h"
 #include "hns_roce_eq.h"
@@ -292,7 +293,7 @@ static int hns_roce_aeq_int(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
 			dev_warn(dev, "Unhandled event %d on EQ %d at index %u\n",
 				 event_type, eq->eqn, eq->cons_index);
 			break;
-		};
+		}
 
 		eq->cons_index++;
 		aeqes_found = 1;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 2540b65e242c..747efd1ae5a6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -2023,7 +2023,6 @@ int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 	struct hns_roce_cq *hr_cq = to_hr_cq(ibcq);
 	u32 notification_flag;
 	u32 doorbell[2];
-	int ret = 0;
 
 	notification_flag = (flags & IB_CQ_SOLICITED_MASK) ==
 			    IB_CQ_SOLICITED ? CQ_DB_REQ_NOT : CQ_DB_REQ_NOT_SOL;
@@ -2043,7 +2042,7 @@ int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 
 	hns_roce_write64_k(doorbell, hr_cq->cq_db_l);
 
-	return ret;
+	return 0;
 }
 
 static int hns_roce_v1_poll_one(struct hns_roce_cq *hr_cq,
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 80fc01ffd8bd..e387360e3780 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/platform_device.h>
+#include <linux/vmalloc.h>
 #include <rdma/ib_umem.h>
 #include "hns_roce_device.h"
 #include "hns_roce_cmd.h"
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 054c52699090..f5dd21c2d275 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -799,7 +799,7 @@ bool hns_roce_wq_overflow(struct hns_roce_wq *hr_wq, int nreq,
 
 	cur = hr_wq->head - hr_wq->tail;
 	if (likely(cur + nreq < hr_wq->max_post))
-		return 0;
+		return false;
 
 	hr_cq = to_hr_cq(ib_cq);
 	spin_lock(&hr_cq->lock);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 5a2fa743676c..14f36ba4e5be 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -1582,15 +1582,14 @@ static enum i40iw_status_code i40iw_del_multiple_qhash(
 }
 
 /**
- * i40iw_netdev_vlan_ipv6 - Gets the netdev and mac
+ * i40iw_netdev_vlan_ipv6 - Gets the netdev and vlan
  * @addr: local IPv6 address
  * @vlan_id: vlan id for the given IPv6 address
- * @mac: mac address for the given IPv6 address
  *
  * Returns the net_device of the IPv6 address and also sets the
- * vlan id and mac for that address.
+ * vlan id for that address.
  */
-static struct net_device *i40iw_netdev_vlan_ipv6(u32 *addr, u16 *vlan_id, u8 *mac)
+static struct net_device *i40iw_netdev_vlan_ipv6(u32 *addr, u16 *vlan_id)
 {
 	struct net_device *ip_dev = NULL;
 	struct in6_addr laddr6;
@@ -1600,15 +1599,11 @@ static struct net_device *i40iw_netdev_vlan_ipv6(u32 *addr, u16 *vlan_id, u8 *ma
 	i40iw_copy_ip_htonl(laddr6.in6_u.u6_addr32, addr);
 	if (vlan_id)
 		*vlan_id = I40IW_NO_VLAN;
-	if (mac)
-		eth_zero_addr(mac);
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, ip_dev) {
 		if (ipv6_chk_addr(&init_net, &laddr6, ip_dev, 1)) {
 			if (vlan_id)
 				*vlan_id = rdma_vlan_dev_vlan_id(ip_dev);
-			if (ip_dev->dev_addr && mac)
-				ether_addr_copy(mac, ip_dev->dev_addr);
 			break;
 		}
 	}
@@ -3588,7 +3583,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		cm_node->vlan_id = i40iw_get_vlan_ipv4(cm_node->loc_addr);
 	} else {
 		cm_node->ipv4 = false;
-		i40iw_netdev_vlan_ipv6(cm_node->loc_addr, &cm_node->vlan_id, NULL);
+		i40iw_netdev_vlan_ipv6(cm_node->loc_addr, &cm_node->vlan_id);
 	}
 	i40iw_debug(cm_node->dev,
 		    I40IW_DEBUG_CM,
@@ -3687,8 +3682,6 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 
 	cm_node->accelerated = 1;
 	if (cm_node->accept_pend) {
-		if (!cm_node->listener)
-			i40iw_pr_err("cm_node->listener NULL for passive node\n");
 		atomic_dec(&cm_node->listener->pend_accepts_cnt);
 		cm_node->accept_pend = 0;
 	}
@@ -3789,7 +3782,7 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 				    raddr6->sin6_addr.in6_u.u6_addr32);
 		cm_info.loc_port = ntohs(laddr6->sin6_port);
 		cm_info.rem_port = ntohs(raddr6->sin6_port);
-		i40iw_netdev_vlan_ipv6(cm_info.loc_addr, &cm_info.vlan_id, NULL);
+		i40iw_netdev_vlan_ipv6(cm_info.loc_addr, &cm_info.vlan_id);
 	}
 	cm_info.cm_id = cm_id;
 	cm_info.tos = cm_id->tos;
@@ -3931,8 +3924,7 @@ int i40iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 		cm_info.loc_port = ntohs(laddr6->sin6_port);
 		if (ipv6_addr_type(&laddr6->sin6_addr) != IPV6_ADDR_ANY)
 			i40iw_netdev_vlan_ipv6(cm_info.loc_addr,
-					       &cm_info.vlan_id,
-					       NULL);
+					       &cm_info.vlan_id);
 		else
 			wildcard = true;
 	}
@@ -4056,12 +4048,7 @@ static void i40iw_cm_event_connected(struct i40iw_cm_event *event)
 	i40iw_modify_qp(&iwqp->ibqp, &attr, IB_QP_STATE, NULL);
 
 	cm_node->accelerated = 1;
-	if (cm_node->accept_pend) {
-		if (!cm_node->listener)
-			i40iw_pr_err("listener is null for passive node\n");
-		atomic_dec(&cm_node->listener->pend_accepts_cnt);
-		cm_node->accept_pend = 0;
-	}
+
 	return;
 
 error:
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index 9ec1ae9a82c9..d1f5345f04f0 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -54,6 +54,17 @@ static inline void i40iw_insert_wqe_hdr(u64 *wqe, u64 header)
 	set_64bit_val(wqe, 24, header);
 }
 
+void i40iw_check_cqp_progress(struct i40iw_cqp_timeout *cqp_timeout, struct i40iw_sc_dev *dev)
+{
+	if (cqp_timeout->compl_cqp_cmds != dev->cqp_cmd_stats[OP_COMPLETED_COMMANDS]) {
+		cqp_timeout->compl_cqp_cmds = dev->cqp_cmd_stats[OP_COMPLETED_COMMANDS];
+		cqp_timeout->count = 0;
+	} else {
+		if (dev->cqp_cmd_stats[OP_REQUESTED_COMMANDS] != cqp_timeout->compl_cqp_cmds)
+			cqp_timeout->count++;
+	}
+}
+
 /**
  * i40iw_get_cqp_reg_info - get head and tail for cqp using registers
  * @cqp: struct for cqp hw
@@ -130,20 +141,32 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_commit_buf(
 	u64 base = 0;
 	u32 i, j;
 	u32 k = 0;
-	u32 low;
 
 	/* copy base values in obj_info */
-	for (i = I40IW_HMC_IW_QP, j = 0;
-			i <= I40IW_HMC_IW_PBLE; i++, j += 8) {
+	for (i = I40IW_HMC_IW_QP, j = 0; i <= I40IW_HMC_IW_PBLE; i++, j += 8) {
+		if ((i == I40IW_HMC_IW_SRQ) ||
+			(i == I40IW_HMC_IW_FSIMC) ||
+			(i == I40IW_HMC_IW_FSIAV)) {
+			info[i].base = 0;
+			info[i].cnt = 0;
+			continue;
+		}
 		get_64bit_val(buf, j, &temp);
 		info[i].base = RS_64_1(temp, 32) * 512;
 		if (info[i].base > base) {
 			base = info[i].base;
 			k = i;
 		}
-		low = (u32)(temp);
-		if (low)
-			info[i].cnt = low;
+		if (i == I40IW_HMC_IW_APBVT_ENTRY) {
+			info[i].cnt = 1;
+			continue;
+		}
+		if (i == I40IW_HMC_IW_QP)
+			info[i].cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS);
+		else if (i == I40IW_HMC_IW_CQ)
+			info[i].cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS);
+		else
+			info[i].cnt = (u32)(temp);
 	}
 	size = info[k].cnt * info[k].size + info[k].base;
 	if (size & 0x1FFFFF)
@@ -155,6 +178,31 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_commit_buf(
 }
 
 /**
+ * i40iw_sc_decode_fpm_query() - Decode a 64 bit value into max count and size
+ * @buf: ptr to fpm query buffer
+ * @buf_idx: index into buf
+ * @info: ptr to i40iw_hmc_obj_info struct
+ * @rsrc_idx: resource index into info
+ *
+ * Decode a 64 bit value from fpm query buffer into max count and size
+ */
+static u64 i40iw_sc_decode_fpm_query(u64 *buf,
+					    u32 buf_idx,
+					    struct i40iw_hmc_obj_info *obj_info,
+					    u32 rsrc_idx)
+{
+	u64 temp;
+	u32 size;
+
+	get_64bit_val(buf, buf_idx, &temp);
+	obj_info[rsrc_idx].max_cnt = (u32)temp;
+	size = (u32)RS_64_1(temp, 32);
+	obj_info[rsrc_idx].size = LS_64_1(1, size);
+
+	return temp;
+}
+
+/**
  * i40iw_sc_parse_fpm_query_buf() - parses fpm query buffer
  * @buf: ptr to fpm query buffer
  * @info: ptr to i40iw_hmc_obj_info struct
@@ -168,9 +216,9 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_query_buf(
 				struct i40iw_hmc_info *hmc_info,
 				struct i40iw_hmc_fpm_misc *hmc_fpm_misc)
 {
-	u64 temp;
 	struct i40iw_hmc_obj_info *obj_info;
-	u32 i, j, size;
+	u64 temp;
+	u32 size;
 	u16 max_pe_sds;
 
 	obj_info = hmc_info->hmc_obj;
@@ -185,41 +233,52 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_query_buf(
 	hmc_fpm_misc->max_sds = max_pe_sds;
 	hmc_info->sd_table.sd_cnt = max_pe_sds + hmc_info->first_sd_index;
 
-	for (i = I40IW_HMC_IW_QP, j = 8;
-	     i <= I40IW_HMC_IW_ARP; i++, j += 8) {
-		get_64bit_val(buf, j, &temp);
-		if (i == I40IW_HMC_IW_QP)
-			obj_info[i].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS);
-		else if (i == I40IW_HMC_IW_CQ)
-			obj_info[i].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS);
-		else
-			obj_info[i].max_cnt = (u32)temp;
+	get_64bit_val(buf, 8, &temp);
+	obj_info[I40IW_HMC_IW_QP].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS);
+	size = (u32)RS_64_1(temp, 32);
+	obj_info[I40IW_HMC_IW_QP].size = LS_64_1(1, size);
 
-		size = (u32)RS_64_1(temp, 32);
-		obj_info[i].size = ((u64)1 << size);
-	}
-	for (i = I40IW_HMC_IW_MR, j = 48;
-			i <= I40IW_HMC_IW_PBLE; i++, j += 8) {
-		get_64bit_val(buf, j, &temp);
-		obj_info[i].max_cnt = (u32)temp;
-		size = (u32)RS_64_1(temp, 32);
-		obj_info[i].size = LS_64_1(1, size);
-	}
+	get_64bit_val(buf, 16, &temp);
+	obj_info[I40IW_HMC_IW_CQ].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS);
+	size = (u32)RS_64_1(temp, 32);
+	obj_info[I40IW_HMC_IW_CQ].size = LS_64_1(1, size);
+
+	i40iw_sc_decode_fpm_query(buf, 32, obj_info, I40IW_HMC_IW_HTE);
+	i40iw_sc_decode_fpm_query(buf, 40, obj_info, I40IW_HMC_IW_ARP);
+
+	obj_info[I40IW_HMC_IW_APBVT_ENTRY].size = 8192;
+	obj_info[I40IW_HMC_IW_APBVT_ENTRY].max_cnt = 1;
+
+	i40iw_sc_decode_fpm_query(buf, 48, obj_info, I40IW_HMC_IW_MR);
+	i40iw_sc_decode_fpm_query(buf, 56, obj_info, I40IW_HMC_IW_XF);
 
-	get_64bit_val(buf, 120, &temp);
-	hmc_fpm_misc->max_ceqs = (u8)RS_64(temp, I40IW_QUERY_FPM_MAX_CEQS);
-	get_64bit_val(buf, 120, &temp);
-	hmc_fpm_misc->ht_multiplier = RS_64(temp, I40IW_QUERY_FPM_HTMULTIPLIER);
-	get_64bit_val(buf, 120, &temp);
-	hmc_fpm_misc->timer_bucket = RS_64(temp, I40IW_QUERY_FPM_TIMERBUCKET);
 	get_64bit_val(buf, 64, &temp);
+	obj_info[I40IW_HMC_IW_XFFL].max_cnt = (u32)temp;
+	obj_info[I40IW_HMC_IW_XFFL].size = 4;
 	hmc_fpm_misc->xf_block_size = RS_64(temp, I40IW_QUERY_FPM_XFBLOCKSIZE);
 	if (!hmc_fpm_misc->xf_block_size)
 		return I40IW_ERR_INVALID_SIZE;
+
+	i40iw_sc_decode_fpm_query(buf, 72, obj_info, I40IW_HMC_IW_Q1);
+
 	get_64bit_val(buf, 80, &temp);
+	obj_info[I40IW_HMC_IW_Q1FL].max_cnt = (u32)temp;
+	obj_info[I40IW_HMC_IW_Q1FL].size = 4;
 	hmc_fpm_misc->q1_block_size = RS_64(temp, I40IW_QUERY_FPM_Q1BLOCKSIZE);
 	if (!hmc_fpm_misc->q1_block_size)
 		return I40IW_ERR_INVALID_SIZE;
+
+	i40iw_sc_decode_fpm_query(buf, 88, obj_info, I40IW_HMC_IW_TIMER);
+
+	get_64bit_val(buf, 112, &temp);
+	obj_info[I40IW_HMC_IW_PBLE].max_cnt = (u32)temp;
+	obj_info[I40IW_HMC_IW_PBLE].size = 8;
+
+	get_64bit_val(buf, 120, &temp);
+	hmc_fpm_misc->max_ceqs = (u8)RS_64(temp, I40IW_QUERY_FPM_MAX_CEQS);
+	hmc_fpm_misc->ht_multiplier = RS_64(temp, I40IW_QUERY_FPM_HTMULTIPLIER);
+	hmc_fpm_misc->timer_bucket = RS_64(temp, I40IW_QUERY_FPM_TIMERBUCKET);
+
 	return 0;
 }
 
@@ -3392,13 +3451,6 @@ enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev, u8 hmc_fn_
 		hmc_info->sd_table.sd_entry = virt_mem.va;
 	}
 
-	/* fill size of objects which are fixed */
-	hmc_info->hmc_obj[I40IW_HMC_IW_XFFL].size = 4;
-	hmc_info->hmc_obj[I40IW_HMC_IW_Q1FL].size = 4;
-	hmc_info->hmc_obj[I40IW_HMC_IW_PBLE].size = 8;
-	hmc_info->hmc_obj[I40IW_HMC_IW_APBVT_ENTRY].size = 8192;
-	hmc_info->hmc_obj[I40IW_HMC_IW_APBVT_ENTRY].max_cnt = 1;
-
 	return ret_code;
 }
 
@@ -4840,7 +4892,7 @@ void i40iw_vsi_stats_free(struct i40iw_sc_vsi *vsi)
 {
 	u8 fcn_id = vsi->fcn_id;
 
-	if ((vsi->stats_fcn_id_alloc) && (fcn_id != I40IW_INVALID_FCN_ID))
+	if (vsi->stats_fcn_id_alloc && fcn_id < I40IW_MAX_STATS_COUNT)
 		vsi->dev->fcn_id_array[fcn_id] = false;
 	i40iw_hw_stats_stop_timer(vsi);
 }
diff --git a/drivers/infiniband/hw/i40iw/i40iw_d.h b/drivers/infiniband/hw/i40iw/i40iw_d.h
index a39ac12b6a7e..2ebaadbed379 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_d.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_d.h
@@ -1507,8 +1507,8 @@ enum {
 	I40IW_CQ0_ALIGNMENT_MASK =		(256 - 1),
 	I40IW_HOST_CTX_ALIGNMENT_MASK =		(4 - 1),
 	I40IW_SHADOWAREA_MASK =			(128 - 1),
-	I40IW_FPM_QUERY_BUF_ALIGNMENT_MASK =	0,
-	I40IW_FPM_COMMIT_BUF_ALIGNMENT_MASK =	0
+	I40IW_FPM_QUERY_BUF_ALIGNMENT_MASK =	(4 - 1),
+	I40IW_FPM_COMMIT_BUF_ALIGNMENT_MASK =	(4 - 1)
 };
 
 enum i40iw_alignment {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index ae8463ff59a7..cc742c3132c6 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -77,7 +77,6 @@ MODULE_PARM_DESC(mpa_version, "MPA version to be used in MPA Req/Resp 1 or 2");
 MODULE_AUTHOR("Intel Corporation, <e1000-rdma@lists.sourceforge.net>");
 MODULE_DESCRIPTION("Intel(R) Ethernet Connection X722 iWARP RDMA Driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 
 static struct i40e_client i40iw_client;
 static char i40iw_client_name[I40E_CLIENT_STR_LENGTH] = "i40iw";
diff --git a/drivers/infiniband/hw/i40iw/i40iw_p.h b/drivers/infiniband/hw/i40iw/i40iw_p.h
index 28a92fee0822..e217a1259f57 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_p.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_p.h
@@ -35,11 +35,13 @@
 #ifndef I40IW_P_H
 #define I40IW_P_H
 
-#define PAUSE_TIMER_VALUE  0xFFFF
-#define REFRESH_THRESHOLD  0x7FFF
-#define HIGH_THRESHOLD     0x800
-#define LOW_THRESHOLD      0x200
-#define ALL_TC2PFC         0xFF
+#define PAUSE_TIMER_VALUE       0xFFFF
+#define REFRESH_THRESHOLD       0x7FFF
+#define HIGH_THRESHOLD          0x800
+#define LOW_THRESHOLD           0x200
+#define ALL_TC2PFC              0xFF
+#define CQP_COMPL_WAIT_TIME     0x3E8
+#define CQP_TIMEOUT_THRESHOLD   5
 
 void i40iw_debug_buf(struct i40iw_sc_dev *dev, enum i40iw_debug_flag mask,
 		     char *desc, u64 *buf, u32 size);
@@ -51,6 +53,8 @@ void i40iw_sc_cqp_post_sq(struct i40iw_sc_cqp *cqp);
 
 u64 *i40iw_sc_cqp_get_next_send_wqe(struct i40iw_sc_cqp *cqp, u64 scratch);
 
+void i40iw_check_cqp_progress(struct i40iw_cqp_timeout *cqp_timeout, struct i40iw_sc_dev *dev);
+
 enum i40iw_status_code i40iw_sc_mr_fast_register(struct i40iw_sc_qp *qp,
 						 struct i40iw_fast_reg_stag_info *info,
 						 bool post_sq);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_pble.c b/drivers/infiniband/hw/i40iw/i40iw_pble.c
index c87ba1617087..540aab5e502d 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_pble.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_pble.c
@@ -269,10 +269,8 @@ static enum i40iw_status_code add_bp_pages(struct i40iw_sc_dev *dev,
 	status = i40iw_add_sd_table_entry(dev->hw, hmc_info,
 					  info->idx.sd_idx, I40IW_SD_TYPE_PAGED,
 					  I40IW_HMC_DIRECT_BP_SIZE);
-	if (status) {
-		i40iw_free_vmalloc_mem(dev->hw, chunk);
-		return status;
-	}
+	if (status)
+		goto error;
 	if (!dev->is_pf) {
 		status = i40iw_vchnl_vf_add_hmc_objs(dev, I40IW_HMC_IW_PBLE,
 						     fpm_to_idx(pble_rsrc,
@@ -280,8 +278,7 @@ static enum i40iw_status_code add_bp_pages(struct i40iw_sc_dev *dev,
 						     (info->pages << PBLE_512_SHIFT));
 		if (status) {
 			i40iw_pr_err("allocate PBLEs in the PF.  Error %i\n", status);
-			i40iw_free_vmalloc_mem(dev->hw, chunk);
-			return status;
+			goto error;
 		}
 	}
 	addr = chunk->vaddr;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c
index 71050c5d29a0..c2cab20c4bc5 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_puda.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c
@@ -685,7 +685,7 @@ static enum i40iw_status_code i40iw_puda_cq_create(struct i40iw_puda_rsrc *rsrc)
 	cqsize = rsrc->cq_size * (sizeof(struct i40iw_cqe));
 	tsize = cqsize + sizeof(struct i40iw_cq_shadow_area);
 	ret = i40iw_allocate_dma_mem(dev->hw, &rsrc->cqmem, tsize,
-				     I40IW_CQ0_ALIGNMENT_MASK);
+				     I40IW_CQ0_ALIGNMENT);
 	if (ret)
 		return ret;
 
@@ -949,14 +949,16 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_vsi *vsi,
 		ret = i40iw_puda_qp_create(rsrc);
 	}
 	if (ret) {
-		i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error qp_create\n", __func__);
+		i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error qp_create\n",
+			    __func__);
 		goto error;
 	}
 	rsrc->completion = PUDA_QP_CREATED;
 
 	ret = i40iw_puda_allocbufs(rsrc, info->tx_buf_cnt + info->rq_size);
 	if (ret) {
-		i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error allloc_buf\n", __func__);
+		i40iw_debug(dev, I40IW_DEBUG_PUDA, "[%s] error alloc_buf\n",
+			    __func__);
 		goto error;
 	}
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_status.h b/drivers/infiniband/hw/i40iw/i40iw_status.h
index 91c421762f06..f7013f11d808 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_status.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_status.h
@@ -62,7 +62,7 @@ enum i40iw_status_code {
 	I40IW_ERR_INVALID_ALIGNMENT = -23,
 	I40IW_ERR_FLUSHED_QUEUE = -24,
 	I40IW_ERR_INVALID_PUSH_PAGE_INDEX = -25,
-	I40IW_ERR_INVALID_IMM_DATA_SIZE = -26,
+	I40IW_ERR_INVALID_INLINE_DATA_SIZE = -26,
 	I40IW_ERR_TIMEOUT = -27,
 	I40IW_ERR_OPCODE_MISMATCH = -28,
 	I40IW_ERR_CQP_COMPL_ERROR = -29,
diff --git a/drivers/infiniband/hw/i40iw/i40iw_type.h b/drivers/infiniband/hw/i40iw/i40iw_type.h
index 959ec81fba99..63118f6d5ab4 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_type.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_type.h
@@ -1345,4 +1345,9 @@ struct i40iw_virtchnl_work_info {
 	void *worker_vf_dev;
 };
 
+struct i40iw_cqp_timeout {
+	u64 compl_cqp_cmds;
+	u8 count;
+};
+
 #endif
diff --git a/drivers/infiniband/hw/i40iw/i40iw_uk.c b/drivers/infiniband/hw/i40iw/i40iw_uk.c
index b0d3a0e8a9b5..0aadb7a0d1aa 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_uk.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_uk.c
@@ -435,7 +435,7 @@ static enum i40iw_status_code i40iw_inline_rdma_write(struct i40iw_qp_uk *qp,
 
 	op_info = &info->op.inline_rdma_write;
 	if (op_info->len > I40IW_MAX_INLINE_DATA_SIZE)
-		return I40IW_ERR_INVALID_IMM_DATA_SIZE;
+		return I40IW_ERR_INVALID_INLINE_DATA_SIZE;
 
 	ret_code = i40iw_inline_data_size_to_wqesize(op_info->len, &wqe_size);
 	if (ret_code)
@@ -511,7 +511,7 @@ static enum i40iw_status_code i40iw_inline_send(struct i40iw_qp_uk *qp,
 
 	op_info = &info->op.inline_send;
 	if (op_info->len > I40IW_MAX_INLINE_DATA_SIZE)
-		return I40IW_ERR_INVALID_IMM_DATA_SIZE;
+		return I40IW_ERR_INVALID_INLINE_DATA_SIZE;
 
 	ret_code = i40iw_inline_data_size_to_wqesize(op_info->len, &wqe_size);
 	if (ret_code)
@@ -784,7 +784,7 @@ static enum i40iw_status_code i40iw_cq_poll_completion(struct i40iw_cq_uk *cq,
 	get_64bit_val(cqe, 0, &qword0);
 	get_64bit_val(cqe, 16, &qword2);
 
-	info->tcp_seq_num = (u8)RS_64(qword0, I40IWCQ_TCPSEQNUM);
+	info->tcp_seq_num = (u32)RS_64(qword0, I40IWCQ_TCPSEQNUM);
 
 	info->qp_id = (u32)RS_64(qword2, I40IWCQ_QPID);
 
@@ -912,7 +912,7 @@ enum i40iw_status_code i40iw_get_wqe_shift(u32 wqdepth, u32 sge, u32 inline_data
 	return 0;
 }
 
-static struct i40iw_qp_uk_ops iw_qp_uk_ops = {
+static const struct i40iw_qp_uk_ops iw_qp_uk_ops = {
 	.iw_qp_post_wr = i40iw_qp_post_wr,
 	.iw_qp_ring_push_db = i40iw_qp_ring_push_db,
 	.iw_rdma_write = i40iw_rdma_write,
@@ -926,14 +926,14 @@ static struct i40iw_qp_uk_ops iw_qp_uk_ops = {
 	.iw_post_nop = i40iw_nop
 };
 
-static struct i40iw_cq_ops iw_cq_ops = {
+static const struct i40iw_cq_ops iw_cq_ops = {
 	.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 = {
+static const struct i40iw_device_uk_ops iw_device_uk_ops = {
 	.iwarp_cq_uk_init = i40iw_cq_uk_init,
 	.iwarp_qp_uk_init = i40iw_qp_uk_init,
 };
@@ -1187,7 +1187,7 @@ enum i40iw_status_code i40iw_inline_data_size_to_wqesize(u32 data_size,
 							 u8 *wqe_size)
 {
 	if (data_size > I40IW_MAX_INLINE_DATA_SIZE)
-		return I40IW_ERR_INVALID_IMM_DATA_SIZE;
+		return I40IW_ERR_INVALID_INLINE_DATA_SIZE;
 
 	if (data_size <= 16)
 		*wqe_size = I40IW_QP_WQE_MIN_SIZE;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index e311ec559f4e..62f1f45b8737 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -445,23 +445,29 @@ static int i40iw_wait_event(struct i40iw_device *iwdev,
 {
 	struct cqp_commands_info *info = &cqp_request->info;
 	struct i40iw_cqp *iwcqp = &iwdev->cqp;
+	struct i40iw_cqp_timeout cqp_timeout;
 	bool cqp_error = false;
 	int err_code = 0;
-	int timeout_ret = 0;
+	memset(&cqp_timeout, 0, sizeof(cqp_timeout));
+	cqp_timeout.compl_cqp_cmds = iwdev->sc_dev.cqp_cmd_stats[OP_COMPLETED_COMMANDS];
+	do {
+		if (wait_event_timeout(cqp_request->waitq,
+				       cqp_request->request_done, CQP_COMPL_WAIT_TIME))
+			break;
 
-	timeout_ret = wait_event_timeout(cqp_request->waitq,
-					 cqp_request->request_done,
-					 I40IW_EVENT_TIMEOUT);
-	if (!timeout_ret) {
-		i40iw_pr_err("error cqp command 0x%x timed out ret = %d\n",
-			     info->cqp_cmd, timeout_ret);
+		i40iw_check_cqp_progress(&cqp_timeout, &iwdev->sc_dev);
+
+		if (cqp_timeout.count < CQP_TIMEOUT_THRESHOLD)
+			continue;
+
+		i40iw_pr_err("error cqp command 0x%x timed out", info->cqp_cmd);
 		err_code = -ETIME;
 		if (!iwdev->reset) {
 			iwdev->reset = true;
 			i40iw_request_reset(iwdev);
 		}
 		goto done;
-	}
+	} while (1);
 	cqp_error = cqp_request->compl_info.error;
 	if (cqp_error) {
 		i40iw_pr_err("error cqp command 0x%x completion maj = 0x%x min=0x%x\n",
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 02d871db7ca5..1aa411034a27 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -2584,13 +2584,12 @@ static const char * const i40iw_hw_stat_names[] = {
 		"iwRdmaInv"
 };
 
-static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str,
-				 size_t str_len)
+static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	u32 firmware_version = I40IW_FW_VERSION;
 
-	snprintf(str, str_len, "%u.%u", firmware_version,
-		       (firmware_version & 0x000000ff));
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u", firmware_version,
+		 (firmware_version & 0x000000ff));
 }
 
 /**
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index ea24230ea0d4..155b4dfc0ae8 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -528,7 +528,7 @@ static int set_guid_rec(struct ib_device *ibdev,
 
 	memset(&guid_info_rec, 0, sizeof (struct ib_sa_guidinfo_rec));
 
-	guid_info_rec.lid = cpu_to_be16(attr.lid);
+	guid_info_rec.lid = ib_lid_be16(attr.lid);
 	guid_info_rec.block_num = index;
 
 	memcpy(guid_info_rec.guid_info_list, rec_det->all_recs,
@@ -781,7 +781,7 @@ void mlx4_ib_init_alias_guid_work(struct mlx4_ib_dev *dev, int port)
 	spin_lock_irqsave(&dev->sriov.going_down_lock, flags);
 	spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1);
 	if (!dev->sriov.is_going_down) {
-		/* If there is pending one should cancell then run, otherwise
+		/* If there is pending one should cancel then run, otherwise
 		  * won't run till previous one is ended as same work
 		  * struct is used.
 		  */
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index ff931c580557..cab796341697 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -218,6 +218,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 			goto err_mtt;
 
 		uar = &to_mucontext(context)->uar;
+		cq->mcq.usage = MLX4_RES_USAGE_USER_VERBS;
 	} else {
 		err = mlx4_db_alloc(dev->dev, &cq->db, 1);
 		if (err)
@@ -233,6 +234,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 			goto err_db;
 
 		uar = &dev->priv_uar;
+		cq->mcq.usage = MLX4_RES_USAGE_DRIVER;
 	}
 
 	if (dev->eq_table)
@@ -635,7 +637,7 @@ static void mlx4_ib_poll_sw_comp(struct mlx4_ib_cq *cq, int num_entries,
 	struct mlx4_ib_qp *qp;
 
 	*npolled = 0;
-	/* Find uncompleted WQEs belonging to that cq and retrun
+	/* Find uncompleted WQEs belonging to that cq and return
 	 * simulated FLUSH_ERR completions
 	 */
 	list_for_each_entry(qp, &cq->send_qp_list, cq_send_list) {
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 21d31cb1325f..0793a21d76f4 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -169,7 +169,7 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= in_wc->slid << 16;
+		in_modifier |= ib_lid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, in_modifier,
@@ -625,7 +625,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 		memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2);
 	} else {
 		tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
-		tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
+		tun_mad->hdr.slid_mac_47_32 = ib_lid_be16(wc->slid);
 	}
 
 	ib_dma_sync_single_for_device(&dev->ib_dev,
@@ -826,7 +826,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		}
 	}
 
-	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
 		forward_trap(to_mdev(ibdev), port_num, in_mad);
@@ -860,7 +860,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = pattr.lid;
+		prev_lid = ib_lid_cpu16(pattr.lid);
 
 	err = mlx4_MAD_IFC(to_mdev(ibdev),
 			   (mad_flags & IB_MAD_IGNORE_MKEY ? MLX4_MAD_IFC_IGNORE_MKEY : 0) |
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index d1b43cbbfea7..c636842c5be0 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -70,7 +70,6 @@
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 
 int mlx4_ib_sm_guid_assign = 0;
 module_param_named(sm_guid_assign, mlx4_ib_sm_guid_assign, int, 0444);
@@ -81,6 +80,8 @@ static const char mlx4_ib_version[] =
 	DRV_VERSION "\n";
 
 static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init);
+static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device,
+						    u8 port_num);
 
 static struct workqueue_struct *wq;
 
@@ -552,6 +553,16 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
 	props->max_ah = INT_MAX;
 
+	if ((dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) &&
+	    (mlx4_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET ||
+	     mlx4_ib_port_link_layer(ibdev, 2) == IB_LINK_LAYER_ETHERNET)) {
+		props->rss_caps.max_rwq_indirection_tables = props->max_qp;
+		props->rss_caps.max_rwq_indirection_table_size =
+			dev->dev->caps.max_rss_tbl_sz;
+		props->rss_caps.supported_qpts = 1 << IB_QPT_RAW_PACKET;
+		props->max_wq_type_rq = props->max_qp;
+	}
+
 	if (!mlx4_is_slave(dev->dev))
 		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
 
@@ -563,6 +574,13 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
+	if (uhw->outlen >= resp.response_length +
+	    sizeof(resp.max_inl_recv_sz)) {
+		resp.response_length += sizeof(resp.max_inl_recv_sz);
+		resp.max_inl_recv_sz  = dev->dev->caps.max_rq_sg *
+			sizeof(struct mlx4_wqe_data_seg);
+	}
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 		if (err)
@@ -1069,6 +1087,9 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
 
+	INIT_LIST_HEAD(&context->wqn_ranges_list);
+	mutex_init(&context->wqn_ranges_mutex);
+
 	if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
 		err = ib_copy_to_udata(udata, &resp_v3, sizeof(resp_v3));
 	else
@@ -2566,12 +2587,11 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_fw_ver_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_fw_ver_str(struct ib_device *device, char *str)
 {
 	struct mlx4_ib_dev *dev =
 		container_of(device, struct mlx4_ib_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
 		 (int) (dev->dev->caps.fw_ver >> 32),
 		 (int) (dev->dev->caps.fw_ver >> 16) & 0xffff,
 		 (int) dev->dev->caps.fw_ver & 0xffff);
@@ -2713,6 +2733,26 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.get_dev_fw_str    = get_fw_ver_str;
 	ibdev->ib_dev.disassociate_ucontext = mlx4_ib_disassociate_ucontext;
 
+	if ((dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) &&
+	    ((mlx4_ib_port_link_layer(&ibdev->ib_dev, 1) ==
+	    IB_LINK_LAYER_ETHERNET) ||
+	    (mlx4_ib_port_link_layer(&ibdev->ib_dev, 2) ==
+	    IB_LINK_LAYER_ETHERNET))) {
+		ibdev->ib_dev.create_wq		= mlx4_ib_create_wq;
+		ibdev->ib_dev.modify_wq		= mlx4_ib_modify_wq;
+		ibdev->ib_dev.destroy_wq	= mlx4_ib_destroy_wq;
+		ibdev->ib_dev.create_rwq_ind_table  =
+			mlx4_ib_create_rwq_ind_table;
+		ibdev->ib_dev.destroy_rwq_ind_table =
+			mlx4_ib_destroy_rwq_ind_table;
+		ibdev->ib_dev.uverbs_ex_cmd_mask |=
+			(1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ)	  |
+			(1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ)	  |
+			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ)	  |
+			(1ull << IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) |
+			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL);
+	}
+
 	if (!mlx4_is_slave(ibdev->dev)) {
 		ibdev->ib_dev.alloc_fmr		= mlx4_ib_fmr_alloc;
 		ibdev->ib_dev.map_phys_fmr	= mlx4_ib_map_phys_fmr;
@@ -2772,7 +2812,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		allocated = 0;
 		if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) ==
 						IB_LINK_LAYER_ETHERNET) {
-			err = mlx4_counter_alloc(ibdev->dev, &counter_index);
+			err = mlx4_counter_alloc(ibdev->dev, &counter_index,
+						 MLX4_RES_USAGE_DRIVER);
 			/* if failed to allocate a new counter, use default */
 			if (err)
 				counter_index =
@@ -2827,7 +2868,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
 		err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
 					    MLX4_IB_UC_STEER_QPN_ALIGN,
-					    &ibdev->steer_qpn_base, 0);
+					    &ibdev->steer_qpn_base, 0,
+					    MLX4_RES_USAGE_DRIVER);
 		if (err)
 			goto err_counter;
 
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index b73f89700ef9..70eb9f917303 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -808,8 +808,7 @@ static ssize_t sysfs_show_group(struct device *dev,
 		struct device_attribute *attr, char *buf);
 
 static struct mcast_group *acquire_group(struct mlx4_ib_demux_ctx *ctx,
-					 union ib_gid *mgid, int create,
-					 gfp_t gfp_mask)
+					 union ib_gid *mgid, int create)
 {
 	struct mcast_group *group, *cur_group;
 	int is_mgid0;
@@ -825,7 +824,7 @@ static struct mcast_group *acquire_group(struct mlx4_ib_demux_ctx *ctx,
 	if (!create)
 		return ERR_PTR(-ENOENT);
 
-	group = kzalloc(sizeof *group, gfp_mask);
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
 	if (!group)
 		return ERR_PTR(-ENOMEM);
 
@@ -892,7 +891,7 @@ int mlx4_ib_mcg_demux_handler(struct ib_device *ibdev, int port, int slave,
 	case IB_MGMT_METHOD_GET_RESP:
 	case IB_SA_METHOD_DELETE_RESP:
 		mutex_lock(&ctx->mcg_table_lock);
-		group = acquire_group(ctx, &rec->mgid, 0, GFP_KERNEL);
+		group = acquire_group(ctx, &rec->mgid, 0);
 		mutex_unlock(&ctx->mcg_table_lock);
 		if (IS_ERR(group)) {
 			if (mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP) {
@@ -954,7 +953,7 @@ int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port,
 		req->sa_mad = *sa_mad;
 
 		mutex_lock(&ctx->mcg_table_lock);
-		group = acquire_group(ctx, &rec->mgid, may_create, GFP_KERNEL);
+		group = acquire_group(ctx, &rec->mgid, may_create);
 		mutex_unlock(&ctx->mcg_table_lock);
 		if (IS_ERR(group)) {
 			kfree(req);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 9db82e67e959..1fa19820355a 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -46,6 +46,7 @@
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
+#include <linux/mlx4/qp.h>
 
 #define MLX4_IB_DRV_NAME	"mlx4_ib"
 
@@ -88,6 +89,8 @@ struct mlx4_ib_ucontext {
 	struct list_head	db_page_list;
 	struct mutex		db_page_mutex;
 	struct mlx4_ib_vma_private_data hw_bar_info[HW_BAR_COUNT];
+	struct list_head	wqn_ranges_list;
+	struct mutex		wqn_ranges_mutex; /* protect wqn_ranges_list */
 };
 
 struct mlx4_ib_pd {
@@ -289,8 +292,25 @@ struct mlx4_roce_smac_vlan_info {
 	int update_vid;
 };
 
+struct mlx4_wqn_range {
+	int			base_wqn;
+	int			size;
+	int			refcount;
+	bool			dirty;
+	struct list_head	list;
+};
+
+struct mlx4_ib_rss {
+	unsigned int		base_qpn_tbl_sz;
+	u8			flags;
+	u8			rss_key[MLX4_EN_RSS_KEY_SIZE];
+};
+
 struct mlx4_ib_qp {
-	struct ib_qp		ibqp;
+	union {
+		struct ib_qp	ibqp;
+		struct ib_wq	ibwq;
+	};
 	struct mlx4_qp		mqp;
 	struct mlx4_buf		buf;
 
@@ -318,6 +338,7 @@ struct mlx4_ib_qp {
 	u8			sq_no_prefetch;
 	u8			state;
 	int			mlx_type;
+	u32			inl_recv_sz;
 	struct list_head	gid_list;
 	struct list_head	steering_rules;
 	struct mlx4_ib_buf	*sqp_proxy_rcv;
@@ -328,6 +349,10 @@ struct mlx4_ib_qp {
 	struct list_head	cq_recv_list;
 	struct list_head	cq_send_list;
 	struct counter_index	*counter_index;
+	struct mlx4_wqn_range	*wqn_range;
+	/* Number of RSS QP parents that uses this WQ */
+	u32			rss_usecnt;
+	struct mlx4_ib_rss	*rss_ctx;
 };
 
 struct mlx4_ib_srq {
@@ -623,6 +648,8 @@ struct mlx4_uverbs_ex_query_device_resp {
 	__u32 comp_mask;
 	__u32 response_length;
 	__u64 hca_core_clock_offset;
+	__u32 max_inl_recv_sz;
+	__u32 reserved;
 };
 
 static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev)
@@ -890,4 +917,17 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
 
 void mlx4_ib_sl2vl_update(struct mlx4_ib_dev *mdev, int port);
 
+struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd,
+				struct ib_wq_init_attr *init_attr,
+				struct ib_udata *udata);
+int mlx4_ib_destroy_wq(struct ib_wq *wq);
+int mlx4_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
+		      u32 wq_attr_mask, struct ib_udata *udata);
+
+struct ib_rwq_ind_table
+*mlx4_ib_create_rwq_ind_table(struct ib_device *device,
+			      struct ib_rwq_ind_table_init_attr *init_attr,
+			      struct ib_udata *udata);
+int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
+
 #endif /* MLX4_IB_H */
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 75c0e6c5dd56..b6b33d99b0b4 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -36,7 +36,6 @@
 #include <net/ip.h>
 #include <linux/slab.h>
 #include <linux/netdevice.h>
-#include <linux/vmalloc.h>
 
 #include <rdma/ib_cache.h>
 #include <rdma/ib_pack.h>
@@ -53,6 +52,7 @@ static void mlx4_ib_lock_cqs(struct mlx4_ib_cq *send_cq,
 			     struct mlx4_ib_cq *recv_cq);
 static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq,
 			       struct mlx4_ib_cq *recv_cq);
+static int _mlx4_ib_modify_wq(struct ib_wq *ibwq, enum ib_wq_state new_state);
 
 enum {
 	MLX4_IB_ACK_REQ_FREQ	= 8,
@@ -116,6 +116,11 @@ static const __be32 mlx4_ib_opcode[] = {
 	[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD]	= cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA),
 };
 
