Merge branch 'from-rc' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git

Patches for 4.16 that are dependent on patches sent to 4.15-rc.

These are small clean ups for the vmw_pvrdma and i40iw drivers.

* 'from-rc' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git:
  RDMA/vmw_pvrdma: Remove usage of BIT() from UAPI header
  RDMA/vmw_pvrdma: Use refcount_t instead of atomic_t
  RDMA/vmw_pvrdma: Use more specific sizeof in kcalloc
  RDMA/vmw_pvrdma: Clarify QP and CQ is_kernel logic
  RDMA/vmw_pvrdma: Add UAR SRQ macros in ABI header file
  i40iw: Change accelerated flag to bool

40 files changed, 422 insertions, 226 deletions

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 98ac46ed7214..cbf186522016 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -1,6 +1,6 @@
 menuconfig INFINIBAND
 	tristate "InfiniBand support"
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAS_DMA
 	depends on NET
 	depends on INET
 	depends on m || IPV6 != m
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 5ab646a24089..7d38c2bff5ea 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -801,6 +801,7 @@ struct rdma_cm_id *rdma_create_id(struct net *net,
 	INIT_LIST_HEAD(&id_priv->mc_list);
 	get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
 	id_priv->id.route.addr.dev_addr.net = get_net(net);
+	id_priv->seq_num &= 0x00ffffff;
 
 	return &id_priv->id;
 }
@@ -4453,7 +4454,7 @@ out:
 	return skb->len;
 }
 
-static const struct rdma_nl_cbs cma_cb_table[] = {
+static const struct rdma_nl_cbs cma_cb_table[RDMA_NL_RDMA_CM_NUM_OPS] = {
 	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index bb2686d56d3c..21302e077be1 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1136,7 +1136,7 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
-static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
+static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
 		.doit = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
@@ -1243,5 +1243,5 @@ static void __exit ib_core_cleanup(void)
 
 MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4);
 
-module_init(ib_core_init);
+subsys_initcall(ib_core_init);
 module_exit(ib_core_cleanup);
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index e9e189ec7502..5d676cff41f4 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 rdma_nl_cbs iwcm_nl_cb_table[] = {
+static struct rdma_nl_cbs iwcm_nl_cb_table[RDMA_NL_IWPM_NUM_OPS] = {
 	[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},
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 2fae850a3eff..9a05245a1acf 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -303,7 +303,7 @@ out:	cb->args[0] = idx;
 	return skb->len;
 }
 
-static const struct rdma_nl_cbs nldev_cb_table[] = {
+static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index 209d0574fc1f..b61dda6b04fc 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -386,6 +386,9 @@ int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev)
 	if (ret)
 		return ret;
 
+	if (!qp->qp_sec)
+		return 0;
+
 	mutex_lock(&real_qp->qp_sec->mutex);
 	ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys,
 					  qp->qp_sec);
@@ -417,8 +420,17 @@ void ib_close_shared_qp_security(struct ib_qp_security *sec)
 
 int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev)
 {
+	u8 i = rdma_start_port(dev);
+	bool is_ib = false;
 	int ret;
 
+	while (i <= rdma_end_port(dev) && !is_ib)
+		is_ib = rdma_protocol_ib(dev, i++);
+
+	/* If this isn't an IB device don't create the security context */
+	if (!is_ib)
+		return 0;
+
 	qp->qp_sec = kzalloc(sizeof(*qp->qp_sec), GFP_KERNEL);
 	if (!qp->qp_sec)
 		return -ENOMEM;
@@ -441,6 +453,10 @@ EXPORT_SYMBOL(ib_create_qp_security);
 
 void ib_destroy_qp_security_begin(struct ib_qp_security *sec)
 {
+	/* Return if not IB */
+	if (!sec)
+		return;
+
 	mutex_lock(&sec->mutex);
 
 	/* Remove the QP from the lists so it won't get added to
@@ -470,6 +486,10 @@ void ib_destroy_qp_security_abort(struct ib_qp_security *sec)
 	int ret;
 	int i;
 
+	/* Return if not IB */
+	if (!sec)
+		return;
+
 	/* If a concurrent cache update is in progress this
 	 * QP security could be marked for an error state
 	 * transition.  Wait for this to complete.
@@ -505,6 +525,10 @@ void ib_destroy_qp_security_end(struct ib_qp_security *sec)
 {
 	int i;
 
+	/* Return if not IB */
+	if (!sec)
+		return;
+
 	/* If a concurrent cache update is occurring we must
 	 * wait until this QP security structure is processed
 	 * in the QP to error flow before destroying it because
@@ -557,7 +581,7 @@ int ib_security_modify_qp(struct ib_qp *qp,
 {
 	int ret = 0;
 	struct ib_ports_pkeys *tmp_pps;
-	struct ib_ports_pkeys *new_pps;
+	struct ib_ports_pkeys *new_pps = NULL;
 	struct ib_qp *real_qp = qp->real_qp;
 	bool special_qp = (real_qp->qp_type == IB_QPT_SMI ||
 			   real_qp->qp_type == IB_QPT_GSI ||
@@ -565,18 +589,27 @@ int ib_security_modify_qp(struct ib_qp *qp,
 	bool pps_change = ((qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) ||
 			   (qp_attr_mask & IB_QP_ALT_PATH));
 
+	WARN_ONCE((qp_attr_mask & IB_QP_PORT &&
+		   rdma_protocol_ib(real_qp->device, qp_attr->port_num) &&
+		   !real_qp->qp_sec),
+		   "%s: QP security is not initialized for IB QP: %d\n",
+		   __func__, real_qp->qp_num);
+
 	/* The port/pkey settings are maintained only for the real QP. Open
 	 * handles on the real QP will be in the shared_qp_list. When
 	 * enforcing security on the real QP all the shared QPs will be
 	 * checked as well.
 	 */
 