+enum mlx4_ib_source_type {
+	MLX4_IB_QP_SRC	= 0,
+	MLX4_IB_RWQ_SRC	= 1,
+};
+
 static struct mlx4_ib_sqp *to_msqp(struct mlx4_ib_qp *mqp)
 {
 	return container_of(mqp, struct mlx4_ib_sqp, qp);
@@ -145,8 +150,8 @@ static int is_sqp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
 	/* VF or PF -- proxy SQP */
 	if (mlx4_is_mfunc(dev->dev)) {
 		for (i = 0; i < dev->dev->caps.num_ports; i++) {
-			if (qp->mqp.qpn == dev->dev->caps.qp0_proxy[i] ||
-			    qp->mqp.qpn == dev->dev->caps.qp1_proxy[i]) {
+			if (qp->mqp.qpn == dev->dev->caps.spec_qps[i].qp0_proxy ||
+			    qp->mqp.qpn == dev->dev->caps.spec_qps[i].qp1_proxy) {
 				proxy_sqp = 1;
 				break;
 			}
@@ -173,7 +178,7 @@ static int is_qp0(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
 	/* VF or PF -- proxy QP0 */
 	if (mlx4_is_mfunc(dev->dev)) {
 		for (i = 0; i < dev->dev->caps.num_ports; i++) {
-			if (qp->mqp.qpn == dev->dev->caps.qp0_proxy[i]) {
+			if (qp->mqp.qpn == dev->dev->caps.spec_qps[i].qp0_proxy) {
 				proxy_qp0 = 1;
 				break;
 			}
@@ -330,6 +335,12 @@ static void mlx4_ib_qp_event(struct mlx4_qp *qp, enum mlx4_event type)
 	}
 }
 
+static void mlx4_ib_wq_event(struct mlx4_qp *qp, enum mlx4_event type)
+{
+	pr_warn_ratelimited("Unexpected event type %d on WQ 0x%06x. Events are not supported for WQs\n",
+			    type, qp->qpn);
+}
+
 static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags)
 {
 	/*
@@ -377,7 +388,8 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags)
 }
 
 static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
-		       int is_user, int has_rq, struct mlx4_ib_qp *qp)
+		       int is_user, int has_rq, struct mlx4_ib_qp *qp,
+		       u32 inl_recv_sz)
 {
 	/* Sanity check RQ size before proceeding */
 	if (cap->max_recv_wr > dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE ||
@@ -385,18 +397,24 @@ static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
 		return -EINVAL;
 
 	if (!has_rq) {
-		if (cap->max_recv_wr)
+		if (cap->max_recv_wr || inl_recv_sz)
 			return -EINVAL;
 
 		qp->rq.wqe_cnt = qp->rq.max_gs = 0;
 	} else {
+		u32 max_inl_recv_sz = dev->dev->caps.max_rq_sg *
+			sizeof(struct mlx4_wqe_data_seg);
+		u32 wqe_size;
+
 		/* HW requires >= 1 RQ entry with >= 1 gather entry */
-		if (is_user && (!cap->max_recv_wr || !cap->max_recv_sge))
+		if (is_user && (!cap->max_recv_wr || !cap->max_recv_sge ||
+				inl_recv_sz > max_inl_recv_sz))
 			return -EINVAL;
 
 		qp->rq.wqe_cnt	 = roundup_pow_of_two(max(1U, cap->max_recv_wr));
 		qp->rq.max_gs	 = roundup_pow_of_two(max(1U, cap->max_recv_sge));
-		qp->rq.wqe_shift = ilog2(qp->rq.max_gs * sizeof (struct mlx4_wqe_data_seg));
+		wqe_size = qp->rq.max_gs * sizeof(struct mlx4_wqe_data_seg);
+		qp->rq.wqe_shift = ilog2(max_t(u32, wqe_size, inl_recv_sz));
 	}
 
 	/* leave userspace return values as they were, so as not to break ABI */
@@ -614,8 +632,8 @@ static int qp0_enabled_vf(struct mlx4_dev *dev, int qpn)
 {
 	int i;
 	for (i = 0; i < dev->caps.num_ports; i++) {
-		if (qpn == dev->caps.qp0_proxy[i])
-			return !!dev->caps.qp0_qkey[i];
+		if (qpn == dev->caps.spec_qps[i].qp0_proxy)
+			return !!dev->caps.spec_qps[i].qp0_qkey;
 	}
 	return 0;
 }
@@ -632,7 +650,300 @@ static void mlx4_ib_free_qp_counter(struct mlx4_ib_dev *dev,
 	qp->counter_index = NULL;
 }
 
+static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx,
+		      struct ib_qp_init_attr *init_attr,
+		      struct mlx4_ib_create_qp_rss *ucmd)
+{
+	rss_ctx->base_qpn_tbl_sz = init_attr->rwq_ind_tbl->ind_tbl[0]->wq_num |
+		(init_attr->rwq_ind_tbl->log_ind_tbl_size << 24);
+
+	if ((ucmd->rx_hash_function == MLX4_IB_RX_HASH_FUNC_TOEPLITZ) &&
+	    (dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) {
+		memcpy(rss_ctx->rss_key, ucmd->rx_hash_key,
+		       MLX4_EN_RSS_KEY_SIZE);
+	} else {
+		pr_debug("RX Hash function is not supported\n");
+		return (-EOPNOTSUPP);
+	}
+
+	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV4) &&
+	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV4)) {
+		rss_ctx->flags = MLX4_RSS_IPV4;
+	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV4) ||
+		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV4)) {
+		pr_debug("RX Hash fields_mask is not supported - both IPv4 SRC and DST must be set\n");
+		return (-EOPNOTSUPP);
+	}
+
+	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV6) &&
+	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV6)) {
+		rss_ctx->flags |= MLX4_RSS_IPV6;
+	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV6) ||
+		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV6)) {
+		pr_debug("RX Hash fields_mask is not supported - both IPv6 SRC and DST must be set\n");
+		return (-EOPNOTSUPP);
+	}
+
+	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_UDP) &&
+	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_UDP)) {
+		if (!(dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UDP_RSS)) {
+			pr_debug("RX Hash fields_mask for UDP is not supported\n");
+			return (-EOPNOTSUPP);
+		}
+
+		if (rss_ctx->flags & MLX4_RSS_IPV4) {
+			rss_ctx->flags |= MLX4_RSS_UDP_IPV4;
+		} else if (rss_ctx->flags & MLX4_RSS_IPV6) {
+			rss_ctx->flags |= MLX4_RSS_UDP_IPV6;
+		} else {
+			pr_debug("RX Hash fields_mask is not supported - UDP must be set with IPv4 or IPv6\n");
+			return (-EOPNOTSUPP);
+		}
+	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_UDP) ||
+		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_UDP)) {
+		pr_debug("RX Hash fields_mask is not supported - both UDP SRC and DST must be set\n");
+		return (-EOPNOTSUPP);
+	}
+
+	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) &&
+	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) {
+		if (rss_ctx->flags & MLX4_RSS_IPV4) {
+			rss_ctx->flags |= MLX4_RSS_TCP_IPV4;
+		} else if (rss_ctx->flags & MLX4_RSS_IPV6) {
+			rss_ctx->flags |= MLX4_RSS_TCP_IPV6;
+		} else {
+			pr_debug("RX Hash fields_mask is not supported - TCP must be set with IPv4 or IPv6\n");
+			return (-EOPNOTSUPP);
+		}
+
+	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) ||
+		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) {
+		pr_debug("RX Hash fields_mask is not supported - both TCP SRC and DST must be set\n");
+		return (-EOPNOTSUPP);
+	}
+
+	return 0;
+}
+
+static int create_qp_rss(struct mlx4_ib_dev *dev, struct ib_pd *ibpd,
+			 struct ib_qp_init_attr *init_attr,
+			 struct mlx4_ib_create_qp_rss *ucmd,
+			 struct mlx4_ib_qp *qp)
+{
+	int qpn;
+	int err;
+
+	qp->mqp.usage = MLX4_RES_USAGE_USER_VERBS;
+
+	err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn, 0, qp->mqp.usage);
+	if (err)
+		return err;
+
+	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
+	if (err)
+		goto err_qpn;
+
+	mutex_init(&qp->mutex);
+
+	INIT_LIST_HEAD(&qp->gid_list);
+	INIT_LIST_HEAD(&qp->steering_rules);
+
+	qp->mlx4_ib_qp_type = MLX4_IB_QPT_RAW_PACKET;
+	qp->state = IB_QPS_RESET;
+
+	/* Set dummy send resources to be compatible with HV and PRM */
+	qp->sq_no_prefetch = 1;
+	qp->sq.wqe_cnt = 1;
+	qp->sq.wqe_shift = MLX4_IB_MIN_SQ_STRIDE;
+	qp->buf_size = qp->sq.wqe_cnt << MLX4_IB_MIN_SQ_STRIDE;
+	qp->mtt = (to_mqp(
+		   (struct ib_qp *)init_attr->rwq_ind_tbl->ind_tbl[0]))->mtt;
+
+	qp->rss_ctx = kzalloc(sizeof(*qp->rss_ctx), GFP_KERNEL);
+	if (!qp->rss_ctx) {
+		err = -ENOMEM;
+		goto err_qp_alloc;
+	}
+
+	err = set_qp_rss(dev, qp->rss_ctx, init_attr, ucmd);
+	if (err)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(qp->rss_ctx);
+
+err_qp_alloc:
+	mlx4_qp_remove(dev->dev, &qp->mqp);
+	mlx4_qp_free(dev->dev, &qp->mqp);
+
+err_qpn:
+	mlx4_qp_release_range(dev->dev, qpn, 1);
+	return err;
+}
+
+static struct ib_qp *_mlx4_ib_create_qp_rss(struct ib_pd *pd,
+					    struct ib_qp_init_attr *init_attr,
+					    struct ib_udata *udata)
+{
+	struct mlx4_ib_qp *qp;
+	struct mlx4_ib_create_qp_rss ucmd = {};
+	size_t required_cmd_sz;
+	int err;
+
+	if (!udata) {
+		pr_debug("RSS QP with NULL udata\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (udata->outlen)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	required_cmd_sz = offsetof(typeof(ucmd), reserved1) +
+					sizeof(ucmd.reserved1);
+	if (udata->inlen < required_cmd_sz) {
+		pr_debug("invalid inlen\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen))) {
+		pr_debug("copy failed\n");
+		return ERR_PTR(-EFAULT);
+	}
+
+	if (memchr_inv(ucmd.reserved, 0, sizeof(ucmd.reserved)))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (ucmd.comp_mask || ucmd.reserved1)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (udata->inlen > sizeof(ucmd) &&
+	    !ib_is_udata_cleared(udata, sizeof(ucmd),
+				 udata->inlen - sizeof(ucmd))) {
+		pr_debug("inlen is not supported\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+		pr_debug("RSS QP with unsupported QP type %d\n",
+			 init_attr->qp_type);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (init_attr->create_flags) {
+		pr_debug("RSS QP doesn't support create flags\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (init_attr->send_cq || init_attr->cap.max_send_wr) {
+		pr_debug("RSS QP with unsupported send attributes\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+	if (!qp)
+		return ERR_PTR(-ENOMEM);
+
+	qp->pri.vid = 0xFFFF;
+	qp->alt.vid = 0xFFFF;
+
+	err = create_qp_rss(to_mdev(pd->device), pd, init_attr, &ucmd, qp);
+	if (err) {
+		kfree(qp);
+		return ERR_PTR(err);
+	}
+
+	qp->ibqp.qp_num = qp->mqp.qpn;
+
+	return &qp->ibqp;
+}
+
+/*
+ * This function allocates a WQN from a range which is consecutive and aligned
+ * to its size. In case the range is full, then it creates a new range and
+ * allocates WQN from it. The new range will be used for following allocations.
+ */
+static int mlx4_ib_alloc_wqn(struct mlx4_ib_ucontext *context,
+			     struct mlx4_ib_qp *qp, int range_size, int *wqn)
+{
+	struct mlx4_ib_dev *dev = to_mdev(context->ibucontext.device);
+	struct mlx4_wqn_range *range;
+	int err = 0;
+
+	mutex_lock(&context->wqn_ranges_mutex);
+
+	range = list_first_entry_or_null(&context->wqn_ranges_list,
+					 struct mlx4_wqn_range, list);
+
+	if (!range || (range->refcount == range->size) || range->dirty) {
+		range = kzalloc(sizeof(*range), GFP_KERNEL);
+		if (!range) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = mlx4_qp_reserve_range(dev->dev, range_size,
+					    range_size, &range->base_wqn, 0,
+					    qp->mqp.usage);
+		if (err) {
+			kfree(range);
+			goto out;
+		}
+
+		range->size = range_size;
+		list_add(&range->list, &context->wqn_ranges_list);
+	} else if (range_size != 1) {
+		/*
+		 * Requesting a new range (>1) when last range is still open, is
+		 * not valid.
+		 */
+		err = -EINVAL;
+		goto out;
+	}
+
+	qp->wqn_range = range;
+
+	*wqn = range->base_wqn + range->refcount;
+
+	range->refcount++;
+
+out:
+	mutex_unlock(&context->wqn_ranges_mutex);
+
+	return err;
+}
+
+static void mlx4_ib_release_wqn(struct mlx4_ib_ucontext *context,
+				struct mlx4_ib_qp *qp, bool dirty_release)
+{
+	struct mlx4_ib_dev *dev = to_mdev(context->ibucontext.device);
+	struct mlx4_wqn_range *range;
+
+	mutex_lock(&context->wqn_ranges_mutex);
+
+	range = qp->wqn_range;
+
+	range->refcount--;
+	if (!range->refcount) {
+		mlx4_qp_release_range(dev->dev, range->base_wqn,
+				      range->size);
+		list_del(&range->list);
+		kfree(range);
+	} else if (dirty_release) {
+	/*
+	 * A range which one of its WQNs is destroyed, won't be able to be
+	 * reused for further WQN allocations.
+	 * The next created WQ will allocate a new range.
+	 */
+		range->dirty = 1;
+	}
+
+	mutex_unlock(&context->wqn_ranges_mutex);
+}
+
 static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
+			    enum mlx4_ib_source_type src,
 			    struct ib_qp_init_attr *init_attr,
 			    struct ib_udata *udata, int sqpn,
 			    struct mlx4_ib_qp **caller_qp)
@@ -645,6 +956,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	enum mlx4_ib_qp_type qp_type = (enum mlx4_ib_qp_type) init_attr->qp_type;
 	struct mlx4_ib_cq *mcq;
 	unsigned long flags;
+	int range_size = 0;
 
 	/* When tunneling special qps, we use a plain UD qp */
 	if (sqpn) {
@@ -719,26 +1031,70 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
 		qp->sq_signal_bits = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE);
 
-	err = set_rq_size(dev, &init_attr->cap, !!pd->uobject, qp_has_rq(init_attr), qp);
-	if (err)
-		goto err;
 
 	if (pd->uobject) {
-		struct mlx4_ib_create_qp ucmd;
+		union {
+			struct mlx4_ib_create_qp qp;
+			struct mlx4_ib_create_wq wq;
+		} ucmd;
+		size_t copy_len;
 
-		if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) {
+		copy_len = (src == MLX4_IB_QP_SRC) ?
+			   sizeof(struct mlx4_ib_create_qp) :
+			   min(sizeof(struct mlx4_ib_create_wq), udata->inlen);
+
+		if (ib_copy_from_udata(&ucmd, udata, copy_len)) {
 			err = -EFAULT;
 			goto err;
 		}
 
-		qp->sq_no_prefetch = ucmd.sq_no_prefetch;
+		if (src == MLX4_IB_RWQ_SRC) {
+			if (ucmd.wq.comp_mask || ucmd.wq.reserved[0] ||
+			    ucmd.wq.reserved[1] || ucmd.wq.reserved[2]) {
+				pr_debug("user command isn't supported\n");
+				err = -EOPNOTSUPP;
+				goto err;
+			}
+
+			if (ucmd.wq.log_range_size >
+			    ilog2(dev->dev->caps.max_rss_tbl_sz)) {
+				pr_debug("WQN range size must be equal or smaller than %d\n",
+					 dev->dev->caps.max_rss_tbl_sz);
+				err = -EOPNOTSUPP;
+				goto err;
+			}
+			range_size = 1 << ucmd.wq.log_range_size;
+		} else {
+			qp->inl_recv_sz = ucmd.qp.inl_recv_sz;
+		}
 
-		err = set_user_sq_size(dev, qp, &ucmd);
+		err = set_rq_size(dev, &init_attr->cap, !!pd->uobject,
+				  qp_has_rq(init_attr), qp, qp->inl_recv_sz);
 		if (err)
 			goto err;
 
-		qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
-				       qp->buf_size, 0, 0);
+		if (src == MLX4_IB_QP_SRC) {
+			qp->sq_no_prefetch = ucmd.qp.sq_no_prefetch;
+
+			err = set_user_sq_size(dev, qp,
+					       (struct mlx4_ib_create_qp *)
+					       &ucmd);
+			if (err)
+				goto err;
+		} else {
+			qp->sq_no_prefetch = 1;
+			qp->sq.wqe_cnt = 1;
+			qp->sq.wqe_shift = MLX4_IB_MIN_SQ_STRIDE;
+			/* Allocated buffer expects to have at least that SQ
+			 * size.
+			 */
+			qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
+				(qp->sq.wqe_cnt << qp->sq.wqe_shift);
+		}
+
+		qp->umem = ib_umem_get(pd->uobject->context,
+				(src == MLX4_IB_QP_SRC) ? ucmd.qp.buf_addr :
+				ucmd.wq.buf_addr, qp->buf_size, 0, 0);
 		if (IS_ERR(qp->umem)) {
 			err = PTR_ERR(qp->umem);
 			goto err;
@@ -755,11 +1111,18 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 
 		if (qp_has_rq(init_attr)) {
 			err = mlx4_ib_db_map_user(to_mucontext(pd->uobject->context),
-						  ucmd.db_addr, &qp->db);
+				(src == MLX4_IB_QP_SRC) ? ucmd.qp.db_addr :
+				ucmd.wq.db_addr, &qp->db);
 			if (err)
 				goto err_mtt;
 		}
+		qp->mqp.usage = MLX4_RES_USAGE_USER_VERBS;
 	} else {
+		err = set_rq_size(dev, &init_attr->cap, !!pd->uobject,
+				  qp_has_rq(init_attr), qp, 0);
+		if (err)
+			goto err;
+
 		qp->sq_no_prefetch = 0;
 
 		if (init_attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO)
@@ -812,20 +1175,15 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (err)
 			goto err_mtt;
 
-		qp->sq.wrid = kmalloc_array(qp->sq.wqe_cnt, sizeof(u64),
-					GFP_KERNEL | __GFP_NOWARN);
-		if (!qp->sq.wrid)
-			qp->sq.wrid = __vmalloc(qp->sq.wqe_cnt * sizeof(u64),
-						GFP_KERNEL, PAGE_KERNEL);
-		qp->rq.wrid = kmalloc_array(qp->rq.wqe_cnt, sizeof(u64),
-					GFP_KERNEL | __GFP_NOWARN);
-		if (!qp->rq.wrid)
-			qp->rq.wrid = __vmalloc(qp->rq.wqe_cnt * sizeof(u64),
-						GFP_KERNEL, PAGE_KERNEL);
+		qp->sq.wrid = kvmalloc_array(qp->sq.wqe_cnt,
+					     sizeof(u64), GFP_KERNEL);
+		qp->rq.wrid = kvmalloc_array(qp->rq.wqe_cnt,
+					     sizeof(u64), GFP_KERNEL);
 		if (!qp->sq.wrid || !qp->rq.wrid) {
 			err = -ENOMEM;
 			goto err_wrid;
 		}
+		qp->mqp.usage = MLX4_RES_USAGE_DRIVER;
 	}
 
 	if (sqpn) {
@@ -836,6 +1194,11 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 				goto err_wrid;
 			}
 		}
+	} else if (src == MLX4_IB_RWQ_SRC) {
+		err = mlx4_ib_alloc_wqn(to_mucontext(pd->uobject->context), qp,
+					range_size, &qpn);
+		if (err)
+			goto err_wrid;
 	} else {
 		/* Raw packet QPNs may not have bits 6,7 set in their qp_num;
 		 * otherwise, the WQE BlueFlame setup flow wrongly causes
@@ -845,13 +1208,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 						    (init_attr->cap.max_send_wr ?
 						     MLX4_RESERVE_ETH_BF_QP : 0) |
 						    (init_attr->cap.max_recv_wr ?
-						     MLX4_RESERVE_A0_QP : 0));
+						     MLX4_RESERVE_A0_QP : 0),
+						    qp->mqp.usage);
 		else
 			if (qp->flags & MLX4_IB_QP_NETIF)
 				err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
 			else
 				err = mlx4_qp_reserve_range(dev->dev, 1, 1,
-							    &qpn, 0);
+							    &qpn, 0, qp->mqp.usage);
 		if (err)
 			goto err_proxy;
 	}
@@ -873,7 +1237,9 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	 */
 	qp->doorbell_qpn = swab32(qp->mqp.qpn << 8);
 
-	qp->mqp.event = mlx4_ib_qp_event;
+	qp->mqp.event = (src == MLX4_IB_QP_SRC) ? mlx4_ib_qp_event :
+						  mlx4_ib_wq_event;
+
 	if (!*caller_qp)
 		*caller_qp = qp;
 
@@ -900,6 +1266,9 @@ err_qpn:
 	if (!sqpn) {
 		if (qp->flags & MLX4_IB_QP_NETIF)
 			mlx4_ib_steer_qp_free(dev, qpn, 1);
+		else if (src == MLX4_IB_RWQ_SRC)
+			mlx4_ib_release_wqn(to_mucontext(pd->uobject->context),
+					    qp, 0);
 		else
 			mlx4_qp_release_range(dev->dev, qpn, 1);
 	}
@@ -998,7 +1367,7 @@ static struct mlx4_ib_pd *get_pd(struct mlx4_ib_qp *qp)
 		return to_mpd(qp->ibqp.pd);
 }
 
-static void get_cqs(struct mlx4_ib_qp *qp,
+static void get_cqs(struct mlx4_ib_qp *qp, enum mlx4_ib_source_type src,
 		    struct mlx4_ib_cq **send_cq, struct mlx4_ib_cq **recv_cq)
 {
 	switch (qp->ibqp.qp_type) {
@@ -1011,14 +1380,46 @@ static void get_cqs(struct mlx4_ib_qp *qp,
 		*recv_cq = *send_cq;
 		break;
 	default:
-		*send_cq = to_mcq(qp->ibqp.send_cq);
-		*recv_cq = to_mcq(qp->ibqp.recv_cq);
+		*recv_cq = (src == MLX4_IB_QP_SRC) ? to_mcq(qp->ibqp.recv_cq) :
+						     to_mcq(qp->ibwq.cq);
+		*send_cq = (src == MLX4_IB_QP_SRC) ? to_mcq(qp->ibqp.send_cq) :
+						     *recv_cq;
 		break;
 	}
 }
 
+static void destroy_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
+{
+	if (qp->state != IB_QPS_RESET) {
+		int i;
+
+		for (i = 0; i < (1 << qp->ibqp.rwq_ind_tbl->log_ind_tbl_size);
+		     i++) {
+			struct ib_wq *ibwq = qp->ibqp.rwq_ind_tbl->ind_tbl[i];
+			struct mlx4_ib_qp *wq =	to_mqp((struct ib_qp *)ibwq);
+
+			mutex_lock(&wq->mutex);
+
+			wq->rss_usecnt--;
+
+			mutex_unlock(&wq->mutex);
+		}
+
+		if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state),
+				   MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp))
+			pr_warn("modify QP %06x to RESET failed.\n",
+				qp->mqp.qpn);
+	}
+
+	mlx4_qp_remove(dev->dev, &qp->mqp);
+	mlx4_qp_free(dev->dev, &qp->mqp);
+	mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
+	del_gid_entries(qp);
+	kfree(qp->rss_ctx);
+}
+
 static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
-			      int is_user)
+			      enum mlx4_ib_source_type src, int is_user)
 {
 	struct mlx4_ib_cq *send_cq, *recv_cq;
 	unsigned long flags;
@@ -1051,7 +1452,7 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 		}
 	}
 
-	get_cqs(qp, &send_cq, &recv_cq);
+	get_cqs(qp, src, &send_cq, &recv_cq);
 
 	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
 	mlx4_ib_lock_cqs(send_cq, recv_cq);
@@ -1077,6 +1478,9 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 	if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp)) {
 		if (qp->flags & MLX4_IB_QP_NETIF)
 			mlx4_ib_steer_qp_free(dev, qp->mqp.qpn, 1);
+		else if (src == MLX4_IB_RWQ_SRC)
+			mlx4_ib_release_wqn(to_mucontext(
+					    qp->ibwq.uobject->context), qp, 1);
 		else
 			mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
 	}
@@ -1084,9 +1488,12 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 	mlx4_mtt_cleanup(dev->dev, &qp->mtt);
 
 	if (is_user) {
-		if (qp->rq.wqe_cnt)
-			mlx4_ib_db_unmap_user(to_mucontext(qp->ibqp.uobject->context),
-					      &qp->db);
+		if (qp->rq.wqe_cnt) {
+			struct mlx4_ib_ucontext *mcontext = !src ?
+				to_mucontext(qp->ibqp.uobject->context) :
+				to_mucontext(qp->ibwq.uobject->context);
+			mlx4_ib_db_unmap_user(mcontext, &qp->db);
+		}
 		ib_umem_release(qp->umem);
 	} else {
 		kvfree(qp->sq.wrid);
@@ -1114,9 +1521,9 @@ static u32 get_sqp_num(struct mlx4_ib_dev *dev, struct ib_qp_init_attr *attr)
 	}
 	/* PF or VF -- creating proxies */
 	if (attr->qp_type == IB_QPT_SMI)
-		return dev->dev->caps.qp0_proxy[attr->port_num - 1];
+		return dev->dev->caps.spec_qps[attr->port_num - 1].qp0_proxy;
 	else
-		return dev->dev->caps.qp1_proxy[attr->port_num - 1];
+		return dev->dev->caps.spec_qps[attr->port_num - 1].qp1_proxy;
 }
 
 static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
@@ -1128,6 +1535,9 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 	int sup_u_create_flags = MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK;
 	u16 xrcdn = 0;
 
+	if (init_attr->rwq_ind_tbl)
+		return _mlx4_ib_create_qp_rss(pd, init_attr, udata);
+
 	/*
 	 * We only support LSO, vendor flag1, and multicast loopback blocking,
 	 * and only for kernel UD QPs.
@@ -1182,8 +1592,8 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 		/* fall through */
 	case IB_QPT_UD:
 	{
-		err = create_qp_common(to_mdev(pd->device), pd, init_attr,
-				       udata, 0, &qp);
+		err = create_qp_common(to_mdev(pd->device), pd,	MLX4_IB_QP_SRC,
+				       init_attr, udata, 0, &qp);
 		if (err) {
 			kfree(qp);
 			return ERR_PTR(err);
@@ -1203,7 +1613,9 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 		if (udata)
 			return ERR_PTR(-EINVAL);
 		if (init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI) {
-			int res = mlx4_qp_reserve_range(to_mdev(pd->device)->dev, 1, 1, &sqpn, 0);
+			int res = mlx4_qp_reserve_range(to_mdev(pd->device)->dev,
+							1, 1, &sqpn, 0,
+							MLX4_RES_USAGE_DRIVER);
 
 			if (res)
 				return ERR_PTR(res);
@@ -1211,8 +1623,8 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 			sqpn = get_sqp_num(to_mdev(pd->device), init_attr);
 		}
 
-		err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata,
-				       sqpn, &qp);
+		err = create_qp_common(to_mdev(pd->device), pd, MLX4_IB_QP_SRC,
+				       init_attr, udata, sqpn, &qp);
 		if (err)
 			return ERR_PTR(err);
 
@@ -1267,7 +1679,6 @@ static int _mlx4_ib_destroy_qp(struct ib_qp *qp)
 {
 	struct mlx4_ib_dev *dev = to_mdev(qp->device);
 	struct mlx4_ib_qp *mqp = to_mqp(qp);
-	struct mlx4_ib_pd *pd;
 
 	if (is_qp0(dev, mqp))
 		mlx4_CLOSE_PORT(dev->dev, mqp->port);
@@ -1282,8 +1693,14 @@ static int _mlx4_ib_destroy_qp(struct ib_qp *qp)
 	if (mqp->counter_index)
 		mlx4_ib_free_qp_counter(dev, mqp);
 
-	pd = get_pd(mqp);
-	destroy_qp_common(dev, mqp, !!pd->ibpd.uobject);
+	if (qp->rwq_ind_tbl) {
+		destroy_qp_rss(dev, mqp);
+	} else {
+		struct mlx4_ib_pd *pd;
+
+		pd = get_pd(mqp);
+		destroy_qp_common(dev, mqp, MLX4_IB_QP_SRC, !!pd->ibpd.uobject);
+	}
 
 	if (is_sqp(dev, mqp))
 		kfree(to_msqp(mqp));
@@ -1566,7 +1983,7 @@ static int create_qp_lb_counter(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
 	    !(dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_LB_SRC_CHK))
 		return 0;
 
-	err = mlx4_counter_alloc(dev->dev, &tmp_idx);
+	err = mlx4_counter_alloc(dev->dev, &tmp_idx, MLX4_RES_USAGE_DRIVER);
 	if (err)
 		return err;
 
@@ -1606,12 +2023,119 @@ static u8 gid_type_to_qpc(enum ib_gid_type gid_type)
 	}
 }
 
-static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
+/*
+ * Go over all RSS QP's childes (WQs) and apply their HW state according to
+ * their logic state if the RSS QP is the first RSS QP associated for the WQ.
+ */
+static int bringup_rss_rwqs(struct ib_rwq_ind_table *ind_tbl, u8 port_num)
+{
+	int err = 0;
+	int i;
+
+	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
+		struct ib_wq *ibwq = ind_tbl->ind_tbl[i];
+		struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq);
+
+		mutex_lock(&wq->mutex);
+
+		/* Mlx4_ib restrictions:
+		 * WQ's is associated to a port according to the RSS QP it is
+		 * associates to.
+		 * In case the WQ is associated to a different port by another
+		 * RSS QP, return a failure.
+		 */
+		if ((wq->rss_usecnt > 0) && (wq->port != port_num)) {
+			err = -EINVAL;
+			mutex_unlock(&wq->mutex);
+			break;
+		}
+		wq->port = port_num;
+		if ((wq->rss_usecnt == 0) && (ibwq->state == IB_WQS_RDY)) {
+			err = _mlx4_ib_modify_wq(ibwq, IB_WQS_RDY);
+			if (err) {
+				mutex_unlock(&wq->mutex);
+				break;
+			}
+		}
+		wq->rss_usecnt++;
+
+		mutex_unlock(&wq->mutex);
+	}
+
+	if (i && err) {
+		int j;
+
+		for (j = (i - 1); j >= 0; j--) {
+			struct ib_wq *ibwq = ind_tbl->ind_tbl[j];
+			struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq);
+
+			mutex_lock(&wq->mutex);
+
+			if ((wq->rss_usecnt == 1) &&
+			    (ibwq->state == IB_WQS_RDY))
+				if (_mlx4_ib_modify_wq(ibwq, IB_WQS_RESET))
+					pr_warn("failed to reverse WQN=0x%06x\n",
+						ibwq->wq_num);
+			wq->rss_usecnt--;
+
+			mutex_unlock(&wq->mutex);
+		}
+	}
+
+	return err;
+}
+
+static void bring_down_rss_rwqs(struct ib_rwq_ind_table *ind_tbl)
+{
+	int i;
+
+	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
+		struct ib_wq *ibwq = ind_tbl->ind_tbl[i];
+		struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq);
+
+		mutex_lock(&wq->mutex);
+
+		if ((wq->rss_usecnt == 1) && (ibwq->state == IB_WQS_RDY))
+			if (_mlx4_ib_modify_wq(ibwq, IB_WQS_RESET))
+				pr_warn("failed to reverse WQN=%x\n",
+					ibwq->wq_num);
+		wq->rss_usecnt--;
+
+		mutex_unlock(&wq->mutex);
+	}
+}
+
+static void fill_qp_rss_context(struct mlx4_qp_context *context,
+				struct mlx4_ib_qp *qp)
+{
+	struct mlx4_rss_context *rss_context;
+
+	rss_context = (void *)context + offsetof(struct mlx4_qp_context,
+			pri_path) + MLX4_RSS_OFFSET_IN_QPC_PRI_PATH;
+
+	rss_context->base_qpn = cpu_to_be32(qp->rss_ctx->base_qpn_tbl_sz);
+	rss_context->default_qpn =
+		cpu_to_be32(qp->rss_ctx->base_qpn_tbl_sz & 0xffffff);
+	if (qp->rss_ctx->flags & (MLX4_RSS_UDP_IPV4 | MLX4_RSS_UDP_IPV6))
+		rss_context->base_qpn_udp = rss_context->default_qpn;
+	rss_context->flags = qp->rss_ctx->flags;
+	/* Currently support just toeplitz */
+	rss_context->hash_fn = MLX4_RSS_HASH_TOP;
+
+	memcpy(rss_context->rss_key, qp->rss_ctx->rss_key,
+	       MLX4_EN_RSS_KEY_SIZE);
+}
+
+static int __mlx4_ib_modify_qp(void *src, enum mlx4_ib_source_type src_type,
 			       const struct ib_qp_attr *attr, int attr_mask,
 			       enum ib_qp_state cur_state, enum ib_qp_state new_state)
 {
-	struct mlx4_ib_dev *dev = to_mdev(ibqp->device);
-	struct mlx4_ib_qp *qp = to_mqp(ibqp);
+	struct ib_uobject *ibuobject;
+	struct ib_srq  *ibsrq;
+	struct ib_rwq_ind_table *rwq_ind_tbl;
+	enum ib_qp_type qp_type;
+	struct mlx4_ib_dev *dev;
+	struct mlx4_ib_qp *qp;
 	struct mlx4_ib_pd *pd;
 	struct mlx4_ib_cq *send_cq, *recv_cq;
 	struct mlx4_qp_context *context;
@@ -1621,6 +2145,30 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	int err = -EINVAL;
 	int counter_index;
 
+	if (src_type == MLX4_IB_RWQ_SRC) {
+		struct ib_wq *ibwq;
+
+		ibwq	    = (struct ib_wq *)src;
+		ibuobject   = ibwq->uobject;
+		ibsrq	    = NULL;
+		rwq_ind_tbl = NULL;
+		qp_type     = IB_QPT_RAW_PACKET;
+		qp	    = to_mqp((struct ib_qp *)ibwq);
+		dev	    = to_mdev(ibwq->device);
+		pd	    = to_mpd(ibwq->pd);
+	} else {
+		struct ib_qp *ibqp;
+
+		ibqp	    = (struct ib_qp *)src;
+		ibuobject   = ibqp->uobject;
+		ibsrq	    = ibqp->srq;
+		rwq_ind_tbl = ibqp->rwq_ind_tbl;
+		qp_type     = ibqp->qp_type;
+		qp	    = to_mqp(ibqp);
+		dev	    = to_mdev(ibqp->device);
+		pd	    = get_pd(qp);
+	}
+
 	/* APM is not supported under RoCE */
 	if (attr_mask & IB_QP_ALT_PATH &&
 	    rdma_port_get_link_layer(&dev->ib_dev, qp->port) ==
@@ -1634,6 +2182,11 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	context->flags = cpu_to_be32((to_mlx4_state(new_state) << 28) |
 				     (to_mlx4_st(dev, qp->mlx4_ib_qp_type) << 16));
 
+	if (rwq_ind_tbl) {
+		fill_qp_rss_context(context, qp);
+		context->flags |= cpu_to_be32(1 << MLX4_RSS_QPC_FLAG_OFFSET);
+	}
+
 	if (!(attr_mask & IB_QP_PATH_MIG_STATE))
 		context->flags |= cpu_to_be32(MLX4_QP_PM_MIGRATED << 11);
 	else {
@@ -1651,11 +2204,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		}
 	}
 
-	if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_SMI)
+	if (qp->inl_recv_sz)
+		context->param3 |= cpu_to_be32(1 << 25);
+
+	if (qp_type == IB_QPT_GSI || qp_type == IB_QPT_SMI)
 		context->mtu_msgmax = (IB_MTU_4096 << 5) | 11;
-	else if (ibqp->qp_type == IB_QPT_RAW_PACKET)
+	else if (qp_type == IB_QPT_RAW_PACKET)
 		context->mtu_msgmax = (MLX4_RAW_QP_MTU << 5) | MLX4_RAW_QP_MSGMAX;
-	else if (ibqp->qp_type == IB_QPT_UD) {
+	else if (qp_type == IB_QPT_UD) {
 		if (qp->flags & MLX4_IB_QP_LSO)
 			context->mtu_msgmax = (IB_MTU_4096 << 5) |
 					      ilog2(dev->dev->caps.max_gso_sz);
@@ -1671,9 +2227,11 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 			ilog2(dev->dev->caps.max_msg_sz);
 	}
 
-	if (qp->rq.wqe_cnt)
-		context->rq_size_stride = ilog2(qp->rq.wqe_cnt) << 3;
-	context->rq_size_stride |= qp->rq.wqe_shift - 4;
+	if (!rwq_ind_tbl) { /* PRM RSS receive side should be left zeros */
+		if (qp->rq.wqe_cnt)
+			context->rq_size_stride = ilog2(qp->rq.wqe_cnt) << 3;
+		context->rq_size_stride |= qp->rq.wqe_shift - 4;
+	}
 
 	if (qp->sq.wqe_cnt)
 		context->sq_size_stride = ilog2(qp->sq.wqe_cnt) << 3;
@@ -1685,14 +2243,15 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
 		context->sq_size_stride |= !!qp->sq_no_prefetch << 7;
 		context->xrcd = cpu_to_be32((u32) qp->xrcdn);
-		if (ibqp->qp_type == IB_QPT_RAW_PACKET)
+		if (qp_type == IB_QPT_RAW_PACKET)
 			context->param3 |= cpu_to_be32(1 << 30);
 	}
 
-	if (qp->ibqp.uobject)
+	if (ibuobject)
 		context->usr_page = cpu_to_be32(
 			mlx4_to_hw_uar_index(dev->dev,
-					     to_mucontext(ibqp->uobject->context)->uar.index));
+					     to_mucontext(ibuobject->context)
+					     ->uar.index));
 	else
 		context->usr_page = cpu_to_be32(
 			mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index));
@@ -1736,7 +2295,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 			steer_qp = 1;
 		}
 
-		if (ibqp->qp_type == IB_QPT_GSI) {
+		if (qp_type == IB_QPT_GSI) {
 			enum ib_gid_type gid_type = qp->flags & MLX4_IB_ROCE_V2_GSI_QP ?
 				IB_GID_TYPE_ROCE_UDP_ENCAP : IB_GID_TYPE_ROCE;
 			u8 qpc_roce_mode = gid_type_to_qpc(gid_type);
@@ -1753,7 +2312,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (attr_mask & IB_QP_AV) {
-		u8 port_num = mlx4_is_bonded(to_mdev(ibqp->device)->dev) ? 1 :
+		u8 port_num = mlx4_is_bonded(dev->dev) ? 1 :
 			attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
 		union ib_gid gid;
 		struct ib_gid_attr gid_attr = {.gid_type = IB_GID_TYPE_IB};
@@ -1768,7 +2327,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 			int index =
 				rdma_ah_read_grh(&attr->ah_attr)->sgid_index;
 
-			status = ib_get_cached_gid(ibqp->device, port_num,
+			status = ib_get_cached_gid(&dev->ib_dev, port_num,
 						   index, &gid, &gid_attr);
 			if (!status && !memcmp(&gid, &zgid, sizeof(gid)))
 				status = -ENOENT;
@@ -1825,15 +2384,20 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		optpar |= MLX4_QP_OPTPAR_ALT_ADDR_PATH;
 	}
 
-	pd = get_pd(qp);
-	get_cqs(qp, &send_cq, &recv_cq);
-	context->pd       = cpu_to_be32(pd->pdn);
+	context->pd = cpu_to_be32(pd->pdn);
+
+	if (!rwq_ind_tbl) {
+		get_cqs(qp, src_type, &send_cq, &recv_cq);
+	} else { /* Set dummy CQs to be compatible with HV and PRM */
+		send_cq = to_mcq(rwq_ind_tbl->ind_tbl[0]->cq);
+		recv_cq = send_cq;
+	}
 	context->cqn_send = cpu_to_be32(send_cq->mcq.cqn);
 	context->cqn_recv = cpu_to_be32(recv_cq->mcq.cqn);
 	context->params1  = cpu_to_be32(MLX4_IB_ACK_REQ_FREQ << 28);
 
 	/* Set "fast registration enabled" for all kernel QPs */
-	if (!qp->ibqp.uobject)
+	if (!ibuobject)
 		context->params1 |= cpu_to_be32(1 << 11);
 
 	if (attr_mask & IB_QP_RNR_RETRY) {
@@ -1868,7 +2432,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		optpar |= MLX4_QP_OPTPAR_RWE | MLX4_QP_OPTPAR_RRE | MLX4_QP_OPTPAR_RAE;
 	}
 
-	if (ibqp->srq)
+	if (ibsrq)
 		context->params2 |= cpu_to_be32(MLX4_QP_BIT_RIC);
 
 	if (attr_mask & IB_QP_MIN_RNR_TIMER) {
@@ -1899,17 +2463,19 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		optpar |= MLX4_QP_OPTPAR_Q_KEY;
 	}
 
-	if (ibqp->srq)
-		context->srqn = cpu_to_be32(1 << 24 | to_msrq(ibqp->srq)->msrq.srqn);
+	if (ibsrq)
+		context->srqn = cpu_to_be32(1 << 24 |
+					    to_msrq(ibsrq)->msrq.srqn);
 
-	if (qp->rq.wqe_cnt && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
+	if (qp->rq.wqe_cnt &&
+	    cur_state == IB_QPS_RESET &&
+	    new_state == IB_QPS_INIT)
 		context->db_rec_addr = cpu_to_be64(qp->db.dma);
 
 	if (cur_state == IB_QPS_INIT &&
 	    new_state == IB_QPS_RTR  &&
-	    (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_SMI ||
-	     ibqp->qp_type == IB_QPT_UD ||
-	     ibqp->qp_type == IB_QPT_RAW_PACKET)) {
+	    (qp_type == IB_QPT_GSI || qp_type == IB_QPT_SMI ||
+	     qp_type == IB_QPT_UD || qp_type == IB_QPT_RAW_PACKET)) {
 		context->pri_path.sched_queue = (qp->port - 1) << 6;
 		if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_SMI ||
 		    qp->mlx4_ib_qp_type &
@@ -1942,7 +2508,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		}
 	}
 