-	if (pps_change && !special_qp) {
+	if (pps_change && !special_qp && real_qp->qp_sec) {
 		mutex_lock(&real_qp->qp_sec->mutex);
 		new_pps = get_new_pps(real_qp,
 				      qp_attr,
 				      qp_attr_mask);
-
+		if (!new_pps) {
+			mutex_unlock(&real_qp->qp_sec->mutex);
+			return -ENOMEM;
+		}
 		/* Add this QP to the lists for the new port
 		 * and pkey settings before checking for permission
 		 * in case there is a concurrent cache update
@@ -600,7 +633,7 @@ int ib_security_modify_qp(struct ib_qp *qp,
 						 qp_attr_mask,
 						 udata);
 
-	if (pps_change && !special_qp) {
+	if (new_pps) {
 		/* Clean up the lists and free the appropriate
 		 * ports_pkeys structure.
 		 */
@@ -630,6 +663,9 @@ static int ib_security_pkey_access(struct ib_device *dev,
 	u16 pkey;
 	int ret;
 
+	if (!rdma_protocol_ib(dev, port_num))
+		return 0;
+
 	ret = ib_get_cached_pkey(dev, port_num, pkey_index, &pkey);
 	if (ret)
 		return ret;
@@ -663,6 +699,9 @@ int ib_mad_agent_security_setup(struct ib_mad_agent *agent,
 {
 	int ret;
 
+	if (!rdma_protocol_ib(agent->device, agent->port_num))
+		return 0;
+
 	ret = security_ib_alloc_security(&agent->security);
 	if (ret)
 		return ret;
@@ -688,6 +727,9 @@ int ib_mad_agent_security_setup(struct ib_mad_agent *agent,
 
 void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent)
 {
+	if (!rdma_protocol_ib(agent->device, agent->port_num))
+		return;
+
 	security_ib_free_security(agent->security);
 	if (agent->lsm_nb_reg)
 		unregister_lsm_notifier(&agent->lsm_nb);
@@ -695,8 +737,14 @@ void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent)
 
 int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index)
 {
-	if (map->agent.qp->qp_type == IB_QPT_SMI && !map->agent.smp_allowed)
-		return -EACCES;
+	if (!rdma_protocol_ib(map->agent.device, map->agent.port_num))
+		return 0;
+
+	if (map->agent.qp->qp_type == IB_QPT_SMI) {
+		if (!map->agent.smp_allowed)
+			return -EACCES;
+		return 0;
+	}
 
 	return ib_security_pkey_access(map->agent.device,
 				       map->agent.port_num,
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index adc6a2379c76..c216d98bb816 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1968,6 +1968,12 @@ static int modify_qp(struct ib_uverbs_file *file,
 		goto release_qp;
 	}
 
+	if ((cmd->base.attr_mask & IB_QP_ALT_PATH) &&
+	    !rdma_is_port_valid(qp->device, cmd->base.alt_port_num)) {
+		ret = -EINVAL;
+		goto release_qp;
+	}
+
 	attr->qp_state		  = cmd->base.qp_state;
 	attr->cur_qp_state	  = cmd->base.cur_qp_state;
 	attr->path_mtu		  = cmd->base.path_mtu;
@@ -2065,8 +2071,8 @@ int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file,
 		return -EOPNOTSUPP;
 
 	if (ucore->inlen > sizeof(cmd)) {
-		if (ib_is_udata_cleared(ucore, sizeof(cmd),
-					ucore->inlen - sizeof(cmd)))
+		if (!ib_is_udata_cleared(ucore, sizeof(cmd),
+					 ucore->inlen - sizeof(cmd)))
 			return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index b53fb0e98751..fe72fb303b01 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1439,7 +1439,8 @@ int ib_close_qp(struct ib_qp *qp)
 	spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags);
 
 	atomic_dec(&real_qp->usecnt);
-	ib_close_shared_qp_security(qp->qp_sec);
+	if (qp->qp_sec)
+		ib_close_shared_qp_security(qp->qp_sec);
 	kfree(qp);
 
 	return 0;
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index ea55e95cd2c5..6f2b26126c64 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -395,6 +395,11 @@ next_cqe:
 
 static int cqe_completes_wr(struct t4_cqe *cqe, struct t4_wq *wq)
 {
+	if (DRAIN_CQE(cqe)) {
+		WARN_ONCE(1, "Unexpected DRAIN CQE qp id %u!\n", wq->sq.qid);
+		return 0;
+	}
+
 	if (CQE_OPCODE(cqe) == FW_RI_TERMINATE)
 		return 0;
 
@@ -489,7 +494,7 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 	/*
 	 * Special cqe for drain WR completions...
 	 */
-	if (CQE_OPCODE(hw_cqe) == C4IW_DRAIN_OPCODE) {
+	if (DRAIN_CQE(hw_cqe)) {
 		*cookie = CQE_DRAIN_COOKIE(hw_cqe);
 		*cqe = *hw_cqe;
 		goto skip_cqe;
@@ -566,10 +571,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 			ret = -EAGAIN;
 			goto skip_cqe;
 		}
-		if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) {
+		if (unlikely(!CQE_STATUS(hw_cqe) &&
+			     CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) {
 			t4_set_wq_in_error(wq);
-			hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN));
-			goto proc_cqe;
+			hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN));
 		}
 		goto proc_cqe;
 	}
@@ -743,9 +748,6 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 				c4iw_invalidate_mr(qhp->rhp,
 						   CQE_WRID_FR_STAG(&cqe));
 			break;
-		case C4IW_DRAIN_OPCODE:
-			wc->opcode = IB_WC_SEND;
-			break;
 		default:
 			pr_err("Unexpected opcode %d in the CQE received for QPID=0x%0x\n",
 			       CQE_OPCODE(&cqe), CQE_QPID(&cqe));
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 37ff2ad8a3d4..cc929002c05e 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -693,8 +693,6 @@ static inline int to_ib_qp_state(int c4iw_qp_state)
 	return IB_QPS_ERR;
 }
 
-#define C4IW_DRAIN_OPCODE FW_RI_SGE_EC_CR_RETURN
-
 static inline u32 c4iw_ib_to_tpt_access(int a)
 {
 	return (a & IB_ACCESS_REMOTE_WRITE ? FW_RI_MEM_ACCESS_REM_WRITE : 0) |
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 8018533ab705..de77b6027d69 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -790,21 +790,57 @@ static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc)
 	return 0;
 }
 
-static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
+static int ib_to_fw_opcode(int ib_opcode)
+{
+	int opcode;
+
+	switch (ib_opcode) {
+	case IB_WR_SEND_WITH_INV:
+		opcode = FW_RI_SEND_WITH_INV;
+		break;
+	case IB_WR_SEND:
+		opcode = FW_RI_SEND;
+		break;
+	case IB_WR_RDMA_WRITE:
+		opcode = FW_RI_RDMA_WRITE;
+		break;
+	case IB_WR_RDMA_READ:
+	case IB_WR_RDMA_READ_WITH_INV:
+		opcode = FW_RI_READ_REQ;
+		break;
+	case IB_WR_REG_MR:
+		opcode = FW_RI_FAST_REGISTER;
+		break;
+	case IB_WR_LOCAL_INV:
+		opcode = FW_RI_LOCAL_INV;
+		break;
+	default:
+		opcode = -EINVAL;
+	}
+	return opcode;
+}
+
+static int complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
 {
 	struct t4_cqe cqe = {};
 	struct c4iw_cq *schp;
 	unsigned long flag;
 	struct t4_cq *cq;
+	int opcode;
 
 	schp = to_c4iw_cq(qhp->ibqp.send_cq);
 	cq = &schp->cq;
 
+	opcode = ib_to_fw_opcode(wr->opcode);
+	if (opcode < 0)
+		return opcode;
+
 	cqe.u.drain_cookie = wr->wr_id;
 	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
-				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_OPCODE_V(opcode) |
 				 CQE_TYPE_V(1) |
 				 CQE_SWCQE_V(1) |
+				 CQE_DRAIN_V(1) |
 				 CQE_QPID_V(qhp->wq.sq.qid));
 
 	spin_lock_irqsave(&schp->lock, flag);
@@ -819,6 +855,23 @@ static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
 					   schp->ibcq.cq_context);
 		spin_unlock_irqrestore(&schp->comp_handler_lock, flag);
 	}
+	return 0;
+}
+
+static int complete_sq_drain_wrs(struct c4iw_qp *qhp, struct ib_send_wr *wr,
+				struct ib_send_wr **bad_wr)
+{
+	int ret = 0;
+
+	while (wr) {
+		ret = complete_sq_drain_wr(qhp, wr);
+		if (ret) {
+			*bad_wr = wr;
+			break;
+		}
+		wr = wr->next;
+	}
+	return ret;
 }
 
 static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
@@ -833,9 +886,10 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
 
 	cqe.u.drain_cookie = wr->wr_id;
 	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
-				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_OPCODE_V(FW_RI_SEND) |
 				 CQE_TYPE_V(0) |
 				 CQE_SWCQE_V(1) |
+				 CQE_DRAIN_V(1) |
 				 CQE_QPID_V(qhp->wq.sq.qid));
 
 	spin_lock_irqsave(&rchp->lock, flag);
@@ -852,6 +906,14 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
 	}
 }
 
+static void complete_rq_drain_wrs(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
+{
+	while (wr) {
+		complete_rq_drain_wr(qhp, wr);
+		wr = wr->next;
+	}
+}
+
 int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		   struct ib_send_wr **bad_wr)
 {
@@ -868,9 +930,14 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 
 	qhp = to_c4iw_qp(ibqp);
 	spin_lock_irqsave(&qhp->lock, flag);
-	if (t4_wq_in_error(&qhp->wq)) {
+
+	/*
+	 * If the qp has been flushed, then just insert a special
+	 * drain cqe.
+	 */
+	if (qhp->wq.flushed) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		complete_sq_drain_wr(qhp, wr);
+		err = complete_sq_drain_wrs(qhp, wr, bad_wr);
 		return err;
 	}
 	num_wrs = t4_sq_avail(&qhp->wq);
@@ -1011,9 +1078,14 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 
 	qhp = to_c4iw_qp(ibqp);
 	spin_lock_irqsave(&qhp->lock, flag);
-	if (t4_wq_in_error(&qhp->wq)) {
+
+	/*
+	 * If the qp has been flushed, then just insert a special
+	 * drain cqe.
+	 */
+	if (qhp->wq.flushed) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		complete_rq_drain_wr(qhp, wr);
+		complete_rq_drain_wrs(qhp, wr);
 		return err;
 	}
 	num_wrs = t4_rq_avail(&qhp->wq);
@@ -1285,21 +1357,21 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
 	spin_unlock_irqrestore(&rchp->lock, flag);
 
 	if (schp == rchp) {
-		if (t4_clear_cq_armed(&rchp->cq) &&
-		    (rq_flushed || sq_flushed)) {
+		if ((rq_flushed || sq_flushed) &&
+		    t4_clear_cq_armed(&rchp->cq)) {
 			spin_lock_irqsave(&rchp->comp_handler_lock, flag);
 			(*rchp->ibcq.comp_handler)(&rchp->ibcq,
 						   rchp->ibcq.cq_context);
 			spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
 		}
 	} else {
-		if (t4_clear_cq_armed(&rchp->cq) && rq_flushed) {
+		if (rq_flushed && t4_clear_cq_armed(&rchp->cq)) {
 			spin_lock_irqsave(&rchp->comp_handler_lock, flag);
 			(*rchp->ibcq.comp_handler)(&rchp->ibcq,
 						   rchp->ibcq.cq_context);
 			spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
 		}
-		if (t4_clear_cq_armed(&schp->cq) && sq_flushed) {
+		if (sq_flushed && t4_clear_cq_armed(&schp->cq)) {
 			spin_lock_irqsave(&schp->comp_handler_lock, flag);
 			(*schp->ibcq.comp_handler)(&schp->ibcq,
 						   schp->ibcq.cq_context);
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index e12377cc024c..8369c7c8de83 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -197,6 +197,11 @@ struct t4_cqe {
 #define CQE_SWCQE_G(x)    ((((x) >> CQE_SWCQE_S)) & CQE_SWCQE_M)
 #define CQE_SWCQE_V(x)	  ((x)<<CQE_SWCQE_S)
 