-	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) {
+	if (qp_type == IB_QPT_RAW_PACKET) {
 		context->pri_path.ackto = (context->pri_path.ackto & 0xf8) |
 					MLX4_IB_LINK_TYPE_ETH;
 		if (dev->dev->caps.tunnel_offload_mode ==  MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
@@ -1952,7 +2518,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		}
 	}
 
-	if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
+	if (qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
 		int is_eth = rdma_port_get_link_layer(
 				&dev->ib_dev, qp->port) ==
 				IB_LINK_LAYER_ETHERNET;
@@ -1962,14 +2528,15 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		}
 	}
 
-
 	if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD	&&
 	    attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify)
 		sqd_event = 1;
 	else
 		sqd_event = 0;
 
-	if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
+	if (!ibuobject &&
+	    cur_state == IB_QPS_RESET &&
+	    new_state == IB_QPS_INIT)
 		context->rlkey_roce_mode |= (1 << 4);
 
 	/*
@@ -1978,7 +2545,9 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	 * headroom is stamped so that the hardware doesn't start
 	 * processing stale work requests.
 	 */
-	if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
+	if (!ibuobject &&
+	    cur_state == IB_QPS_RESET &&
+	    new_state == IB_QPS_INIT) {
 		struct mlx4_wqe_ctrl_seg *ctrl;
 		int i;
 
@@ -2035,9 +2604,9 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	 * entries and reinitialize the QP.
 	 */
 	if (new_state == IB_QPS_RESET) {
-		if (!ibqp->uobject) {
+		if (!ibuobject) {
 			mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
-					 ibqp->srq ? to_msrq(ibqp->srq) : NULL);
+					 ibsrq ? to_msrq(ibsrq) : NULL);
 			if (send_cq != recv_cq)
 				mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
 
@@ -2148,22 +2717,25 @@ out:
 	return err;
 }
 
+enum {
+	MLX4_IB_MODIFY_QP_RSS_SUP_ATTR_MSK = (IB_QP_STATE	|
+					      IB_QP_PORT),
+};
+
 static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 			      int attr_mask, struct ib_udata *udata)
 {
+	enum rdma_link_layer ll = IB_LINK_LAYER_UNSPECIFIED;
 	struct mlx4_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx4_ib_qp *qp = to_mqp(ibqp);
 	enum ib_qp_state cur_state, new_state;
 	int err = -EINVAL;
-	int ll;
 	mutex_lock(&qp->mutex);
 
 	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
-	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
-		ll = IB_LINK_LAYER_UNSPECIFIED;
-	} else {
+	if (cur_state != new_state || cur_state != IB_QPS_RESET) {
 		int port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
 		ll = rdma_port_get_link_layer(&dev->ib_dev, port);
 	}
@@ -2178,6 +2750,27 @@ static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		goto out;
 	}
 
+	if (ibqp->rwq_ind_tbl) {
+		if (!(((cur_state == IB_QPS_RESET) &&
+		       (new_state == IB_QPS_INIT)) ||
+		      ((cur_state == IB_QPS_INIT)  &&
+		       (new_state == IB_QPS_RTR)))) {
+			pr_debug("qpn 0x%x: RSS QP unsupported transition %d to %d\n",
+				 ibqp->qp_num, cur_state, new_state);
+
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+
+		if (attr_mask & ~MLX4_IB_MODIFY_QP_RSS_SUP_ATTR_MSK) {
+			pr_debug("qpn 0x%x: RSS QP unsupported attribute mask 0x%x for transition %d to %d\n",
+				 ibqp->qp_num, attr_mask, cur_state, new_state);
+
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+	}
+
 	if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT)) {
 		if ((cur_state == IB_QPS_RESET) && (new_state == IB_QPS_INIT)) {
 			if ((ibqp->qp_type == IB_QPT_RC) ||
@@ -2242,7 +2835,17 @@ static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		goto out;
 	}
 
-	err = __mlx4_ib_modify_qp(ibqp, attr, attr_mask, cur_state, new_state);
+	if (ibqp->rwq_ind_tbl && (new_state == IB_QPS_INIT)) {
+		err = bringup_rss_rwqs(ibqp->rwq_ind_tbl, attr->port_num);
+		if (err)
+			goto out;
+	}
+
+	err = __mlx4_ib_modify_qp(ibqp, MLX4_IB_QP_SRC, attr, attr_mask,
+				  cur_state, new_state);
+
+	if (ibqp->rwq_ind_tbl && err)
+		bring_down_rss_rwqs(ibqp->rwq_ind_tbl);
 
 	if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT))
 		attr->port_num = 1;
@@ -2277,9 +2880,9 @@ static int vf_get_qp0_qkey(struct mlx4_dev *dev, int qpn, u32 *qkey)
 {
 	int i;
 	for (i = 0; i < dev->caps.num_ports; i++) {
-		if (qpn == dev->caps.qp0_proxy[i] ||
-		    qpn == dev->caps.qp0_tunnel[i]) {
-			*qkey = dev->caps.qp0_qkey[i];
+		if (qpn == dev->caps.spec_qps[i].qp0_proxy ||
+		    qpn == dev->caps.spec_qps[i].qp0_tunnel) {
+			*qkey = dev->caps.spec_qps[i].qp0_qkey;
 			return 0;
 		}
 	}
@@ -2340,7 +2943,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
 		sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
 	else
 		sqp->ud_header.bth.destination_qpn =
-			cpu_to_be32(mdev->dev->caps.qp0_tunnel[sqp->qp.port - 1]);
+			cpu_to_be32(mdev->dev->caps.spec_qps[sqp->qp.port - 1].qp0_tunnel);
 
 	sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
 	if (mlx4_is_master(mdev->dev)) {
@@ -2800,9 +3403,9 @@ static void set_tunnel_datagram_seg(struct mlx4_ib_dev *dev,
 
 	memcpy(dseg->av, &sqp_av, sizeof (struct mlx4_av));
 	if (qpt == MLX4_IB_QPT_PROXY_GSI)
-		dseg->dqpn = cpu_to_be32(dev->dev->caps.qp1_tunnel[port - 1]);
+		dseg->dqpn = cpu_to_be32(dev->dev->caps.spec_qps[port - 1].qp1_tunnel);
 	else
-		dseg->dqpn = cpu_to_be32(dev->dev->caps.qp0_tunnel[port - 1]);
+		dseg->dqpn = cpu_to_be32(dev->dev->caps.spec_qps[port - 1].qp0_tunnel);
 	/* Use QKEY from the QP context, which is set by master */
 	dseg->qkey = cpu_to_be32(IB_QP_SET_QKEY);
 }
@@ -3432,6 +4035,9 @@ int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
 	int mlx4_state;
 	int err = 0;
 
+	if (ibqp->rwq_ind_tbl)
+		return -EOPNOTSUPP;
+
 	mutex_lock(&qp->mutex);
 
 	if (qp->state == IB_QPS_RESET) {
@@ -3527,3 +4133,285 @@ out:
 	return err;
 }
 
+struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd,
+				struct ib_wq_init_attr *init_attr,
+				struct ib_udata *udata)
+{
+	struct mlx4_ib_dev *dev;
+	struct ib_qp_init_attr ib_qp_init_attr;
+	struct mlx4_ib_qp *qp;
+	struct mlx4_ib_create_wq ucmd;
+	int err, required_cmd_sz;
+
+	if (!(udata && pd->uobject))
+		return ERR_PTR(-EINVAL);
+
+	required_cmd_sz = offsetof(typeof(ucmd), comp_mask) +
+			  sizeof(ucmd.comp_mask);
+	if (udata->inlen < required_cmd_sz) {
+		pr_debug("invalid inlen\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (udata->inlen > sizeof(ucmd) &&
+	    !ib_is_udata_cleared(udata, sizeof(ucmd),
+				 udata->inlen - sizeof(ucmd))) {
+		pr_debug("inlen is not supported\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (udata->outlen)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	dev = to_mdev(pd->device);
+
+	if (init_attr->wq_type != IB_WQT_RQ) {
+		pr_debug("unsupported wq type %d\n", init_attr->wq_type);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (init_attr->create_flags) {
+		pr_debug("unsupported create_flags %u\n",
+			 init_attr->create_flags);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+	if (!qp)
+		return ERR_PTR(-ENOMEM);
+
+	qp->pri.vid = 0xFFFF;
+	qp->alt.vid = 0xFFFF;
+
+	memset(&ib_qp_init_attr, 0, sizeof(ib_qp_init_attr));
+	ib_qp_init_attr.qp_context = init_attr->wq_context;
+	ib_qp_init_attr.qp_type = IB_QPT_RAW_PACKET;
+	ib_qp_init_attr.cap.max_recv_wr = init_attr->max_wr;
+	ib_qp_init_attr.cap.max_recv_sge = init_attr->max_sge;
+	ib_qp_init_attr.recv_cq = init_attr->cq;
+	ib_qp_init_attr.send_cq = ib_qp_init_attr.recv_cq; /* Dummy CQ */
+
+	err = create_qp_common(dev, pd, MLX4_IB_RWQ_SRC, &ib_qp_init_attr,
+			       udata, 0, &qp);
+	if (err) {
+		kfree(qp);
+		return ERR_PTR(err);
+	}
+
+	qp->ibwq.event_handler = init_attr->event_handler;
+	qp->ibwq.wq_num = qp->mqp.qpn;
+	qp->ibwq.state = IB_WQS_RESET;
+
+	return &qp->ibwq;
+}
+
+static int ib_wq2qp_state(enum ib_wq_state state)
+{
+	switch (state) {
+	case IB_WQS_RESET:
+		return IB_QPS_RESET;
+	case IB_WQS_RDY:
+		return IB_QPS_RTR;
+	default:
+		return IB_QPS_ERR;
+	}
+}
+
+static int _mlx4_ib_modify_wq(struct ib_wq *ibwq, enum ib_wq_state new_state)
+{
+	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
+	enum ib_qp_state qp_cur_state;
+	enum ib_qp_state qp_new_state;
+	int attr_mask;
+	int err;
+
+	/* ib_qp.state represents the WQ HW state while ib_wq.state represents
+	 * the WQ logic state.
+	 */
+	qp_cur_state = qp->state;
+	qp_new_state = ib_wq2qp_state(new_state);
+
+	if (ib_wq2qp_state(new_state) == qp_cur_state)
+		return 0;
+
+	if (new_state == IB_WQS_RDY) {
+		struct ib_qp_attr attr = {};
+
+		attr.port_num = qp->port;
+		attr_mask = IB_QP_PORT;
+
+		err = __mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, &attr,
+					  attr_mask, IB_QPS_RESET, IB_QPS_INIT);
+		if (err) {
+			pr_debug("WQN=0x%06x failed to apply RST->INIT on the HW QP\n",
+				 ibwq->wq_num);
+			return err;
+		}
+
+		qp_cur_state = IB_QPS_INIT;
+	}
+
+	attr_mask = 0;
+	err = __mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, NULL, attr_mask,
+				  qp_cur_state,  qp_new_state);
+
+	if (err && (qp_cur_state == IB_QPS_INIT)) {
+		qp_new_state = IB_QPS_RESET;
+		if (__mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, NULL,
+					attr_mask, IB_QPS_INIT, IB_QPS_RESET)) {
+			pr_warn("WQN=0x%06x failed with reverting HW's resources failure\n",
+				ibwq->wq_num);
+			qp_new_state = IB_QPS_INIT;
+		}
+	}
+
+	qp->state = qp_new_state;
+
+	return err;
+}
+
+int mlx4_ib_modify_wq(struct ib_wq *ibwq, struct ib_wq_attr *wq_attr,
+		      u32 wq_attr_mask, struct ib_udata *udata)
+{
+	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
+	struct mlx4_ib_modify_wq ucmd = {};
+	size_t required_cmd_sz;
+	enum ib_wq_state cur_state, new_state;
+	int err = 0;
+
+	required_cmd_sz = offsetof(typeof(ucmd), reserved) +
+				   sizeof(ucmd.reserved);
+	if (udata->inlen < required_cmd_sz)
+		return -EINVAL;
+
+	if (udata->inlen > sizeof(ucmd) &&
+	    !ib_is_udata_cleared(udata, sizeof(ucmd),
+				 udata->inlen - sizeof(ucmd)))
+		return -EOPNOTSUPP;
+
+	if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen)))
+		return -EFAULT;
+
+	if (ucmd.comp_mask || ucmd.reserved)
+		return -EOPNOTSUPP;
+
+	if (wq_attr_mask & IB_WQ_FLAGS)
+		return -EOPNOTSUPP;
+
+	cur_state = wq_attr_mask & IB_WQ_CUR_STATE ? wq_attr->curr_wq_state :
+						     ibwq->state;
+	new_state = wq_attr_mask & IB_WQ_STATE ? wq_attr->wq_state : cur_state;
+
+	if (cur_state  < IB_WQS_RESET || cur_state  > IB_WQS_ERR ||
+	    new_state < IB_WQS_RESET || new_state > IB_WQS_ERR)
+		return -EINVAL;
+
+	if ((new_state == IB_WQS_RDY) && (cur_state == IB_WQS_ERR))
+		return -EINVAL;
+
+	if ((new_state == IB_WQS_ERR) && (cur_state == IB_WQS_RESET))
+		return -EINVAL;
+
+	/* Need to protect against the parent RSS which also may modify WQ
+	 * state.
+	 */
+	mutex_lock(&qp->mutex);
+
+	/* Can update HW state only if a RSS QP has already associated to this
+	 * WQ, so we can apply its port on the WQ.
+	 */
+	if (qp->rss_usecnt)
+		err = _mlx4_ib_modify_wq(ibwq, new_state);
+
+	if (!err)
+		ibwq->state = new_state;
+
+	mutex_unlock(&qp->mutex);
+
+	return err;
+}
+
+int mlx4_ib_destroy_wq(struct ib_wq *ibwq)
+{
+	struct mlx4_ib_dev *dev = to_mdev(ibwq->device);
+	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
+
+	if (qp->counter_index)
+		mlx4_ib_free_qp_counter(dev, qp);
+
+	destroy_qp_common(dev, qp, MLX4_IB_RWQ_SRC, 1);
+
+	kfree(qp);
+
+	return 0;
+}
+
+struct ib_rwq_ind_table
+*mlx4_ib_create_rwq_ind_table(struct ib_device *device,
+			      struct ib_rwq_ind_table_init_attr *init_attr,
+			      struct ib_udata *udata)
+{
+	struct ib_rwq_ind_table *rwq_ind_table;
+	struct mlx4_ib_create_rwq_ind_tbl_resp resp = {};
+	unsigned int ind_tbl_size = 1 << init_attr->log_ind_tbl_size;
+	unsigned int base_wqn;
+	size_t min_resp_len;
+	int i;
+	int err;
+
+	if (udata->inlen > 0 &&
+	    !ib_is_udata_cleared(udata, 0,
+				 udata->inlen))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	min_resp_len = offsetof(typeof(resp), reserved) + sizeof(resp.reserved);
+	if (udata->outlen && udata->outlen < min_resp_len)
+		return ERR_PTR(-EINVAL);
+
+	if (ind_tbl_size >
+	    device->attrs.rss_caps.max_rwq_indirection_table_size) {
+		pr_debug("log_ind_tbl_size = %d is bigger than supported = %d\n",
+			 ind_tbl_size,
+			 device->attrs.rss_caps.max_rwq_indirection_table_size);
+		return ERR_PTR(-EINVAL);
+	}
+
+	base_wqn = init_attr->ind_tbl[0]->wq_num;
+
+	if (base_wqn % ind_tbl_size) {
+		pr_debug("WQN=0x%x isn't aligned with indirection table size\n",
+			 base_wqn);
+		return ERR_PTR(-EINVAL);
+	}
+
+	for (i = 1; i < ind_tbl_size; i++) {
+		if (++base_wqn != init_attr->ind_tbl[i]->wq_num) {
+			pr_debug("indirection table's WQNs aren't consecutive\n");
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	rwq_ind_table = kzalloc(sizeof(*rwq_ind_table), GFP_KERNEL);
+	if (!rwq_ind_table)
+		return ERR_PTR(-ENOMEM);
+
+	if (udata->outlen) {
+		resp.response_length = offsetof(typeof(resp), response_length) +
+					sizeof(resp.response_length);
+		err = ib_copy_to_udata(udata, &resp, resp.response_length);
+		if (err)
+			goto err;
+	}
+
+	return rwq_ind_table;
+
+err:
+	kfree(rwq_ind_table);
+	return ERR_PTR(err);
+}
+
+int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl)
+{
+	kfree(ib_rwq_ind_tbl);
+	return 0;
+}
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 0facaf5f6d23..ebee56cbc0e2 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -34,7 +34,6 @@
 #include <linux/mlx4/qp.h>
 #include <linux/mlx4/srq.h>
 #include <linux/slab.h>
-#include <linux/vmalloc.h>
 
 #include "mlx4_ib.h"
 #include <rdma/mlx4-abi.h>
@@ -171,20 +170,16 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		if (err)
 			goto err_mtt;
 
-		srq->wrid = kmalloc_array(srq->msrq.max, sizeof(u64),
-					GFP_KERNEL | __GFP_NOWARN);
+		srq->wrid = kvmalloc_array(srq->msrq.max,
+					   sizeof(u64), GFP_KERNEL);
 		if (!srq->wrid) {
-			srq->wrid = __vmalloc(srq->msrq.max * sizeof(u64),
-					      GFP_KERNEL, PAGE_KERNEL);
-			if (!srq->wrid) {
-				err = -ENOMEM;
-				goto err_mtt;
-			}
+			err = -ENOMEM;
+			goto err_mtt;
 		}
 	}
 
-	cqn = (init_attr->srq_type == IB_SRQT_XRC) ?
-		to_mcq(init_attr->ext.xrc.cq)->mcq.cqn : 0;
+	cqn = ib_srq_has_cq(init_attr->srq_type) ?
+		to_mcq(init_attr->ext.cq)->mcq.cqn : 0;
 	xrcdn = (init_attr->srq_type == IB_SRQT_XRC) ?
 		to_mxrcd(init_attr->ext.xrc.xrcd)->xrcdn :
 		(u16) dev->dev->caps.reserved_xrcds;
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index 0ba5ba7540c8..e219093d2764 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -221,7 +221,7 @@ void del_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num,
 static int add_port_entries(struct mlx4_ib_dev *device, int port_num)
 {
 	int i;
-	char buff[10];
+	char buff[11];
 	struct mlx4_ib_iov_port *port = NULL;
 	int ret = 0 ;
 	struct ib_port_attr attr;
diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile
index 90ad2adc752f..bc6299697dda 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 cmd.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 cong.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
index 18d5e1db93ed..470995fa38d2 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -57,3 +57,23 @@ int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
 	MLX5_SET(query_cong_statistics_in, in, clear, reset);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
 }
+
+int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
+			       void *out, int out_size)
+{
+	u32 in[MLX5_ST_SZ_DW(query_cong_params_in)] = { };
+
+	MLX5_SET(query_cong_params_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_CONG_PARAMS);
+	MLX5_SET(query_cong_params_in, in, cong_protocol, cong_point);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
+}
+
+int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *dev,
+				void *in, int in_size)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_cong_params_out)] = { };
+
+	return mlx5_cmd_exec(dev, in, in_size, out, sizeof(out));
+}
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index fa09228193a6..af4c24596274 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -39,4 +39,8 @@
 int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey);
 int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
 				bool reset, void *out, int out_size);
+int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
+			       void *out, int out_size);
+int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev,
+				void *in, int in_size);
 #endif /* MLX5_IB_CMD_H */
diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c
new file mode 100644
index 000000000000..2d32b519bb61
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/cong.c
@@ -0,0 +1,421 @@
+/*
+ * Copyright (c) 2013-2017, 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 <linux/debugfs.h>
+
+#include "mlx5_ib.h"
+#include "cmd.h"
+
+enum mlx5_ib_cong_node_type {
+	MLX5_IB_RROCE_ECN_RP = 1,
+	MLX5_IB_RROCE_ECN_NP = 2,
+};
+
+static const char * const mlx5_ib_dbg_cc_name[] = {
+	"rp_clamp_tgt_rate",
+	"rp_clamp_tgt_rate_ati",
+	"rp_time_reset",
+	"rp_byte_reset",
+	"rp_threshold",
+	"rp_ai_rate",
+	"rp_hai_rate",
+	"rp_min_dec_fac",
+	"rp_min_rate",
+	"rp_rate_to_set_on_first_cnp",
+	"rp_dce_tcp_g",
+	"rp_dce_tcp_rtt",
+	"rp_rate_reduce_monitor_period",
+	"rp_initial_alpha_value",
+	"rp_gd",
+	"np_cnp_dscp",
+	"np_cnp_prio_mode",
+	"np_cnp_prio",
+};
+
+#define MLX5_IB_RP_CLAMP_TGT_RATE_ATTR			BIT(1)
+#define MLX5_IB_RP_CLAMP_TGT_RATE_ATI_ATTR		BIT(2)
+#define MLX5_IB_RP_TIME_RESET_ATTR			BIT(3)
+#define MLX5_IB_RP_BYTE_RESET_ATTR			BIT(4)
+#define MLX5_IB_RP_THRESHOLD_ATTR			BIT(5)
+#define MLX5_IB_RP_AI_RATE_ATTR				BIT(7)
+#define MLX5_IB_RP_HAI_RATE_ATTR			BIT(8)
+#define MLX5_IB_RP_MIN_DEC_FAC_ATTR			BIT(9)
+#define MLX5_IB_RP_MIN_RATE_ATTR			BIT(10)
+#define MLX5_IB_RP_RATE_TO_SET_ON_FIRST_CNP_ATTR	BIT(11)
+#define MLX5_IB_RP_DCE_TCP_G_ATTR			BIT(12)
+#define MLX5_IB_RP_DCE_TCP_RTT_ATTR			BIT(13)
+#define MLX5_IB_RP_RATE_REDUCE_MONITOR_PERIOD_ATTR	BIT(14)
+#define MLX5_IB_RP_INITIAL_ALPHA_VALUE_ATTR		BIT(15)
+#define MLX5_IB_RP_GD_ATTR				BIT(16)
+
+#define MLX5_IB_NP_CNP_DSCP_ATTR			BIT(3)
+#define MLX5_IB_NP_CNP_PRIO_MODE_ATTR			BIT(4)
+
+static enum mlx5_ib_cong_node_type
+mlx5_ib_param_to_node(enum mlx5_ib_dbg_cc_types param_offset)
+{
+	if (param_offset >= MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE &&
+	    param_offset <= MLX5_IB_DBG_CC_RP_GD)
+		return MLX5_IB_RROCE_ECN_RP;
+	else
+		return MLX5_IB_RROCE_ECN_NP;
+}
+
+static u32 mlx5_get_cc_param_val(void *field, int offset)
+{
+	switch (offset) {
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				clamp_tgt_rate);
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				clamp_tgt_rate_after_time_inc);
+	case MLX5_IB_DBG_CC_RP_TIME_RESET:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_time_reset);
+	case MLX5_IB_DBG_CC_RP_BYTE_RESET:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_byte_reset);
+	case MLX5_IB_DBG_CC_RP_THRESHOLD:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_threshold);
+	case MLX5_IB_DBG_CC_RP_AI_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_ai_rate);
+	case MLX5_IB_DBG_CC_RP_HAI_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_hai_rate);
+	case MLX5_IB_DBG_CC_RP_MIN_DEC_FAC:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_min_dec_fac);
+	case MLX5_IB_DBG_CC_RP_MIN_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_min_rate);
+	case MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rate_to_set_on_first_cnp);
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_G:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				dce_tcp_g);
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_RTT:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				dce_tcp_rtt);
+	case MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rate_reduce_monitor_period);
+	case MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				initial_alpha_value);
+	case MLX5_IB_DBG_CC_RP_GD:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_gd);
+	case MLX5_IB_DBG_CC_NP_CNP_DSCP:
+		return MLX5_GET(cong_control_r_roce_ecn_np, field,
+				cnp_dscp);
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE:
+		return MLX5_GET(cong_control_r_roce_ecn_np, field,
+				cnp_prio_mode);
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO:
+		return MLX5_GET(cong_control_r_roce_ecn_np, field,
+				cnp_802p_prio);
+	default:
+		return 0;
+	}
+}
+
+static void mlx5_ib_set_cc_param_mask_val(void *field, int offset,
+					  u32 var, u32 *attr_mask)
+{
+	switch (offset) {
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE:
+		*attr_mask |= MLX5_IB_RP_CLAMP_TGT_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 clamp_tgt_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI:
+		*attr_mask |= MLX5_IB_RP_CLAMP_TGT_RATE_ATI_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 clamp_tgt_rate_after_time_inc, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_TIME_RESET:
+		*attr_mask |= MLX5_IB_RP_TIME_RESET_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_time_reset, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_BYTE_RESET:
+		*attr_mask |= MLX5_IB_RP_BYTE_RESET_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_byte_reset, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_THRESHOLD:
+		*attr_mask |= MLX5_IB_RP_THRESHOLD_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_threshold, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_AI_RATE:
+		*attr_mask |= MLX5_IB_RP_AI_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_ai_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_HAI_RATE:
+		*attr_mask |= MLX5_IB_RP_HAI_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_hai_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_MIN_DEC_FAC:
+		*attr_mask |= MLX5_IB_RP_MIN_DEC_FAC_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_min_dec_fac, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_MIN_RATE:
+		*attr_mask |= MLX5_IB_RP_MIN_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_min_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP:
+		*attr_mask |= MLX5_IB_RP_RATE_TO_SET_ON_FIRST_CNP_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rate_to_set_on_first_cnp, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_G:
+		*attr_mask |= MLX5_IB_RP_DCE_TCP_G_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 dce_tcp_g, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_RTT:
+		*attr_mask |= MLX5_IB_RP_DCE_TCP_RTT_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 dce_tcp_rtt, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD:
+		*attr_mask |= MLX5_IB_RP_RATE_REDUCE_MONITOR_PERIOD_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rate_reduce_monitor_period, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE:
+		*attr_mask |= MLX5_IB_RP_INITIAL_ALPHA_VALUE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 initial_alpha_value, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_GD:
+		*attr_mask |= MLX5_IB_RP_GD_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_gd, var);
+		break;
+	case MLX5_IB_DBG_CC_NP_CNP_DSCP:
+		*attr_mask |= MLX5_IB_NP_CNP_DSCP_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_dscp, var);
+		break;
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE:
+		*attr_mask |= MLX5_IB_NP_CNP_PRIO_MODE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, var);
+		break;
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO:
+		*attr_mask |= MLX5_IB_NP_CNP_PRIO_MODE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, 0);
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_802p_prio, var);
+		break;
+	}
+}
+
+static int mlx5_ib_get_cc_params(struct mlx5_ib_dev *dev, int offset, u32 *var)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_cong_params_out);
+	void *out;
+	void *field;
+	int err;
+	enum mlx5_ib_cong_node_type node;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	node = mlx5_ib_param_to_node(offset);
+
+	err = mlx5_cmd_query_cong_params(dev->mdev, node, out, outlen);
+	if (err)
+		goto free;
+
+	field = MLX5_ADDR_OF(query_cong_params_out, out, congestion_parameters);
+	*var = mlx5_get_cc_param_val(field, offset);
+
+free:
+	kvfree(out);
+	return err;
+}
+
+static int mlx5_ib_set_cc_params(struct mlx5_ib_dev *dev, int offset, u32 var)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_cong_params_in);
+	void *in;
+	void *field;
+	enum mlx5_ib_cong_node_type node;
+	u32 attr_mask = 0;
+	int err;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_cong_params_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_CONG_PARAMS);
+
+	node = mlx5_ib_param_to_node(offset);
+	MLX5_SET(modify_cong_params_in, in, cong_protocol, node);
+
+	field = MLX5_ADDR_OF(modify_cong_params_in, in, congestion_parameters);
+	mlx5_ib_set_cc_param_mask_val(field, offset, var, &attr_mask);
+
+	field = MLX5_ADDR_OF(modify_cong_params_in, in, field_select);
+	MLX5_SET(field_select_r_roce_rp, field, field_select_r_roce_rp,
+		 attr_mask);
+
+	err = mlx5_cmd_modify_cong_params(dev->mdev, in, inlen);
+	kvfree(in);
+	return err;
+}
+
+static ssize_t set_param(struct file *filp, const char __user *buf,
+			 size_t count, loff_t *pos)
+{
+	struct mlx5_ib_dbg_param *param = filp->private_data;
+	int offset = param->offset;
+	char lbuf[11] = { };
+	u32 var;
+	int ret;
+
+	if (count > sizeof(lbuf))
+		return -EINVAL;
+
+	if (copy_from_user(lbuf, buf, count))
+		return -EFAULT;
+
+	lbuf[sizeof(lbuf) - 1] = '\0';
+
+	if (kstrtou32(lbuf, 0, &var))
+		return -EINVAL;
+
+	ret = mlx5_ib_set_cc_params(param->dev, offset, var);
+	return ret ? ret : count;
+}
+
+static ssize_t get_param(struct file *filp, char __user *buf, size_t count,
+			 loff_t *pos)
+{
+	struct mlx5_ib_dbg_param *param = filp->private_data;
+	int offset = param->offset;
+	u32 var = 0;
+	int ret;
+	char lbuf[11];
+
+	if (*pos)
+		return 0;
+
+	ret = mlx5_ib_get_cc_params(param->dev, offset, &var);
+	if (ret)
+		return ret;
+
+	ret = snprintf(lbuf, sizeof(lbuf), "%d\n", var);
+	if (ret < 0)
+		return ret;
+
+	if (copy_to_user(buf, lbuf, ret))
+		return -EFAULT;
+
+	*pos += ret;
+	return ret;
+}
+
+static const struct file_operations dbg_cc_fops = {
+	.owner	= THIS_MODULE,
+	.open	= simple_open,
+	.write	= set_param,
+	.read	= get_param,
+};
+
+void mlx5_ib_cleanup_cong_debugfs(struct mlx5_ib_dev *dev)
+{
+	if (!mlx5_debugfs_root ||
+	    !dev->dbg_cc_params ||
+	    !dev->dbg_cc_params->root)
+		return;
+
+	debugfs_remove_recursive(dev->dbg_cc_params->root);
+	kfree(dev->dbg_cc_params);
+	dev->dbg_cc_params = NULL;
+}
+
+int mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_ib_dbg_cc_params *dbg_cc_params;
+	int i;
+
+	if (!mlx5_debugfs_root)
+		goto out;
+
+	if (!MLX5_CAP_GEN(dev->mdev, cc_query_allowed) ||
+	    !MLX5_CAP_GEN(dev->mdev, cc_modify_allowed))
+		goto out;
+
+	dbg_cc_params = kzalloc(sizeof(*dbg_cc_params), GFP_KERNEL);
+	if (!dbg_cc_params)
+		goto out;
+
+	dev->dbg_cc_params = dbg_cc_params;
+
+	dbg_cc_params->root = debugfs_create_dir("cc_params",
+						 dev->mdev->priv.dbg_root);
+	if (!dbg_cc_params->root)
+		goto err;
+
+	for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) {
+		dbg_cc_params->params[i].offset = i;
+		dbg_cc_params->params[i].dev = dev;
+		dbg_cc_params->params[i].dentry =
+			debugfs_create_file(mlx5_ib_dbg_cc_name[i],
+					    0600, dbg_cc_params->root,
+					    &dbg_cc_params->params[i],
+					    &dbg_cc_fops);
+		if (!dbg_cc_params->params[i].dentry)
+			goto err;
+	}
+out:	return 0;
+
+err:
+	mlx5_ib_warn(dev, "cong debugfs failure\n");
+	mlx5_ib_cleanup_cong_debugfs(dev);
+	/*
+	 * We don't want to fail driver if debugfs failed to initialize,
+	 * so we are not forwarding error to the user.
+	 */
+	return 0;
+}
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index a384d72ea3cd..2aa53f427685 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -499,7 +499,7 @@ static void mlx5_ib_poll_sw_comp(struct mlx5_ib_cq *cq, int num_entries,
 	struct mlx5_ib_qp *qp;
 
 	*npolled = 0;
-	/* Find uncompleted WQEs belonging to that cq and retrun mmics ones */
+	/* Find uncompleted WQEs belonging to that cq and return mmics ones */
 	list_for_each_entry(qp, &cq->list_send_qp, cq_send_list) {
 		sw_send_comp(qp, num_entries, wc + *npolled, npolled);
 		if (*npolled >= num_entries)
@@ -751,10 +751,8 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	void *cqc;
 	int err;
 
-	ucmdlen =
-		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
-		 sizeof(ucmd)) ? (sizeof(ucmd) -
-				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+	ucmdlen = udata->inlen < sizeof(ucmd) ?
+		  (sizeof(ucmd) - sizeof(ucmd.reserved)) : sizeof(ucmd);
 
 	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
 		return -EFAULT;
diff --git a/drivers/infiniband/hw/mlx5/ib_virt.c b/drivers/infiniband/hw/mlx5/ib_virt.c
index c1b9de800fe5..649a3364f838 100644
--- a/drivers/infiniband/hw/mlx5/ib_virt.c
+++ b/drivers/infiniband/hw/mlx5/ib_virt.c
@@ -96,6 +96,7 @@ int mlx5_ib_set_vf_link_state(struct ib_device *device, int vf,
 	struct mlx5_ib_dev *dev = to_mdev(device);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	struct mlx5_hca_vport_context *in;
+	struct mlx5_vf_context *vfs_ctx = mdev->priv.sriov.vfs_ctx;
 	int err;
 
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
@@ -109,6 +110,8 @@ int mlx5_ib_set_vf_link_state(struct ib_device *device, int vf,
 	}
 	in->field_select = MLX5_HCA_VPORT_SEL_STATE_POLICY;
 	err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in);
+	if (!err)
+		vfs_ctx[vf].policy = in->policy;
 
 out:
 	kfree(in);
@@ -151,6 +154,7 @@ static int set_vf_node_guid(struct ib_device *device, int vf, u8 port, u64 guid)
 	struct mlx5_ib_dev *dev = to_mdev(device);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	struct mlx5_hca_vport_context *in;
+	struct mlx5_vf_context *vfs_ctx = mdev->priv.sriov.vfs_ctx;
 	int err;
 
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
@@ -160,6 +164,8 @@ static int set_vf_node_guid(struct ib_device *device, int vf, u8 port, u64 guid)
 	in->field_select = MLX5_HCA_VPORT_SEL_NODE_GUID;
 	in->node_guid = guid;
 	err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in);
+	if (!err)
+		vfs_ctx[vf].node_guid = guid;
 	kfree(in);
 	return err;
 }
@@ -169,6 +175,7 @@ static int set_vf_port_guid(struct ib_device *device, int vf, u8 port, u64 guid)
 	struct mlx5_ib_dev *dev = to_mdev(device);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	struct mlx5_hca_vport_context *in;
+	struct mlx5_vf_context *vfs_ctx = mdev->priv.sriov.vfs_ctx;
 	int err;
 
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
@@ -178,6 +185,8 @@ static int set_vf_port_guid(struct ib_device *device, int vf, u8 port, u64 guid)
 	in->field_select = MLX5_HCA_VPORT_SEL_PORT_GUID;
 	in->port_guid = guid;
 	err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in);
+	if (!err)
+		vfs_ctx[vf].port_guid = guid;
 	kfree(in);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 95db929bdc34..1003b0133a49 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -78,7 +78,7 @@ static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	u16 slid;
 	int err;
 
-	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0)
 		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
@@ -204,7 +204,7 @@ static int process_pma_cmd(struct ib_device *ibdev, u8 port_num,
 	int err;
 	void *out_cnt;
 
-	/* Decalring support of extended counters */
+	/* Declaring support of extended counters */
 	if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) {
 		struct ib_class_port_info cpi = {};
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index a7f2e60085c4..ab3c562d5ba7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/debugfs.h>
 #include <linux/highmem.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -58,6 +59,7 @@
 #include <linux/mlx5/vport.h>
 #include "mlx5_ib.h"
 #include "cmd.h"
+#include <linux/mlx5/vport.h>
 
 #define DRIVER_NAME "mlx5_ib"
 #define DRIVER_VERSION "5.0-0"
@@ -65,7 +67,6 @@
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRIVER_VERSION);
 
 static char mlx5_version[] =
 	DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v"
@@ -97,6 +98,20 @@ mlx5_ib_port_link_layer(struct ib_device *device, u8 port_num)
 	return mlx5_port_type_cap_to_rdma_ll(port_type_cap);
 }
 
+static int get_port_state(struct ib_device *ibdev,
+			  u8 port_num,
+			  enum ib_port_state *state)
+{
+	struct ib_port_attr attr;
+	int ret;
+
+	memset(&attr, 0, sizeof(attr));
+	ret = mlx5_ib_query_port(ibdev, port_num, &attr);
+	if (!ret)
+		*state = attr.state;
+	return ret;
+}
+
 static int mlx5_netdev_event(struct notifier_block *this,
 			     unsigned long event, void *ptr)
 {
@@ -114,6 +129,7 @@ static int mlx5_netdev_event(struct notifier_block *this,
 		write_unlock(&ibdev->roce.netdev_lock);
 		break;
 
+	case NETDEV_CHANGE:
 	case NETDEV_UP:
 	case NETDEV_DOWN: {
 		struct net_device *lag_ndev = mlx5_lag_get_roce_netdev(ibdev->mdev);
@@ -127,10 +143,23 @@ static int mlx5_netdev_event(struct notifier_block *this,
 		if ((upper == ndev || (!upper && ndev == ibdev->roce.netdev))
 		    && ibdev->ib_active) {
 			struct ib_event ibev = { };
+			enum ib_port_state port_state;
 
+			if (get_port_state(&ibdev->ib_dev, 1, &port_state))
+				return NOTIFY_DONE;
+
+			if (ibdev->roce.last_port_state == port_state)
+				return NOTIFY_DONE;
+
+			ibdev->roce.last_port_state = port_state;
 			ibev.device = &ibdev->ib_dev;
-			ibev.event = (event == NETDEV_UP) ?
-				     IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
+			if (port_state == IB_PORT_DOWN)
+				ibev.event = IB_EVENT_PORT_ERR;
+			else if (port_state == IB_PORT_ACTIVE)
+				ibev.event = IB_EVENT_PORT_ACTIVE;
+			else
+				return NOTIFY_DONE;
+
 			ibev.element.port_num = 1;
 			ib_dispatch_event(&ibev);
 		}
@@ -668,6 +697,14 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_UD_TSO;
 	}
 
+	if (MLX5_CAP_GEN(dev->mdev, rq_delay_drop) &&
+	    MLX5_CAP_GEN(dev->mdev, general_notification_event))
+		props->raw_packet_caps |= IB_RAW_PACKET_CAP_DELAY_DROP;
+
+	if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads) &&
+	    MLX5_CAP_IPOIB_ENHANCED(mdev, csum_cap))
+		props->device_cap_flags |= IB_DEVICE_UD_IP_CSUM;
+
 	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
 	    MLX5_CAP_ETH(dev->mdev, scatter_fcs)) {
 		/* Legacy bit to support old userspace libraries */
@@ -740,6 +777,16 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			1 << MLX5_CAP_GEN(dev->mdev, log_max_rq);
 	}
 
+	if (MLX5_CAP_GEN(mdev, tag_matching)) {
+		props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
+		props->xrq_caps.max_num_tags =
+			(1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1;
+		props->xrq_caps.flags = IB_TM_CAP_RC;
+		props->xrq_caps.max_ops =
+			1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
+		props->xrq_caps.max_sge = MLX5_TM_MAX_SGE;
+	}
+
 	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
 		resp.cqe_comp_caps.max_num =
 			MLX5_CAP_GEN(dev->mdev, cqe_compression) ?
@@ -765,8 +812,14 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 
 	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);
+		if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
+			resp.mlx5_ib_support_multi_pkt_send_wqes =
+				MLX5_IB_ALLOW_MPW;
+
+		if (MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe))
+			resp.mlx5_ib_support_multi_pkt_send_wqes |=
+				MLX5_IB_SUPPORT_EMPW;
+
 		resp.response_length +=
 			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
 	}
@@ -774,6 +827,27 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	if (field_avail(typeof(resp), reserved, uhw->outlen))
 		resp.response_length += sizeof(resp.reserved);
 
+	if (field_avail(typeof(resp), sw_parsing_caps,
+			uhw->outlen)) {
+		resp.response_length += sizeof(resp.sw_parsing_caps);
+		if (MLX5_CAP_ETH(mdev, swp)) {
+			resp.sw_parsing_caps.sw_parsing_offloads |=
+				MLX5_IB_SW_PARSING;
+
+			if (MLX5_CAP_ETH(mdev, swp_csum))
+				resp.sw_parsing_caps.sw_parsing_offloads |=
+					MLX5_IB_SW_PARSING_CSUM;
+
+			if (MLX5_CAP_ETH(mdev, swp_lso))
+				resp.sw_parsing_caps.sw_parsing_offloads |=
+					MLX5_IB_SW_PARSING_LSO;
+
+			if (resp.sw_parsing_caps.sw_parsing_offloads)
+				resp.sw_parsing_caps.supported_qpts =
+					BIT(IB_QPT_RAW_PACKET);
+		}
+	}
+
 	if (uhw->outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
@@ -1085,6 +1159,12 @@ static int mlx5_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 	bool is_ib = (mlx5_ib_port_link_layer(ibdev, port) ==
 		      IB_LINK_LAYER_INFINIBAND);
 
+	/* CM layer calls ib_modify_port() regardless of the link layer. For
+	 * Ethernet ports, qkey violation and Port capabilities are meaningless.
+	 */
+	if (!is_ib)
+		return 0;
+
 	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;
@@ -1138,7 +1218,7 @@ static int calc_total_bfregs(struct mlx5_ib_dev *dev, bool lib_uar_4k,
 	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_ib_dbg(dev, "uar_4k: fw support %s, lib support %s, user requested %d bfregs, allocated %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);
@@ -1187,6 +1267,45 @@ static int deallocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *con
 	return 0;
 }
 