+#define CQE_DRAIN_S       10
+#define CQE_DRAIN_M       0x1
+#define CQE_DRAIN_G(x)    ((((x) >> CQE_DRAIN_S)) & CQE_DRAIN_M)
+#define CQE_DRAIN_V(x)	  ((x)<<CQE_DRAIN_S)
+
 #define CQE_STATUS_S      5
 #define CQE_STATUS_M      0x1F
 #define CQE_STATUS_G(x)   ((((x) >> CQE_STATUS_S)) & CQE_STATUS_M)
@@ -213,6 +218,7 @@ struct t4_cqe {
 #define CQE_OPCODE_V(x)   ((x)<<CQE_OPCODE_S)
 
 #define SW_CQE(x)         (CQE_SWCQE_G(be32_to_cpu((x)->header)))
+#define DRAIN_CQE(x)      (CQE_DRAIN_G(be32_to_cpu((x)->header)))
 #define CQE_QPID(x)       (CQE_QPID_G(be32_to_cpu((x)->header)))
 #define CQE_TYPE(x)       (CQE_TYPE_G(be32_to_cpu((x)->header)))
 #define SQ_TYPE(x)	  (CQE_TYPE((x)))
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 85b95520db5d..99921acd2ab4 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1131,7 +1131,6 @@ struct hfi1_devdata {
 	u16 pcie_lnkctl;
 	u16 pcie_devctl2;
 	u32 pci_msix0;
-	u32 pci_lnkctl3;
 	u32 pci_tph2;
 
 	/*
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 09e50fd2a08f..8c7e7a60b715 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -411,15 +411,12 @@ int restore_pci_variables(struct hfi1_devdata *dd)
 	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;
-
+	if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+		ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+					     dd->pci_tph2);
+		if (ret)
+			goto error;
+	}
 	return 0;
 
 error:
@@ -469,15 +466,12 @@ int save_pci_variables(struct hfi1_devdata *dd)
 	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;
-
+	if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+		ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+					    &dd->pci_tph2);
+		if (ret)
+			goto error;
+	}
 	return 0;
 
 error:
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index e6fa9365de49..68d5c3cce2eb 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -814,7 +814,7 @@ static inline void hfi1_make_rc_ack_16B(struct rvt_qp *qp,
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct hfi1_16b_header *hdr = &opa_hdr->opah;
 	struct ib_other_headers *ohdr;
-	u32 bth0, bth1;
+	u32 bth0, bth1 = 0;
 	u16 len, pkey;
 	u8 becn = !!is_fecn;
 	u8 l4 = OPA_16B_L4_IB_LOCAL;
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index 3e4c5253ab5c..a40ec939ece5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -162,14 +162,10 @@ void hns_roce_buf_free(struct hns_roce_dev *hr_dev, u32 size,
 {
 	int i;
 	struct device *dev = hr_dev->dev;
-	u32 bits_per_long = BITS_PER_LONG;
 
 	if (buf->nbufs == 1) {
 		dma_free_coherent(dev, size, buf->direct.buf, buf->direct.map);
 	} else {
-		if (bits_per_long == 64 && buf->page_shift == PAGE_SHIFT)
-			vunmap(buf->direct.buf);
-
 		for (i = 0; i < buf->nbufs; ++i)
 			if (buf->page_list[i].buf)
 				dma_free_coherent(dev, 1 << buf->page_shift,
@@ -185,9 +181,7 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
 {
 	int i = 0;
 	dma_addr_t t;
-	struct page **pages;
 	struct device *dev = hr_dev->dev;
-	u32 bits_per_long = BITS_PER_LONG;
 	u32 page_size = 1 << page_shift;
 	u32 order;
 
@@ -236,23 +230,6 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
 			buf->page_list[i].map = t;
 			memset(buf->page_list[i].buf, 0, page_size);
 		}
-		if (bits_per_long == 64 && page_shift == PAGE_SHIFT) {
-			pages = kmalloc_array(buf->nbufs, sizeof(*pages),
-					      GFP_KERNEL);
-			if (!pages)
-				goto err_free;
-
-			for (i = 0; i < buf->nbufs; ++i)
-				pages[i] = virt_to_page(buf->page_list[i].buf);
-
-			buf->direct.buf = vmap(pages, buf->nbufs, VM_MAP,
-					       PAGE_KERNEL);
-			kfree(pages);
-			if (!buf->direct.buf)
-				goto err_free;
-		} else {
-			buf->direct.buf = NULL;
-		}
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index dde51787cbfd..dcfd2099bac1 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -795,11 +795,9 @@ static inline struct hns_roce_qp
 
 static inline void *hns_roce_buf_offset(struct hns_roce_buf *buf, int offset)
 {
-	u32 bits_per_long_val = BITS_PER_LONG;
 	u32 page_size = 1 << buf->page_shift;
 
-	if ((bits_per_long_val == 64 && buf->page_shift == PAGE_SHIFT) ||
-	    buf->nbufs == 1)
+	if (buf->nbufs == 1)
 		return (char *)(buf->direct.buf) + offset;
 	else
 		return (char *)(buf->page_list[offset >> buf->page_shift].buf) +
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index 8b733a66fae5..0eeabfbee192 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -224,6 +224,7 @@ static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev,
 			sg_init_table(chunk->mem, HNS_ROCE_HEM_CHUNK_LEN);
 			chunk->npages = 0;
 			chunk->nsg = 0;
+			memset(chunk->buf, 0, sizeof(chunk->buf));
 			list_add_tail(&chunk->list, &hem->chunk_list);
 		}
 
@@ -240,8 +241,7 @@ static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev,
 		if (!buf)
 			goto fail;
 
-		sg_set_buf(mem, buf, PAGE_SIZE << order);
-		WARN_ON(mem->offset);
+		chunk->buf[chunk->npages] = buf;
 		sg_dma_len(mem) = PAGE_SIZE << order;
 