+static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn)
+{
+	int err;
+
+	err = mlx5_core_alloc_transport_domain(dev->mdev, tdn);
+	if (err)
+		return err;
+
+	if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) ||
+	    !MLX5_CAP_GEN(dev->mdev, disable_local_lb))
+		return err;
+
+	mutex_lock(&dev->lb_mutex);
+	dev->user_td++;
+
+	if (dev->user_td == 2)
+		err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
+
+	mutex_unlock(&dev->lb_mutex);
+	return err;
+}
+
+static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn)
+{
+	mlx5_core_dealloc_transport_domain(dev->mdev, tdn);
+
+	if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) ||
+	    !MLX5_CAP_GEN(dev->mdev, disable_local_lb))
+		return;
+
+	mutex_lock(&dev->lb_mutex);
+	dev->user_td--;
+
+	if (dev->user_td < 2)
+		mlx5_nic_vport_update_local_lb(dev->mdev, false);
+
+	mutex_unlock(&dev->lb_mutex);
+}
+
 static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 						  struct ib_udata *udata)
 {
@@ -1197,7 +1316,6 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_bfreg_info *bfregi;
 	int ver;
 	int err;
-	size_t reqlen;
 	size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
 				     max_cqe_version);
 	bool lib_uar_4k;
@@ -1205,18 +1323,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
 
-	if (udata->inlen < sizeof(struct ib_uverbs_cmd_hdr))
-		return ERR_PTR(-EINVAL);
-
-	reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr);
-	if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
+	if (udata->inlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
 		ver = 0;
-	else if (reqlen >= min_req_v2)
+	else if (udata->inlen >= min_req_v2)
 		ver = 2;
 	else
 		return ERR_PTR(-EINVAL);
 
-	err = ib_copy_from_udata(&req, udata, min(reqlen, sizeof(req)));
+	err = ib_copy_from_udata(&req, udata, min(udata->inlen, sizeof(req)));
 	if (err)
 		return ERR_PTR(err);
 
@@ -1295,8 +1409,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	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);
+		err = mlx5_ib_alloc_transport_domain(dev, &context->tdn);
 		if (err)
 			goto out_page;
 	}
@@ -1362,7 +1475,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 
 out_td:
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
-		mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
+		mlx5_ib_dealloc_transport_domain(dev, context->tdn);
 
 out_page:
 	free_page(context->upd_xlt_page);
@@ -1390,7 +1503,7 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
 
 	bfregi = &context->bfregi;
 	if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
-		mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
+		mlx5_ib_dealloc_transport_domain(dev, context->tdn);
 
 	free_page(context->upd_xlt_page);
 	deallocate_uars(dev, context);
@@ -2028,23 +2141,34 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
  * it won't fall into the multicast flow steering table and this rule
  * could steal other multicast packets.
  */
-static bool flow_is_multicast_only(struct ib_flow_attr *ib_attr)
+static bool flow_is_multicast_only(const struct ib_flow_attr *ib_attr)
 {
-	struct ib_flow_spec_eth *eth_spec;
+	union ib_flow_spec *flow_spec;
 
 	if (ib_attr->type != IB_FLOW_ATTR_NORMAL ||
-	    ib_attr->size < sizeof(struct ib_flow_attr) +
-	    sizeof(struct ib_flow_spec_eth) ||
 	    ib_attr->num_of_specs < 1)
 		return false;
 
-	eth_spec = (struct ib_flow_spec_eth *)(ib_attr + 1);
-	if (eth_spec->type != IB_FLOW_SPEC_ETH ||
-	    eth_spec->size != sizeof(*eth_spec))
+	flow_spec = (union ib_flow_spec *)(ib_attr + 1);
+	if (flow_spec->type == IB_FLOW_SPEC_IPV4) {
+		struct ib_flow_spec_ipv4 *ipv4_spec;
+
+		ipv4_spec = (struct ib_flow_spec_ipv4 *)flow_spec;
+		if (ipv4_is_multicast(ipv4_spec->val.dst_ip))
+			return true;
+
 		return false;
+	}
+
+	if (flow_spec->type == IB_FLOW_SPEC_ETH) {
+		struct ib_flow_spec_eth *eth_spec;
+
+		eth_spec = (struct ib_flow_spec_eth *)flow_spec;
+		return is_multicast_ether_addr(eth_spec->mask.dst_mac) &&
+		       is_multicast_ether_addr(eth_spec->val.dst_mac);
+	}
 
-	return is_multicast_ether_addr(eth_spec->mask.dst_mac) &&
-	       is_multicast_ether_addr(eth_spec->val.dst_mac);
+	return false;
 }
 
 static bool is_valid_ethertype(struct mlx5_core_dev *mdev,
@@ -2229,10 +2353,31 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
 	return err ? ERR_PTR(err) : prio;
 }
 
-static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
-						     struct mlx5_ib_flow_prio *ft_prio,
-						     const struct ib_flow_attr *flow_attr,
-						     struct mlx5_flow_destination *dst)
+static void set_underlay_qp(struct mlx5_ib_dev *dev,
+			    struct mlx5_flow_spec *spec,
+			    u32 underlay_qpn)
+{
+	void *misc_params_c = MLX5_ADDR_OF(fte_match_param,
+					   spec->match_criteria,
+					   misc_parameters);
+	void *misc_params_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+					   misc_parameters);
+
+	if (underlay_qpn &&
+	    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
+				      ft_field_support.bth_dst_qp)) {
+		MLX5_SET(fte_match_set_misc,
+			 misc_params_v, bth_dst_qp, underlay_qpn);
+		MLX5_SET(fte_match_set_misc,
+			 misc_params_c, bth_dst_qp, 0xffffff);
+	}
+}
+
+static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
+						      struct mlx5_ib_flow_prio *ft_prio,
+						      const struct ib_flow_attr *flow_attr,
+						      struct mlx5_flow_destination *dst,
+						      u32 underlay_qpn)
 {
 	struct mlx5_flow_table	*ft = ft_prio->flow_table;
 	struct mlx5_ib_flow_handler *handler;
@@ -2268,6 +2413,9 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 		ib_flow += ((union ib_flow_spec *)ib_flow)->size;
 	}
 
+	if (!flow_is_multicast_only(flow_attr))
+		set_underlay_qp(dev, spec, underlay_qpn);
+
 	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
 	if (is_drop) {
 		flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
@@ -2307,6 +2455,14 @@ free:
 	return err ? ERR_PTR(err) : handler;
 }
 
+static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
+						     struct mlx5_ib_flow_prio *ft_prio,
+						     const struct ib_flow_attr *flow_attr,
+						     struct mlx5_flow_destination *dst)
+{
+	return _create_flow_rule(dev, ft_prio, flow_attr, dst, 0);
+}
+
 static struct mlx5_ib_flow_handler *create_dont_trap_rule(struct mlx5_ib_dev *dev,
 							  struct mlx5_ib_flow_prio *ft_prio,
 							  struct ib_flow_attr *flow_attr,
@@ -2443,6 +2599,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 	struct mlx5_ib_flow_prio *ft_prio_tx = NULL;
 	struct mlx5_ib_flow_prio *ft_prio;
 	int err;
+	int underlay_qpn;
 
 	if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO)
 		return ERR_PTR(-ENOMEM);
@@ -2483,8 +2640,10 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 			handler = create_dont_trap_rule(dev, ft_prio,
 							flow_attr, dst);
 		} else {
-			handler = create_flow_rule(dev, ft_prio, flow_attr,
-						   dst);
+			underlay_qpn = (mqp->flags & MLX5_IB_QP_UNDERLAY) ?
+					mqp->underlay_qpn : 0;
+			handler = _create_flow_rule(dev, ft_prio, flow_attr,
+						    dst, underlay_qpn);
 		}
 	} else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
 		   flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
@@ -2522,8 +2681,14 @@ unlock:
 static int mlx5_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
+	struct mlx5_ib_qp *mqp = to_mqp(ibqp);
 	int err;
 
+	if (mqp->flags & MLX5_IB_QP_UNDERLAY) {
+		mlx5_ib_dbg(dev, "Attaching a multi cast group to underlay QP is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
 	err = mlx5_core_attach_mcg(dev->mdev, gid, ibqp->qp_num);
 	if (err)
 		mlx5_ib_warn(dev, "failed attaching QPN 0x%x, MGID %pI6\n",
@@ -2685,6 +2850,26 @@ static void mlx5_ib_handle_internal_error(struct mlx5_ib_dev *ibdev)
 	spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags);
 }
 
+static void delay_drop_handler(struct work_struct *work)
+{
+	int err;
+	struct mlx5_ib_delay_drop *delay_drop =
+		container_of(work, struct mlx5_ib_delay_drop,
+			     delay_drop_work);
+
+	atomic_inc(&delay_drop->events_cnt);
+
+	mutex_lock(&delay_drop->lock);
+	err = mlx5_core_set_delay_drop(delay_drop->dev->mdev,
+				       delay_drop->timeout);
+	if (err) {
+		mlx5_ib_warn(delay_drop->dev, "Failed to set delay drop, timeout=%u\n",
+			     delay_drop->timeout);
+		delay_drop->activate = false;
+	}
+	mutex_unlock(&delay_drop->lock);
+}
+
 static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 			  enum mlx5_dev_event event, unsigned long param)
 {
@@ -2737,8 +2922,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 		ibev.event = IB_EVENT_CLIENT_REREGISTER;
 		port = (u8)param;
 		break;
+	case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT:
+		schedule_work(&ibdev->delay_drop.delay_drop_work);
+		goto out;
 	default:
-		return;
+		goto out;
 	}
 
 	ibev.device	      = &ibdev->ib_dev;
@@ -2746,7 +2934,7 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 
 	if (port < 1 || port > ibdev->num_ports) {
 		mlx5_ib_warn(ibdev, "warning: event on port %d\n", port);
-		return;
+		goto out;
 	}
 
 	if (ibdev->ib_active)
@@ -2754,6 +2942,9 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 
 	if (fatal)
 		ibdev->ib_active = false;
+
+out:
+	return;
 }
 
 static int set_has_smi_cap(struct mlx5_ib_dev *dev)
@@ -3036,7 +3227,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	attr.attr.max_sge = 1;
 	attr.attr.max_wr = 1;
 	attr.srq_type = IB_SRQT_XRC;
-	attr.ext.xrc.cq = devr->c0;
+	attr.ext.cq = devr->c0;
 	attr.ext.xrc.xrcd = devr->x0;
 
 	devr->s0 = mlx5_ib_create_srq(devr->p0, &attr, NULL);
@@ -3051,9 +3242,9 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->s0->srq_context   = NULL;
 	devr->s0->srq_type      = IB_SRQT_XRC;
 	devr->s0->ext.xrc.xrcd	= devr->x0;
-	devr->s0->ext.xrc.cq	= devr->c0;
+	devr->s0->ext.cq	= devr->c0;
 	atomic_inc(&devr->s0->ext.xrc.xrcd->usecnt);
-	atomic_inc(&devr->s0->ext.xrc.cq->usecnt);
+	atomic_inc(&devr->s0->ext.cq->usecnt);
 	atomic_inc(&devr->p0->usecnt);
 	atomic_set(&devr->s0->usecnt, 0);
 
@@ -3072,9 +3263,9 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->s1->event_handler = NULL;
 	devr->s1->srq_context   = NULL;
 	devr->s1->srq_type      = IB_SRQT_BASIC;
-	devr->s1->ext.xrc.cq	= devr->c0;
+	devr->s1->ext.cq	= devr->c0;
 	atomic_inc(&devr->p0->usecnt);
-	atomic_set(&devr->s0->usecnt, 0);
+	atomic_set(&devr->s1->usecnt, 0);
 
 	for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) {
 		INIT_WORK(&devr->ports[port].pkey_change_work,
@@ -3167,13 +3358,13 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *ibdev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct mlx5_ib_dev *dev =
 		container_of(ibdev, struct mlx5_ib_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%04d", fw_rev_maj(dev->mdev),
-		       fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%04d",
+		 fw_rev_maj(dev->mdev), fw_rev_min(dev->mdev),
+		 fw_rev_sub(dev->mdev));
 }
 
 static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
@@ -3313,6 +3504,17 @@ static const struct mlx5_ib_counter cong_cnts[] = {
 	INIT_CONG_COUNTER(np_cnp_sent),
 };
 
+static const struct mlx5_ib_counter extended_err_cnts[] = {
+	INIT_Q_COUNTER(resp_local_length_error),
+	INIT_Q_COUNTER(resp_cqe_error),
+	INIT_Q_COUNTER(req_cqe_error),
+	INIT_Q_COUNTER(req_remote_invalid_request),
+	INIT_Q_COUNTER(req_remote_access_errors),
+	INIT_Q_COUNTER(resp_remote_access_errors),
+	INIT_Q_COUNTER(resp_cqe_flush_error),
+	INIT_Q_COUNTER(req_cqe_flush_error),
+};
+
 static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev)
 {
 	unsigned int i;
@@ -3337,6 +3539,10 @@ static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev,
 
 	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters))
 		num_counters += ARRAY_SIZE(retrans_q_cnts);
+
+	if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters))
+		num_counters += ARRAY_SIZE(extended_err_cnts);
+
 	cnts->num_q_counters = num_counters;
 
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
@@ -3386,6 +3592,13 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev,
 		}
 	}
 
+	if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters)) {
+		for (i = 0; i < ARRAY_SIZE(extended_err_cnts); i++, j++) {
+			names[j] = extended_err_cnts[i].name;
+			offsets[j] = extended_err_cnts[i].offset;
+		}
+	}
+
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
 		for (i = 0; i < ARRAY_SIZE(cong_cnts); i++, j++) {
 			names[j] = cong_cnts[i].name;
@@ -3556,6 +3769,136 @@ mlx5_ib_alloc_rdma_netdev(struct ib_device *hca,
 	return netdev;
 }
 
+static void delay_drop_debugfs_cleanup(struct mlx5_ib_dev *dev)
+{
+	if (!dev->delay_drop.dbg)
+		return;
+	debugfs_remove_recursive(dev->delay_drop.dbg->dir_debugfs);
+	kfree(dev->delay_drop.dbg);
+	dev->delay_drop.dbg = NULL;
+}
+
+static void cancel_delay_drop(struct mlx5_ib_dev *dev)
+{
+	if (!(dev->ib_dev.attrs.raw_packet_caps & IB_RAW_PACKET_CAP_DELAY_DROP))
+		return;
+
+	cancel_work_sync(&dev->delay_drop.delay_drop_work);
+	delay_drop_debugfs_cleanup(dev);
+}
+
+static ssize_t delay_drop_timeout_read(struct file *filp, char __user *buf,
+				       size_t count, loff_t *pos)
+{
+	struct mlx5_ib_delay_drop *delay_drop = filp->private_data;
+	char lbuf[20];
+	int len;
+
+	len = snprintf(lbuf, sizeof(lbuf), "%u\n", delay_drop->timeout);
+	return simple_read_from_buffer(buf, count, pos, lbuf, len);
+}
+
+static ssize_t delay_drop_timeout_write(struct file *filp, const char __user *buf,
+					size_t count, loff_t *pos)
+{
+	struct mlx5_ib_delay_drop *delay_drop = filp->private_data;
+	u32 timeout;
+	u32 var;
+
+	if (kstrtouint_from_user(buf, count, 0, &var))
+		return -EFAULT;
+
+	timeout = min_t(u32, roundup(var, 100), MLX5_MAX_DELAY_DROP_TIMEOUT_MS *
+			1000);
+	if (timeout != var)
+		mlx5_ib_dbg(delay_drop->dev, "Round delay drop timeout to %u usec\n",
+			    timeout);
+
+	delay_drop->timeout = timeout;
+
+	return count;
+}
+
+static const struct file_operations fops_delay_drop_timeout = {
+	.owner	= THIS_MODULE,
+	.open	= simple_open,
+	.write	= delay_drop_timeout_write,
+	.read	= delay_drop_timeout_read,
+};
+
+static int delay_drop_debugfs_init(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_ib_dbg_delay_drop *dbg;
+
+	if (!mlx5_debugfs_root)
+		return 0;
+
+	dbg = kzalloc(sizeof(*dbg), GFP_KERNEL);
+	if (!dbg)
+		return -ENOMEM;
+
+	dbg->dir_debugfs =
+		debugfs_create_dir("delay_drop",
+				   dev->mdev->priv.dbg_root);
+	if (!dbg->dir_debugfs)
+		return -ENOMEM;
+
+	dbg->events_cnt_debugfs =
+		debugfs_create_atomic_t("num_timeout_events", 0400,
+					dbg->dir_debugfs,
+					&dev->delay_drop.events_cnt);
+	if (!dbg->events_cnt_debugfs)
+		goto out_debugfs;
+
+	dbg->rqs_cnt_debugfs =
+		debugfs_create_atomic_t("num_rqs", 0400,
+					dbg->dir_debugfs,
+					&dev->delay_drop.rqs_cnt);
+	if (!dbg->rqs_cnt_debugfs)
+		goto out_debugfs;
+
+	dbg->timeout_debugfs =
+		debugfs_create_file("timeout", 0600,
+				    dbg->dir_debugfs,
+				    &dev->delay_drop,
+				    &fops_delay_drop_timeout);
+	if (!dbg->timeout_debugfs)
+		goto out_debugfs;
+
+	dev->delay_drop.dbg = dbg;
+
+	return 0;
+
+out_debugfs:
+	delay_drop_debugfs_cleanup(dev);
+	return -ENOMEM;
+}
+
+static void init_delay_drop(struct mlx5_ib_dev *dev)
+{
+	if (!(dev->ib_dev.attrs.raw_packet_caps & IB_RAW_PACKET_CAP_DELAY_DROP))
+		return;
+
+	mutex_init(&dev->delay_drop.lock);
+	dev->delay_drop.dev = dev;
+	dev->delay_drop.activate = false;
+	dev->delay_drop.timeout = MLX5_MAX_DELAY_DROP_TIMEOUT_MS * 1000;
+	INIT_WORK(&dev->delay_drop.delay_drop_work, delay_drop_handler);
+	atomic_set(&dev->delay_drop.rqs_cnt, 0);
+	atomic_set(&dev->delay_drop.events_cnt, 0);
+
+	if (delay_drop_debugfs_init(dev))
+		mlx5_ib_warn(dev, "Failed to init delay drop debugfs\n");
+}
+
+static const struct cpumask *
+mlx5_ib_get_vector_affinity(struct ib_device *ibdev, int comp_vector)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+
+	return mlx5_get_vector_affinity(dev->mdev, comp_vector);
+}
+
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_dev *dev;
@@ -3686,6 +4029,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
 	dev->ib_dev.get_port_immutable  = mlx5_port_immutable;
 	dev->ib_dev.get_dev_fw_str      = get_dev_fw_str;
+	dev->ib_dev.get_vector_affinity	= mlx5_ib_get_vector_affinity;
 	if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads))
 		dev->ib_dev.alloc_rdma_netdev	= mlx5_ib_alloc_rdma_netdev;
 
@@ -3723,18 +4067,20 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 			(1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
 	}
 
+	dev->ib_dev.create_flow	= mlx5_ib_create_flow;
+	dev->ib_dev.destroy_flow = mlx5_ib_destroy_flow;
+	dev->ib_dev.uverbs_ex_cmd_mask |=
+			(1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) |
+			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW);
+
 	if (mlx5_ib_port_link_layer(&dev->ib_dev, 1) ==
 	    IB_LINK_LAYER_ETHERNET) {
-		dev->ib_dev.create_flow	= mlx5_ib_create_flow;
-		dev->ib_dev.destroy_flow = mlx5_ib_destroy_flow;
 		dev->ib_dev.create_wq	 = mlx5_ib_create_wq;
 		dev->ib_dev.modify_wq	 = mlx5_ib_modify_wq;
 		dev->ib_dev.destroy_wq	 = mlx5_ib_destroy_wq;
 		dev->ib_dev.create_rwq_ind_table = mlx5_ib_create_rwq_ind_table;
 		dev->ib_dev.destroy_rwq_ind_table = mlx5_ib_destroy_rwq_ind_table;
 		dev->ib_dev.uverbs_ex_cmd_mask |=
-			(1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) |
-			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW) |
 			(1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) |
 			(1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) |
 			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) |
@@ -3754,6 +4100,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 		err = mlx5_enable_eth(dev);
 		if (err)
 			goto err_free_port;
+		dev->roce.last_port_state = IB_PORT_DOWN;
 	}
 
 	err = create_dev_resources(&dev->devr);
@@ -3770,9 +4117,13 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 			goto err_odp;
 	}
 
+	err = mlx5_ib_init_cong_debugfs(dev);
+	if (err)
+		goto err_cnt;
+
 	dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev);
 	if (!dev->mdev->priv.uar)
-		goto err_cnt;
+		goto err_cong;
 
 	err = mlx5_alloc_bfreg(dev->mdev, &dev->bfreg, false, false);
 	if (err)
@@ -3790,18 +4141,25 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (err)
 		goto err_dev;
 
+	init_delay_drop(dev);
+
 	for (i = 0; i < ARRAY_SIZE(mlx5_class_attributes); i++) {
 		err = device_create_file(&dev->ib_dev.dev,
 					 mlx5_class_attributes[i]);
 		if (err)
-			goto err_umrc;
+			goto err_delay_drop;
 	}
 
+	if ((MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
+	    MLX5_CAP_GEN(mdev, disable_local_lb))
+		mutex_init(&dev->lb_mutex);
+
 	dev->ib_active = true;
 
 	return dev;
 
-err_umrc:
+err_delay_drop:
+	cancel_delay_drop(dev);
 	destroy_umrc_res(dev);
 
 err_dev:
@@ -3817,6 +4175,8 @@ err_uar_page:
 	mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar);
 
 err_cnt:
+	mlx5_ib_cleanup_cong_debugfs(dev);
+err_cong:
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
 		mlx5_ib_dealloc_counters(dev);
 
@@ -3846,11 +4206,13 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 	struct mlx5_ib_dev *dev = context;
 	enum rdma_link_layer ll = mlx5_ib_port_link_layer(&dev->ib_dev, 1);
 
+	cancel_delay_drop(dev);
 	mlx5_remove_netdev_notifier(dev);
 	ib_unregister_device(&dev->ib_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);
+	mlx5_ib_cleanup_cong_debugfs(dev);
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
 		mlx5_ib_dealloc_counters(dev);
 	destroy_umrc_res(dev);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bdcf25410c99..189e80cd6b2f 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -107,6 +107,11 @@ enum {
 	MLX5_CQE_VERSION_V1,
 };
 
+enum {
+	MLX5_TM_MAX_RNDV_MSG_SIZE	= 64,
+	MLX5_TM_MAX_SGE			= 1,
+};
+
 struct mlx5_ib_vma_private_data {
 	struct list_head list;
 	struct vm_area_struct *vma;
@@ -247,6 +252,10 @@ struct mlx5_ib_wq {
 	void		       *qend;
 };
 
+enum mlx5_ib_wq_flags {
+	MLX5_IB_WQ_FLAGS_DELAY_DROP = 0x1,
+};
+
 struct mlx5_ib_rwq {
 	struct ib_wq		ibwq;
 	struct mlx5_core_qp	core_qp;
@@ -264,6 +273,7 @@ struct mlx5_ib_rwq {
 	u32			wqe_count;
 	u32			wqe_shift;
 	int			wq_sig;
+	u32			create_flags; /* Use enum mlx5_ib_wq_flags */
 };
 
 enum {
@@ -378,6 +388,7 @@ struct mlx5_ib_qp {
 	struct list_head	cq_recv_list;
 	struct list_head	cq_send_list;
 	u32			rate_limit;
+	u32                     underlay_qpn;
 };
 
 struct mlx5_ib_cq_buf {
@@ -399,6 +410,7 @@ enum mlx5_ib_qp_flags {
 	MLX5_IB_QP_CAP_SCATTER_FCS		= 1 << 7,
 	MLX5_IB_QP_RSS				= 1 << 8,
 	MLX5_IB_QP_CVLAN_STRIPPING		= 1 << 9,
+	MLX5_IB_QP_UNDERLAY			= 1 << 10,
 };
 
 struct mlx5_umr_wr {
@@ -496,7 +508,7 @@ struct mlx5_ib_mr {
 	struct mlx5_shared_mr_info	*smr_info;
 	struct list_head	list;
 	int			order;
-	int			umred;
+	bool			allocated_from_cache;
 	int			npages;
 	struct mlx5_ib_dev     *dev;
 	u32 out[MLX5_ST_SZ_DW(create_mkey_out)];
@@ -616,6 +628,63 @@ struct mlx5_roce {
 	struct net_device	*netdev;
 	struct notifier_block	nb;
 	atomic_t		next_port;
+	enum ib_port_state last_port_state;
+};
+
+struct mlx5_ib_dbg_param {
+	int			offset;
+	struct mlx5_ib_dev	*dev;
+	struct dentry		*dentry;
+};
+
+enum mlx5_ib_dbg_cc_types {
+	MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE,
+	MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI,
+	MLX5_IB_DBG_CC_RP_TIME_RESET,
+	MLX5_IB_DBG_CC_RP_BYTE_RESET,
+	MLX5_IB_DBG_CC_RP_THRESHOLD,
+	MLX5_IB_DBG_CC_RP_AI_RATE,
+	MLX5_IB_DBG_CC_RP_HAI_RATE,
+	MLX5_IB_DBG_CC_RP_MIN_DEC_FAC,
+	MLX5_IB_DBG_CC_RP_MIN_RATE,
+	MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP,
+	MLX5_IB_DBG_CC_RP_DCE_TCP_G,
+	MLX5_IB_DBG_CC_RP_DCE_TCP_RTT,
+	MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD,
+	MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE,
+	MLX5_IB_DBG_CC_RP_GD,
+	MLX5_IB_DBG_CC_NP_CNP_DSCP,
+	MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE,
+	MLX5_IB_DBG_CC_NP_CNP_PRIO,
+	MLX5_IB_DBG_CC_MAX,
+};
+
+struct mlx5_ib_dbg_cc_params {
+	struct dentry			*root;
+	struct mlx5_ib_dbg_param	params[MLX5_IB_DBG_CC_MAX];
+};
+
+enum {
+	MLX5_MAX_DELAY_DROP_TIMEOUT_MS = 100,
+};
+
+struct mlx5_ib_dbg_delay_drop {
+	struct dentry		*dir_debugfs;
+	struct dentry		*rqs_cnt_debugfs;
+	struct dentry		*events_cnt_debugfs;
+	struct dentry		*timeout_debugfs;
+};
+
+struct mlx5_ib_delay_drop {
+	struct mlx5_ib_dev     *dev;
+	struct work_struct	delay_drop_work;
+	/* serialize setting of delay drop */
+	struct mutex		lock;
+	u32			timeout;
+	bool			activate;
+	atomic_t		events_cnt;
+	atomic_t		rqs_cnt;
+	struct mlx5_ib_dbg_delay_drop *dbg;
 };
 
 struct mlx5_ib_dev {
@@ -652,9 +721,15 @@ 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;
-	u8				umr_fence;
+	struct mlx5_sq_bfreg	bfreg;
+	struct mlx5_sq_bfreg	fp_bfreg;
+	struct mlx5_ib_delay_drop	delay_drop;
+	struct mlx5_ib_dbg_cc_params	*dbg_cc_params;
+
+	/* protect the user_td */
+	struct mutex		lb_mutex;
+	u32			user_td;
+	u8			umr_fence;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
@@ -904,6 +979,9 @@ __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
 int mlx5_get_roce_gid_type(struct mlx5_ib_dev *dev, u8 port_num,
 			   int index, enum ib_gid_type *gid_type);
 
+void mlx5_ib_cleanup_cong_debugfs(struct mlx5_ib_dev *dev);
+int mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev);
+
 /* GSI QP helper functions */
 struct ib_qp *mlx5_ib_gsi_create_qp(struct ib_pd *pd,
 				    struct ib_qp_init_attr *init_attr);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 2c40a2e989d2..0e2789d9bb4d 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -48,7 +48,7 @@ enum {
 #define MLX5_UMR_ALIGN 2048
 
 static int clean_mr(struct mlx5_ib_mr *mr);
-static int use_umr(struct mlx5_ib_dev *dev, int order);
+static int mr_cache_max_order(struct mlx5_ib_dev *dev);
 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)
@@ -183,7 +183,7 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 			break;
 		}
 		mr->order = ent->order;
-		mr->umred = 1;
+		mr->allocated_from_cache = 1;
 		mr->dev = dev;
 
 		MLX5_SET(mkc, mkc, free, 1);
@@ -491,16 +491,18 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
 	struct mlx5_mr_cache *cache = &dev->cache;
 	struct mlx5_ib_mr *mr = NULL;
 	struct mlx5_cache_ent *ent;
+	int last_umr_cache_entry;
 	int c;
 	int i;
 
 	c = order2idx(dev, order);
-	if (c < 0 || c > MAX_UMR_CACHE_ENTRY) {
+	last_umr_cache_entry = order2idx(dev, mr_cache_max_order(dev));
+	if (c < 0 || c > last_umr_cache_entry) {
 		mlx5_ib_warn(dev, "order %d, cache index %d\n", order, c);
 		return NULL;
 	}
 
-	for (i = c; i < MAX_UMR_CACHE_ENTRY; i++) {
+	for (i = c; i <= last_umr_cache_entry; i++) {
 		ent = &cache->ent[i];
 
 		mlx5_ib_dbg(dev, "order %d, cache index %d\n", ent->order, i);
@@ -674,12 +676,12 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
 		queue_work(cache->wq, &ent->work);
 
-		if (i > MAX_UMR_CACHE_ENTRY) {
+		if (i > MR_CACHE_LAST_STD_ENTRY) {
 			mlx5_odp_init_mr_cache_entry(ent);
 			continue;
 		}
 
-		if (!use_umr(dev, ent->order))
+		if (ent->order > mr_cache_max_order(dev))
 			continue;
 
 		ent->page = PAGE_SHIFT;
@@ -806,21 +808,22 @@ err_free:
 	return ERR_PTR(err);
 }
 
-static int get_octo_len(u64 addr, u64 len, int page_size)
+static int get_octo_len(u64 addr, u64 len, int page_shift)
 {
+	u64 page_size = 1ULL << page_shift;
 	u64 offset;
 	int npages;
 
 	offset = addr & (page_size - 1);
-	npages = ALIGN(len + offset, page_size) >> ilog2(page_size);
+	npages = ALIGN(len + offset, page_size) >> page_shift;
 	return (npages + 1) / 2;
 }
 
-static int use_umr(struct mlx5_ib_dev *dev, int order)
+static int mr_cache_max_order(struct mlx5_ib_dev *dev)
 {
 	if (MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
-		return order <= MAX_UMR_CACHE_ENTRY + 2;
-	return order <= MLX5_MAX_UMR_SHIFT;
+		return MR_CACHE_LAST_STD_ENTRY + 2;
+	return MLX5_MAX_UMR_SHIFT;
 }
 
 static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length,
@@ -896,7 +899,8 @@ static int mlx5_ib_post_send_wait(struct mlx5_ib_dev *dev,
 	return err;
 }
 
-static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
+static struct mlx5_ib_mr *alloc_mr_from_cache(
+				  struct ib_pd *pd, struct ib_umem *umem,
 				  u64 virt_addr, u64 len, int npages,
 				  int page_shift, int order, int access_flags)
 {
@@ -928,16 +932,6 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	mr->mmkey.size = len;
 	mr->mmkey.pd = to_mpd(pd)->pdn;
 
-	err = mlx5_ib_update_xlt(mr, 0, npages, page_shift,
-				 MLX5_IB_UPD_XLT_ENABLE);
-
-	if (err) {
-		mlx5_mr_cache_free(dev, mr);
-		return ERR_PTR(err);
-	}
-
-	mr->live = 1;
-
 	return mr;
 }
 
@@ -1103,7 +1097,8 @@ free_xlt:
 static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 				     u64 virt_addr, u64 length,
 				     struct ib_umem *umem, int npages,
-				     int page_shift, int access_flags)
+				     int page_shift, int access_flags,
+				     bool populate)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct mlx5_ib_mr *mr;
@@ -1118,15 +1113,19 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
-	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
-		sizeof(*pas) * ((npages + 1) / 2) * 2;
+	mr->ibmr.pd = pd;
+	mr->access_flags = access_flags;
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+	if (populate)
+		inlen += sizeof(*pas) * roundup(npages, 2);
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		err = -ENOMEM;
 		goto err_1;
 	}
 	pas = (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
-	if (!(access_flags & IB_ACCESS_ON_DEMAND))
+	if (populate && !(access_flags & IB_ACCESS_ON_DEMAND))
 		mlx5_ib_populate_pas(dev, umem, page_shift, pas,
 				     pg_cap ? MLX5_IB_MTT_PRESENT : 0);
 
@@ -1135,23 +1134,27 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	MLX5_SET(create_mkey_in, in, pg_access, !!(pg_cap));
 
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+	MLX5_SET(mkc, mkc, free, !populate);
 	MLX5_SET(mkc, mkc, access_mode, MLX5_MKC_ACCESS_MODE_MTT);
 	MLX5_SET(mkc, mkc, a, !!(access_flags & IB_ACCESS_REMOTE_ATOMIC));
 	MLX5_SET(mkc, mkc, rw, !!(access_flags & IB_ACCESS_REMOTE_WRITE));
 	MLX5_SET(mkc, mkc, rr, !!(access_flags & IB_ACCESS_REMOTE_READ));
 	MLX5_SET(mkc, mkc, lw, !!(access_flags & IB_ACCESS_LOCAL_WRITE));
 	MLX5_SET(mkc, mkc, lr, 1);
+	MLX5_SET(mkc, mkc, umr_en, 1);
 
 	MLX5_SET64(mkc, mkc, start_addr, virt_addr);
 	MLX5_SET64(mkc, mkc, len, length);
 	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
 	MLX5_SET(mkc, mkc, bsf_octword_size, 0);
 	MLX5_SET(mkc, mkc, translations_octword_size,
-		 get_octo_len(virt_addr, length, 1 << page_shift));
+		 get_octo_len(virt_addr, length, page_shift));
 	MLX5_SET(mkc, mkc, log_page_size, page_shift);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
-	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
-		 get_octo_len(virt_addr, length, 1 << page_shift));
+	if (populate) {
+		MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+			 get_octo_len(virt_addr, length, page_shift));
+	}
 
 	err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen);
 	if (err) {
@@ -1160,9 +1163,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	}
 	mr->mmkey.type = MLX5_MKEY_MR;
 	mr->desc_size = sizeof(struct mlx5_mtt);
-	mr->umem = umem;
 	mr->dev = dev;
-	mr->live = 1;
 	kvfree(in);
 
 	mlx5_ib_dbg(dev, "mkey = 0x%x\n", mr->mmkey.key);
@@ -1202,6 +1203,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int ncont;
 	int order;
 	int err;
+	bool use_umr = true;
 
 	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);
@@ -1220,27 +1222,29 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	err = mr_umem_get(pd, start, length, access_flags, &umem, &npages,
 			   &page_shift, &ncont, &order);
 
-        if (err < 0)
+	if (err < 0)
 		return ERR_PTR(err);
 
-	if (use_umr(dev, order)) {
-		mr = reg_umr(pd, umem, virt_addr, length, ncont, page_shift,
-			     order, access_flags);
+	if (order <= mr_cache_max_order(dev)) {
+		mr = alloc_mr_from_cache(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 &&
-		   !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;
+	} else if (!MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) {
+		if (access_flags & IB_ACCESS_ON_DEMAND) {
+			err = -EINVAL;
+			pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB");
+			goto error;
+		}
+		use_umr = false;
 	}
 
 	if (!mr) {
 		mutex_lock(&dev->slow_path_mutex);
 		mr = reg_create(NULL, pd, virt_addr, length, umem, ncont,
-				page_shift, access_flags);
+				page_shift, access_flags, !use_umr);
 		mutex_unlock(&dev->slow_path_mutex);
 	}
 
@@ -1258,8 +1262,22 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	update_odp_mr(mr);
 #endif
 
-	return &mr->ibmr;
+	if (use_umr) {
+		int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE;
 
+		if (access_flags & IB_ACCESS_ON_DEMAND)
+			update_xlt_flags |= MLX5_IB_UPD_XLT_ZAP;
+
+		err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift,
+					 update_xlt_flags);
+		if (err) {
+			mlx5_ib_dereg_mr(&mr->ibmr);
+			return ERR_PTR(err);
+		}
+	}
+
+	mr->live = 1;
+	return &mr->ibmr;
 error:
 	ib_umem_release(umem);
 	return ERR_PTR(err);
@@ -1347,7 +1365,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		/*
 		 * UMR can't be used - MKey needs to be replaced.
 		 */
-		if (mr->umred) {
+		if (mr->allocated_from_cache) {
 			err = unreg_umr(dev, mr);
 			if (err)
 				mlx5_ib_warn(dev, "Failed to unregister MR\n");
@@ -1360,12 +1378,13 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 			return err;
 
 		mr = reg_create(ib_mr, pd, addr, len, mr->umem, ncont,
-				page_shift, access_flags);
+				page_shift, access_flags, true);
 
 		if (IS_ERR(mr))
 			return PTR_ERR(mr);
 
-		mr->umred = 0;
+		mr->allocated_from_cache = 0;
+		mr->live = 1;
 	} else {
 		/*
 		 * Send a UMR WQE
@@ -1453,7 +1472,7 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 static int clean_mr(struct mlx5_ib_mr *mr)
 {
 	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
-	int umred = mr->umred;
+	int allocated_from_cache = mr->allocated_from_cache;
 	int err;
 
 	if (mr->sig) {
@@ -1471,20 +1490,20 @@ static int clean_mr(struct mlx5_ib_mr *mr)
 
 	mlx5_free_priv_descs(mr);
 
-	if (!umred) {
+	if (!allocated_from_cache) {
+		u32 key = mr->mmkey.key;
+
 		err = destroy_mkey(dev, mr);
+		kfree(mr);
 		if (err) {
 			mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n",
-				     mr->mmkey.key, err);
+				     key, err);
 			return err;
 		}
 	} else {
 		mlx5_mr_cache_free(dev, mr);
 	}
 
-	if (!umred)
-		kfree(mr);
-
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 0889ff367c86..acb79d3a4f1d 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -34,6 +34,7 @@
 #include <rdma/ib_umem.h>
 #include <rdma/ib_cache.h>
 #include <rdma/ib_user_verbs.h>
+#include <linux/mlx5/fs.h>
 #include "mlx5_ib.h"
 
 /* not supported currently */
@@ -453,7 +454,8 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev,
 		return -EINVAL;
 	}
 
-	if (attr->qp_type == IB_QPT_RAW_PACKET) {
+	if (attr->qp_type == IB_QPT_RAW_PACKET ||
+	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		base->ubuffer.buf_size = qp->rq.wqe_cnt << qp->rq.wqe_shift;
 		qp->raw_packet_qp.sq.ubuffer.buf_size = qp->sq.wqe_cnt << 6;
 	} else {
@@ -675,10 +677,14 @@ err_umem:
 	return err;
 }
 
-static void destroy_user_rq(struct ib_pd *pd, struct mlx5_ib_rwq *rwq)
+static void destroy_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd,
+			    struct mlx5_ib_rwq *rwq)
 {
 	struct mlx5_ib_ucontext *context;
 
+	if (rwq->create_flags & MLX5_IB_WQ_FLAGS_DELAY_DROP)
+		atomic_dec(&dev->delay_drop.rqs_cnt);
+
 	context = to_mucontext(pd->uobject->context);
 	mlx5_ib_db_unmap_user(context, &rwq->db);
 	if (rwq->umem)
@@ -959,11 +965,16 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 		goto err_free;
 	}
 
-	qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof(*qp->sq.wrid), GFP_KERNEL);
-	qp->sq.wr_data = kmalloc(qp->sq.wqe_cnt * sizeof(*qp->sq.wr_data), GFP_KERNEL);
-	qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof(*qp->rq.wrid), GFP_KERNEL);
-	qp->sq.w_list = kmalloc(qp->sq.wqe_cnt * sizeof(*qp->sq.w_list), GFP_KERNEL);
-	qp->sq.wqe_head = kmalloc(qp->sq.wqe_cnt * sizeof(*qp->sq.wqe_head), GFP_KERNEL);
+	qp->sq.wrid = kvmalloc_array(qp->sq.wqe_cnt,
+				     sizeof(*qp->sq.wrid), GFP_KERNEL);
+	qp->sq.wr_data = kvmalloc_array(qp->sq.wqe_cnt,
+					sizeof(*qp->sq.wr_data), GFP_KERNEL);
+	qp->rq.wrid = kvmalloc_array(qp->rq.wqe_cnt,
+				     sizeof(*qp->rq.wrid), GFP_KERNEL);
+	qp->sq.w_list = kvmalloc_array(qp->sq.wqe_cnt,
+				       sizeof(*qp->sq.w_list), GFP_KERNEL);
+	qp->sq.wqe_head = kvmalloc_array(qp->sq.wqe_cnt,
+					 sizeof(*qp->sq.wqe_head), GFP_KERNEL);
 
 	if (!qp->sq.wrid || !qp->sq.wr_data || !qp->rq.wrid ||
 	    !qp->sq.w_list || !qp->sq.wqe_head) {
@@ -975,11 +986,11 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	return 0;
 
 err_wrid:
-	kfree(qp->sq.wqe_head);
-	kfree(qp->sq.w_list);
-	kfree(qp->sq.wrid);
-	kfree(qp->sq.wr_data);
-	kfree(qp->rq.wrid);
+	kvfree(qp->sq.wqe_head);
+	kvfree(qp->sq.w_list);
+	kvfree(qp->sq.wrid);
+	kvfree(qp->sq.wr_data);
+	kvfree(qp->rq.wrid);
 	mlx5_db_free(dev->mdev, &qp->db);
 
 err_free:
@@ -992,11 +1003,11 @@ err_buf:
 
 static void destroy_qp_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 {
-	kfree(qp->sq.wqe_head);
-	kfree(qp->sq.w_list);
-	kfree(qp->sq.wrid);
-	kfree(qp->sq.wr_data);
-	kfree(qp->rq.wrid);
+	kvfree(qp->sq.wqe_head);
+	kvfree(qp->sq.w_list);
+	kvfree(qp->sq.wrid);
+	kvfree(qp->sq.wr_data);
+	kvfree(qp->rq.wrid);
 	mlx5_db_free(dev->mdev, &qp->db);
 	mlx5_buf_free(dev->mdev, &qp->buf);
 }
@@ -1021,12 +1032,16 @@ static int is_connected(enum ib_qp_type qp_type)
 }
 
 static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev,
+				    struct mlx5_ib_qp *qp,
 				    struct mlx5_ib_sq *sq, u32 tdn)
 {
 	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0};
 	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
 