 		++chunk->npages;
@@ -267,8 +267,8 @@ void hns_roce_free_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem *hem)
 	list_for_each_entry_safe(chunk, tmp, &hem->chunk_list, list) {
 		for (i = 0; i < chunk->npages; ++i)
 			dma_free_coherent(hr_dev->dev,
-				   chunk->mem[i].length,
-				   lowmem_page_address(sg_page(&chunk->mem[i])),
+				   sg_dma_len(&chunk->mem[i]),
+				   chunk->buf[i],
 				   sg_dma_address(&chunk->mem[i]));
 		kfree(chunk);
 	}
@@ -722,11 +722,12 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 	struct hns_roce_hem_chunk *chunk;
 	struct hns_roce_hem_mhop mhop;
 	struct hns_roce_hem *hem;
-	struct page *page = NULL;
+	void *addr = NULL;
 	unsigned long mhop_obj = obj;
 	unsigned long obj_per_chunk;
 	unsigned long idx_offset;
 	int offset, dma_offset;
+	int length;
 	int i, j;
 	u32 hem_idx = 0;
 
@@ -763,25 +764,25 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 
 	list_for_each_entry(chunk, &hem->chunk_list, list) {
 		for (i = 0; i < chunk->npages; ++i) {
+			length = sg_dma_len(&chunk->mem[i]);
 			if (dma_handle && dma_offset >= 0) {
-				if (sg_dma_len(&chunk->mem[i]) >
-				    (u32)dma_offset)
+				if (length > (u32)dma_offset)
 					*dma_handle = sg_dma_address(
 						&chunk->mem[i]) + dma_offset;
-				dma_offset -= sg_dma_len(&chunk->mem[i]);
+				dma_offset -= length;
 			}
 
-			if (chunk->mem[i].length > (u32)offset) {
-				page = sg_page(&chunk->mem[i]);
+			if (length > (u32)offset) {
+				addr = chunk->buf[i] + offset;
 				goto out;
 			}
-			offset -= chunk->mem[i].length;
+			offset -= length;
 		}
 	}
 
 out:
 	mutex_unlock(&table->mutex);
-	return page ? lowmem_page_address(page) + offset : NULL;
+	return addr;
 }
 EXPORT_SYMBOL_GPL(hns_roce_table_find);
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h
index db66db12075e..e8850d59e780 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.h
@@ -78,6 +78,7 @@ struct hns_roce_hem_chunk {
 	int			 npages;
 	int			 nsg;
 	struct scatterlist	 mem[HNS_ROCE_HEM_CHUNK_LEN];
+	void			 *buf[HNS_ROCE_HEM_CHUNK_LEN];
 };
 
 struct hns_roce_hem {
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 04281d0c0b42..4d3e97622f39 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1131,9 +1131,11 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
 {
 	struct hns_roce_v2_mpt_entry *mpt_entry;
 	struct scatterlist *sg;
+	u64 page_addr;
 	u64 *pages;
+	int i, j;
+	int len;
 	int entry;
-	int i;
 
 	mpt_entry = mb_buf;
 	memset(mpt_entry, 0, sizeof(*mpt_entry));
@@ -1191,14 +1193,20 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
 
 	i = 0;
 	for_each_sg(mr->umem->sg_head.sgl, sg, mr->umem->nmap, entry) {
-		pages[i] = ((u64)sg_dma_address(sg)) >> 6;
-
-		/* Record the first 2 entry directly to MTPT table */
-		if (i >= HNS_ROCE_V2_MAX_INNER_MTPT_NUM - 1)
-			break;
-		i++;
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		for (j = 0; j < len; ++j) {
+			page_addr = sg_dma_address(sg) +
+				    (j << mr->umem->page_shift);
+			pages[i] = page_addr >> 6;
+
+			/* Record the first 2 entry directly to MTPT table */
+			if (i >= HNS_ROCE_V2_MAX_INNER_MTPT_NUM - 1)
+				goto found;
+			i++;
+		}
 	}
 
+found:
 	mpt_entry->pa0_l = cpu_to_le32(lower_32_bits(pages[0]));
 	roce_set_field(mpt_entry->byte_56_pa0_h, V2_MPT_BYTE_56_PA0_H_M,
 		       V2_MPT_BYTE_56_PA0_H_S,
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 97b620382faf..abf4cd897849 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -1041,7 +1041,7 @@ negotiate_done:
  * i40iw_schedule_cm_timer
  * @@cm_node: connection's node
  * @sqbuf: buffer to send
- * @type: if it es send ot close
+ * @type: if it is send or close
  * @send_retrans: if rexmits to be done
  * @close_when_complete: is cm_node to be removed
  *
@@ -1065,7 +1065,8 @@ int i40iw_schedule_cm_timer(struct i40iw_cm_node *cm_node,
 
 	new_send = kzalloc(sizeof(*new_send), GFP_ATOMIC);
 	if (!new_send) {
-		i40iw_free_sqbuf(vsi, (void *)sqbuf);
+		if (type != I40IW_TIMER_TYPE_CLOSE)
+			i40iw_free_sqbuf(vsi, (void *)sqbuf);
 		return -ENOMEM;
 	}
 	new_send->retrycount = I40IW_DEFAULT_RETRYS;
@@ -1080,7 +1081,6 @@ int i40iw_schedule_cm_timer(struct i40iw_cm_node *cm_node,
 		new_send->timetosend += (HZ / 10);
 		if (cm_node->close_entry) {
 			kfree(new_send);
-			i40iw_free_sqbuf(vsi, (void *)sqbuf);
 			i40iw_pr_err("already close entry\n");
 			return -EINVAL;
 		}
@@ -2952,8 +2952,6 @@ static struct i40iw_cm_node *i40iw_create_cm_node(
 			loopback_remotenode->tcp_cntxt.snd_wnd = cm_node->tcp_cntxt.rcv_wnd;
 			cm_node->tcp_cntxt.snd_wscale = loopback_remotenode->tcp_cntxt.rcv_wscale;
 			loopback_remotenode->tcp_cntxt.snd_wscale = cm_node->tcp_cntxt.rcv_wscale;
-			loopback_remotenode->state = I40IW_CM_STATE_MPAREQ_RCVD;
-			i40iw_create_event(loopback_remotenode, I40IW_CM_EVENT_MPA_REQ);
 		}
 		return cm_node;
 	}
@@ -3694,11 +3692,16 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	cm_id->add_ref(cm_id);
 	i40iw_add_ref(&iwqp->ibqp);
 