 	MLX5_SET(tisc, tisc, transport_domain, tdn);
+	if (qp->flags & MLX5_IB_QP_UNDERLAY)
+		MLX5_SET(tisc, tisc, underlay_qpn, qp->underlay_qpn);
+
 	return mlx5_core_create_tis(dev->mdev, in, sizeof(in), &sq->tisn);
 }
 
@@ -1068,11 +1083,16 @@ static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
 
 	sqc = MLX5_ADDR_OF(create_sq_in, in, ctx);
 	MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+	if (MLX5_CAP_ETH(dev->mdev, multi_pkt_send_wqe))
+		MLX5_SET(sqc, sqc, allow_multi_pkt_send_wqe, 1);
 	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
 	MLX5_SET(sqc, sqc, user_index, MLX5_GET(qpc, qpc, user_index));
 	MLX5_SET(sqc, sqc, cqn, MLX5_GET(qpc, qpc, cqn_snd));
 	MLX5_SET(sqc, sqc, tis_lst_sz, 1);
 	MLX5_SET(sqc, sqc, tis_num_0, sq->tisn);
+	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
+	    MLX5_CAP_ETH(dev->mdev, swp))
+		MLX5_SET(sqc, sqc, allow_swp, 1);
 
 	wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
@@ -1229,7 +1249,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	u32 tdn = mucontext->tdn;
 
 	if (qp->sq.wqe_cnt) {
-		err = create_raw_packet_qp_tis(dev, sq, tdn);
+		err = create_raw_packet_qp_tis(dev, qp, sq, tdn);
 		if (err)
 			return err;
 
@@ -1238,6 +1258,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 			goto err_destroy_tis;
 
 		sq->base.container_mibqp = qp;
+		sq->base.mqp.event = mlx5_ib_qp_event;
 	}
 
 	if (qp->rq.wqe_cnt) {
@@ -1502,10 +1523,6 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	u32 *in;
 	int err;
 
-	base = init_attr->qp_type == IB_QPT_RAW_PACKET ?
-	       &qp->raw_packet_qp.rq.base :
-	       &qp->trans_qp.base;
-
 	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
@@ -1587,10 +1604,28 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 
 		qp->wq_sig = !!(ucmd.flags & MLX5_QP_FLAG_SIGNATURE);
 		qp->scat_cqe = !!(ucmd.flags & MLX5_QP_FLAG_SCATTER_CQE);
+
+		if (init_attr->create_flags & IB_QP_CREATE_SOURCE_QPN) {
+			if (init_attr->qp_type != IB_QPT_UD ||
+			    (MLX5_CAP_GEN(dev->mdev, port_type) !=
+			     MLX5_CAP_PORT_TYPE_IB) ||
+			    !mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS)) {
+				mlx5_ib_dbg(dev, "Source QP option isn't supported\n");
+				return -EOPNOTSUPP;
+			}
+
+			qp->flags |= MLX5_IB_QP_UNDERLAY;
+			qp->underlay_qpn = init_attr->source_qpn;
+		}
 	} else {
 		qp->wq_sig = !!wq_signature;
 	}
 
+	base = (init_attr->qp_type == IB_QPT_RAW_PACKET ||
+		qp->flags & MLX5_IB_QP_UNDERLAY) ?
+	       &qp->raw_packet_qp.rq.base :
+	       &qp->trans_qp.base;
+
 	qp->has_rq = qp_has_rq(init_attr);
 	err = set_rq_size(dev, &init_attr->cap, qp->has_rq,
 			  qp, (pd && pd->uobject) ? &ucmd : NULL);
@@ -1694,10 +1729,15 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 
 	MLX5_SET(qpc, qpc, rq_type, get_rx_type(qp, init_attr));
 
-	if (qp->sq.wqe_cnt)
+	if (qp->sq.wqe_cnt) {
 		MLX5_SET(qpc, qpc, log_sq_size, ilog2(qp->sq.wqe_cnt));
-	else
+	} else {
 		MLX5_SET(qpc, qpc, no_sq, 1);
+		if (init_attr->srq &&
+		    init_attr->srq->srq_type == IB_SRQT_TM)
+			MLX5_SET(qpc, qpc, offload_type,
+				 MLX5_QPC_OFFLOAD_TYPE_RNDV);
+	}
 
 	/* Set default resources */
 	switch (init_attr->qp_type) {
@@ -1741,7 +1781,8 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		qp->flags |= MLX5_IB_QP_LSO;
 	}
 
-	if (init_attr->qp_type == IB_QPT_RAW_PACKET) {
+	if (init_attr->qp_type == IB_QPT_RAW_PACKET ||
+	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr;
 		raw_packet_qp_copy_info(qp, &qp->raw_packet_qp);
 		err = create_raw_packet_qp(dev, qp, in, pd);
@@ -1893,7 +1934,7 @@ static int modify_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 {
 	struct mlx5_ib_cq *send_cq, *recv_cq;
-	struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
+	struct mlx5_ib_qp_base *base;
 	unsigned long flags;
 	int err;
 
@@ -1902,12 +1943,14 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 		return;
 	}
 
-	base = qp->ibqp.qp_type == IB_QPT_RAW_PACKET ?
+	base = (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+		qp->flags & MLX5_IB_QP_UNDERLAY) ?
 	       &qp->raw_packet_qp.rq.base :
 	       &qp->trans_qp.base;
 
 	if (qp->state != IB_QPS_RESET) {
-		if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET) {
+		if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET &&
+		    !(qp->flags & MLX5_IB_QP_UNDERLAY)) {
 			err = mlx5_core_qp_modify(dev->mdev,
 						  MLX5_CMD_OP_2RST_QP, 0,
 						  NULL, &base->mqp);
@@ -1946,7 +1989,8 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 	mlx5_ib_unlock_cqs(send_cq, recv_cq);
 	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
 
-	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) {
+	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		destroy_raw_packet_qp(dev, qp);
 	} else {
 		err = mlx5_core_destroy_qp(dev->mdev, &base->mqp);
@@ -2702,7 +2746,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 
 	if (is_sqp(ibqp->qp_type)) {
 		context->mtu_msgmax = (IB_MTU_256 << 5) | 8;
-	} else if (ibqp->qp_type == IB_QPT_UD ||
+	} else if ((ibqp->qp_type == IB_QPT_UD &&
+		    !(qp->flags & MLX5_IB_QP_UNDERLAY)) ||
 		   ibqp->qp_type == MLX5_IB_QPT_REG_UMR) {
 		context->mtu_msgmax = (IB_MTU_4096 << 5) | 12;
 	} else if (attr_mask & IB_QP_PATH_MTU) {
@@ -2799,6 +2844,11 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
 		u8 port_num = (attr_mask & IB_QP_PORT ? attr->port_num :
 			       qp->port) - 1;
+
+		/* Underlay port should be used - index 0 function per port */
+		if (qp->flags & MLX5_IB_QP_UNDERLAY)
+			port_num = 0;
+
 		mibport = &dev->port[port_num];
 		context->qp_counter_set_usr_page |=
 			cpu_to_be32((u32)(mibport->cnts.set_id) << 24);
@@ -2824,7 +2874,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	optpar = ib_mask_to_mlx5_opt(attr_mask);
 	optpar &= opt_mask[mlx5_cur][mlx5_new][mlx5_st];
 
-	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) {
+	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		struct mlx5_modify_raw_qp_param raw_qp_param = {};
 
 		raw_qp_param.operation = op;
@@ -2913,7 +2964,13 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		ll = dev->ib_dev.get_link_layer(&dev->ib_dev, port);
 	}
 
-	if (qp_type != MLX5_IB_QPT_REG_UMR &&
+	if (qp->flags & MLX5_IB_QP_UNDERLAY) {
+		if (attr_mask & ~(IB_QP_STATE | IB_QP_CUR_STATE)) {
+			mlx5_ib_dbg(dev, "invalid attr_mask 0x%x when underlay QP is used\n",
+				    attr_mask);
+			goto out;
+		}
+	} else if (qp_type != MLX5_IB_QPT_REG_UMR &&
 	    !ib_modify_qp_is_ok(cur_state, new_state, qp_type, attr_mask, ll)) {
 		mlx5_ib_dbg(dev, "invalid QP state transition from %d to %d, qp_type %d, attr_mask 0x%x\n",
 			    cur_state, new_state, ibqp->qp_type, attr_mask);
@@ -4477,9 +4534,14 @@ 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);
 
+	/* Not all of output fields are applicable, make sure to zero them */
+	memset(qp_init_attr, 0, sizeof(*qp_init_attr));
+	memset(qp_attr, 0, sizeof(*qp_attr));
+
 	mutex_lock(&qp->mutex);
 
-	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) {
+	if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET ||
+	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		err = query_raw_packet_qp_state(dev, qp, &raw_packet_qp_state);
 		if (err)
 			goto out;
@@ -4597,6 +4659,27 @@ static void mlx5_ib_wq_event(struct mlx5_core_qp *core_qp, int type)
 	}
 }
 
+static int set_delay_drop(struct mlx5_ib_dev *dev)
+{
+	int err = 0;
+
+	mutex_lock(&dev->delay_drop.lock);
+	if (dev->delay_drop.activate)
+		goto out;
+
+	err = mlx5_core_set_delay_drop(dev->mdev, dev->delay_drop.timeout);
+	if (err)
+		goto out;
+
+	dev->delay_drop.activate = true;
+out:
+	mutex_unlock(&dev->delay_drop.lock);
+
+	if (!err)
+		atomic_inc(&dev->delay_drop.rqs_cnt);
+	return err;
+}
+
 static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 		      struct ib_wq_init_attr *init_attr)
 {
@@ -4651,9 +4734,28 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 		}
 		MLX5_SET(rqc, rqc, scatter_fcs, 1);
 	}
+	if (init_attr->create_flags & IB_WQ_FLAGS_DELAY_DROP) {
+		if (!(dev->ib_dev.attrs.raw_packet_caps &
+		      IB_RAW_PACKET_CAP_DELAY_DROP)) {
+			mlx5_ib_dbg(dev, "Delay drop is not supported\n");
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+		MLX5_SET(rqc, rqc, delay_drop_en, 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);
+	if (!err && init_attr->create_flags & IB_WQ_FLAGS_DELAY_DROP) {
+		err = set_delay_drop(dev);
+		if (err) {
+			mlx5_ib_warn(dev, "Failed to enable delay drop err=%d\n",
+				     err);
+			mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp);
+		} else {
+			rwq->create_flags |= MLX5_IB_WQ_FLAGS_DELAY_DROP;
+		}
+	}
 out:
 	kvfree(in);
 	return err;
@@ -4787,7 +4889,7 @@ struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
 err_copy:
 	mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp);
 err_user_rq:
-	destroy_user_rq(pd, rwq);
+	destroy_user_rq(dev, pd, rwq);
 err:
 	kfree(rwq);
 	return ERR_PTR(err);
@@ -4799,7 +4901,7 @@ int mlx5_ib_destroy_wq(struct ib_wq *wq)
 	struct mlx5_ib_rwq *rwq = to_mrwq(wq);
 
 	mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp);
-	destroy_user_rq(wq->pd, rwq);
+	destroy_user_rq(dev, wq->pd, rwq);
 	kfree(rwq);
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 43707b101f47..6d5fadad9090 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -101,7 +101,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 				 udata->inlen - sizeof(ucmd)))
 		return -EINVAL;
 
-	if (in->type == IB_SRQT_XRC) {
+	if (in->type != IB_SRQT_BASIC) {
 		err = get_srq_user_index(to_mucontext(pd->uobject->context),
 					 &ucmd, udata->inlen, &uidx);
 		if (err)
@@ -145,7 +145,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 	in->log_page_size = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 	in->page_offset = offset;
 	if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1 &&
-	    in->type == IB_SRQT_XRC)
+	    in->type != IB_SRQT_BASIC)
 		in->user_index = uidx;
 
 	return 0;
@@ -196,7 +196,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 	}
 	mlx5_fill_page_array(&srq->buf, in->pas);
 
-	srq->wrid = kmalloc(srq->msrq.max * sizeof(u64), GFP_KERNEL);
+	srq->wrid = kvmalloc_array(srq->msrq.max, sizeof(u64), GFP_KERNEL);
 	if (!srq->wrid) {
 		err = -ENOMEM;
 		goto err_in;
@@ -205,7 +205,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 
 	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->type != IB_SRQT_BASIC)
 		in->user_index = MLX5_IB_DEFAULT_UIDX;
 
 	return 0;
@@ -230,7 +230,7 @@ static void destroy_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq)
 
 static void destroy_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq)
 {
-	kfree(srq->wrid);
+	kvfree(srq->wrid);
 	mlx5_buf_free(dev->mdev, &srq->buf);
 	mlx5_db_free(dev->mdev, &srq->db);
 }
@@ -292,14 +292,29 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 	in.wqe_shift = srq->msrq.wqe_shift - 4;
 	if (srq->wq_sig)
 		in.flags |= MLX5_SRQ_FLAG_WQ_SIG;
-	if (init_attr->srq_type == IB_SRQT_XRC) {
+
+	if (init_attr->srq_type == IB_SRQT_XRC)
 		in.xrcd = to_mxrcd(init_attr->ext.xrc.xrcd)->xrcdn;
-		in.cqn = to_mcq(init_attr->ext.xrc.cq)->mcq.cqn;
-	} else if (init_attr->srq_type == IB_SRQT_BASIC) {
+	else
 		in.xrcd = to_mxrcd(dev->devr.x0)->xrcdn;
-		in.cqn = to_mcq(dev->devr.c0)->mcq.cqn;
+
+	if (init_attr->srq_type == IB_SRQT_TM) {
+		in.tm_log_list_size =
+			ilog2(init_attr->ext.tag_matching.max_num_tags) + 1;
+		if (in.tm_log_list_size >
+		    MLX5_CAP_GEN(dev->mdev, log_tag_matching_list_sz)) {
+			mlx5_ib_dbg(dev, "TM SRQ max_num_tags exceeding limit\n");
+			err = -EINVAL;
+			goto err_usr_kern_srq;
+		}
+		in.flags |= MLX5_SRQ_FLAG_RNDV;
 	}
 
+	if (ib_srq_has_cq(init_attr->srq_type))
+		in.cqn = to_mcq(init_attr->ext.cq)->mcq.cqn;
+	else
+		in.cqn = to_mcq(dev->devr.c0)->mcq.cqn;
+
 	in.pd = to_mpd(pd)->pdn;
 	in.db_record = srq->db.dma;
 	err = mlx5_core_create_srq(dev->mdev, &srq->msrq, &in);
diff --git a/drivers/infiniband/hw/mthca/mthca_av.c b/drivers/infiniband/hw/mthca/mthca_av.c
index 2aec9908c40a..e7f6223e9c60 100644
--- a/drivers/infiniband/hw/mthca/mthca_av.c
+++ b/drivers/infiniband/hw/mthca/mthca_av.c
@@ -186,7 +186,7 @@ int mthca_create_ah(struct mthca_dev *dev,
 
 on_hca_fail:
 	if (ah->type == MTHCA_AH_PCI_POOL) {
-		ah->av = pci_pool_zalloc(dev->av_table.pool,
+		ah->av = dma_pool_zalloc(dev->av_table.pool,
 					 GFP_ATOMIC, &ah->avdma);
 		if (!ah->av)
 			return -ENOMEM;
@@ -250,7 +250,7 @@ int mthca_destroy_ah(struct mthca_dev *dev, struct mthca_ah *ah)
 		break;
 
 	case MTHCA_AH_PCI_POOL:
-		pci_pool_free(dev->av_table.pool, ah->av, ah->avdma);
+		dma_pool_free(dev->av_table.pool, ah->av, ah->avdma);
 		break;
 
 	case MTHCA_AH_KMALLOC:
@@ -340,7 +340,7 @@ int mthca_init_av_table(struct mthca_dev *dev)
 	if (err)
 		return err;
 
-	dev->av_table.pool = pci_pool_create("mthca_av", dev->pdev,
+	dev->av_table.pool = dma_pool_create("mthca_av", &dev->pdev->dev,
 					     MTHCA_AV_SIZE,
 					     MTHCA_AV_SIZE, 0);
 	if (!dev->av_table.pool)
@@ -360,7 +360,7 @@ int mthca_init_av_table(struct mthca_dev *dev)
 	return 0;
 
  out_free_pool:
-	pci_pool_destroy(dev->av_table.pool);
+	dma_pool_destroy(dev->av_table.pool);
 
  out_free_alloc:
 	mthca_alloc_cleanup(&dev->av_table.alloc);
@@ -374,6 +374,6 @@ void mthca_cleanup_av_table(struct mthca_dev *dev)
 
 	if (dev->av_table.av_map)
 		iounmap(dev->av_table.av_map);
-	pci_pool_destroy(dev->av_table.pool);
+	dma_pool_destroy(dev->av_table.pool);
 	mthca_alloc_cleanup(&dev->av_table.alloc);
 }
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 9d83a53c0c67..419a2a20c047 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -538,7 +538,7 @@ int mthca_cmd_init(struct mthca_dev *dev)
 		return -ENOMEM;
 	}
 
-	dev->cmd.pool = pci_pool_create("mthca_cmd", dev->pdev,
+	dev->cmd.pool = dma_pool_create("mthca_cmd", &dev->pdev->dev,
 					MTHCA_MAILBOX_SIZE,
 					MTHCA_MAILBOX_SIZE, 0);
 	if (!dev->cmd.pool) {
@@ -551,7 +551,7 @@ int mthca_cmd_init(struct mthca_dev *dev)
 
 void mthca_cmd_cleanup(struct mthca_dev *dev)
 {
-	pci_pool_destroy(dev->cmd.pool);
+	dma_pool_destroy(dev->cmd.pool);
 	iounmap(dev->hcr);
 	if (dev->cmd.flags & MTHCA_CMD_POST_DOORBELLS)
 		iounmap(dev->cmd.dbell_map);
@@ -621,7 +621,7 @@ struct mthca_mailbox *mthca_alloc_mailbox(struct mthca_dev *dev,
 	if (!mailbox)
 		return ERR_PTR(-ENOMEM);
 
-	mailbox->buf = pci_pool_alloc(dev->cmd.pool, gfp_mask, &mailbox->dma);
+	mailbox->buf = dma_pool_alloc(dev->cmd.pool, gfp_mask, &mailbox->dma);
 	if (!mailbox->buf) {
 		kfree(mailbox);
 		return ERR_PTR(-ENOMEM);
@@ -635,7 +635,7 @@ void mthca_free_mailbox(struct mthca_dev *dev, struct mthca_mailbox *mailbox)
 	if (!mailbox)
 		return;
 
-	pci_pool_free(dev->cmd.pool, mailbox->buf, mailbox->dma);
+	dma_pool_free(dev->cmd.pool, mailbox->buf, mailbox->dma);
 	kfree(mailbox);
 }
 
@@ -698,7 +698,7 @@ static int mthca_map_cmd(struct mthca_dev *dev, u16 op, struct mthca_icm *icm,
 		for (i = 0; i < mthca_icm_size(&iter) >> lg; ++i) {
 			if (virt != -1) {
 				pages[nent * 2] = cpu_to_be64(virt);
-				virt += 1 << lg;
+				virt += 1ULL << lg;
 			}
 
 			pages[nent * 2 + 1] =
@@ -1921,7 +1921,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 			(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
 		MTHCA_PUT(inbox, val,               MAD_IFC_G_PATH_OFFSET);
 
-		MTHCA_PUT(inbox, in_wc->slid,       MAD_IFC_RLID_OFFSET);
+		MTHCA_PUT(inbox, ib_lid_cpu16(in_wc->slid), MAD_IFC_RLID_OFFSET);
 		MTHCA_PUT(inbox, in_wc->pkey_index, MAD_IFC_PKEY_OFFSET);
 
 		if (in_grh)
@@ -1929,7 +1929,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= in_wc->slid << 16;
+		in_modifier |= ib_lid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mthca_cmd_box(dev, inmailbox->dma, outmailbox->dma,
diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h
index ec7da9a474cd..5508afbf1c67 100644
--- a/drivers/infiniband/hw/mthca/mthca_dev.h
+++ b/drivers/infiniband/hw/mthca/mthca_dev.h
@@ -118,7 +118,7 @@ enum {
 };
 
 struct mthca_cmd {
-	struct pci_pool          *pool;
+	struct dma_pool          *pool;
 	struct mutex              hcr_mutex;
 	struct semaphore 	  poll_sem;
 	struct semaphore 	  event_sem;
@@ -263,7 +263,7 @@ struct mthca_qp_table {
 };
 
 struct mthca_av_table {
-	struct pci_pool   *pool;
+	struct dma_pool   *pool;
 	int                num_ddr_avs;
 	u64                ddr_av_base;
 	void __iomem      *av_map;
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index 7df3db71777a..093f7755c843 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -205,7 +205,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 		      u16 *out_mad_pkey_index)
 {
 	int err;
-	u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	u16 slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
@@ -256,7 +256,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = pattr.lid;
+		prev_lid = ib_lid_cpu16(pattr.lid);
 
 	err = mthca_MAD_IFC(to_mdev(ibdev),
 			    mad_flags & IB_MAD_IGNORE_MKEY,
diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c
index c309e5c96383..e36a9bc52268 100644
--- a/drivers/infiniband/hw/mthca/mthca_main.c
+++ b/drivers/infiniband/hw/mthca/mthca_main.c
@@ -49,7 +49,6 @@
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("Mellanox InfiniBand HCA low-level driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 
 #ifdef CONFIG_INFINIBAND_MTHCA_DEBUG
 
@@ -1162,7 +1161,7 @@ static void mthca_remove_one(struct pci_dev *pdev)
 	mutex_unlock(&mthca_device_mutex);
 }
 
-static struct pci_device_id mthca_pci_table[] = {
+static const struct pci_device_id mthca_pci_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MELLANOX, PCI_DEVICE_ID_MELLANOX_TAVOR),
 	  .driver_data = TAVOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_TOPSPIN, PCI_DEVICE_ID_MELLANOX_TAVOR),
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index c197cd9b193f..6fee7795d1c8 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -914,7 +914,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int err = 0;
 	int write_mtt_size;
 
-	if (udata->inlen - sizeof (struct ib_uverbs_cmd_hdr) < sizeof ucmd) {
+	if (udata->inlen < sizeof ucmd) {
 		if (!to_mucontext(pd->uobject->context)->reg_mr_warned) {
 			mthca_warn(dev, "Process '%s' did not pass in MR attrs.\n",
 				   current->comm);
@@ -1178,12 +1178,11 @@ static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct mthca_dev *dev =
 		container_of(device, struct mthca_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
 		 (int) (dev->fw_ver >> 32),
 		 (int) (dev->fw_ver >> 16) & 0xffff,
 		 (int) dev->fw_ver & 0xffff);
diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index a30aa6527f7e..942ca84713c9 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -63,7 +63,6 @@
 MODULE_AUTHOR("NetEffect");
 MODULE_DESCRIPTION("NetEffect RNIC Low-level iWARP Driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 
 int interrupt_mod_interval = 0;
 
@@ -102,7 +101,7 @@ static unsigned int ee_flsh_adapter;
 static unsigned int sysfs_nonidx_addr;
 static unsigned int sysfs_idx_addr;
 
-static struct pci_device_id nes_pci_table[] = {
+static const struct pci_device_id nes_pci_table[] = {
 	{ PCI_VDEVICE(NETEFFECT, PCI_DEVICE_ID_NETEFFECT_NE020), },
 	{ PCI_VDEVICE(NETEFFECT, PCI_DEVICE_ID_NETEFFECT_NE020_KR), },
 	{0}
@@ -808,13 +807,6 @@ static void nes_remove(struct pci_dev *pcidev)
 }
 
 
-static struct pci_driver nes_pci_driver = {
-	.name = DRV_NAME,
-	.id_table = nes_pci_table,
-	.probe = nes_probe,
-	.remove = nes_remove,
-};
-
 static ssize_t adapter_show(struct device_driver *ddp, char *buf)
 {
 	unsigned int  devfn = 0xffffffff;
@@ -1156,35 +1148,29 @@ static DRIVER_ATTR_RW(idx_addr);
 static DRIVER_ATTR_RW(idx_data);
 static DRIVER_ATTR_RW(wqm_quanta);
 
-static int nes_create_driver_sysfs(struct pci_driver *drv)
-{
-	int error;
-	error  = driver_create_file(&drv->driver, &driver_attr_adapter);
-	error |= driver_create_file(&drv->driver, &driver_attr_eeprom_cmd);
-	error |= driver_create_file(&drv->driver, &driver_attr_eeprom_data);
-	error |= driver_create_file(&drv->driver, &driver_attr_flash_cmd);
-	error |= driver_create_file(&drv->driver, &driver_attr_flash_data);
-	error |= driver_create_file(&drv->driver, &driver_attr_nonidx_addr);
-	error |= driver_create_file(&drv->driver, &driver_attr_nonidx_data);
-	error |= driver_create_file(&drv->driver, &driver_attr_idx_addr);
-	error |= driver_create_file(&drv->driver, &driver_attr_idx_data);
-	error |= driver_create_file(&drv->driver, &driver_attr_wqm_quanta);
-	return error;
-}
+static struct attribute *nes_attrs[] = {
+	&driver_attr_adapter.attr,
+	&driver_attr_eeprom_cmd.attr,
+	&driver_attr_eeprom_data.attr,
+	&driver_attr_flash_cmd.attr,
+	&driver_attr_flash_data.attr,
+	&driver_attr_nonidx_addr.attr,
+	&driver_attr_nonidx_data.attr,
+	&driver_attr_idx_addr.attr,
+	&driver_attr_idx_data.attr,
+	&driver_attr_wqm_quanta.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(nes);
+
+static struct pci_driver nes_pci_driver = {
+	.name = DRV_NAME,
+	.id_table = nes_pci_table,
+	.probe = nes_probe,
+	.remove = nes_remove,
+	.groups = nes_groups,
+};
 
-static void nes_remove_driver_sysfs(struct pci_driver *drv)
-{
-	driver_remove_file(&drv->driver, &driver_attr_adapter);
-	driver_remove_file(&drv->driver, &driver_attr_eeprom_cmd);
-	driver_remove_file(&drv->driver, &driver_attr_eeprom_data);
-	driver_remove_file(&drv->driver, &driver_attr_flash_cmd);
-	driver_remove_file(&drv->driver, &driver_attr_flash_data);
-	driver_remove_file(&drv->driver, &driver_attr_nonidx_addr);
-	driver_remove_file(&drv->driver, &driver_attr_nonidx_data);
-	driver_remove_file(&drv->driver, &driver_attr_idx_addr);
-	driver_remove_file(&drv->driver, &driver_attr_idx_data);
-	driver_remove_file(&drv->driver, &driver_attr_wqm_quanta);
-}
 
 /**
  * nes_init_module - module initialization entry point
@@ -1192,20 +1178,13 @@ static void nes_remove_driver_sysfs(struct pci_driver *drv)
 static int __init nes_init_module(void)
 {
 	int retval;
-	int retval1;
 
 	retval = nes_cm_start();
 	if (retval) {
 		printk(KERN_ERR PFX "Unable to start NetEffect iWARP CM.\n");
 		return retval;
 	}
-	retval = pci_register_driver(&nes_pci_driver);
-	if (retval >= 0) {
-		retval1 = nes_create_driver_sysfs(&nes_pci_driver);
-		if (retval1 < 0)
-			printk(KERN_ERR PFX "Unable to create NetEffect sys files.\n");
-	}
-	return retval;
+	return pci_register_driver(&nes_pci_driver);
 }
 
 
@@ -1215,7 +1194,6 @@ static int __init nes_init_module(void)
 static void __exit nes_exit_module(void)
 {
 	nes_cm_stop();
-	nes_remove_driver_sysfs(&nes_pci_driver);
 
 	pci_unregister_driver(&nes_pci_driver);
 }
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 25dcd7573df9..f0dc5f4aa177 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -481,21 +481,16 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr
 	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
 	props->lid = 1;
-	props->lmc = 0;
-	props->sm_lid = 0;
-	props->sm_sl = 0;
 	if (netif_queue_stopped(netdev))
 		props->state = IB_PORT_DOWN;
 	else if (nesvnic->linkup)
 		props->state = IB_PORT_ACTIVE;
 	else
 		props->state = IB_PORT_DOWN;
-	props->phys_state = 0;
 	props->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_REINIT_SUP |
 			IB_PORT_VENDOR_CLASS_SUP | IB_PORT_BOOT_MGMT_SUP;
 	props->gid_tbl_len = 1;
 	props->pkey_tbl_len = 1;
-	props->qkey_viol_cntr = 0;
 	props->active_width = IB_WIDTH_4X;
 	props->active_speed = IB_SPEED_SDR;
 	props->max_msg_sz = 0x80000000;
@@ -3672,15 +3667,14 @@ static int nes_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *dev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	struct nes_ib_device *nesibdev =
 			container_of(dev, struct nes_ib_device, ibdev);
 	struct nes_vnic *nesvnic = nesibdev->nesvnic;
 
 	nes_debug(NES_DBG_INIT, "\n");
-	snprintf(str, str_len, "%u.%u",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u",
 		 (nesvnic->nesdev->nesadapter->firmware_version >> 16),
 		 (nesvnic->nesdev->nesadapter->firmware_version & 0x000000ff));
 }
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 57c9a2ad0260..fbfbd9e96147 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -58,7 +58,6 @@
 #include "ocrdma_stats.h"
 #include <rdma/ocrdma-abi.h>
 
-MODULE_VERSION(OCRDMA_ROCE_DRV_VERSION);
 MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION);
 MODULE_AUTHOR("Emulex Corporation");
 MODULE_LICENSE("Dual BSD/GPL");
@@ -108,12 +107,11 @@ static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct ocrdma_dev *dev = get_ocrdma_dev(device);
 
-	snprintf(str, str_len, "%s", &dev->attr.fw_ver[0]);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", &dev->attr.fw_ver[0]);
 }
 
 static int ocrdma_register_device(struct ocrdma_dev *dev)
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index b5851fd67d4f..97d033f51dc9 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -47,7 +47,6 @@
 MODULE_DESCRIPTION("QLogic 40G/100G ROCE Driver");
 MODULE_AUTHOR("QLogic Corporation");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(QEDR_MODULE_VERSION);
 
 #define QEDR_WQ_MULTIPLIER_DFT	(3)
 
@@ -69,13 +68,12 @@ static enum rdma_link_layer qedr_link_layer(struct ib_device *device,
 	return IB_LINK_LAYER_ETHERNET;
 }
 
-static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str,
-				size_t str_len)
+static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct qedr_dev *qedr = get_qedr_dev(ibdev);
 	u32 fw_ver = (u32)qedr->attr.fw_ver;
 
-	snprintf(str, str_len, "%d. %d. %d. %d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d. %d. %d. %d",
 		 (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF,
 		 (fw_ver >> 8) & 0xFF, fw_ver & 0xFF);
 }
@@ -778,6 +776,7 @@ static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev,
 	if (rc)
 		goto init_err;
 
+	dev->user_dpm_enabled = dev_info.user_dpm_enabled;
 	dev->num_hwfns = dev_info.common.num_hwfns;
 	dev->rdma_ctx = dev->ops->rdma_get_rdma_ctx(cdev);
 
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index ab7784bfdac6..b2bb42e2805d 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -41,7 +41,6 @@
 #include <linux/qed/roce_common.h>
 #include "qedr_hsi_rdma.h"
 
-#define QEDR_MODULE_VERSION	"8.10.10.0"
 #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA"
 #define DP_NAME(dev) ((dev)->ibdev.name)
 
@@ -163,6 +162,8 @@ struct qedr_dev {
 	struct qedr_qp		*gsi_qp;
 
 	unsigned long enet_state;
+
+	u8 user_dpm_enabled;
 };
 
 #define QEDR_MAX_SQ_PBL			(0x8000)
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 2ae71b8f1ba8..769ac07c3c8e 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -376,6 +376,9 @@ struct ib_ucontext *qedr_alloc_ucontext(struct ib_device *ibdev,
 
 	memset(&uresp, 0, sizeof(uresp));
 
+	uresp.dpm_enabled = dev->user_dpm_enabled;
+	uresp.wids_enabled = 1;
+	uresp.wid_count = oparams.wid_count;
 	uresp.db_pa = ctx->dpi_phys_addr;
 	uresp.db_size = ctx->dpi_size;
 	uresp.max_send_wr = dev->attr.max_sqe;
@@ -488,7 +491,7 @@ struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
 		 (udata && context) ? "User Lib" : "Kernel");
 
 	if (!dev->rdma_ctx) {
-		DP_ERR(dev, "invlaid RDMA context\n");
+		DP_ERR(dev, "invalid RDMA context\n");
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index a3e21a25cea5..f9e1c69603a5 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -1,7 +1,7 @@
 #ifndef _QIB_KERNEL_H
 #define _QIB_KERNEL_H
 /*
- * Copyright (c) 2012, 2013 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2012 - 2017 Intel Corporation.  All rights reserved.
  * Copyright (c) 2006 - 2012 QLogic Corporation. All rights reserved.
  * Copyright (c) 2003, 2004, 2005, 2006 PathScale, Inc. All rights reserved.
  *
@@ -443,7 +443,7 @@ struct qib_irq_notify;
 #endif
 
 struct qib_msix_entry {
-	struct msix_entry msix;
+	int irq;
 	void *arg;
 #ifdef CONFIG_INFINIBAND_QIB_DCA
 	int dca;
@@ -1433,9 +1433,9 @@ int qib_pcie_init(struct pci_dev *, const struct pci_device_id *);
 int qib_pcie_ddinit(struct qib_devdata *, struct pci_dev *,
 		    const struct pci_device_id *);
 void qib_pcie_ddcleanup(struct qib_devdata *);
-int qib_pcie_params(struct qib_devdata *, u32, u32 *, struct qib_msix_entry *);
+int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent);
 int qib_reinit_intr(struct qib_devdata *);
-void qib_enable_intx(struct pci_dev *);
+void qib_enable_intx(struct qib_devdata *dd);
 void qib_nomsi(struct qib_devdata *);
 void qib_nomsix(struct qib_devdata *);
 void qib_pcie_getcmd(struct qib_devdata *, u16 *, u8 *, u8 *);
diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c
index 5bad8e3b40bb..5ed1ed93380f 100644
--- a/drivers/infiniband/hw/qib/qib_debugfs.c
+++ b/drivers/infiniband/hw/qib/qib_debugfs.c
@@ -1,6 +1,5 @@
-#ifdef CONFIG_DEBUG_FS
 /*
- * Copyright (c) 2013 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2013 - 2017 Intel 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
@@ -191,10 +190,10 @@ DEBUGFS_FILE(ctx_stats)
 static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
 	__acquires(RCU)
 {
-	struct qib_qp_iter *iter;
+	struct rvt_qp_iter *iter;
 	loff_t n = *pos;
 
-	iter = qib_qp_iter_init(s->private);
+	iter = rvt_qp_iter_init(s->private, 0, NULL);
 
 	/* stop calls rcu_read_unlock */
 	rcu_read_lock();
@@ -203,7 +202,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
 		return NULL;
 
 	do {
-		if (qib_qp_iter_next(iter)) {
+		if (rvt_qp_iter_next(iter)) {
 			kfree(iter);
 			return NULL;
 		}
@@ -216,11 +215,11 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr,
 				   loff_t *pos)
 	__must_hold(RCU)
 {
-	struct qib_qp_iter *iter = iter_ptr;
+	struct rvt_qp_iter *iter = iter_ptr;
 
 	(*pos)++;
 
-	if (qib_qp_iter_next(iter)) {
+	if (rvt_qp_iter_next(iter)) {
 		kfree(iter);
 		return NULL;
 	}
@@ -236,7 +235,7 @@ static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr)
 
 static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr)
 {
-	struct qib_qp_iter *iter = iter_ptr;
+	struct rvt_qp_iter *iter = iter_ptr;
 
 	if (!iter)
 		return 0;
@@ -284,6 +283,3 @@ void qib_dbg_exit(void)
 	debugfs_remove_recursive(qib_dbg_root);
 	qib_dbg_root = NULL;
 }
-
-#endif
-
diff --git a/drivers/infiniband/hw/qib/qib_driver.c b/drivers/infiniband/hw/qib/qib_driver.c
index 2b5982f743ef..719906a9fd51 100644
--- a/drivers/infiniband/hw/qib/qib_driver.c
+++ b/drivers/infiniband/hw/qib/qib_driver.c
@@ -66,7 +66,6 @@ MODULE_PARM_DESC(compat_ddr_negotiate,
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel <ibsupport@intel.com>");
 MODULE_DESCRIPTION("Intel IB driver");
-MODULE_VERSION(QIB_DRIVER_VERSION);
 
 /*
  * QIB_PIO_MAXIBHDR is the max IB header size allowed for in our
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index e423b71e6ea0..3259a60e4f4f 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2013 Intel Corporation. All rights reserved.
+ * Copyright (c) 2013 - 2017 Intel Corporation. All rights reserved.
  * Copyright (c) 2006, 2007, 2008, 2009, 2010 QLogic Corporation.
  * All rights reserved.
  * Copyright (c) 2003, 2004, 2005, 2006 PathScale, Inc. All rights reserved.
@@ -1742,38 +1742,32 @@ static void qib_setup_6120_interrupt(struct qib_devdata *dd)
  */
 static void pe_boardname(struct qib_devdata *dd)
 {
-	char *n;
-	u32 boardid, namelen;
+	u32 boardid;
 
 	boardid = SYM_FIELD(dd->revision, Revision,
 			    BoardID);
 
 	switch (boardid) {
 	case 2:
-		n = "InfiniPath_QLE7140";
+		dd->boardname = "InfiniPath_QLE7140";
 		break;
 	default:
 		qib_dev_err(dd, "Unknown 6120 board with ID %u\n", boardid);
-		n = "Unknown_InfiniPath_6120";
+		dd->boardname = "Unknown_InfiniPath_6120";
 		break;
 	}
-	namelen = strlen(n) + 1;
-	dd->boardname = kmalloc(namelen, GFP_KERNEL);
-	if (dd->boardname)
-		snprintf(dd->boardname, namelen, "%s", n);
 
 	if (dd->majrev != 4 || !dd->minrev || dd->minrev > 2)
 		qib_dev_err(dd,
-			"Unsupported InfiniPath hardware revision %u.%u!\n",
-			dd->majrev, dd->minrev);
+			    "Unsupported InfiniPath hardware revision %u.%u!\n",
+			    dd->majrev, dd->minrev);
 
 	snprintf(dd->boardversion, sizeof(dd->boardversion),
 		 "ChipABI %u.%u, %s, InfiniPath%u %u.%u, SW Compat %u\n",
 		 QIB_CHIP_VERS_MAJ, QIB_CHIP_VERS_MIN, dd->boardname,
-		 (unsigned)SYM_FIELD(dd->revision, Revision_R, Arch),
+		 (unsigned int)SYM_FIELD(dd->revision, Revision_R, Arch),
 		 dd->majrev, dd->minrev,
-		 (unsigned)SYM_FIELD(dd->revision, Revision_R, SW));
-
+		 (unsigned int)SYM_FIELD(dd->revision, Revision_R, SW));
 }
 
 /*
@@ -1838,7 +1832,7 @@ static int qib_6120_setup_reset(struct qib_devdata *dd)
 
 bail:
 	if (ret) {
-		if (qib_pcie_params(dd, dd->lbus_width, NULL, NULL))
+		if (qib_pcie_params(dd, dd->lbus_width, NULL))
 			qib_dev_err(dd,
 				"Reset failed to setup PCIe or interrupts; continuing anyway\n");
 		/* clear the reset error, init error/hwerror mask */
@@ -3562,7 +3556,7 @@ struct qib_devdata *qib_init_iba6120_funcs(struct pci_dev *pdev,
 	if (qib_mini_init)
 		goto bail;
 
-	if (qib_pcie_params(dd, 8, NULL, NULL))
+	if (qib_pcie_params(dd, 8, NULL))
 		qib_dev_err(dd,
 			"Failed to setup PCIe or interrupts; continuing anyway\n");
 	dd->cspec->irq = pdev->irq; /* save IRQ */
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index c3679c48e61c..04bdd3d487b1 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2011 - 2017 Intel Corporation.  All rights reserved.
  * Copyright (c) 2006, 2007, 2008, 2009, 2010 QLogic Corporation.
  * All rights reserved.
  * Copyright (c) 2003, 2004, 2005, 2006 PathScale, Inc. All rights reserved.
@@ -2049,41 +2050,35 @@ static void qib_setup_7220_interrupt(struct qib_devdata *dd)
  */
 static void qib_7220_boardname(struct qib_devdata *dd)
 {
-	char *n;
-	u32 boardid, namelen;
+	u32 boardid;
 
 	boardid = SYM_FIELD(dd->revision, Revision,
 			    BoardID);
 
 	switch (boardid) {
 	case 1:
-		n = "InfiniPath_QLE7240";
+		dd->boardname = "InfiniPath_QLE7240";
 		break;
 	case 2:
-		n = "InfiniPath_QLE7280";
+		dd->boardname = "InfiniPath_QLE7280";
 		break;
 	default:
 		qib_dev_err(dd, "Unknown 7220 board with ID %u\n", boardid);
-		n = "Unknown_InfiniPath_7220";
+		dd->boardname = "Unknown_InfiniPath_7220";
 		break;
 	}
 
-	namelen = strlen(n) + 1;
-	dd->boardname = kmalloc(namelen, GFP_KERNEL);
-	if (dd->boardname)
-		snprintf(dd->boardname, namelen, "%s", n);
-
 	if (dd->majrev != 5 || !dd->minrev || dd->minrev > 2)
 		qib_dev_err(dd,
-			"Unsupported InfiniPath hardware revision %u.%u!\n",
-			dd->majrev, dd->minrev);
+			    "Unsupported InfiniPath hardware revision %u.%u!\n",
+			    dd->majrev, dd->minrev);
 
 	snprintf(dd->boardversion, sizeof(dd->boardversion),
 		 "ChipABI %u.%u, %s, InfiniPath%u %u.%u, SW Compat %u\n",
 		 QIB_CHIP_VERS_MAJ, QIB_CHIP_VERS_MIN, dd->boardname,
-		 (unsigned)SYM_FIELD(dd->revision, Revision_R, Arch),
+		 (unsigned int)SYM_FIELD(dd->revision, Revision_R, Arch),
 		 dd->majrev, dd->minrev,
-		 (unsigned)SYM_FIELD(dd->revision, Revision_R, SW));
+		 (unsigned int)SYM_FIELD(dd->revision, Revision_R, SW));
 }
 