-	i40iw_send_cm_event(cm_node, cm_id, IW_CM_EVENT_ESTABLISHED, 0);
-
 	attr.qp_state = IB_QPS_RTS;
 	cm_node->qhash_set = false;
 	i40iw_modify_qp(&iwqp->ibqp, &attr, IB_QP_STATE, NULL);
+
+	cm_node->accelerated = true;
+	status =
+		i40iw_send_cm_event(cm_node, cm_id, IW_CM_EVENT_ESTABLISHED, 0);
+	if (status)
+		i40iw_debug(dev, I40IW_DEBUG_CM, "error sending cm event - ESTABLISHED\n");
+
 	if (cm_node->loopbackpartner) {
 		cm_node->loopbackpartner->pdata.size = conn_param->private_data_len;
 
@@ -3709,7 +3712,6 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		i40iw_create_event(cm_node->loopbackpartner, I40IW_CM_EVENT_CONNECTED);
 	}
 
-	cm_node->accelerated = 1;
 	if (cm_node->accept_pend) {
 		atomic_dec(&cm_node->listener->pend_accepts_cnt);
 		cm_node->accept_pend = 0;
@@ -3862,6 +3864,12 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 			goto err;
 	}
 
+	if (cm_node->loopbackpartner) {
+		cm_node->loopbackpartner->state = I40IW_CM_STATE_MPAREQ_RCVD;
+		i40iw_create_event(cm_node->loopbackpartner,
+				   I40IW_CM_EVENT_MPA_REQ);
+	}
+
 	i40iw_debug(cm_node->dev,
 		    I40IW_DEBUG_CM,
 		    "Api - connect(): port=0x%04x, cm_node=%p, cm_id = %p.\n",
@@ -4042,16 +4050,17 @@ static void i40iw_cm_event_connected(struct i40iw_cm_event *event)
 	dev->iw_priv_qp_ops->qp_send_rtt(&iwqp->sc_qp, read0);
 	if (iwqp->page)
 		kunmap(iwqp->page);
-	status = i40iw_send_cm_event(cm_node, cm_id, IW_CM_EVENT_CONNECT_REPLY, 0);
-	if (status)
-		i40iw_pr_err("send cm event\n");
 
 	memset(&attr, 0, sizeof(attr));
 	attr.qp_state = IB_QPS_RTS;
 	cm_node->qhash_set = false;
 	i40iw_modify_qp(&iwqp->ibqp, &attr, IB_QP_STATE, NULL);
 
-	cm_node->accelerated = 1;
+	cm_node->accelerated = true;
+	status = i40iw_send_cm_event(cm_node, cm_id, IW_CM_EVENT_CONNECT_REPLY,
+				     0);
+	if (status)
+		i40iw_debug(dev, I40IW_DEBUG_CM, "error sending cm event - CONNECT_REPLY\n");
 
 	return;
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.h b/drivers/infiniband/hw/i40iw/i40iw_cm.h
index 47638a44e60b..cf60c451e071 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.h
@@ -335,7 +335,7 @@ struct i40iw_cm_node {
 	u16     mpav2_ird_ord;
 	struct iw_cm_id *cm_id;
 	struct list_head list;
-	int accelerated;
+	bool accelerated;
 	struct i40iw_cm_listener *listener;
 	int apbvt_set;
 	int accept_pend;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index e857f287a0c0..caa958177631 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -513,7 +513,7 @@ static enum i40iw_status_code i40iw_sc_cqp_create(struct i40iw_sc_cqp *cqp,
 
 	ret_code = i40iw_allocate_dma_mem(cqp->dev->hw,
 					  &cqp->sdbuf,
-					  128,
+					  I40IW_UPDATE_SD_BUF_SIZE * cqp->sq_size,
 					  I40IW_SD_BUF_ALIGNMENT);
 
 	if (ret_code)
@@ -596,14 +596,15 @@ void i40iw_sc_cqp_post_sq(struct i40iw_sc_cqp *cqp)
 }
 
 /**
- * i40iw_sc_cqp_get_next_send_wqe - get next wqe on cqp sq
- * @cqp: struct for cqp hw
- * @wqe_idx: we index of cqp ring
+ * i40iw_sc_cqp_get_next_send_wqe_idx - get next WQE on CQP SQ and pass back the index
+ * @cqp: pointer to CQP structure
+ * @scratch: private data for CQP WQE
+ * @wqe_idx: WQE index for next WQE on CQP SQ
  */
-u64 *i40iw_sc_cqp_get_next_send_wqe(struct i40iw_sc_cqp *cqp, u64 scratch)
+static u64 *i40iw_sc_cqp_get_next_send_wqe_idx(struct i40iw_sc_cqp *cqp,
+					       u64 scratch, u32 *wqe_idx)
 {
 	u64 *wqe = NULL;
-	u32	wqe_idx;
 	enum i40iw_status_code ret_code;
 
 	if (I40IW_RING_FULL_ERR(cqp->sq_ring)) {
@@ -616,21 +617,33 @@ u64 *i40iw_sc_cqp_get_next_send_wqe(struct i40iw_sc_cqp *cqp, u64 scratch)
 			    cqp->sq_ring.size);
 		return NULL;
 	}
-	I40IW_ATOMIC_RING_MOVE_HEAD(cqp->sq_ring, wqe_idx, ret_code);
+	I40IW_ATOMIC_RING_MOVE_HEAD(cqp->sq_ring, *wqe_idx, ret_code);
 	cqp->dev->cqp_cmd_stats[OP_REQUESTED_COMMANDS]++;
 	if (ret_code)
 		return NULL;
-	if (!wqe_idx)
+	if (!*wqe_idx)
 		cqp->polarity = !cqp->polarity;
 