 /*
@@ -2148,7 +2143,7 @@ static int qib_setup_7220_reset(struct qib_devdata *dd)
 
 bail:
 	if (ret) {
-		if (qib_pcie_params(dd, dd->lbus_width, NULL, NULL))
+		if (qib_pcie_params(dd, dd->lbus_width, NULL))
 			qib_dev_err(dd,
 				"Reset failed to setup PCIe or interrupts; continuing anyway\n");
 
@@ -3309,7 +3304,7 @@ static int qib_7220_intr_fallback(struct qib_devdata *dd)
 	qib_devinfo(dd->pcidev,
 		"MSI interrupt not detected, trying INTx interrupts\n");
 	qib_7220_free_irq(dd);
-	qib_enable_intx(dd->pcidev);
+	qib_enable_intx(dd);
 	/*
 	 * Some newer kernels require free_irq before disable_msi,
 	 * and irq can be changed during disable and INTx enable
@@ -4619,7 +4614,7 @@ struct qib_devdata *qib_init_iba7220_funcs(struct pci_dev *pdev,
 		minwidth = 8; /* x8 capable boards */
 		break;
 	}
-	if (qib_pcie_params(dd, minwidth, NULL, NULL))
+	if (qib_pcie_params(dd, minwidth, NULL))
 		qib_dev_err(dd,
 			"Failed to setup PCIe or interrupts; continuing anyway\n");
 
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index bb2439fff8fa..14cadf6d6214 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2012 - 2017 Intel Corporation.  All rights reserved.
  * Copyright (c) 2008 - 2012 QLogic Corporation. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -2841,10 +2841,10 @@ static void qib_7322_nomsix(struct qib_devdata *dd)
 			reset_dca_notifier(dd, &dd->cspec->msix_entries[i]);
 #endif
 			irq_set_affinity_hint(
-			  dd->cspec->msix_entries[i].msix.vector, NULL);
+				dd->cspec->msix_entries[i].irq, NULL);
 			free_cpumask_var(dd->cspec->msix_entries[i].mask);
-			free_irq(dd->cspec->msix_entries[i].msix.vector,
-			   dd->cspec->msix_entries[i].arg);
+			free_irq(dd->cspec->msix_entries[i].irq,
+				 dd->cspec->msix_entries[i].arg);
 		}
 		qib_nomsix(dd);
 	}
@@ -3336,9 +3336,9 @@ static void reset_dca_notifier(struct qib_devdata *dd, struct qib_msix_entry *m)
 	qib_devinfo(dd->pcidev,
 		"Disabling notifier on HCA %d irq %d\n",
 		dd->unit,
-		m->msix.vector);
+		m->irq);
 	irq_set_affinity_notifier(
-		m->msix.vector,
+		m->irq,
 		NULL);
 	m->notifier = NULL;
 }
@@ -3354,7 +3354,7 @@ static void setup_dca_notifier(struct qib_devdata *dd, struct qib_msix_entry *m)
 		int ret;
 
 		m->notifier = n;
-		n->notify.irq = m->msix.vector;
+		n->notify.irq = m->irq;
 		n->notify.notify = qib_irq_notifier_notify;
 		n->notify.release = qib_irq_notifier_release;
 		n->arg = m->arg;
@@ -3500,10 +3500,21 @@ try_intx:
 				 - 1,
 				QIB_DRV_NAME "%d (kctx)", dd->unit);
 		}
-		ret = request_irq(
-			dd->cspec->msix_entries[msixnum].msix.vector,
-			handler, 0, dd->cspec->msix_entries[msixnum].name,
-			arg);
+
+		dd->cspec->msix_entries[msixnum].irq = pci_irq_vector(
+			dd->pcidev, msixnum);
+		if (dd->cspec->msix_entries[msixnum].irq < 0) {
+			qib_dev_err(dd,
+				    "Couldn't get MSIx irq (vec=%d): %d\n",
+				    msixnum,
+				    dd->cspec->msix_entries[msixnum].irq);
+			qib_7322_nomsix(dd);
+			goto try_intx;
+		}
+		ret = request_irq(dd->cspec->msix_entries[msixnum].irq,
+				  handler, 0,
+				  dd->cspec->msix_entries[msixnum].name,
+				  arg);
 		if (ret) {
 			/*
 			 * Shouldn't happen since the enable said we could
@@ -3512,7 +3523,7 @@ try_intx:
 			qib_dev_err(dd,
 				"Couldn't setup MSIx interrupt (vec=%d, irq=%d): %d\n",
 				msixnum,
-				dd->cspec->msix_entries[msixnum].msix.vector,
+				dd->cspec->msix_entries[msixnum].irq,
 				ret);
 			qib_7322_nomsix(dd);
 			goto try_intx;
@@ -3548,7 +3559,7 @@ try_intx:
 					dd->cspec->msix_entries[msixnum].mask);
 			}
 			irq_set_affinity_hint(
-				dd->cspec->msix_entries[msixnum].msix.vector,
+				dd->cspec->msix_entries[msixnum].irq,
 				dd->cspec->msix_entries[msixnum].mask);
 		}
 		msixnum++;
@@ -3571,75 +3582,69 @@ bail:;
 static unsigned qib_7322_boardname(struct qib_devdata *dd)
 {
 	/* Will need enumeration of board-types here */
-	char *n;
-	u32 boardid, namelen;
-	unsigned features = DUAL_PORT_CAP;
+	u32 boardid;
+	unsigned int features = DUAL_PORT_CAP;
 
 	boardid = SYM_FIELD(dd->revision, Revision, BoardID);
 
 	switch (boardid) {
 	case 0:
-		n = "InfiniPath_QLE7342_Emulation";
+		dd->boardname = "InfiniPath_QLE7342_Emulation";
 		break;
 	case 1:
-		n = "InfiniPath_QLE7340";
+		dd->boardname = "InfiniPath_QLE7340";
 		dd->flags |= QIB_HAS_QSFP;
 		features = PORT_SPD_CAP;
 		break;
 	case 2:
-		n = "InfiniPath_QLE7342";
+		dd->boardname = "InfiniPath_QLE7342";
 		dd->flags |= QIB_HAS_QSFP;
 		break;
 	case 3:
-		n = "InfiniPath_QMI7342";
+		dd->boardname = "InfiniPath_QMI7342";
 		break;
 	case 4:
-		n = "InfiniPath_Unsupported7342";
+		dd->boardname = "InfiniPath_Unsupported7342";
 		qib_dev_err(dd, "Unsupported version of QMH7342\n");
 		features = 0;
 		break;
 	case BOARD_QMH7342:
-		n = "InfiniPath_QMH7342";
+		dd->boardname = "InfiniPath_QMH7342";
 		features = 0x24;
 		break;
 	case BOARD_QME7342:
-		n = "InfiniPath_QME7342";
+		dd->boardname = "InfiniPath_QME7342";
 		break;
 	case 8:
-		n = "InfiniPath_QME7362";
+		dd->boardname = "InfiniPath_QME7362";
 		dd->flags |= QIB_HAS_QSFP;
 		break;
 	case BOARD_QMH7360:
-		n = "Intel IB QDR 1P FLR-QSFP Adptr";
+		dd->boardname = "Intel IB QDR 1P FLR-QSFP Adptr";
 		dd->flags |= QIB_HAS_QSFP;
 		break;
 	case 15:
-		n = "InfiniPath_QLE7342_TEST";
+		dd->boardname = "InfiniPath_QLE7342_TEST";
 		dd->flags |= QIB_HAS_QSFP;
 		break;
 	default:
-		n = "InfiniPath_QLE73xy_UNKNOWN";
+		dd->boardname = "InfiniPath_QLE73xy_UNKNOWN";
 		qib_dev_err(dd, "Unknown 7322 board type %u\n", boardid);
 		break;
 	}
 	dd->board_atten = 1; /* index into txdds_Xdr */
 
-	namelen = strlen(n) + 1;
-	dd->boardname = kmalloc(namelen, GFP_KERNEL);
-	if (dd->boardname)
-		snprintf(dd->boardname, namelen, "%s", n);
-
 	snprintf(dd->boardversion, sizeof(dd->boardversion),
 		 "ChipABI %u.%u, %s, InfiniPath%u %u.%u, SW Compat %u\n",
 		 QIB_CHIP_VERS_MAJ, QIB_CHIP_VERS_MIN, dd->boardname,
-		 (unsigned)SYM_FIELD(dd->revision, Revision_R, Arch),
+		 (unsigned int)SYM_FIELD(dd->revision, Revision_R, Arch),
 		 dd->majrev, dd->minrev,
-		 (unsigned)SYM_FIELD(dd->revision, Revision_R, SW));
+		 (unsigned int)SYM_FIELD(dd->revision, Revision_R, SW));
 
 	if (qib_singleport && (features >> PORT_SPD_CAP_SHIFT) & PORT_SPD_CAP) {
 		qib_devinfo(dd->pcidev,
-			"IB%u: Forced to single port mode by module parameter\n",
-			dd->unit);
+			    "IB%u: Forced to single port mode by module parameter\n",
+			    dd->unit);
 		features &= PORT_SPD_CAP;
 	}
 
@@ -3744,7 +3749,6 @@ static int qib_do_7322_reset(struct qib_devdata *dd)
 	if (msix_entries) {
 		/* restore the MSIx vector address and data if saved above */
 		for (i = 0; i < msix_entries; i++) {
-			dd->cspec->msix_entries[i].msix.entry = i;
 			if (!msix_vecsave || !msix_vecsave[2 * i])
 				continue;
 			qib_write_kreg(dd, 2 * i +
@@ -3762,8 +3766,7 @@ static int qib_do_7322_reset(struct qib_devdata *dd)
 	write_7322_initregs(dd);
 
 	if (qib_pcie_params(dd, dd->lbus_width,
-			    &dd->cspec->num_msix_entries,
-			    dd->cspec->msix_entries))
+			    &dd->cspec->num_msix_entries))
 		qib_dev_err(dd,
 			"Reset failed to setup PCIe or interrupts; continuing anyway\n");
 
@@ -5195,7 +5198,7 @@ static int qib_7322_intr_fallback(struct qib_devdata *dd)
 	qib_devinfo(dd->pcidev,
 		"MSIx interrupt not detected, trying INTx interrupts\n");
 	qib_7322_nomsix(dd);
-	qib_enable_intx(dd->pcidev);
+	qib_enable_intx(dd);
 	qib_setup_7322_interrupt(dd, 0);
 	return 1;
 }
@@ -6172,7 +6175,7 @@ static int setup_txselect(const char *str, struct kernel_param *kp)
 	unsigned long val;
 	char *n;
 
-	if (strlen(str) >= MAX_ATTEN_LEN) {
+	if (strlen(str) >= ARRAY_SIZE(txselect_list)) {
 		pr_info("txselect_values string too long\n");
 		return -ENOSPC;
 	}
@@ -6183,7 +6186,7 @@ static int setup_txselect(const char *str, struct kernel_param *kp)
 			TXDDS_TABLE_SZ + TXDDS_EXTRA_SZ + TXDDS_MFG_SZ);
 		return -EINVAL;
 	}
-	strcpy(txselect_list, str);
+	strncpy(txselect_list, str, ARRAY_SIZE(txselect_list) - 1);
 
 	list_for_each_entry(dd, &qib_dev_list, list)
 		if (dd->deviceid == PCI_DEVICE_ID_QLOGIC_IB_7322)
@@ -7327,10 +7330,7 @@ struct qib_devdata *qib_init_iba7322_funcs(struct pci_dev *pdev,
 	if (!dd->cspec->msix_entries)
 		tabsize = 0;
 
-	for (i = 0; i < tabsize; i++)
-		dd->cspec->msix_entries[i].msix.entry = i;
-
-	if (qib_pcie_params(dd, 8, &tabsize, dd->cspec->msix_entries))
+	if (qib_pcie_params(dd, 8, &tabsize))
 		qib_dev_err(dd,
 			"Failed to setup PCIe or interrupts; continuing anyway\n");
 	/* may be less than we wanted, if not enough available */
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 6c16ba1107ba..c5a4c65636d6 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -399,7 +399,7 @@ static int loadtime_init(struct qib_devdata *dd)
 	if (((dd->revision >> QLOGIC_IB_R_SOFTWARE_SHIFT) &
 	     QLOGIC_IB_R_SOFTWARE_MASK) != QIB_CHIP_SWVERSION) {
 		qib_dev_err(dd,
-			"Driver only handles version %d, chip swversion is %d (%llx), failng\n",
+			"Driver only handles version %d, chip swversion is %d (%llx), failing\n",
 			QIB_CHIP_SWVERSION,
 			(int)(dd->revision >>
 				QLOGIC_IB_R_SOFTWARE_SHIFT) &
@@ -1398,7 +1398,6 @@ static void cleanup_device_data(struct qib_devdata *dd)
 		qib_free_ctxtdata(dd, rcd);
 	}
 	kfree(tmp);
-	kfree(dd->boardname);
 }
 
 /*
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index da295e0392ed..82d9da9b6997 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -105,7 +105,7 @@ static void qib_send_trap(struct qib_ibport *ibp, void *data, unsigned len)
 		if (ibp->rvp.sm_lid != be16_to_cpu(IB_LID_PERMISSIVE)) {
 			struct ib_ah *ah;
 
-			ah = qib_create_qp0_ah(ibp, ibp->rvp.sm_lid);
+			ah = qib_create_qp0_ah(ibp, (u16)ibp->rvp.sm_lid);
 			if (IS_ERR(ah))
 				ret = PTR_ERR(ah);
 			else {
@@ -134,24 +134,21 @@ static void qib_send_trap(struct qib_ibport *ibp, void *data, unsigned len)
 }
 
 /*
- * Send a bad [PQ]_Key trap (ch. 14.3.8).
+ * Send a bad P_Key trap (ch. 14.3.8).
  */
-void qib_bad_pqkey(struct qib_ibport *ibp, __be16 trap_num, u32 key, u32 sl,
-		   u32 qp1, u32 qp2, __be16 lid1, __be16 lid2)
+void qib_bad_pkey(struct qib_ibport *ibp, u32 key, u32 sl,
+		  u32 qp1, u32 qp2, __be16 lid1, __be16 lid2)
 {
 	struct ib_mad_notice_attr data;
 
-	if (trap_num == IB_NOTICE_TRAP_BAD_PKEY)
-		ibp->rvp.pkey_violations++;
-	else
-		ibp->rvp.qkey_violations++;
 	ibp->rvp.n_pkt_drops++;
+	ibp->rvp.pkey_violations++;
 
 	/* Send violation trap */
 	data.generic_type = IB_NOTICE_TYPE_SECURITY;
 	data.prod_type_msb = 0;
 	data.prod_type_lsb = IB_NOTICE_PROD_CA;
-	data.trap_num = trap_num;
+	data.trap_num = IB_NOTICE_TRAP_BAD_PKEY;
 	data.issuer_lid = cpu_to_be16(ppd_from_ibp(ibp)->lid);
 	data.toggle_count = 0;
 	memset(&data.details, 0, sizeof(data.details));
@@ -499,7 +496,7 @@ static int subn_get_portinfo(struct ib_smp *smp, struct ib_device *ibdev,
 		pip->mkey = ibp->rvp.mkey;
 	pip->gid_prefix = ibp->rvp.gid_prefix;
 	pip->lid = cpu_to_be16(ppd->lid);
-	pip->sm_lid = cpu_to_be16(ibp->rvp.sm_lid);
+	pip->sm_lid = cpu_to_be16((u16)ibp->rvp.sm_lid);
 	pip->cap_mask = cpu_to_be32(ibp->rvp.port_cap_flags);
 	/* pip->diag_code; */
 	pip->mkey_lease_period = cpu_to_be16(ibp->rvp.mkey_lease_period);
@@ -874,8 +871,6 @@ static int subn_set_portinfo(struct ib_smp *smp, struct ib_device *ibdev,
 		ib_dispatch_event(&event);
 	}
 
-	ret = subn_get_portinfo(smp, ibdev, port);
-
 	/* restore re-reg bit per o14-12.2.1 */
 	pip->clientrereg_resv_subnetto |= clientrereg;
 
@@ -1578,8 +1573,8 @@ static int pma_get_portcounters_cong(struct ib_pma_mad *pmp,
 	cntrs.port_xmit_packets -= ibp->z_port_xmit_packets;
 	cntrs.port_rcv_packets -= ibp->z_port_rcv_packets;
 
-	memset(pmp->reserved, 0, sizeof(pmp->reserved) +
-	       sizeof(pmp->data));
+	memset(pmp->reserved, 0, sizeof(pmp->reserved));
+	memset(pmp->data, 0, sizeof(pmp->data));
 
 	/*
 	 * Set top 3 bits to indicate interval in picoseconds in
diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c
index c379b8342a09..d90403e31a9d 100644
--- a/drivers/infiniband/hw/qib/qib_pcie.c
+++ b/drivers/infiniband/hw/qib/qib_pcie.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2010 - 2017 Intel Corporation.  All rights reserved.
  * Copyright (c) 2008, 2009 QLogic Corporation. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -187,112 +188,84 @@ void qib_pcie_ddcleanup(struct qib_devdata *dd)
 	pci_set_drvdata(dd->pcidev, NULL);
 }
 
-static void qib_msix_setup(struct qib_devdata *dd, int pos, u32 *msixcnt,
-			   struct qib_msix_entry *qib_msix_entry)
-{
-	int ret;
-	int nvec = *msixcnt;
-	struct msix_entry *msix_entry;
-	int i;
-
-	ret = pci_msix_vec_count(dd->pcidev);
-	if (ret < 0)
-		goto do_intx;
-
-	nvec = min(nvec, ret);
-
-	/* We can't pass qib_msix_entry array to qib_msix_setup
-	 * so use a dummy msix_entry array and copy the allocated
-	 * irq back to the qib_msix_entry array. */
-	msix_entry = kcalloc(nvec, sizeof(*msix_entry), GFP_KERNEL);
-	if (!msix_entry)
-		goto do_intx;
-
-	for (i = 0; i < nvec; i++)
-		msix_entry[i] = qib_msix_entry[i].msix;
-
-	ret = pci_enable_msix_range(dd->pcidev, msix_entry, 1, nvec);
-	if (ret < 0)
-		goto free_msix_entry;
-	else
-		nvec = ret;
-
-	for (i = 0; i < nvec; i++)
-		qib_msix_entry[i].msix = msix_entry[i];
-
-	kfree(msix_entry);
-	*msixcnt = nvec;
-	return;
-
-free_msix_entry:
-	kfree(msix_entry);
-
-do_intx:
-	qib_dev_err(
-		dd,
-		"pci_enable_msix_range %d vectors failed: %d, falling back to INTx\n",
-		nvec, ret);
-	*msixcnt = 0;
-	qib_enable_intx(dd->pcidev);
-}
-
 /**
  * We save the msi lo and hi values, so we can restore them after
  * chip reset (the kernel PCI infrastructure doesn't yet handle that
  * correctly.
  */
-static int qib_msi_setup(struct qib_devdata *dd, int pos)
+static void qib_msi_setup(struct qib_devdata *dd, int pos)
 {
 	struct pci_dev *pdev = dd->pcidev;
 	u16 control;
-	int ret;
 
-	ret = pci_enable_msi(pdev);
-	if (ret)
-		qib_dev_err(dd,
-			"pci_enable_msi failed: %d, interrupts may not work\n",
-			ret);
-	/* continue even if it fails, we may still be OK... */
-
-	pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_LO,
-			      &dd->msi_lo);
-	pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_HI,
-			      &dd->msi_hi);
+	pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_LO, &dd->msi_lo);
+	pci_read_config_dword(pdev, pos + PCI_MSI_ADDRESS_HI, &dd->msi_hi);
 	pci_read_config_word(pdev, pos + PCI_MSI_FLAGS, &control);
+
 	/* now save the data (vector) info */
-	pci_read_config_word(pdev, pos + ((control & PCI_MSI_FLAGS_64BIT)
-				    ? 12 : 8),
+	pci_read_config_word(pdev,
+			     pos + ((control & PCI_MSI_FLAGS_64BIT) ? 12 : 8),
 			     &dd->msi_data);
-	return ret;
 }
 
-int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent,
-		    struct qib_msix_entry *entry)
+static int qib_allocate_irqs(struct qib_devdata *dd, u32 maxvec)
+{
+	unsigned int flags = PCI_IRQ_LEGACY;
+
+	/* Check our capabilities */
+	if (dd->pcidev->msix_cap) {
+		flags |= PCI_IRQ_MSIX;
+	} else {
+		if (dd->pcidev->msi_cap) {
+			flags |= PCI_IRQ_MSI;
+			/* Get msi_lo and msi_hi */
+			qib_msi_setup(dd, dd->pcidev->msi_cap);
+		}
+	}
+
+	if (!(flags & (PCI_IRQ_MSIX | PCI_IRQ_MSI)))
+		qib_dev_err(dd, "No PCI MSI or MSIx capability!\n");
+
+	return pci_alloc_irq_vectors(dd->pcidev, 1, maxvec, flags);
+}
+
+int qib_pcie_params(struct qib_devdata *dd, u32 minw, u32 *nent)
 {
 	u16 linkstat, speed;
-	int pos = 0, ret = 1;
+	int nvec;
+	int maxvec;
+	int ret = 0;
 
 	if (!pci_is_pcie(dd->pcidev)) {
 		qib_dev_err(dd, "Can't find PCI Express capability!\n");
 		/* set up something... */
 		dd->lbus_width = 1;
 		dd->lbus_speed = 2500; /* Gen1, 2.5GHz */
+		ret = -1;
 		goto bail;
 	}
 
-	pos = dd->pcidev->msix_cap;
-	if (nent && *nent && pos) {
-		qib_msix_setup(dd, pos, nent, entry);
-		ret = 0; /* did it, either MSIx or INTx */
-	} else {
-		pos = dd->pcidev->msi_cap;
-		if (pos)
-			ret = qib_msi_setup(dd, pos);
-		else
-			qib_dev_err(dd, "No PCI MSI or MSIx capability!\n");
+	maxvec = (nent && *nent) ? *nent : 1;
+	nvec = qib_allocate_irqs(dd, maxvec);
+	if (nvec < 0) {
+		ret = nvec;
+		goto bail;
+	}
+
+	/*
+	 * If nent exists, make sure to record how many vectors were allocated
+	 */
+	if (nent) {
+		*nent = nvec;
+
+		/*
+		 * If we requested (nent) MSIX, but msix_enabled is not set,
+		 * pci_alloc_irq_vectors() enabled INTx.
+		 */
+		if (!dd->pcidev->msix_enabled)
+			qib_dev_err(dd,
+				    "no msix vectors allocated, using INTx\n");
 	}
-	if (!pos)
-		qib_enable_intx(dd->pcidev);
 
 	pcie_capability_read_word(dd->pcidev, PCI_EXP_LNKSTA, &linkstat);
 	/*
@@ -379,7 +352,7 @@ int qib_reinit_intr(struct qib_devdata *dd)
 	ret = 1;
 bail:
 	if (!ret && (dd->flags & QIB_HAS_INTX)) {
-		qib_enable_intx(dd->pcidev);
+		qib_enable_intx(dd);
 		ret = 1;
 	}
 
@@ -397,7 +370,7 @@ bail:
 void qib_nomsi(struct qib_devdata *dd)
 {
 	dd->msi_lo = 0;
-	pci_disable_msi(dd->pcidev);
+	pci_free_irq_vectors(dd->pcidev);
 }
 
 /*
@@ -405,23 +378,21 @@ void qib_nomsi(struct qib_devdata *dd)
  */
 void qib_nomsix(struct qib_devdata *dd)
 {
-	pci_disable_msix(dd->pcidev);
+	pci_free_irq_vectors(dd->pcidev);
 }
 
 /*
  * Similar to pci_intx(pdev, 1), except that we make sure
  * msi(x) is off.
  */
-void qib_enable_intx(struct pci_dev *pdev)
+void qib_enable_intx(struct qib_devdata *dd)
 {
 	u16 cw, new;
 	int pos;
+	struct pci_dev *pdev = dd->pcidev;
 
-	/* first, turn on INTx */
-	pci_read_config_word(pdev, PCI_COMMAND, &cw);
-	new = cw & ~PCI_COMMAND_INTX_DISABLE;
-	if (new != cw)
-		pci_write_config_word(pdev, PCI_COMMAND, new);
+	if (pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY) < 0)
+		qib_dev_err(dd,	"Failed to enable INTx\n");
 
 	pos = pdev->msi_cap;
 	if (pos) {
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index a343e3b5d4cb..344e401915f7 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012, 2013 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2012 - 2017 Intel Corporation.  All rights reserved.
  * Copyright (c) 2006 - 2012 QLogic Corporation.  * All rights reserved.
  * Copyright (c) 2005, 2006 PathScale, Inc. All rights reserved.
  *
@@ -415,53 +415,16 @@ int qib_check_send_wqe(struct rvt_qp *qp,
 
 #ifdef CONFIG_DEBUG_FS
 
-struct qib_qp_iter {
-	struct qib_ibdev *dev;
-	struct rvt_qp *qp;
-	int n;
-};
-
-struct qib_qp_iter *qib_qp_iter_init(struct qib_ibdev *dev)
-{
-	struct qib_qp_iter *iter;
-
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (!iter)
-		return NULL;
-
-	iter->dev = dev;
-
-	return iter;
-}
-
-int qib_qp_iter_next(struct qib_qp_iter *iter)
-{
-	struct qib_ibdev *dev = iter->dev;
-	int n = iter->n;
-	int ret = 1;
-	struct rvt_qp *pqp = iter->qp;
-	struct rvt_qp *qp;
-
-	for (; n < dev->rdi.qp_dev->qp_table_size; n++) {
-		if (pqp)
-			qp = rcu_dereference(pqp->next);
-		else
-			qp = rcu_dereference(dev->rdi.qp_dev->qp_table[n]);
-		pqp = qp;
-		if (qp) {
-			iter->qp = qp;
-			iter->n = n;
-			return 0;
-		}
-	}
-	return ret;
-}
-
 static const char * const qp_type_str[] = {
 	"SMI", "GSI", "RC", "UC", "UD",
 };
 
-void qib_qp_iter_print(struct seq_file *s, struct qib_qp_iter *iter)
+/**
+ * qib_qp_iter_print - print information to seq_file
+ * @s - the seq_file
+ * @iter - the iterator
+ */
+void qib_qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter)
 {
 	struct rvt_swqe *wqe;
 	struct rvt_qp *qp = iter->qp;
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index 4ddbcac5eabe..e9a91736b12d 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -348,7 +348,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 		case IB_WR_RDMA_WRITE:
 			if (newreq && !(qp->s_flags & RVT_S_UNLIMITED_CREDIT))
 				qp->s_lsn++;
-			/* FALLTHROUGH */
+			goto no_flow_control;
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			/* If no credit, return. */
 			if (!(qp->s_flags & RVT_S_UNLIMITED_CREDIT) &&
@@ -356,7 +356,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
 				qp->s_flags |= RVT_S_WAIT_SSN_CREDIT;
 				goto bail;
 			}
-
+no_flow_control:
 			ohdr->u.rc.reth.vaddr =
 				cpu_to_be64(wqe->rdma_wr.remote_addr);
 			ohdr->u.rc.reth.rkey =
diff --git a/drivers/infiniband/hw/qib/qib_ruc.c b/drivers/infiniband/hw/qib/qib_ruc.c
index bd09de7c6e56..53efbb0b40c4 100644
--- a/drivers/infiniband/hw/qib/qib_ruc.c
+++ b/drivers/infiniband/hw/qib/qib_ruc.c
@@ -58,8 +58,10 @@ static int qib_init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
 		if (wqe->sg_list[i].length == 0)
 			continue;
 		/* Check LKEY */
-		if (!rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
-				 &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE))
+		ret = rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
+				  NULL, &wqe->sg_list[i],
+				  IB_ACCESS_LOCAL_WRITE);
+		if (unlikely(ret <= 0))
 			goto bad_lkey;
 		qp->r_len += wqe->sg_list[i].length;
 		j++;
@@ -256,11 +258,11 @@ int qib_ruc_check_hdr(struct qib_ibport *ibp, struct ib_header *hdr,
 		}
 		if (!qib_pkey_ok((u16)bth0,
 				 qib_get_pkey(ibp, qp->s_alt_pkey_index))) {
-			qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY,
-				      (u16)bth0,
-				      (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF,
-				      0, qp->ibqp.qp_num,
-				      hdr->lrh[3], hdr->lrh[1]);
+			qib_bad_pkey(ibp,
+				     (u16)bth0,
+				     (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF,
+				     0, qp->ibqp.qp_num,
+				     hdr->lrh[3], hdr->lrh[1]);
 			goto err;
 		}
 		/* Validate the SLID. See Ch. 9.6.1.5 and 17.2.8 */
@@ -295,11 +297,11 @@ int qib_ruc_check_hdr(struct qib_ibport *ibp, struct ib_header *hdr,
 		}
 		if (!qib_pkey_ok((u16)bth0,
 				 qib_get_pkey(ibp, qp->s_pkey_index))) {
-			qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY,
-				      (u16)bth0,
-				      (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF,
-				      0, qp->ibqp.qp_num,
-				      hdr->lrh[3], hdr->lrh[1]);
+			qib_bad_pkey(ibp,
+				     (u16)bth0,
+				     (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF,
+				     0, qp->ibqp.qp_num,
+				     hdr->lrh[3], hdr->lrh[1]);
 			goto err;
 		}
 		/* Validate the SLID. See Ch. 9.6.1.5 */
@@ -643,8 +645,10 @@ u32 qib_make_grh(struct qib_ibport *ibp, struct ib_grh *hdr,
 	hdr->hop_limit = grh->hop_limit;
 	/* The SGID is 32-bit aligned. */
 	hdr->sgid.global.subnet_prefix = ibp->rvp.gid_prefix;
-	hdr->sgid.global.interface_id = grh->sgid_index ?
-		ibp->guids[grh->sgid_index - 1] : ppd_from_ibp(ibp)->guid;
+	if (!grh->sgid_index)
+		hdr->sgid.global.interface_id = ppd_from_ibp(ibp)->guid;
+	else if (grh->sgid_index < QIB_GUIDS_PER_PORT)
+		hdr->sgid.global.interface_id = ibp->guids[grh->sgid_index - 1];
 	hdr->dgid = grh->dgid;
 
 	/* GRH header size in 32-bit words. */
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index fe4cf5e4acec..ca2638d8f35e 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -247,7 +247,7 @@ static struct kobj_type qib_port_cc_ktype = {
 	.release = qib_port_release,
 };
 
-static struct bin_attribute cc_table_bin_attr = {
+static const struct bin_attribute cc_table_bin_attr = {
 	.attr = {.name = "cc_table_bin", .mode = 0444},
 	.read = read_cc_table_bin,
 	.size = PAGE_SIZE,
@@ -286,7 +286,7 @@ static ssize_t read_cc_setting_bin(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute cc_setting_bin_attr = {
+static const struct bin_attribute cc_setting_bin_attr = {
 	.attr = {.name = "cc_settings_bin", .mode = 0444},
 	.read = read_cc_setting_bin,
 	.size = PAGE_SIZE,
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index 341a123ee95c..be4907453ac4 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -66,8 +66,7 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 	qp = rvt_lookup_qpn(rdi, &ibp->rvp, swqe->ud_wr.remote_qpn);
 	if (!qp) {
 		ibp->rvp.n_pkt_drops++;
-		rcu_read_unlock();
-		return;
+		goto drop;
 	}
 
 	sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ?
@@ -94,11 +93,11 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 		if (unlikely(!qib_pkey_ok(pkey1, pkey2))) {
 			lid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
 					  ((1 << ppd->lmc) - 1));
-			qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY, pkey1,
-				      rdma_ah_get_sl(ah_attr),
-				      sqp->ibqp.qp_num, qp->ibqp.qp_num,
-				      cpu_to_be16(lid),
-				      cpu_to_be16(rdma_ah_get_dlid(ah_attr)));
+			qib_bad_pkey(ibp, pkey1,
+				     rdma_ah_get_sl(ah_attr),
+				     sqp->ibqp.qp_num, qp->ibqp.qp_num,
+				     cpu_to_be16(lid),
+				     cpu_to_be16(rdma_ah_get_dlid(ah_attr)));
 			goto drop;
 		}
 	}
@@ -113,18 +112,8 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 
 		qkey = (int)swqe->ud_wr.remote_qkey < 0 ?
 			sqp->qkey : swqe->ud_wr.remote_qkey;
-		if (unlikely(qkey != qp->qkey)) {
-			u16 lid;
-
-			lid = ppd->lid | (rdma_ah_get_path_bits(ah_attr) &
-					  ((1 << ppd->lmc) - 1));
-			qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_QKEY, qkey,
-				      rdma_ah_get_sl(ah_attr),
-				      sqp->ibqp.qp_num, qp->ibqp.qp_num,
-				      cpu_to_be16(lid),
-				      cpu_to_be16(rdma_ah_get_dlid(ah_attr)));
+		if (unlikely(qkey != qp->qkey))
 			goto drop;
-		}
 	}
 
 	/*
@@ -487,22 +476,18 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
 			pkey1 = be32_to_cpu(ohdr->bth[0]);
 			pkey2 = qib_get_pkey(ibp, qp->s_pkey_index);
 			if (unlikely(!qib_pkey_ok(pkey1, pkey2))) {
-				qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_PKEY,
-					      pkey1,
-					      (be16_to_cpu(hdr->lrh[0]) >> 4) &
+				qib_bad_pkey(ibp,
+					     pkey1,
+					     (be16_to_cpu(hdr->lrh[0]) >> 4) &
 						0xF,
-					      src_qp, qp->ibqp.qp_num,
-					      hdr->lrh[3], hdr->lrh[1]);
+					     src_qp, qp->ibqp.qp_num,
+					     hdr->lrh[3], hdr->lrh[1]);
 				return;
 			}
 		}
-		if (unlikely(qkey != qp->qkey)) {
-			qib_bad_pqkey(ibp, IB_NOTICE_TRAP_BAD_QKEY, qkey,
-				      (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF,
-				      src_qp, qp->ibqp.qp_num,
-				      hdr->lrh[3], hdr->lrh[1]);
+		if (unlikely(qkey != qp->qkey))
 			return;
-		}
+
 		/* Drop invalid MAD packets (see 13.5.3.1). */
 		if (unlikely(qp->ibqp.qp_num == 1 &&
 			     (tlen != 256 ||
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index ac42dce7e281..9d92aeb8d9a1 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -1341,6 +1341,15 @@ int qib_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr)
 	if (rdma_ah_get_sl(ah_attr) > 15)
 		return -EINVAL;
 
+	if (rdma_ah_get_dlid(ah_attr) == 0)
+		return -EINVAL;
+	if (rdma_ah_get_dlid(ah_attr) >=
+		be16_to_cpu(IB_MULTICAST_LID_BASE) &&
+	    rdma_ah_get_dlid(ah_attr) !=
+		be16_to_cpu(IB_LID_PERMISSIVE) &&
+	    !(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH))
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index a52fc67b40d7..f887737ac142 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012, 2013 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2012 - 2017 Intel Corporation.  All rights reserved.
  * Copyright (c) 2006 - 2012 QLogic Corporation. All rights reserved.
  * Copyright (c) 2005, 2006 PathScale, Inc. All rights reserved.
  *
@@ -241,8 +241,8 @@ static inline int qib_pkey_ok(u16 pkey1, u16 pkey2)
 	return p1 && p1 == p2 && ((__s16)pkey1 < 0 || (__s16)pkey2 < 0);
 }
 
-void qib_bad_pqkey(struct qib_ibport *ibp, __be16 trap_num, u32 key, u32 sl,
-		   u32 qp1, u32 qp2, __be16 lid1, __be16 lid2);
+void qib_bad_pkey(struct qib_ibport *ibp, u32 key, u32 sl,
+		  u32 qp1, u32 qp2, __be16 lid1, __be16 lid2);
 void qib_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num);
 void qib_sys_guid_chg(struct qib_ibport *ibp);
 void qib_node_desc_chg(struct qib_ibport *ibp);
@@ -282,13 +282,7 @@ int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 void qib_restart_rc(struct rvt_qp *qp, u32 psn, int wait);
 #ifdef CONFIG_DEBUG_FS
 
-struct qib_qp_iter;
-
-struct qib_qp_iter *qib_qp_iter_init(struct qib_ibdev *dev);
-
-int qib_qp_iter_next(struct qib_qp_iter *iter);
-
-void qib_qp_iter_print(struct seq_file *s, struct qib_qp_iter *iter);
+void qib_qp_iter_print(struct seq_file *s, struct rvt_qp_iter *iter);
 
 #endif
 
diff --git a/drivers/infiniband/hw/usnic/usnic_fwd.c b/drivers/infiniband/hw/usnic/usnic_fwd.c
index 3c37dd59c04e..995a26b65156 100644
--- a/drivers/infiniband/hw/usnic/usnic_fwd.c
+++ b/drivers/infiniband/hw/usnic/usnic_fwd.c
@@ -110,20 +110,12 @@ void usnic_fwd_set_mac(struct usnic_fwd_dev *ufdev, char mac[ETH_ALEN])
 	spin_unlock(&ufdev->lock);
 }
 
-int usnic_fwd_add_ipaddr(struct usnic_fwd_dev *ufdev, __be32 inaddr)
+void usnic_fwd_add_ipaddr(struct usnic_fwd_dev *ufdev, __be32 inaddr)
 {
-	int status;
-
 	spin_lock(&ufdev->lock);
-	if (ufdev->inaddr == 0) {
+	if (!ufdev->inaddr)
 		ufdev->inaddr = inaddr;
-		status = 0;
-	} else {
-		status = -EFAULT;
-	}
 	spin_unlock(&ufdev->lock);
-
-	return status;
 }
 
 void usnic_fwd_del_ipaddr(struct usnic_fwd_dev *ufdev)
diff --git a/drivers/infiniband/hw/usnic/usnic_fwd.h b/drivers/infiniband/hw/usnic/usnic_fwd.h
index b2ac22be0731..0b2cc4e79707 100644
--- a/drivers/infiniband/hw/usnic/usnic_fwd.h
+++ b/drivers/infiniband/hw/usnic/usnic_fwd.h
@@ -75,7 +75,7 @@ struct usnic_fwd_dev *usnic_fwd_dev_alloc(struct pci_dev *pdev);
 void usnic_fwd_dev_free(struct usnic_fwd_dev *ufdev);
 
 void usnic_fwd_set_mac(struct usnic_fwd_dev *ufdev, char mac[ETH_ALEN]);
-int usnic_fwd_add_ipaddr(struct usnic_fwd_dev *ufdev, __be32 inaddr);
+void usnic_fwd_add_ipaddr(struct usnic_fwd_dev *ufdev, __be32 inaddr);
 void usnic_fwd_del_ipaddr(struct usnic_fwd_dev *ufdev);
 void usnic_fwd_carrier_up(struct usnic_fwd_dev *ufdev);
 void usnic_fwd_carrier_down(struct usnic_fwd_dev *ufdev);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index c0c1e8b027b1..f45e99a938e0 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -333,9 +333,7 @@ static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void usnic_get_dev_fw_str(struct ib_device *device,
-				 char *str,
-				 size_t str_len)
+static void usnic_get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct usnic_ib_dev *us_ibdev =
 		container_of(device, struct usnic_ib_dev, ib_dev);
@@ -345,7 +343,7 @@ static void usnic_get_dev_fw_str(struct ib_device *device,
 	us_ibdev->netdev->ethtool_ops->get_drvinfo(us_ibdev->netdev, &info);
 	mutex_unlock(&us_ibdev->usdev_lock);
 
-	snprintf(str, str_len, "%s", info.fw_version);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version);
 }
 
 /* Start of PF discovery section */
@@ -353,7 +351,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 {
 	struct usnic_ib_dev *us_ibdev;
 	union ib_gid gid;
-	struct in_ifaddr *in;
+	struct in_device *ind;
 	struct net_device *netdev;
 
 	usnic_dbg("\n");
@@ -409,6 +407,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	us_ibdev->ib_dev.query_port = usnic_ib_query_port;
 	us_ibdev->ib_dev.query_pkey = usnic_ib_query_pkey;
 	us_ibdev->ib_dev.query_gid = usnic_ib_query_gid;
+	us_ibdev->ib_dev.get_netdev = usnic_get_netdev;
 	us_ibdev->ib_dev.get_link_layer = usnic_ib_port_link_layer;
 	us_ibdev->ib_dev.alloc_pd = usnic_ib_alloc_pd;
 	us_ibdev->ib_dev.dealloc_pd = usnic_ib_dealloc_pd;
@@ -442,9 +441,11 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	if (netif_carrier_ok(us_ibdev->netdev))
 		usnic_fwd_carrier_up(us_ibdev->ufdev);
 
-	in = ((struct in_device *)(netdev->ip_ptr))->ifa_list;
-	if (in != NULL)
-		usnic_fwd_add_ipaddr(us_ibdev->ufdev, in->ifa_address);
+	ind = in_dev_get(netdev);
+	if (ind->ifa_list)
+		usnic_fwd_add_ipaddr(us_ibdev->ufdev,
+				     ind->ifa_list->ifa_address);
+	in_dev_put(ind);
 
 	usnic_mac_ip_to_gid(us_ibdev->netdev->perm_addr,
 				us_ibdev->ufdev->inaddr, &gid.raw[0]);
@@ -720,7 +721,6 @@ static void __exit usnic_ib_destroy(void)
 MODULE_DESCRIPTION("Cisco VIC (usNIC) Verbs Driver");
 MODULE_AUTHOR("Upinder Malhi <umalhi@cisco.com>");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 module_param(usnic_log_lvl, uint, S_IRUGO | S_IWUSR);
 module_param(usnic_ib_share_vf, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(usnic_log_lvl, " Off=0, Err=1, Info=2, Debug=3");
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 4996984885c2..e4113ef09315 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -164,6 +164,8 @@ find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev,
 	if (usnic_ib_share_vf) {
 		/* Try to find resouces on a used vf which is in pd */
 		dev_list = usnic_uiom_get_dev_list(pd->umem_pd);
+		if (IS_ERR(dev_list))
+			return ERR_CAST(dev_list);
 		for (i = 0; dev_list[i]; i++) {
 			dev = dev_list[i];
 			vf = pci_get_drvdata(to_pci_dev(dev));
@@ -226,27 +228,6 @@ static void qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp)
 	spin_unlock(&vf->lock);
 }
 