-	wqe = cqp->sq_base[wqe_idx].elem;
-	cqp->scratch_array[wqe_idx] = scratch;
+	wqe = cqp->sq_base[*wqe_idx].elem;
+	cqp->scratch_array[*wqe_idx] = scratch;
 	I40IW_CQP_INIT_WQE(wqe);
 
 	return wqe;
 }
 
 /**
+ * i40iw_sc_cqp_get_next_send_wqe - get next wqe on cqp sq
+ * @cqp: struct for cqp hw
+ * @scratch: private data for CQP WQE
+ */
+u64 *i40iw_sc_cqp_get_next_send_wqe(struct i40iw_sc_cqp *cqp, u64 scratch)
+{
+	u32 wqe_idx;
+
+	return i40iw_sc_cqp_get_next_send_wqe_idx(cqp, scratch, &wqe_idx);
+}
+
+/**
  * i40iw_sc_cqp_destroy - destroy cqp during close
  * @cqp: struct for cqp hw
  */
@@ -3587,8 +3600,10 @@ static enum i40iw_status_code cqp_sds_wqe_fill(struct i40iw_sc_cqp *cqp,
 	u64 *wqe;
 	int mem_entries, wqe_entries;
 	struct i40iw_dma_mem *sdbuf = &cqp->sdbuf;
+	u64 offset;
+	u32 wqe_idx;
 
-	wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch);
+	wqe = i40iw_sc_cqp_get_next_send_wqe_idx(cqp, scratch, &wqe_idx);
 	if (!wqe)
 		return I40IW_ERR_RING_FULL;
 
@@ -3601,8 +3616,10 @@ static enum i40iw_status_code cqp_sds_wqe_fill(struct i40iw_sc_cqp *cqp,
 		 LS_64(mem_entries, I40IW_CQPSQ_UPESD_ENTRY_COUNT);
 
 	if (mem_entries) {
-		memcpy(sdbuf->va, &info->entry[3], (mem_entries << 4));
-		data = sdbuf->pa;
+		offset = wqe_idx * I40IW_UPDATE_SD_BUF_SIZE;
+		memcpy((char *)sdbuf->va + offset, &info->entry[3],
+		       mem_entries << 4);
+		data = (u64)sdbuf->pa + offset;
 	} else {
 		data = 0;
 	}
diff --git a/drivers/infiniband/hw/i40iw/i40iw_d.h b/drivers/infiniband/hw/i40iw/i40iw_d.h
index b8565872d744..4b65e4140bd7 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_d.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_d.h
@@ -1115,7 +1115,7 @@
 #define I40IWQPC_VLANTAG_MASK (0xffffULL << I40IWQPC_VLANTAG_SHIFT)
 
 #define I40IWQPC_ARPIDX_SHIFT 48
-#define I40IWQPC_ARPIDX_MASK (0xfffULL << I40IWQPC_ARPIDX_SHIFT)
+#define I40IWQPC_ARPIDX_MASK (0xffffULL << I40IWQPC_ARPIDX_SHIFT)
 
 #define I40IWQPC_FLOWLABEL_SHIFT 0
 #define I40IWQPC_FLOWLABEL_MASK (0xfffffUL << I40IWQPC_FLOWLABEL_SHIFT)
@@ -1527,7 +1527,7 @@ enum i40iw_alignment {
 	I40IW_AEQ_ALIGNMENT =		0x100,
 	I40IW_CEQ_ALIGNMENT =		0x100,
 	I40IW_CQ0_ALIGNMENT =		0x100,
-	I40IW_SD_BUF_ALIGNMENT =	0x100
+	I40IW_SD_BUF_ALIGNMENT =	0x80
 };
 
 #define I40IW_WQE_SIZE_64	64
@@ -1535,6 +1535,8 @@ enum i40iw_alignment {
 #define I40IW_QP_WQE_MIN_SIZE	32
 #define I40IW_QP_WQE_MAX_SIZE	128
 
+#define I40IW_UPDATE_SD_BUF_SIZE 128
+
 #define I40IW_CQE_QTYPE_RQ 0
 #define I40IW_CQE_QTYPE_SQ 1
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 16dea0e3d50f..f5f5c5960bba 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -666,6 +666,19 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx,
 		return (-EOPNOTSUPP);
 	}
 
+	if (ucmd->rx_hash_fields_mask & ~(MLX4_IB_RX_HASH_SRC_IPV4	|
+					  MLX4_IB_RX_HASH_DST_IPV4	|
+					  MLX4_IB_RX_HASH_SRC_IPV6	|
+					  MLX4_IB_RX_HASH_DST_IPV6	|
+					  MLX4_IB_RX_HASH_SRC_PORT_TCP	|
+					  MLX4_IB_RX_HASH_DST_PORT_TCP	|
+					  MLX4_IB_RX_HASH_SRC_PORT_UDP	|
+					  MLX4_IB_RX_HASH_DST_PORT_UDP)) {
+		pr_debug("RX Hash fields_mask has unsupported mask (0x%llx)\n",
+			 ucmd->rx_hash_fields_mask);
+		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;
@@ -691,11 +704,11 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx,
 			return (-EOPNOTSUPP);
 		}
 
-		if (rss_ctx->flags & MLX4_RSS_IPV4) {
+		if (rss_ctx->flags & MLX4_RSS_IPV4)
 			rss_ctx->flags |= MLX4_RSS_UDP_IPV4;
-		} else if (rss_ctx->flags & MLX4_RSS_IPV6) {
+		if (rss_ctx->flags & MLX4_RSS_IPV6)
 			rss_ctx->flags |= MLX4_RSS_UDP_IPV6;
-		} else {
+		if (!(rss_ctx->flags & (MLX4_RSS_IPV6 | MLX4_RSS_IPV4))) {
 			pr_debug("RX Hash fields_mask is not supported - UDP must be set with IPv4 or IPv6\n");
 			return (-EOPNOTSUPP);
 		}
@@ -707,15 +720,14 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx,
 
 	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) {
+		if (rss_ctx->flags & MLX4_RSS_IPV4)
 			rss_ctx->flags |= MLX4_RSS_TCP_IPV4;
-		} else if (rss_ctx->flags & MLX4_RSS_IPV6) {
+		if (rss_ctx->flags & MLX4_RSS_IPV6)
 			rss_ctx->flags |= MLX4_RSS_TCP_IPV6;
-		} else {
+		if (!(rss_ctx->flags & (MLX4_RSS_IPV6 | MLX4_RSS_IPV4))) {
 			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");
diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index 470995fa38d2..6f6712f87a73 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -47,17 +47,6 @@ int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey)
 	return err;
 }
 