-static void eth_speed_to_ib_speed(int speed, u8 *active_speed,
-					u8 *active_width)
-{
-	if (speed <= 10000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_FDR10;
-	} else if (speed <= 20000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_DDR;
-	} else if (speed <= 30000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_QDR;
-	} else if (speed <= 40000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_FDR10;
-	} else {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_EDR;
-	}
-}
-
 static int create_qp_validate_user_data(struct usnic_ib_create_qp_cmd cmd)
 {
 	if (cmd.spec.trans_type <= USNIC_TRANSPORT_UNKNOWN ||
@@ -326,12 +307,16 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 				struct ib_port_attr *props)
 {
 	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
-	struct ethtool_link_ksettings cmd;
 
 	usnic_dbg("\n");
 
 	mutex_lock(&us_ibdev->usdev_lock);
-	__ethtool_get_link_ksettings(us_ibdev->netdev, &cmd);
+	if (ib_get_eth_speed(ibdev, port, &props->active_speed,
+			     &props->active_width)) {
+		mutex_unlock(&us_ibdev->usdev_lock);
+		return -EINVAL;
+	}
+
 	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->lid = 0;
@@ -355,8 +340,6 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 	props->pkey_tbl_len = 1;
 	props->bad_pkey_cntr = 0;
 	props->qkey_viol_cntr = 0;
-	eth_speed_to_ib_speed(cmd.base.speed, &props->active_speed,
-			      &props->active_width);
 	props->max_mtu = IB_MTU_4096;
 	props->active_mtu = iboe_get_mtu(us_ibdev->ufdev->mtu);
 	/* Userspace will adjust for hdrs */
@@ -424,6 +407,16 @@ int usnic_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
 	return 0;
 }
 
+struct net_device *usnic_get_netdev(struct ib_device *device, u8 port_num)
+{
+	struct usnic_ib_dev *us_ibdev = to_usdev(device);
+
+	if (us_ibdev->netdev)
+		dev_hold(us_ibdev->netdev);
+
+	return us_ibdev->netdev;
+}
+
 int usnic_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
 				u16 *pkey)
 {
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
index 172e43b6fa95..1fda94425116 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
@@ -48,6 +48,7 @@ int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
 				struct ib_qp_init_attr *qp_init_attr);
 int usnic_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
 				union ib_gid *gid);
+struct net_device *usnic_get_netdev(struct ib_device *device, u8 port_num);
 int usnic_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
 				u16 *pkey);
 struct ib_pd *usnic_ib_alloc_pd(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index c49db7c33979..4381c0a9a873 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -227,7 +227,7 @@ static void __usnic_uiom_reg_release(struct usnic_uiom_pd *pd,
 	vpn_last = vpn_start + npages - 1;
 
 	spin_lock(&pd->lock);
-	usnic_uiom_remove_interval(&pd->rb_root, vpn_start,
+	usnic_uiom_remove_interval(&pd->root, vpn_start,
 					vpn_last, &rm_intervals);
 	usnic_uiom_unmap_sorted_intervals(&rm_intervals, pd);
 
@@ -379,7 +379,7 @@ struct usnic_uiom_reg *usnic_uiom_reg_get(struct usnic_uiom_pd *pd,
 	err = usnic_uiom_get_intervals_diff(vpn_start, vpn_last,
 						(writable) ? IOMMU_WRITE : 0,
 						IOMMU_WRITE,
-						&pd->rb_root,
+						&pd->root,
 						&sorted_diff_intervals);
 	if (err) {
 		usnic_err("Failed disjoint interval vpn [0x%lx,0x%lx] err %d\n",
@@ -395,7 +395,7 @@ struct usnic_uiom_reg *usnic_uiom_reg_get(struct usnic_uiom_pd *pd,
 
 	}
 
-	err = usnic_uiom_insert_interval(&pd->rb_root, vpn_start, vpn_last,
+	err = usnic_uiom_insert_interval(&pd->root, vpn_start, vpn_last,
 					(writable) ? IOMMU_WRITE : 0);
 	if (err) {
 		usnic_err("Failed insert interval vpn [0x%lx,0x%lx] err %d\n",
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.h b/drivers/infiniband/hw/usnic/usnic_uiom.h
index 45ca7c1613a7..431efe4143f4 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.h
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.h
@@ -55,7 +55,7 @@ struct usnic_uiom_dev {
 struct usnic_uiom_pd {
 	struct iommu_domain		*domain;
 	spinlock_t			lock;
-	struct rb_root			rb_root;
+	struct rb_root_cached		root;
 	struct list_head		devs;
 	int				dev_cnt;
 };
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c
index 42b4b4c4e452..d399523206c7 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c
@@ -100,9 +100,9 @@ static int interval_cmp(void *priv, struct list_head *a, struct list_head *b)
 }
 
 static void
-find_intervals_intersection_sorted(struct rb_root *root, unsigned long start,
-					unsigned long last,
-					struct list_head *list)
+find_intervals_intersection_sorted(struct rb_root_cached *root,
+				   unsigned long start, unsigned long last,
+				   struct list_head *list)
 {
 	struct usnic_uiom_interval_node *node;
 
@@ -118,7 +118,7 @@ find_intervals_intersection_sorted(struct rb_root *root, unsigned long start,
 
 int usnic_uiom_get_intervals_diff(unsigned long start, unsigned long last,
 					int flags, int flag_mask,
-					struct rb_root *root,
+					struct rb_root_cached *root,
 					struct list_head *diff_set)
 {
 	struct usnic_uiom_interval_node *interval, *tmp;
@@ -175,7 +175,7 @@ void usnic_uiom_put_interval_set(struct list_head *intervals)
 		kfree(interval);
 }
 
-int usnic_uiom_insert_interval(struct rb_root *root, unsigned long start,
+int usnic_uiom_insert_interval(struct rb_root_cached *root, unsigned long start,
 				unsigned long last, int flags)
 {
 	struct usnic_uiom_interval_node *interval, *tmp;
@@ -246,8 +246,9 @@ err_out:
 	return err;
 }
 
-void usnic_uiom_remove_interval(struct rb_root *root, unsigned long start,
-				unsigned long last, struct list_head *removed)
+void usnic_uiom_remove_interval(struct rb_root_cached *root,
+				unsigned long start, unsigned long last,
+				struct list_head *removed)
 {
 	struct usnic_uiom_interval_node *interval;
 
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h
index c0b0b876ab90..1d7fc3226bca 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h
+++ b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h
@@ -48,12 +48,12 @@ struct usnic_uiom_interval_node {
 
 extern void
 usnic_uiom_interval_tree_insert(struct usnic_uiom_interval_node *node,
-					struct rb_root *root);
+					struct rb_root_cached *root);
 extern void
 usnic_uiom_interval_tree_remove(struct usnic_uiom_interval_node *node,
-					struct rb_root *root);
+					struct rb_root_cached *root);
 extern struct usnic_uiom_interval_node *
-usnic_uiom_interval_tree_iter_first(struct rb_root *root,
+usnic_uiom_interval_tree_iter_first(struct rb_root_cached *root,
 					unsigned long start,
 					unsigned long last);
 extern struct usnic_uiom_interval_node *
@@ -63,7 +63,7 @@ usnic_uiom_interval_tree_iter_next(struct usnic_uiom_interval_node *node,
  * Inserts {start...last} into {root}.  If there are overlaps,
  * nodes will be broken up and merged
  */
-int usnic_uiom_insert_interval(struct rb_root *root,
+int usnic_uiom_insert_interval(struct rb_root_cached *root,
 				unsigned long start, unsigned long last,
 				int flags);
 /*
@@ -71,7 +71,7 @@ int usnic_uiom_insert_interval(struct rb_root *root,
  * 'removed.' The caller is responsibile for freeing memory of nodes in
  * 'removed.'
  */
-void usnic_uiom_remove_interval(struct rb_root *root,
+void usnic_uiom_remove_interval(struct rb_root_cached *root,
 				unsigned long start, unsigned long last,
 				struct list_head *removed);
 /*
@@ -81,7 +81,7 @@ void usnic_uiom_remove_interval(struct rb_root *root,
 int usnic_uiom_get_intervals_diff(unsigned long start,
 					unsigned long last, int flags,
 					int flag_mask,
-					struct rb_root *root,
+					struct rb_root_cached *root,
 					struct list_head *diff_set);
 /* Call this to free diff_set returned by usnic_uiom_get_intervals_diff */
 void usnic_uiom_put_interval_set(struct list_head *intervals);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 8e2f0a11690f..663a0c301c43 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -194,6 +194,7 @@ struct pvrdma_dev {
 	void *resp_slot;
 	unsigned long flags;
 	struct list_head device_link;
+	unsigned int dsr_version;
 
 	/* Locking and interrupt information. */
 	spinlock_t cmd_lock; /* Command lock. */
@@ -444,6 +445,7 @@ void pvrdma_ah_attr_to_rdma(struct rdma_ah_attr *dst,
 			    const struct pvrdma_ah_attr *src);
 void rdma_ah_attr_to_pvrdma(struct pvrdma_ah_attr *dst,
 			    const struct rdma_ah_attr *src);
+u8 ib_gid_type_to_pvrdma(enum ib_gid_type gid_type);
 
 int pvrdma_uar_table_init(struct pvrdma_dev *dev);
 void pvrdma_uar_table_cleanup(struct pvrdma_dev *dev);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
index 69bda611d313..3562c0c30492 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
@@ -65,13 +65,28 @@ int pvrdma_req_notify_cq(struct ib_cq *ibcq,
 	struct pvrdma_dev *dev = to_vdev(ibcq->device);
 	struct pvrdma_cq *cq = to_vcq(ibcq);
 	u32 val = cq->cq_handle;
+	unsigned long flags;
+	int has_data = 0;
 
 	val |= (notify_flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
 		PVRDMA_UAR_CQ_ARM_SOL : PVRDMA_UAR_CQ_ARM;
 
+	spin_lock_irqsave(&cq->cq_lock, flags);
+
 	pvrdma_write_uar_cq(dev, val);
 
-	return 0;
+	if (notify_flags & IB_CQ_REPORT_MISSED_EVENTS) {
+		unsigned int head;
+
+		has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
+						    cq->ibcq.cqe, &head);
+		if (unlikely(has_data == PVRDMA_INVALID_IDX))
+			dev_err(&dev->pdev->dev, "CQ ring state invalid\n");
+	}
+
+	spin_unlock_irqrestore(&cq->cq_lock, flags);
+
+	return has_data;
 }
 
 /**
@@ -284,7 +299,7 @@ static inline struct pvrdma_cqe *get_cqe(struct pvrdma_cq *cq, int i)
 
 void _pvrdma_flush_cqe(struct pvrdma_qp *qp, struct pvrdma_cq *cq)
 {
-	int head;
+	unsigned int head;
 	int has_data;
 
 	if (!cq->is_kernel)
@@ -374,6 +389,7 @@ retry:
 	wc->dlid_path_bits = cqe->dlid_path_bits;
 	wc->port_num = cqe->port_num;
 	wc->vendor_err = cqe->vendor_err;
+	wc->network_hdr_type = cqe->network_hdr_type;
 
 	/* 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 09078ccfaec7..df0a6b525021 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
@@ -50,7 +50,15 @@
 
 #include "pvrdma_verbs.h"
 
-#define PVRDMA_VERSION			17
+/*
+ * PVRDMA version macros. Some new features require updates to PVRDMA_VERSION.
+ * These macros allow us to check for different features if necessary.
+ */
+
+#define PVRDMA_ROCEV1_VERSION		17
+#define PVRDMA_ROCEV2_VERSION		18
+#define PVRDMA_VERSION			PVRDMA_ROCEV2_VERSION
+
 #define PVRDMA_BOARD_ID			1
 #define PVRDMA_REV_ID			1
 
@@ -123,6 +131,31 @@
 #define PVRDMA_GID_TYPE_FLAG_ROCE_V1	BIT(0)
 #define PVRDMA_GID_TYPE_FLAG_ROCE_V2	BIT(1)
 
+/*
+ * Version checks. This checks whether each version supports specific
+ * capabilities from the device.
+ */
+
+#define PVRDMA_IS_VERSION17(_dev)					\
+	(_dev->dsr_version == PVRDMA_ROCEV1_VERSION &&			\
+	 _dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V1)
+
+#define PVRDMA_IS_VERSION18(_dev)					\
+	(_dev->dsr_version >= PVRDMA_ROCEV2_VERSION &&			\
+	 (_dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V1 ||  \
+	  _dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V2))	\
+
+#define PVRDMA_SUPPORTED(_dev)						\
+	((_dev->dsr->caps.mode == PVRDMA_DEVICE_MODE_ROCE) &&		\
+	 (PVRDMA_IS_VERSION17(_dev) || PVRDMA_IS_VERSION18(_dev)))
+
+/*
+ * Get capability values based on device version.
+ */
+
+#define PVRDMA_GET_CAP(_dev, _old_val, _val) \
+	((PVRDMA_IS_VERSION18(_dev)) ? _val : _old_val)
+
 enum pvrdma_pci_resource {
 	PVRDMA_PCI_RESOURCE_MSIX,	/* BAR0: MSI-X, MMIO. */
 	PVRDMA_PCI_RESOURCE_REG,	/* BAR1: Registers, MMIO. */
@@ -225,7 +258,7 @@ struct pvrdma_device_caps {
 	u8  atomic_ops;				/* PVRDMA_ATOMIC_OP_* bits */
 	u8  bmme_flags;				/* FRWR Mem Mgmt Extensions */
 	u8  gid_types;				/* PVRDMA_GID_TYPE_FLAG_ */
-	u8  reserved[4];
+	u32 max_fast_reg_page_list_len;
 };
 
 struct pvrdma_ring_page_info {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 34ebc7615411..6ce709a67959 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -102,12 +102,11 @@ static struct device_attribute *pvrdma_class_attributes[] = {
 	&dev_attr_board_id
 };
 
-static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str,
-				  size_t str_len)
+static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str)
 {
 	struct pvrdma_dev *dev =
 		container_of(device, struct pvrdma_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d\n",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d\n",
 		 (int) (dev->dsr->caps.fw_ver >> 32),
 		 (int) (dev->dsr->caps.fw_ver >> 16) & 0xffff,
 		 (int) dev->dsr->caps.fw_ver & 0xffff);
@@ -129,10 +128,14 @@ static int pvrdma_init_device(struct pvrdma_dev *dev)
 static int pvrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
 				 struct ib_port_immutable *immutable)
 {
+	struct pvrdma_dev *dev = to_vdev(ibdev);
 	struct ib_port_attr attr;
 	int err;
 
-	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+	if (dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V1)
+		immutable->core_cap_flags |= RDMA_CORE_PORT_IBA_ROCE;
+	else if (dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V2)
+		immutable->core_cap_flags |= RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
 
 	err = ib_query_port(ibdev, port_num, &attr);
 	if (err)
@@ -570,6 +573,7 @@ static void pvrdma_free_slots(struct pvrdma_dev *dev)
 
 static int pvrdma_add_gid_at_index(struct pvrdma_dev *dev,
 				   const union ib_gid *gid,
+				   u8 gid_type,
 				   int index)
 {
 	int ret;
@@ -587,7 +591,7 @@ static int pvrdma_add_gid_at_index(struct pvrdma_dev *dev,
 	cmd_bind->mtu = ib_mtu_enum_to_int(IB_MTU_1024);
 	cmd_bind->vlan = 0xfff;
 	cmd_bind->index = index;
-	cmd_bind->gid_type = PVRDMA_GID_TYPE_FLAG_ROCE_V1;
+	cmd_bind->gid_type = gid_type;
 
 	ret = pvrdma_cmd_post(dev, &req, NULL, 0);
 	if (ret < 0) {
@@ -608,7 +612,9 @@ static int pvrdma_add_gid(struct ib_device *ibdev,
 {
 	struct pvrdma_dev *dev = to_vdev(ibdev);
 
-	return pvrdma_add_gid_at_index(dev, gid, index);
+	return pvrdma_add_gid_at_index(dev, gid,
+				       ib_gid_type_to_pvrdma(attr->gid_type),
+				       index);
 }
 
 static int pvrdma_del_gid_at_index(struct pvrdma_dev *dev, int index)
@@ -723,7 +729,6 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	int ret;
 	unsigned long start;
 	unsigned long len;
-	unsigned int version;
 	dma_addr_t slot_dma = 0;
 
 	dev_dbg(&pdev->dev, "initializing driver %s\n", pci_name(pdev));
@@ -820,13 +825,9 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 		goto err_unmap_regs;
 	}
 
-	version = pvrdma_read_reg(dev, PVRDMA_REG_VERSION);
+	dev->dsr_version = pvrdma_read_reg(dev, PVRDMA_REG_VERSION);
 	dev_info(&pdev->dev, "device version %d, driver version %d\n",
-		 version, PVRDMA_VERSION);
-	if (version < PVRDMA_VERSION) {
-		dev_err(&pdev->dev, "incompatible device version\n");
-		goto err_uar_unmap;
-	}
+		 dev->dsr_version, PVRDMA_VERSION);
 
 	dev->dsr = dma_alloc_coherent(&pdev->dev, sizeof(*dev->dsr),
 				      &dev->dsrbase, GFP_KERNEL);
@@ -897,17 +898,9 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	/* Make sure the write is complete before reading status. */
 	mb();
 
-	/* Currently, the driver only supports RoCE mode. */
-	if (dev->dsr->caps.mode != PVRDMA_DEVICE_MODE_ROCE) {
-		dev_err(&pdev->dev, "unsupported transport %d\n",
-			dev->dsr->caps.mode);
-		ret = -EFAULT;
-		goto err_free_cq_ring;
-	}
-
-	/* Currently, the driver only supports RoCE V1. */
-	if (!(dev->dsr->caps.gid_types & PVRDMA_GID_TYPE_FLAG_ROCE_V1)) {
-		dev_err(&pdev->dev, "driver needs RoCE v1 support\n");
+	/* The driver supports RoCE V1 and V2. */
+	if (!PVRDMA_SUPPORTED(dev)) {
+		dev_err(&pdev->dev, "driver needs RoCE v1 or v2 support\n");
 		ret = -EFAULT;
 		goto err_free_cq_ring;
 	}
@@ -1078,7 +1071,7 @@ static void pvrdma_pci_remove(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, NULL);
 }
 
-static struct pci_device_id pvrdma_pci_table[] = {
+static const struct pci_device_id pvrdma_pci_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_VMWARE, PCI_DEVICE_ID_VMWARE_PVRDMA), },
 	{ 0 },
 };
@@ -1119,5 +1112,4 @@ module_exit(pvrdma_cleanup);
 
 MODULE_AUTHOR("VMware, Inc");
 MODULE_DESCRIPTION("VMware Paravirtual RDMA driver");
-MODULE_VERSION(DRV_VERSION);
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_misc.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_misc.c
index ec6a4ca1eeb7..fb0c5c0976b3 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_misc.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_misc.c
@@ -303,3 +303,10 @@ void rdma_ah_attr_to_pvrdma(struct pvrdma_ah_attr *dst,
 	dst->port_num = rdma_ah_get_port_num(src);
 	memcpy(&dst->dmac, src->roce.dmac, sizeof(dst->dmac));
 }
+
+u8 ib_gid_type_to_pvrdma(enum ib_gid_type gid_type)
+{
+	return (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ?
+		PVRDMA_GID_TYPE_FLAG_ROCE_V2 :
+		PVRDMA_GID_TYPE_FLAG_ROCE_V1;
+}
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_ring.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_ring.h
index ed9022a91a1d..8b558ae234c8 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_ring.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_ring.h
@@ -111,21 +111,4 @@ static inline __s32 pvrdma_idx_ring_has_data(const struct pvrdma_ring *r,
 	return PVRDMA_INVALID_IDX;
 }
 
-static inline bool pvrdma_idx_ring_is_valid_idx(const struct pvrdma_ring *r,
-						__u32 max_elems, __u32 *idx)
-{
-	const __u32 tail = atomic_read(&r->prod_tail);
-	const __u32 head = atomic_read(&r->cons_head);
-
-	if (pvrdma_idx_valid(tail, max_elems) &&
-	    pvrdma_idx_valid(head, max_elems) &&
-	    pvrdma_idx_valid(*idx, max_elems)) {
-		if (tail > head && (*idx < tail && *idx >= head))
-			return true;
-		else if (head > tail && (*idx >= head || *idx < tail))
-			return true;
-	}
-	return false;
-}
-
 #endif /* __PVRDMA_RING_H__ */
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
index 28517042011d..48776f5ffb0e 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
@@ -83,6 +83,8 @@ int pvrdma_query_device(struct ib_device *ibdev,
 	props->max_qp_wr = dev->dsr->caps.max_qp_wr;
 	props->device_cap_flags = dev->dsr->caps.device_cap_flags;
 	props->max_sge = dev->dsr->caps.max_sge;
+	props->max_sge_rd = PVRDMA_GET_CAP(dev, dev->dsr->caps.max_sge,
+					   dev->dsr->caps.max_sge_rd);
 	props->max_cq = dev->dsr->caps.max_cq;
 	props->max_cqe = dev->dsr->caps.max_cqe;
 	props->max_mr = dev->dsr->caps.max_mr;
@@ -101,8 +103,14 @@ int pvrdma_query_device(struct ib_device *ibdev,
 	    (dev->dsr->caps.bmme_flags & PVRDMA_BMME_FLAG_REMOTE_INV) &&
 	    (dev->dsr->caps.bmme_flags & PVRDMA_BMME_FLAG_FAST_REG_WR)) {
 		props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
+		props->max_fast_reg_page_list_len = PVRDMA_GET_CAP(dev,
+				PVRDMA_MAX_FAST_REG_PAGES,
+				dev->dsr->caps.max_fast_reg_page_list_len);
 	}
 
+	props->device_cap_flags |= IB_DEVICE_PORT_ACTIVE_EVENT |
+				   IB_DEVICE_RC_RNR_NAK_GEN;
+
 	return 0;
 }
 
@@ -143,6 +151,7 @@ int pvrdma_query_port(struct ib_device *ibdev, u8 port,
 	props->gid_tbl_len = resp->attrs.gid_tbl_len;
 	props->port_cap_flags =
 		pvrdma_port_cap_flags_to_ib(resp->attrs.port_cap_flags);
+	props->port_cap_flags |= IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
 	props->max_msg_sz = resp->attrs.max_msg_sz;
 	props->bad_pkey_cntr = resp->attrs.bad_pkey_cntr;
 	props->qkey_viol_cntr = resp->attrs.qkey_viol_cntr;
diff --git a/drivers/infiniband/sw/rdmavt/ah.c b/drivers/infiniband/sw/rdmavt/ah.c
index a96d4aa80ae8..ba3639a0d77c 100644
--- a/drivers/infiniband/sw/rdmavt/ah.c
+++ b/drivers/infiniband/sw/rdmavt/ah.c
@@ -66,8 +66,6 @@ int rvt_check_ah(struct ib_device *ibdev,
 	int port_num = rdma_ah_get_port_num(ah_attr);
 	struct ib_port_attr port_attr;
 	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
-	enum rdma_link_layer link = rdma_port_get_link_layer(ibdev, port_num);
-	u32 dlid = rdma_ah_get_dlid(ah_attr);
 	u8 ah_flags = rdma_ah_get_ah_flags(ah_attr);
 	u8 static_rate = rdma_ah_get_static_rate(ah_attr);
 
@@ -83,14 +81,6 @@ int rvt_check_ah(struct ib_device *ibdev,
 	if ((ah_flags & IB_AH_GRH) &&
 	    rdma_ah_read_grh(ah_attr)->sgid_index >= port_attr.gid_tbl_len)
 		return -EINVAL;
-	if (link != IB_LINK_LAYER_ETHERNET) {
-		if (dlid == 0)
-			return -EINVAL;
-		if (dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE) &&
-		    dlid != be16_to_cpu(IB_LID_PERMISSIVE) &&
-		    !(ah_flags & IB_AH_GRH))
-			return -EINVAL;
-	}
 	if (rdi->driver_f.check_ah)
 		return rdi->driver_f.check_ah(ibdev, ah_attr);
 	return 0;
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 0ae2ff8cf81e..97d71e49c092 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -107,7 +107,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		wc->uqueue[head].src_qp = entry->src_qp;
 		wc->uqueue[head].wc_flags = entry->wc_flags;
 		wc->uqueue[head].pkey_index = entry->pkey_index;
-		wc->uqueue[head].slid = entry->slid;
+		wc->uqueue[head].slid = ib_lid_cpu16(entry->slid);
 		wc->uqueue[head].sl = entry->sl;
 		wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits;
 		wc->uqueue[head].port_num = entry->port_num;
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index aa5f9ea318e4..42713511b53b 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -441,6 +441,105 @@ bail_umem:
 }
 
 /**
+ * rvt_dereg_clean_qp_cb - callback from iterator
+ * @qp - the qp
+ * @v - the mregion (as u64)
+ *
+ * This routine fields the callback for all QPs and
+ * for QPs in the same PD as the MR will call the
+ * rvt_qp_mr_clean() to potentially cleanup references.
+ */
+static void rvt_dereg_clean_qp_cb(struct rvt_qp *qp, u64 v)
+{
+	struct rvt_mregion *mr = (struct rvt_mregion *)v;
+
+	/* skip PDs that are not ours */
+	if (mr->pd != qp->ibqp.pd)
+		return;
+	rvt_qp_mr_clean(qp, mr->lkey);
+}
+
+/**
+ * rvt_dereg_clean_qps - find QPs for reference cleanup
+ * @mr - the MR that is being deregistered
+ *
+ * This routine iterates RC QPs looking for references
+ * to the lkey noted in mr.
+ */
+static void rvt_dereg_clean_qps(struct rvt_mregion *mr)
+{
+	struct rvt_dev_info *rdi = ib_to_rvt(mr->pd->device);
+
+	rvt_qp_iter(rdi, (u64)mr, rvt_dereg_clean_qp_cb);
+}
+
+/**
+ * rvt_check_refs - check references
+ * @mr - the megion
+ * @t - the caller identification
+ *
+ * This routine checks MRs holding a reference during
+ * when being de-registered.
+ *
+ * If the count is non-zero, the code calls a clean routine then
+ * waits for the timeout for the count to zero.
+ */
+static int rvt_check_refs(struct rvt_mregion *mr, const char *t)
+{
+	unsigned long timeout;
+	struct rvt_dev_info *rdi = ib_to_rvt(mr->pd->device);
+
+	if (percpu_ref_is_zero(&mr->refcount))
+		return 0;
+	/* avoid dma mr */
+	if (mr->lkey)
+		rvt_dereg_clean_qps(mr);
+	timeout = wait_for_completion_timeout(&mr->comp, 5 * HZ);
+	if (!timeout) {
+		rvt_pr_err(rdi,
+			   "%s timeout mr %p pd %p lkey %x refcount %ld\n",
+			   t, mr, mr->pd, mr->lkey,
+			   atomic_long_read(&mr->refcount.count));
+		rvt_get_mr(mr);
+		return -EBUSY;
+	}
+	return 0;
+}
+
+/**
+ * rvt_mr_has_lkey - is MR
+ * @mr - the mregion
+ * @lkey - the lkey
+ */
+bool rvt_mr_has_lkey(struct rvt_mregion *mr, u32 lkey)
+{
+	return mr && lkey == mr->lkey;
+}
+
+/**
+ * rvt_ss_has_lkey - is mr in sge tests
+ * @ss - the sge state
+ * @lkey
+ *
+ * This code tests for an MR in the indicated
+ * sge state.
+ */
+bool rvt_ss_has_lkey(struct rvt_sge_state *ss, u32 lkey)
+{
+	int i;
+	bool rval = false;
+
+	if (!ss->num_sge)
+		return rval;
+	/* first one */
+	rval = rvt_mr_has_lkey(ss->sge.mr, lkey);
+	/* any others */
+	for (i = 0; !rval && i < ss->num_sge - 1; i++)
+		rval = rvt_mr_has_lkey(ss->sg_list[i].mr, lkey);
+	return rval;
+}
+
+/**
  * rvt_dereg_mr - unregister and free a memory region
  * @ibmr: the memory region to free
  *
@@ -453,22 +552,14 @@ bail_umem:
 int rvt_dereg_mr(struct ib_mr *ibmr)
 {
 	struct rvt_mr *mr = to_imr(ibmr);
-	struct rvt_dev_info *rdi = ib_to_rvt(ibmr->pd->device);
-	int ret = 0;
-	unsigned long timeout;
+	int ret;
 
 	rvt_free_lkey(&mr->mr);
 
 	rvt_put_mr(&mr->mr); /* will set completion if last */
-	timeout = wait_for_completion_timeout(&mr->mr.comp, 5 * HZ);
-	if (!timeout) {
-		rvt_pr_err(rdi,
-			   "rvt_dereg_mr timeout mr %p pd %p\n",
-			   mr, mr->mr.pd);
-		rvt_get_mr(&mr->mr);
-		ret = -EBUSY;
+	ret = rvt_check_refs(&mr->mr, __func__);
+	if (ret)
 		goto out;
-	}
 	rvt_deinit_mregion(&mr->mr);
 	if (mr->umem)
 		ib_umem_release(mr->umem);
@@ -761,16 +852,12 @@ int rvt_dealloc_fmr(struct ib_fmr *ibfmr)
 {
 	struct rvt_fmr *fmr = to_ifmr(ibfmr);
 	int ret = 0;
-	unsigned long timeout;
 
 	rvt_free_lkey(&fmr->mr);
 	rvt_put_mr(&fmr->mr); /* will set completion if last */
-	timeout = wait_for_completion_timeout(&fmr->mr.comp, 5 * HZ);
-	if (!timeout) {
-		rvt_get_mr(&fmr->mr);
-		ret = -EBUSY;
+	ret = rvt_check_refs(&fmr->mr, __func__);
+	if (ret)
 		goto out;
-	}
 	rvt_deinit_mregion(&fmr->mr);
 	kfree(fmr);
 out:
@@ -778,23 +865,52 @@ out:
 }
 
 /**
+ * rvt_sge_adjacent - is isge compressible
+ * @last_sge: last outgoing SGE written
+ * @sge: SGE to check
+ *
+ * If adjacent will update last_sge to add length.
+ *
+ * Return: true if isge is adjacent to last sge
+ */
+static inline bool rvt_sge_adjacent(struct rvt_sge *last_sge,
+				    struct ib_sge *sge)
+{
+	if (last_sge && sge->lkey == last_sge->mr->lkey &&
+	    ((uint64_t)(last_sge->vaddr + last_sge->length) == sge->addr)) {
+		if (sge->lkey) {
+			if (unlikely((sge->addr - last_sge->mr->user_base +
+			      sge->length > last_sge->mr->length)))
+				return false; /* overrun, caller will catch */
+		} else {
+			last_sge->length += sge->length;
+		}
+		last_sge->sge_length += sge->length;
+		trace_rvt_sge_adjacent(last_sge, sge);
+		return true;
+	}
+	return false;
+}
+
+/**
  * rvt_lkey_ok - check IB SGE for validity and initialize
  * @rkt: table containing lkey to check SGE against
  * @pd: protection domain
  * @isge: outgoing internal SGE
+ * @last_sge: last outgoing SGE written
  * @sge: SGE to check
  * @acc: access flags
  *
  * Check the IB SGE for validity and initialize our internal version
  * of it.
  *
- * Return: 1 if valid and successful, otherwise returns 0.
- *
- * increments the reference count upon success
+ * Increments the reference count when a new sge is stored.
  *
+ * Return: 0 if compressed, 1 if added , otherwise returns -errno.
  */
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
-		struct rvt_sge *isge, struct ib_sge *sge, int acc)
+		struct rvt_sge *isge, struct rvt_sge *last_sge,
+		struct ib_sge *sge, int acc)
 {
 	struct rvt_mregion *mr;
 	unsigned n, m;
@@ -804,12 +920,14 @@ 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_virt_ops).
 	 */
-	rcu_read_lock();
 	if (sge->lkey == 0) {
 		struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device);
 
 		if (pd->user)
-			goto bail;
+			return -EINVAL;
+		if (rvt_sge_adjacent(last_sge, sge))
+			return 0;
+		rcu_read_lock();
 		mr = rcu_dereference(dev->dma_mr);
 		if (!mr)
 			goto bail;
@@ -824,6 +942,9 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 		isge->n = 0;
 		goto ok;
 	}
+	if (rvt_sge_adjacent(last_sge, sge))
+		return 0;
+	rcu_read_lock();
 	mr = rcu_dereference(rkt->table[sge->lkey >> rkt->shift]);
 	if (!mr)
 		goto bail;
@@ -874,12 +995,13 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 	isge->m = m;
 	isge->n = n;
 ok:
+	trace_rvt_sge_new(isge, sge);
 	return 1;
 bail_unref:
 	rvt_put_mr(mr);
 bail:
 	rcu_read_unlock();
-	return 0;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(rvt_lkey_ok);
 
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 8876ee7bc326..22df09ae809e 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -52,6 +52,7 @@
 #include <linux/slab.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_hdrs.h>
+#include <rdma/opa_addr.h>
 #include "qp.h"
 #include "vt.h"
 #include "trace.h"
@@ -421,15 +422,6 @@ bail:
 	return ret;
 }
 
-static void free_qpn(struct rvt_qpn_table *qpt, u32 qpn)
-{
-	struct rvt_qpn_map *map;
-
-	map = qpt->map + qpn / RVT_BITS_PER_PAGE;
-	if (map->page)
-		clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page);
-}
-
 /**
  * rvt_clear_mr_refs - Drop help mr refs
  * @qp: rvt qp data structure
@@ -448,13 +440,9 @@ static void rvt_clear_mr_refs(struct rvt_qp *qp, int clr_sends)
 	if (clr_sends) {
 		while (qp->s_last != qp->s_head) {
 			struct rvt_swqe *wqe = rvt_get_swqe_ptr(qp, qp->s_last);
-			unsigned i;
 
-			for (i = 0; i < wqe->wr.num_sge; i++) {
-				struct rvt_sge *sge = &wqe->sg_list[i];
+			rvt_put_swqe(wqe);
 
-				rvt_put_mr(sge->mr);
-			}
 			if (qp->ibqp.qp_type == IB_QPT_UD ||
 			    qp->ibqp.qp_type == IB_QPT_SMI ||
 			    qp->ibqp.qp_type == IB_QPT_GSI)
@@ -470,10 +458,7 @@ static void rvt_clear_mr_refs(struct rvt_qp *qp, int clr_sends)
 		}
 	}
 
-	if (qp->ibqp.qp_type != IB_QPT_RC)
-		return;
-
-	for (n = 0; n < rvt_max_atomic(rdi); n++) {
+	for (n = 0; qp->s_ack_queue && n < rvt_max_atomic(rdi); n++) {
 		struct rvt_ack_entry *e = &qp->s_ack_queue[n];
 
 		if (e->rdma_sge.mr) {
@@ -484,6 +469,113 @@ static void rvt_clear_mr_refs(struct rvt_qp *qp, int clr_sends)
 }
 
 /**
+ * rvt_swqe_has_lkey - return true if lkey is used by swqe
+ * @wqe - the send wqe
+ * @lkey - the lkey
+ *
+ * Test the swqe for using lkey
+ */
+static bool rvt_swqe_has_lkey(struct rvt_swqe *wqe, u32 lkey)
+{
+	int i;
+
+	for (i = 0; i < wqe->wr.num_sge; i++) {
+		struct rvt_sge *sge = &wqe->sg_list[i];
+
+		if (rvt_mr_has_lkey(sge->mr, lkey))
+			return true;
+	}
+	return false;
+}
+
+/**
+ * rvt_qp_sends_has_lkey - return true is qp sends use lkey
+ * @qp - the rvt_qp
+ * @lkey - the lkey
+ */
+static bool rvt_qp_sends_has_lkey(struct rvt_qp *qp, u32 lkey)
+{
+	u32 s_last = qp->s_last;
+
+	while (s_last != qp->s_head) {
+		struct rvt_swqe *wqe = rvt_get_swqe_ptr(qp, s_last);
+
+		if (rvt_swqe_has_lkey(wqe, lkey))
+			return true;
+
+		if (++s_last >= qp->s_size)
+			s_last = 0;
+	}
+	if (qp->s_rdma_mr)
+		if (rvt_mr_has_lkey(qp->s_rdma_mr, lkey))
+			return true;
+	return false;
+}
+
+/**
+ * rvt_qp_acks_has_lkey - return true if acks have lkey
+ * @qp - the qp
+ * @lkey - the lkey
+ */
+static bool rvt_qp_acks_has_lkey(struct rvt_qp *qp, u32 lkey)
+{
+	int i;
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+
+	for (i = 0; qp->s_ack_queue && i < rvt_max_atomic(rdi); i++) {
+		struct rvt_ack_entry *e = &qp->s_ack_queue[i];
+
+		if (rvt_mr_has_lkey(e->rdma_sge.mr, lkey))
+			return true;
+	}
+	return false;
+}
+
+/*
+ * rvt_qp_mr_clean - clean up remote ops for lkey
+ * @qp - the qp
+ * @lkey - the lkey that is being de-registered
+ *
+ * This routine checks if the lkey is being used by
+ * the qp.
+ *
+ * If so, the qp is put into an error state to elminate
+ * any references from the qp.
+ */
+void rvt_qp_mr_clean(struct rvt_qp *qp, u32 lkey)
+{
+	bool lastwqe = false;
+
+	if (qp->ibqp.qp_type == IB_QPT_SMI ||
+	    qp->ibqp.qp_type == IB_QPT_GSI)
+		/* avoid special QPs */
+		return;
+	spin_lock_irq(&qp->r_lock);
+	spin_lock(&qp->s_hlock);
+	spin_lock(&qp->s_lock);
+
+	if (qp->state == IB_QPS_ERR || qp->state == IB_QPS_RESET)
+		goto check_lwqe;
+
+	if (rvt_ss_has_lkey(&qp->r_sge, lkey) ||
+	    rvt_qp_sends_has_lkey(qp, lkey) ||
+	    rvt_qp_acks_has_lkey(qp, lkey))
+		lastwqe = rvt_error_qp(qp, IB_WC_LOC_PROT_ERR);
+check_lwqe:
+	spin_unlock(&qp->s_lock);
+	spin_unlock(&qp->s_hlock);
+	spin_unlock_irq(&qp->r_lock);
+	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);
+	}
+}
+
+/**
  * rvt_remove_qp - remove qp form table
  * @rdi: rvt dev struct
  * @qp: qp to remove
@@ -645,6 +737,19 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 	lockdep_assert_held(&qp->s_lock);
 }
 
+/** rvt_free_qpn - Free a qpn from the bit map
+ * @qpt: QP table
+ * @qpn: queue pair number to free
+ */
+static void rvt_free_qpn(struct rvt_qpn_table *qpt, u32 qpn)
+{
+	struct rvt_qpn_map *map;
+
+	map = qpt->map + (qpn & RVT_QPN_MASK) / RVT_BITS_PER_PAGE;
+	if (map->page)
+		clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page);
+}
+
 /**
  * rvt_create_qp - create a queue pair for a device
  * @ibpd: the protection domain who's device we create the queue pair for
@@ -914,7 +1019,7 @@ bail_ip:
 		kref_put(&qp->ip->ref, rvt_release_mmap_info);
 
 bail_qpn:
-	free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
+	rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
 
 bail_rq_wq:
 	if (!qp->ip)
@@ -1062,6 +1167,7 @@ int rvt_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	int mig = 0;
 	int pmtu = 0; /* for gcc warning only */
 	enum rdma_link_layer link;
+	int opa_ah;
 
 	link = rdma_port_get_link_layer(ibqp->device, qp->port_num);
 
@@ -1072,6 +1178,7 @@ int rvt_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	cur_state = attr_mask & IB_QP_CUR_STATE ?
 		attr->cur_qp_state : qp->state;
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
+	opa_ah = rdma_cap_opa_ah(ibqp->device, qp->port_num);
 
 	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
 				attr_mask, link))
@@ -1082,17 +1189,31 @@ int rvt_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		goto inval;
 
 	if (attr_mask & IB_QP_AV) {
-		if (rdma_ah_get_dlid(&attr->ah_attr) >=
-		    be16_to_cpu(IB_MULTICAST_LID_BASE))
-			goto inval;
+		if (opa_ah) {
+			if (rdma_ah_get_dlid(&attr->ah_attr) >=
+				opa_get_mcast_base(OPA_MCAST_NR))
+				goto inval;
+		} else {
+			if (rdma_ah_get_dlid(&attr->ah_attr) >=
+				be16_to_cpu(IB_MULTICAST_LID_BASE))
+				goto inval;
+		}
+
 		if (rvt_check_ah(qp->ibqp.device, &attr->ah_attr))
 			goto inval;
 	}
 
 	if (attr_mask & IB_QP_ALT_PATH) {
-		if (rdma_ah_get_dlid(&attr->alt_ah_attr) >=
-		    be16_to_cpu(IB_MULTICAST_LID_BASE))
-			goto inval;
+		if (opa_ah) {
+			if (rdma_ah_get_dlid(&attr->alt_ah_attr) >=
+				opa_get_mcast_base(OPA_MCAST_NR))
+				goto inval;
+		} else {
+			if (rdma_ah_get_dlid(&attr->alt_ah_attr) >=
+				be16_to_cpu(IB_MULTICAST_LID_BASE))
+				goto inval;
+		}
+
 		if (rvt_check_ah(qp->ibqp.device, &attr->alt_ah_attr))
 			goto inval;
 		if (attr->alt_pkey_index >= rvt_get_npkeys(rdi))
@@ -1239,7 +1360,6 @@ int rvt_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 	if (attr_mask & IB_QP_PATH_MTU) {
 		qp->pmtu = rdi->driver_f.mtu_from_qp(rdi, qp, pmtu);
-		qp->path_mtu = rdi->driver_f.mtu_to_path_mtu(qp->pmtu);
 		qp->log_pmtu = ilog2(qp->pmtu);
 	}
 
@@ -1301,19 +1421,6 @@ inval:
 	return -EINVAL;
 }
 
-/** rvt_free_qpn - Free a qpn from the bit map
- * @qpt: QP table
- * @qpn: queue pair number to free
- */
-static void rvt_free_qpn(struct rvt_qpn_table *qpt, u32 qpn)
-{
-	struct rvt_qpn_map *map;
-
-	map = qpt->map + qpn / RVT_BITS_PER_PAGE;
-	if (map->page)
-		clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page);
-}
-
 /**
  * rvt_destroy_qp - destroy a queue pair
  * @ibqp: the queue pair to destroy
@@ -1375,7 +1482,7 @@ int rvt_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 	attr->qp_state = qp->state;
 	attr->cur_qp_state = attr->qp_state;
-	attr->path_mtu = qp->path_mtu;
+	attr->path_mtu = rdi->driver_f.mtu_to_path_mtu(qp->pmtu);
 	attr->path_mig_state = qp->s_mig_state;
 	attr->qkey = qp->qkey;
 	attr->rq_psn = qp->r_psn & rdi->dparms.psn_mask;
@@ -1695,22 +1802,23 @@ static int rvt_post_one_wr(struct rvt_qp *qp,
 	wqe->length = 0;
 	j = 0;
 	if (wr->num_sge) {
+		struct rvt_sge *last_sge = NULL;
+
 		acc = wr->opcode >= IB_WR_RDMA_READ ?
 			IB_ACCESS_LOCAL_WRITE : 0;
 		for (i = 0; i < wr->num_sge; i++) {
 			u32 length = wr->sg_list[i].length;
-			int ok;
 
 			if (length == 0)
 				continue;
-			ok = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j],
-					 &wr->sg_list[i], acc);
-			if (!ok) {
-				ret = -EINVAL;
+			ret = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j], last_sge,
+					  &wr->sg_list[i], acc);
+			if (unlikely(ret < 0))
 				goto bail_inval_free;
-			}
 			wqe->length += length;
-			j++;
+			if (ret)
+				last_sge = &wqe->sg_list[j];
+			j += ret;
 		}
 		wqe->wr.num_sge = j;
 	}
@@ -1757,7 +1865,7 @@ static int rvt_post_one_wr(struct rvt_qp *qp,
 		wqe->wr.send_flags &= ~RVT_SEND_RESERVE_USED;
 		qp->s_avail--;
 	}
-	trace_rvt_post_one_wr(qp, wqe);
+	trace_rvt_post_one_wr(qp, wqe, wr->num_sge);
 	smp_wmb(); /* see request builders */
 	qp->s_head = next;
 
@@ -2065,3 +2173,147 @@ enum hrtimer_restart rvt_rc_rnr_retry(struct hrtimer *t)
 	return HRTIMER_NORESTART;
 }
 EXPORT_SYMBOL(rvt_rc_rnr_retry);
+
+/**
+ * rvt_qp_iter_init - initial for QP iteration
+ * @rdi - rvt devinfo
+ * @v - u64 value
+ *
+ * This returns an iterator suitable for iterating QPs
+ * in the system.
+ *
+ * The @cb is a user defined callback and @v is a 64
+ * bit value passed to and relevant for processing in the
+ * @cb.  An example use case would be to alter QP processing
+ * based on criteria not part of the rvt_qp.
+ *
+ * Use cases that require memory allocation to succeed
+ * must preallocate appropriately.
+ *
+ * Return: a pointer to an rvt_qp_iter or NULL
+ */
+struct rvt_qp_iter *rvt_qp_iter_init(struct rvt_dev_info *rdi,
+				     u64 v,
+				     void (*cb)(struct rvt_qp *qp, u64 v))
+{
+	struct rvt_qp_iter *i;
+
+	i = kzalloc(sizeof(*i), GFP_KERNEL);
+	if (!i)
+		return NULL;
+
+	i->rdi = rdi;
+	/* number of special QPs (SMI/GSI) for device */
+	i->specials = rdi->ibdev.phys_port_cnt * 2;
+	i->v = v;
+	i->cb = cb;
+
+	return i;
+}
+EXPORT_SYMBOL(rvt_qp_iter_init);
+
+/**
+ * rvt_qp_iter_next - return the next QP in iter
+ * @iter - the iterator
+ *
+ * Fine grained QP iterator suitable for use
+ * with debugfs seq_file mechanisms.
+ *
+ * Updates iter->qp with the current QP when the return
+ * value is 0.
+ *
+ * Return: 0 - iter->qp is valid 1 - no more QPs
+ */
+int rvt_qp_iter_next(struct rvt_qp_iter *iter)
+	__must_hold(RCU)
+{
+	int n = iter->n;
+	int ret = 1;
+	struct rvt_qp *pqp = iter->qp;
+	struct rvt_qp *qp;
+	struct rvt_dev_info *rdi = iter->rdi;
+
+	/*
+	 * The approach is to consider the special qps
+	 * as additional table entries before the
+	 * real hash table.  Since the qp code sets
+	 * the qp->next hash link to NULL, this works just fine.
+	 *
+	 * iter->specials is 2 * # ports
+	 *
+	 * n = 0..iter->specials is the special qp indices
+	 *
+	 * n = iter->specials..rdi->qp_dev->qp_table_size+iter->specials are
+	 * the potential hash bucket entries
+	 *
+	 */
+	for (; n <  rdi->qp_dev->qp_table_size + iter->specials; n++) {
+		if (pqp) {
+			qp = rcu_dereference(pqp->next);
+		} else {
+			if (n < iter->specials) {
+				struct rvt_ibport *rvp;
+				int pidx;
+
+				pidx = n % rdi->ibdev.phys_port_cnt;
+				rvp = rdi->ports[pidx];
+				qp = rcu_dereference(rvp->qp[n & 1]);
+			} else {
+				qp = rcu_dereference(
+					rdi->qp_dev->qp_table[
+						(n - iter->specials)]);
+			}
+		}
+		pqp = qp;
+		if (qp) {
+			iter->qp = qp;
+			iter->n = n;
+			return 0;
+		}
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rvt_qp_iter_next);
+
+/**
+ * rvt_qp_iter - iterate all QPs
+ * @rdi - rvt devinfo
+ * @v - a 64 bit value
+ * @cb - a callback
+ *
+ * This provides a way for iterating all QPs.
+ *
+ * The @cb is a user defined callback and @v is a 64
+ * bit value passed to and relevant for processing in the
+ * cb.  An example use case would be to alter QP processing
+ * based on criteria not part of the rvt_qp.
+ *
+ * The code has an internal iterator to simplify
+ * non seq_file use cases.
+ */
+void rvt_qp_iter(struct rvt_dev_info *rdi,
+		 u64 v,
+		 void (*cb)(struct rvt_qp *qp, u64 v))
+{
+	int ret;
+	struct rvt_qp_iter i = {
+		.rdi = rdi,
+		.specials = rdi->ibdev.phys_port_cnt * 2,
+		.v = v,
+		.cb = cb
+	};
+
+	rcu_read_lock();
+	do {
+		ret = rvt_qp_iter_next(&i);
+		if (!ret) {
+			rvt_get_qp(i.qp);
+			rcu_read_unlock();
+			i.cb(i.qp, i.v);
+			rcu_read_lock();
+			rvt_put_qp(i.qp);
+		}
+	} while (!ret);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(rvt_qp_iter);
diff --git a/drivers/infiniband/sw/rdmavt/trace_mr.h b/drivers/infiniband/sw/rdmavt/trace_mr.h
index 3318a6c36373..976e482930a3 100644
--- a/drivers/infiniband/sw/rdmavt/trace_mr.h
+++ b/drivers/infiniband/sw/rdmavt/trace_mr.h
@@ -103,6 +103,68 @@ DEFINE_EVENT(
 	TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len),
 	TP_ARGS(mr, m, n, v, len));
 
+DECLARE_EVENT_CLASS(
+	rvt_sge_template,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge),
+	TP_STRUCT__entry(
+		RDI_DEV_ENTRY(ib_to_rvt(sge->mr->pd->device))
+		__field(struct rvt_mregion *, mr)
+		__field(struct rvt_sge *, sge)
+		__field(struct ib_sge *, isge)
+		__field(void *, vaddr)
+		__field(u64, ivaddr)
+		__field(u32, lkey)
+		__field(u32, sge_length)
+		__field(u32, length)
+		__field(u32, ilength)
+		__field(int, user)
+		__field(u16, m)
+		__field(u16, n)
+	),
+	TP_fast_assign(
+		RDI_DEV_ASSIGN(ib_to_rvt(sge->mr->pd->device));
+		__entry->mr = sge->mr;
+		__entry->sge = sge;
+		__entry->isge = isge;
+		__entry->vaddr = sge->vaddr;
+		__entry->ivaddr = isge->addr;
+		__entry->lkey = sge->mr->lkey;
+		__entry->sge_length = sge->sge_length;
+		__entry->length = sge->length;
+		__entry->ilength = isge->length;
+		__entry->m = sge->m;
+		__entry->n = sge->m;
+		__entry->user = ibpd_to_rvtpd(sge->mr->pd)->user;
+	),
+	TP_printk(
+		"[%s] mr %p sge %p isge %p vaddr %p ivaddr %llx lkey %x sge_length %u length %u ilength %u m %u n %u user %u",
+		__get_str(dev),
+		__entry->mr,
+		__entry->sge,
+		__entry->isge,
+		__entry->vaddr,
+		__entry->ivaddr,
+		__entry->lkey,
+		__entry->sge_length,
+		__entry->length,
+		__entry->ilength,
+		__entry->m,
+		__entry->n,
+		__entry->user
+	)
+);
+
+DEFINE_EVENT(
+	rvt_sge_template, rvt_sge_adjacent,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge));
+
+DEFINE_EVENT(
+	rvt_sge_template, rvt_sge_new,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge));
+
 #endif /* __RVT_TRACE_MR_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/infiniband/sw/rdmavt/trace_tx.h b/drivers/infiniband/sw/rdmavt/trace_tx.h
index a613a2223751..0ef25fc49f25 100644
--- a/drivers/infiniband/sw/rdmavt/trace_tx.h
+++ b/drivers/infiniband/sw/rdmavt/trace_tx.h
@@ -84,12 +84,12 @@ __print_symbolic(opcode,                                   \
 	wr_opcode_name(RESERVED10))
 
 #define POS_PRN \
-"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u"
+"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u wr_num_sge %u"
 
 TRACE_EVENT(
 	rvt_post_one_wr,
-	TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe),
-	TP_ARGS(qp, wqe),
+	TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe, int wr_num_sge),
+	TP_ARGS(qp, wqe, wr_num_sge),
 	TP_STRUCT__entry(
 		RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device))
 		__field(u64, wr_id)
@@ -108,6 +108,7 @@ TRACE_EVENT(
 		__field(int, send_flags)
 		__field(pid_t, pid)
 		__field(int, num_sge)
+		__field(int, wr_num_sge)
 	),
 	TP_fast_assign(
 		RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device))
@@ -127,6 +128,7 @@ TRACE_EVENT(
 		__entry->ssn = wqe->ssn;
 		__entry->send_flags = wqe->wr.send_flags;
 		__entry->num_sge = wqe->wr.num_sge;
+		__entry->wr_num_sge = wr_num_sge;
 	),
 	TP_printk(
 		POS_PRN,
@@ -146,7 +148,8 @@ TRACE_EVENT(
 		__entry->head,
 		__entry->last,
 		__entry->pid,
-		__entry->num_sge
+		__entry->num_sge,
+		__entry->wr_num_sge
 	)
 );
 
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index 0d7c6bb551d9..64bdd442078a 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -202,8 +202,13 @@ static int rvt_modify_port(struct ib_device *ibdev, u8 port_num,
 		return -EINVAL;
 
 	rvp = rdi->ports[port_index];
-	rvp->port_cap_flags |= props->set_port_cap_mask;
-	rvp->port_cap_flags &= ~props->clr_port_cap_mask;
+	if (port_modify_mask & IB_PORT_OPA_MASK_CHG) {
+		rvp->port_cap3_flags |= props->set_port_cap_mask;
+		rvp->port_cap3_flags &= ~props->clr_port_cap_mask;
+	} else {
+		rvp->port_cap_flags |= props->set_port_cap_mask;
+		rvp->port_cap_flags &= ~props->clr_port_cap_mask;
+	}
 
 	if (props->set_port_cap_mask || props->clr_port_cap_mask)
 		rdi->driver_f.cap_mask_chg(rdi, port_num);
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index c21c913f911a..8c3d30b3092d 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -38,7 +38,6 @@
 MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib");
 MODULE_DESCRIPTION("Soft RDMA transport");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION("0.2");
 
 /* free resources for all ports on a device */
 static void rxe_cleanup_ports(struct rxe_dev *rxe)
diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h
index 1ac5b8551a4d..6447d736d5a4 100644
--- a/drivers/infiniband/sw/rxe/rxe.h
+++ b/drivers/infiniband/sw/rxe/rxe.h
@@ -97,7 +97,7 @@ int rxe_rcv(struct sk_buff *skb);
 
 void rxe_dev_put(struct rxe_dev *rxe);
 struct rxe_dev *net_to_rxe(struct net_device *ndev);
-struct rxe_dev *get_rxe_by_name(const char* name);
+struct rxe_dev *get_rxe_by_name(const char *name);
 
 void rxe_port_up(struct rxe_dev *rxe);
 void rxe_port_down(struct rxe_dev *rxe);
diff --git a/drivers/infiniband/sw/rxe/rxe_av.c b/drivers/infiniband/sw/rxe/rxe_av.c
index 5bddf469361b..1cc9e2e1365d 100644
--- a/drivers/infiniband/sw/rxe/rxe_av.c
+++ b/drivers/infiniband/sw/rxe/rxe_av.c
@@ -38,18 +38,13 @@ int rxe_av_chk_attr(struct rxe_dev *rxe, struct rdma_ah_attr *attr)
 {
 	struct rxe_port *port;
 
-	if (rdma_ah_get_port_num(attr) != 1) {
-		pr_info("invalid port_num = %d\n", rdma_ah_get_port_num(attr));
-		return -EINVAL;
-	}
-
 	port = &rxe->port;
 
 	if (rdma_ah_get_ah_flags(attr) & IB_AH_GRH) {
 		u8 sgid_index = rdma_ah_read_grh(attr)->sgid_index;
 
 		if (sgid_index > port->attr.gid_tbl_len) {
-			pr_info("invalid sgid index = %d\n", sgid_index);
+			pr_warn("invalid sgid index = %d\n", sgid_index);
 			return -EINVAL;
 		}
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index 49fe42c23f4d..c4aabf78dc90 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -69,6 +69,14 @@ err1:
 static void rxe_send_complete(unsigned long data)
 {
 	struct rxe_cq *cq = (struct rxe_cq *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cq->cq_lock, flags);
+	if (cq->is_dying) {
+		spin_unlock_irqrestore(&cq->cq_lock, flags);
+		return;
+	}
+	spin_unlock_irqrestore(&cq->cq_lock, flags);
 
 	cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
 }
@@ -97,6 +105,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
 	if (udata)
 		cq->is_user = 1;
 
+	cq->is_dying = false;
+
 	tasklet_init(&cq->comp_task, rxe_send_complete, (unsigned long)cq);
 
 	spin_lock_init(&cq->cq_lock);
@@ -156,6 +166,15 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited)
 	return 0;
 }
 
+void rxe_cq_disable(struct rxe_cq *cq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cq->cq_lock, flags);
+	cq->is_dying = true;
+	spin_unlock_irqrestore(&cq->cq_lock, flags);
+}
+
 void rxe_cq_cleanup(struct rxe_pool_entry *arg)
 {
 	struct rxe_cq *cq = container_of(arg, typeof(*cq), pelem);
diff --git a/drivers/infiniband/sw/rxe/rxe_hw_counters.c b/drivers/infiniband/sw/rxe/rxe_hw_counters.c
index 7ef90aad7dfd..6aeb7a165e46 100644
--- a/drivers/infiniband/sw/rxe/rxe_hw_counters.c
+++ b/drivers/infiniband/sw/rxe/rxe_hw_counters.c
@@ -33,7 +33,7 @@
 #include "rxe.h"
 #include "rxe_hw_counters.h"
 
-const char * const rxe_counter_name[] = {
+static const char * const rxe_counter_name[] = {
 	[RXE_CNT_SENT_PKTS]           =  "sent_pkts",
 	[RXE_CNT_RCVD_PKTS]           =  "rcvd_pkts",
 	[RXE_CNT_DUP_REQ]             =  "duplicate_request",
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index d6299edf9a5b..77b3ed0df936 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -64,6 +64,8 @@ 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_disable(struct rxe_cq *cq);
+
 void rxe_cq_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_mcast.c */
@@ -219,8 +221,6 @@ static inline void rxe_advance_resp_resource(struct rxe_qp *qp)
 void retransmit_timer(unsigned long data);
 void rnr_nak_timer(unsigned long data);
 
-void dump_qp(struct rxe_qp *qp);
-
 /* rxe_srq.c */
 #define IB_SRQ_INIT_MASK (~IB_SRQ_LIMIT)
 
@@ -250,7 +250,7 @@ void rxe_resp_queue_pkt(struct rxe_dev *rxe,
 void rxe_comp_queue_pkt(struct rxe_dev *rxe,
 			struct rxe_qp *qp, struct sk_buff *skb);
 
-static inline unsigned wr_opcode_mask(int opcode, struct rxe_qp *qp)
+static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp)
 {
 	return rxe_wr_opcode_info[opcode].mask[qp->ibqp.qp_type];
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c
index bd812e00988e..d22431e3a908 100644
--- a/drivers/infiniband/sw/rxe/rxe_mmap.c
+++ b/drivers/infiniband/sw/rxe/rxe_mmap.c
@@ -76,7 +76,7 @@ static void rxe_vma_close(struct vm_area_struct *vma)
 	kref_put(&ip->ref, rxe_mmap_release);
 }
 
-static struct vm_operations_struct rxe_vm_ops = {
+static const struct vm_operations_struct rxe_vm_ops = {
 	.open = rxe_vma_open,
 	.close = rxe_vma_close,
 };
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index e37cc89987e1..5c2684bf430f 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -367,11 +367,11 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
 		dest = (dir == to_mem_obj) ?
 			((void *)(uintptr_t)iova) : addr;
 
+		memcpy(dest, src, length);
+
 		if (crcp)
 			*crcp = rxe_crc32(to_rdev(mem->pd->ibpd.device),
-					*crcp, src, length);
-
-		memcpy(dest, src, length);
+					*crcp, dest, length);
 
 		return 0;
 	}
@@ -401,11 +401,11 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
 		if (bytes > length)
 			bytes = length;
 
+		memcpy(dest, src, bytes);
+
 		if (crcp)
 			crc = rxe_crc32(to_rdev(mem->pd->ibpd.device),
-					crc, src, bytes);
-
-		memcpy(dest, src, bytes);
+					crc, dest, bytes);
 
 		length	-= bytes;
 		addr	+= bytes;
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 08f3f90d2912..59dee10bebcb 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -191,7 +191,7 @@ static struct dst_entry *rxe_find_route(struct rxe_dev *rxe,
 	if (qp_type(qp) == IB_QPT_RC)
 		dst = sk_dst_get(qp->sk->sk);
 
-	if (!dst || !(dst->obsolete && dst->ops->check(dst, 0))) {
+	if (!dst || !dst_check(dst, qp->dst_cookie)) {
 		if (dst)
 			dst_release(dst);
 
@@ -209,6 +209,11 @@ static struct dst_entry *rxe_find_route(struct rxe_dev *rxe,
 			saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr;
 			daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr;
 			dst = rxe_find_route6(rxe->ndev, saddr6, daddr6);
+#if IS_ENABLED(CONFIG_IPV6)
+			if (dst)
+				qp->dst_cookie =
+					rt6_get_cookie((struct rt6_info *)dst);
+#endif
 		}
 	}
 
@@ -337,7 +342,7 @@ static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb,
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
 			    | IPSKB_REROUTED);
-	skb_dst_set(skb, dst);
+	skb_dst_set(skb, dst_clone(dst));
 
 	__skb_push(skb, sizeof(*ip6h));
 	skb_reset_network_header(skb);
@@ -388,7 +393,7 @@ static int prepare6(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
 		    struct sk_buff *skb, struct rxe_av *av)
 {
 	struct rxe_qp *qp = pkt->qp;
-	struct dst_entry *dst = NULL;
+	struct dst_entry *dst;
 	struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr;
 	struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr;
 
@@ -460,12 +465,17 @@ int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb)
 	nskb->destructor = rxe_skb_tx_dtor;
 	nskb->sk = pkt->qp->sk->sk;
 
+	rxe_add_ref(pkt->qp);
+	atomic_inc(&pkt->qp->skb_out);
+
 	if (av->network_type == RDMA_NETWORK_IPV4) {
 		err = ip_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb);
 	} else if (av->network_type == RDMA_NETWORK_IPV6) {
 		err = ip6_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb);
 	} else {
 		pr_err("Unknown layer 3 protocol: %d\n", av->network_type);
+		atomic_dec(&pkt->qp->skb_out);
+		rxe_drop_ref(pkt->qp);
 		kfree_skb(nskb);
 		return -EINVAL;
 	}
@@ -475,10 +485,7 @@ int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb)
 		return -EAGAIN;
 	}
 
-	rxe_add_ref(pkt->qp);
-	atomic_inc(&pkt->qp->skb_out);
 	kfree_skb(skb);
-
 	return 0;
 }
 
@@ -644,8 +651,13 @@ static int rxe_notify(struct notifier_block *not_blk,
 		pr_info("%s changed mtu to %d\n", ndev->name, ndev->mtu);
 		rxe_set_mtu(rxe, ndev->mtu);
 		break;
-	case NETDEV_REBOOT:
 	case NETDEV_CHANGE:
+		if (netif_running(ndev) && netif_carrier_ok(ndev))
+			rxe_port_up(rxe);
+		else
+			rxe_port_down(rxe);
+		break;
+	case NETDEV_REBOOT:
 	case NETDEV_GOING_DOWN:
 	case NETDEV_CHANGEADDR:
 	case NETDEV_CHANGENAME:
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 75d11ee635ec..c1b5f38f31a5 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -188,7 +188,7 @@ int rxe_pool_init(
 	struct rxe_dev		*rxe,
 	struct rxe_pool		*pool,
 	enum rxe_elem_type	type,
-	unsigned		max_elem)
+	unsigned int		max_elem)
 {
 	int			err = 0;
 	size_t			size = rxe_type_info[type].size;
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 80ccc7c7c341..00bda9380a2e 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -851,13 +851,8 @@ void rxe_qp_cleanup(struct rxe_pool_entry *arg)
 		qp->resp.mr = NULL;
 	}
 
-	if (qp_type(qp) == IB_QPT_RC) {
-		struct dst_entry *dst = NULL;
-
-		dst = sk_dst_get(qp->sk->sk);
-		if (dst)
-			dst_release(dst);
-	}
+	if (qp_type(qp) == IB_QPT_RC)
+		sk_dst_reset(qp->sk->sk);
 
 	free_rd_atomic_resources(qp);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 7ee465d1a1e1..d84222f9d5d2 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -43,7 +43,7 @@ static int next_opcode(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 
 static inline void retry_first_write_send(struct rxe_qp *qp,
 					  struct rxe_send_wqe *wqe,
-					  unsigned mask, int npsn)
+					  unsigned int mask, int npsn)
 {
 	int i;
 
@@ -594,8 +594,10 @@ int rxe_requester(void *arg)
 	rxe_add_ref(qp);
 
 next_wqe:
-	if (unlikely(!qp->valid))
+	if (unlikely(!qp->valid)) {
+		rxe_drain_req_pkts(qp, true);
 		goto exit;
+	}
 
 	if (unlikely(qp->req.state == QP_STATE_ERROR)) {
 		rxe_drain_req_pkts(qp, true);
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index a958ee918a49..4240866a5331 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -1055,7 +1055,7 @@ static struct resp_res *find_resource(struct rxe_qp *qp, u32 psn)
 {
 	int i;
 
-	for (i = 0; i < qp->attr.max_rd_atomic; i++) {
+	for (i = 0; i < qp->attr.max_dest_rd_atomic; i++) {
 		struct resp_res *res = &qp->resp.resources[i];
 
 		if (res->type == 0)
diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c
index d2a14a1bdc7f..ea3810b29273 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.c
+++ b/drivers/infiniband/sw/rxe/rxe_task.c
@@ -78,7 +78,7 @@ void rxe_do_task(unsigned long data)
 
 	default:
 		spin_unlock_irqrestore(&task->state_lock, flags);
-		pr_warn("bad state = %d in rxe_do_task\n", task->state);
+		pr_warn("%s failed with bad state %d\n", __func__, task->state);
 		return;
 	}
 
@@ -105,7 +105,7 @@ void rxe_do_task(unsigned long data)
 			break;
 
 		default:
-			pr_warn("bad state = %d in rxe_do_task\n",
+			pr_warn("%s failed with bad state %d\n", __func__,
 				task->state);
 		}
 		spin_unlock_irqrestore(&task->state_lock, flags);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index af90a7d42b96..0b362f49a10a 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -51,40 +51,16 @@ static int rxe_query_device(struct ib_device *dev,
 	return 0;
 }
 
-static void rxe_eth_speed_to_ib_speed(int speed, u8 *active_speed,
-				      u8 *active_width)
-{
-	if (speed <= 1000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_SDR;
-	} else if (speed <= 10000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_FDR10;
-	} else if (speed <= 20000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_DDR;
-	} else if (speed <= 30000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_QDR;
-	} else if (speed <= 40000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_FDR10;
-	} else {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_EDR;
-	}
-}
-
 static int rxe_query_port(struct ib_device *dev,
 			  u8 port_num, struct ib_port_attr *attr)
 {
 	struct rxe_dev *rxe = to_rdev(dev);
 	struct rxe_port *port;
-	u32 speed;
+	int rc = -EINVAL;
 
 	if (unlikely(port_num != 1)) {
 		pr_warn("invalid port_number %d\n", port_num);
-		goto err1;
+		goto out;
 	}
 
 	port = &rxe->port;
@@ -93,29 +69,12 @@ static int rxe_query_port(struct ib_device *dev,
 	*attr = port->attr;
 
 	mutex_lock(&rxe->usdev_lock);
-	if (rxe->ndev->ethtool_ops->get_link_ksettings) {
-		struct ethtool_link_ksettings ks;
-
-		rxe->ndev->ethtool_ops->get_link_ksettings(rxe->ndev, &ks);
-		speed = ks.base.speed;
-	} else if (rxe->ndev->ethtool_ops->get_settings) {
-		struct ethtool_cmd cmd;
-
-		rxe->ndev->ethtool_ops->get_settings(rxe->ndev, &cmd);
-		speed = cmd.speed;
-	} else {
-		pr_warn("%s speed is unknown, defaulting to 1000\n",
-			rxe->ndev->name);
-		speed = 1000;
-	}
-	rxe_eth_speed_to_ib_speed(speed, &attr->active_speed,
-				  &attr->active_width);
+	rc = ib_get_eth_speed(dev, port_num, &attr->active_speed,
+			      &attr->active_width);
 	mutex_unlock(&rxe->usdev_lock);
 
-	return 0;
-
-err1:
-	return -EINVAL;
+out:
+	return rc;
 }
 
 static int rxe_query_gid(struct ib_device *device,
@@ -960,6 +919,8 @@ static int rxe_destroy_cq(struct ib_cq *ibcq)
 {
 	struct rxe_cq *cq = to_rcq(ibcq);
 
+	rxe_cq_disable(cq);
+
 	rxe_drop_ref(cq);
 	return 0;
 }
@@ -1210,8 +1171,8 @@ static int rxe_detach_mcast(struct ib_qp *ibqp, union ib_gid *mgid, u16 mlid)
 	return rxe_mcast_drop_grp_elem(rxe, qp, mgid);
 }
 
-static ssize_t rxe_show_parent(struct device *device,
-			       struct device_attribute *attr, char *buf)
+static ssize_t parent_show(struct device *device,
+			   struct device_attribute *attr, char *buf)
 {
 	struct rxe_dev *rxe = container_of(device, struct rxe_dev,
 					   ib_dev.dev);
@@ -1219,7 +1180,7 @@ static ssize_t rxe_show_parent(struct device *device,
 	return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1));
 }
 
-static DEVICE_ATTR(parent, S_IRUGO, rxe_show_parent, NULL);
+static DEVICE_ATTR_RO(parent);
 
 static struct device_attribute *rxe_dev_attributes[] = {
 	&dev_attr_parent,
@@ -1336,15 +1297,15 @@ int rxe_register_device(struct rxe_dev *rxe)
 
 	err = ib_register_device(dev, NULL);
 	if (err) {
-		pr_warn("rxe_register_device failed, err = %d\n", err);
+		pr_warn("%s failed with error %d\n", __func__, err);
 		goto err1;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(rxe_dev_attributes); ++i) {
 		err = device_create_file(&dev->dev, rxe_dev_attributes[i]);
 		if (err) {
-			pr_warn("device_create_file failed, i = %d, err = %d\n",
-				i, err);
+			pr_warn("%s failed with error %d for attr number %d\n",
+				__func__, err, i);
 			goto err2;
 		}
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 5a180fbe40d9..0c2dbe45c729 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -89,6 +89,7 @@ struct rxe_cq {
 	struct rxe_queue	*queue;
 	spinlock_t		cq_lock;
 	u8			notify;
+	bool			is_dying;
 	int			is_user;
 	struct tasklet_struct	comp_task;
 };
@@ -247,6 +248,7 @@ struct rxe_qp {
 	struct rxe_rq		rq;
 
 	struct socket		*sk;
+	u32			dst_cookie;
 
 	struct rxe_av		pri_av;
 	struct rxe_av		alt_av;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 7ac25059c40f..4a5c7a07a631 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -337,6 +337,7 @@ struct ipoib_dev_priv {
 
 	struct rw_semaphore vlan_rwsem;
 	struct mutex mcast_mutex;
+	struct mutex sysfs_mutex;
 
 	struct rb_root  path_tree;
 	struct list_head path_list;
@@ -367,7 +368,7 @@ struct ipoib_dev_priv {
 	u32		  qkey;
 
 	union ib_gid local_gid;
-	u16	     local_lid;
+	u32	     local_lid;
 
 	unsigned int admin_mtu;
 	unsigned int mcast_mtu;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index d69410c2ed97..14b62f7472b4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1506,9 +1506,14 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 	if (test_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags))
 		return -EPERM;
 
-	if (!rtnl_trylock())
+	if (!mutex_trylock(&priv->sysfs_mutex))
 		return restart_syscall();
 
+	if (!rtnl_trylock()) {
+		mutex_unlock(&priv->sysfs_mutex);
+		return restart_syscall();
+	}
+
 	ret = ipoib_set_mode(dev, buf);
 
 	/* The assumption is that the function ipoib_set_mode returned
@@ -1517,6 +1522,7 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 	 */
 	if (ret != -EBUSY)
 		rtnl_unlock();
+	mutex_unlock(&priv->sysfs_mutex);
 
 	return (!ret || ret == -EBUSY) ? count : ret;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
index 184a22f48027..8dc1e6225cc8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
@@ -63,8 +63,7 @@ static void ipoib_get_drvinfo(struct net_device *netdev,
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(netdev);
 
-	ib_get_device_fw_str(priv->ca, drvinfo->fw_version,
-			     sizeof(drvinfo->fw_version));
+	ib_get_device_fw_str(priv->ca, drvinfo->fw_version);
 
 	strlcpy(drvinfo->bus_info, dev_name(priv->ca->dev.parent),
 		sizeof(drvinfo->bus_info));
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 6c77df34869d..bac95b509a9b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -60,7 +60,6 @@ const char ipoib_driver_version[] = DRV_VERSION;
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("IP-over-InfiniBand net driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 
 int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE;
 int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE;
@@ -100,6 +99,8 @@ static struct net_device *ipoib_get_net_dev_by_params(
 		const union ib_gid *gid, const struct sockaddr *addr,
 		void *client_data);
 static int ipoib_set_mac(struct net_device *dev, void *addr);
+static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr,
+		       int cmd);
 
 static struct ib_client ipoib_client = {
 	.name   = "ipoib",
@@ -1681,6 +1682,17 @@ out:
 	return -ENOMEM;
 }
 
+static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr,
+		       int cmd)
+{
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+	if (!priv->rn_ops->ndo_do_ioctl)
+		return -EOPNOTSUPP;
+
+	return priv->rn_ops->ndo_do_ioctl(dev, ifr, cmd);
+}
+
 int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -1835,6 +1847,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = {
 	.ndo_set_vf_guid	 = ipoib_set_vf_guid,
 	.ndo_set_mac_address	 = ipoib_set_mac,
 	.ndo_get_stats64	 = ipoib_get_stats,
+	.ndo_do_ioctl		 = ipoib_ioctl,
 };
 
 static const struct net_device_ops ipoib_netdev_ops_vf = {
@@ -1848,6 +1861,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = {
 	.ndo_set_rx_mode	 = ipoib_set_mcast_list,
 	.ndo_get_iflink		 = ipoib_get_iflink,
 	.ndo_get_stats64	 = ipoib_get_stats,
+	.ndo_do_ioctl		 = ipoib_ioctl,
 };
 
 void ipoib_setup_common(struct net_device *dev)
@@ -1879,6 +1893,7 @@ static void ipoib_build_priv(struct net_device *dev)
 	spin_lock_init(&priv->lock);
 	init_rwsem(&priv->vlan_rwsem);
 	mutex_init(&priv->mcast_mutex);
+	mutex_init(&priv->sysfs_mutex);
 
 	INIT_LIST_HEAD(&priv->path_list);
 	INIT_LIST_HEAD(&priv->child_intfs);
@@ -2228,13 +2243,7 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	INIT_IB_EVENT_HANDLER(&priv->event_handler,
 			      priv->ca, ipoib_event);
-	result = ib_register_event_handler(&priv->event_handler);
-	if (result < 0) {
-		printk(KERN_WARNING "%s: ib_register_event_handler failed for "
-		       "port %d (ret = %d)\n",
-		       hca->name, port, result);
-		goto event_failed;
-	}
+	ib_register_event_handler(&priv->event_handler);
 
 	result = register_netdev(priv->dev);
 	if (result) {
@@ -2267,8 +2276,6 @@ register_failed:
 	set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	cancel_delayed_work(&priv->neigh_reap_task);
 	flush_workqueue(priv->wq);
-
-event_failed:
 	ipoib_dev_cleanup(priv->dev);
 
 device_init_failed:
@@ -2338,7 +2345,11 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 		cancel_delayed_work(&priv->neigh_reap_task);
 		flush_workqueue(priv->wq);
 
+		/* Wrap rtnl_lock/unlock with mutex to protect sysfs calls */
+		mutex_lock(&priv->sysfs_mutex);
 		unregister_netdev(priv->dev);
+		mutex_unlock(&priv->sysfs_mutex);
+
 		rn->free_rdma_netdev(priv->dev);
 
 		list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 081b33deff1b..9927cd6b7082 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -133,12 +133,20 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 	snprintf(intf_name, sizeof intf_name, "%s.%04x",
 		 ppriv->dev->name, pkey);
 
-	if (!rtnl_trylock())
+	if (!mutex_trylock(&ppriv->sysfs_mutex))
 		return restart_syscall();
 
+	if (!rtnl_trylock()) {
+		mutex_unlock(&ppriv->sysfs_mutex);
+		return restart_syscall();
+	}
+
 	priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name);
-	if (!priv)
+	if (!priv) {
+		rtnl_unlock();
+		mutex_unlock(&ppriv->sysfs_mutex);
 		return -ENOMEM;
+	}
 
 	down_write(&ppriv->vlan_rwsem);
 
@@ -164,8 +172,8 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 
 out:
 	up_write(&ppriv->vlan_rwsem);
-
 	rtnl_unlock();
+	mutex_unlock(&ppriv->sysfs_mutex);
 
 	if (result) {
 		free_netdev(priv->dev);
@@ -188,8 +196,13 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 	if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
 		return -EPERM;
 
-	if (!rtnl_trylock())
+	if (!mutex_trylock(&ppriv->sysfs_mutex))
+		return restart_syscall();
+
+	if (!rtnl_trylock()) {
+		mutex_unlock(&ppriv->sysfs_mutex);
 		return restart_syscall();
+	}
 
 	down_write(&ppriv->vlan_rwsem);
 	list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
@@ -208,6 +221,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 	}
 
 	rtnl_unlock();
+	mutex_unlock(&ppriv->sysfs_mutex);
 
 	if (dev) {
 		free_netdev(dev);
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 37b33d708c2d..19624e023ebd 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -77,7 +77,6 @@
 MODULE_DESCRIPTION("iSER (iSCSI Extensions for RDMA) Datamover");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Alex Nezhinsky, Dan Bar Dov, Or Gerlitz");
-MODULE_VERSION(DRV_VER);
 
 static struct scsi_host_template iscsi_iser_sht;
 static struct iscsi_transport iscsi_iser_transport;
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 26a004e97ae0..55a73b0ed4c6 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -106,9 +106,7 @@ static int iser_create_device_ib_res(struct iser_device *device)
 
 	INIT_IB_EVENT_HANDLER(&device->event_handler, ib_dev,
 			      iser_event_handler);
-	if (ib_register_event_handler(&device->event_handler))
-		goto cq_err;
-
+	ib_register_event_handler(&device->event_handler);
 	return 0;
 
 cq_err:
@@ -141,7 +139,7 @@ static void iser_free_device_ib_res(struct iser_device *device)
 		comp->cq = NULL;
 	}
 
-	(void)ib_unregister_event_handler(&device->event_handler);
+	ib_unregister_event_handler(&device->event_handler);
 	ib_dealloc_pd(device->pd);
 
 	kfree(device->comps);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 0e662656ef42..ceabdb85df8b 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -2710,7 +2710,6 @@ static void __exit isert_exit(void)
 }
 
 MODULE_DESCRIPTION("iSER-Target for mainline target infrastructure");
-MODULE_VERSION("1.0");
 MODULE_AUTHOR("nab@Linux-iSCSI.org");
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
index cf768dd78d1b..21f0b481edcc 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
@@ -52,7 +52,9 @@
 
 #include <linux/module.h>
 #include <rdma/ib_addr.h>
-#include <rdma/ib_smi.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/opa_smi.h>
+#include <rdma/opa_port_info.h>
 
 #include "opa_vnic_internal.h"
 
@@ -952,12 +954,7 @@ static int vema_register(struct opa_vnic_ctrl_port *cport)
 
 		INIT_IB_EVENT_HANDLER(&port->event_handler,
 				      cport->ibdev, opa_vnic_event);
-		ret = ib_register_event_handler(&port->event_handler);
-		if (ret) {
-			c_err("port %d: event handler register failed\n", i);
-			vema_unregister(cport);
-			return ret;
-		}
+		ib_register_event_handler(&port->event_handler);
 
 		idr_init(&port->vport_idr);
 		mutex_init(&port->lock);
@@ -980,6 +977,27 @@ static int vema_register(struct opa_vnic_ctrl_port *cport)
 }
 
 /**
+ * opa_vnic_ctrl_config_dev -- This function sends a trap to the EM
+ * by way of ib_modify_port to indicate support for ethernet on the
+ * fabric.
+ * @cport: pointer to control port
+ * @en: enable or disable ethernet on fabric support
+ */
+static void opa_vnic_ctrl_config_dev(struct opa_vnic_ctrl_port *cport, bool en)
+{
+	struct ib_port_modify pm = { 0 };
+	int i;
+
+	if (en)
+		pm.set_port_cap_mask = OPA_CAP_MASK3_IsEthOnFabricSupported;
+	else
+		pm.clr_port_cap_mask = OPA_CAP_MASK3_IsEthOnFabricSupported;
+
+	for (i = 1; i <= cport->num_ports; i++)
+		ib_modify_port(cport->ibdev, i, IB_PORT_OPA_MASK_CHG, &pm);
+}
+
+/**
  * opa_vnic_vema_add_one -- Handle new ib device
  * @device: ib device pointer
  *
@@ -1007,6 +1025,7 @@ static void opa_vnic_vema_add_one(struct ib_device *device)
 		c_info("VNIC client initialized\n");
 
 	ib_set_client_data(device, &opa_vnic_client, cport);
+	opa_vnic_ctrl_config_dev(cport, true);
 }
 
 /**
@@ -1025,6 +1044,7 @@ static void opa_vnic_vema_rem_one(struct ib_device *device,
 		return;
 
 	c_info("removing VNIC client\n");
+	opa_vnic_ctrl_config_dev(cport, false);
 	vema_unregister(cport);
 	kfree(cport);
 }
@@ -1053,4 +1073,3 @@ module_exit(opa_vnic_deinit);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel Corporation");
 MODULE_DESCRIPTION("Intel OPA Virtual Network driver");
-MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 2354c742caa1..fa5ccdb3bb2a 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -62,7 +62,6 @@
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 MODULE_INFO(release_date, DRV_RELDATE);
 
 #if !defined(CONFIG_DYNAMIC_DEBUG)
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 402275be0931..9e8e9220f816 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2238,7 +2238,7 @@ static int srpt_write_pending(struct se_cmd *se_cmd)
 				cqe, first_wr);
 		cqe = NULL;
 	}
-	
+
 	ret = ib_post_send(ch->qp, first_wr, &bad_wr);
 	if (ret) {
 		pr_err("%s: ib_post_send() returned %d for %d (avail: %d)\n",
@@ -2530,8 +2530,7 @@ static void srpt_add_one(struct ib_device *device)
 
 	INIT_IB_EVENT_HANDLER(&sdev->event_handler, sdev->device,
 			      srpt_event_handler);
-	if (ib_register_event_handler(&sdev->event_handler))
-		goto err_cm;
+	ib_register_event_handler(&sdev->event_handler);
 
 	sdev->ioctx_ring = (struct srpt_recv_ioctx **)
 		srpt_alloc_ioctx_ring(sdev, sdev->srq_size,
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index cc1183851af5..1b817e51b84b 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -328,8 +328,8 @@ struct srpt_port {
 	u8			port_guid[24];
 	u8			port_gid[64];
 	u8			port;
-	u16			sm_lid;
-	u16			lid;
+	u32			sm_lid;
+	u32			lid;
 	union ib_gid		gid;
 	struct work_struct	work;
 	struct se_portal_group	port_guid_tpg;