-int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
-				bool reset, void *out, int out_size)
-{
-	u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { };
-
-	MLX5_SET(query_cong_statistics_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
-	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)
 {
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index af4c24596274..78ffded7cc2c 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -37,8 +37,6 @@
 #include <linux/mlx5/driver.h>
 
 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,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index fe435edf305b..46c7367d3255 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1461,6 +1461,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	}
 
 	INIT_LIST_HEAD(&context->vma_private_list);
+	mutex_init(&context->vma_private_list_mutex);
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
 
@@ -1622,7 +1623,9 @@ static void  mlx5_ib_vma_close(struct vm_area_struct *area)
 	 * mlx5_ib_disassociate_ucontext().
 	 */
 	mlx5_ib_vma_priv_data->vma = NULL;
+	mutex_lock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
 	list_del(&mlx5_ib_vma_priv_data->list);
+	mutex_unlock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
 	kfree(mlx5_ib_vma_priv_data);
 }
 
@@ -1642,10 +1645,13 @@ static int mlx5_ib_set_vma_data(struct vm_area_struct *vma,
 		return -ENOMEM;
 
 	vma_prv->vma = vma;
+	vma_prv->vma_private_list_mutex = &ctx->vma_private_list_mutex;
 	vma->vm_private_data = vma_prv;
 	vma->vm_ops =  &mlx5_ib_vm_ops;
 
+	mutex_lock(&ctx->vma_private_list_mutex);
 	list_add(&vma_prv->list, vma_head);
+	mutex_unlock(&ctx->vma_private_list_mutex);
 
 	return 0;
 }
@@ -1688,6 +1694,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 	 * mlx5_ib_vma_close.
 	 */
 	down_write(&owning_mm->mmap_sem);
+	mutex_lock(&context->vma_private_list_mutex);
 	list_for_each_entry_safe(vma_private, n, &context->vma_private_list,
 				 list) {
 		vma = vma_private->vma;
@@ -1702,6 +1709,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 		list_del(&vma_private->list);
 		kfree(vma_private);
 	}
+	mutex_unlock(&context->vma_private_list_mutex);
 	up_write(&owning_mm->mmap_sem);
 	mmput(owning_mm);
 	put_task_struct(owning_process);
@@ -3735,34 +3743,6 @@ free:
 	return ret;
 }
 
-static int mlx5_ib_query_cong_counters(struct mlx5_ib_dev *dev,
-				       struct mlx5_ib_port *port,
-				       struct rdma_hw_stats *stats)
-{
-	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
-	void *out;
-	int ret, i;
-	int offset = port->cnts.num_q_counters;
-
-	out = kvzalloc(outlen, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	ret = mlx5_cmd_query_cong_counter(dev->mdev, false, out, outlen);
-	if (ret)
-		goto free;
-
-	for (i = 0; i < port->cnts.num_cong_counters; i++) {
-		stats->value[i + offset] =
-			be64_to_cpup((__be64 *)(out +
-				     port->cnts.offsets[i + offset]));
-	}
-
-free:
-	kvfree(out);
-	return ret;
-}
-
 static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 				struct rdma_hw_stats *stats,
 				u8 port_num, int index)
@@ -3780,7 +3760,12 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 	num_counters = port->cnts.num_q_counters;
 
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
-		ret = mlx5_ib_query_cong_counters(dev, port, stats);
+		ret = mlx5_lag_query_cong_counters(dev->mdev,
+						   stats->value +
+						   port->cnts.num_q_counters,
+						   port->cnts.num_cong_counters,
+						   port->cnts.offsets +
+						   port->cnts.num_q_counters);
 		if (ret)
 			return ret;
 		num_counters += port->cnts.num_cong_counters;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 6dd8cac78de2..2c5f3533bbc9 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -115,6 +115,8 @@ enum {
 struct mlx5_ib_vma_private_data {
 	struct list_head list;
 	struct vm_area_struct *vma;
+	/* protect vma_private_list add/del */
+	struct mutex *vma_private_list_mutex;
 };
 
 struct mlx5_ib_ucontext {
@@ -129,6 +131,8 @@ struct mlx5_ib_ucontext {
 	/* Transport Domain number */
 	u32			tdn;
 	struct list_head	vma_private_list;
+	/* protect vma_private_list add/del */
+	struct mutex		vma_private_list_mutex;
 
 	unsigned long		upd_xlt_page;
 	/* protect ODP/KSM */
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index ad37d8441fa2..556e015678de 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1640,6 +1640,7 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 	MLX5_SET(mkc, mkc, access_mode, mr->access_mode);
 	MLX5_SET(mkc, mkc, umr_en, 1);
 
+	mr->ibmr.device = pd->device;
 	err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen);
 	if (err)
 		goto err_destroy_psv;
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 63bc2efc34eb..44cb1cfba417 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -93,8 +93,8 @@ struct pvrdma_cq {
 	struct pvrdma_page_dir pdir;
 	u32 cq_handle;
 	bool is_kernel;
-	atomic_t refcnt;
-	wait_queue_head_t wait;
+	refcount_t refcnt;
+	struct completion free;
 };
 
 struct pvrdma_id_table {
@@ -175,7 +175,7 @@ struct pvrdma_srq {
 	u32 srq_handle;
 	int npages;
 	refcount_t refcnt;
-	wait_queue_head_t wait;
+	struct completion free;
 };
 
 struct pvrdma_qp {
@@ -196,8 +196,8 @@ struct pvrdma_qp {
 	u8 state;
 	bool is_kernel;
 	struct mutex mutex; /* QP state mutex. */
-	atomic_t refcnt;
-	wait_queue_head_t wait;
+	refcount_t refcnt;
+	struct completion free;
 };
 
 struct pvrdma_dev {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
index 3562c0c30492..faa9478c14a6 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
@@ -132,8 +132,9 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev,
 	}
 
 	cq->ibcq.cqe = entries;
+	cq->is_kernel = !context;
 
-	if (context) {
+	if (!cq->is_kernel) {
 		if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
 			ret = -EFAULT;
 			goto err_cq;
@@ -148,8 +149,6 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev,
 
 		npages = ib_umem_page_count(cq->umem);
 	} else {
-		cq->is_kernel = true;
-
 		/* One extra page for shared ring state */
 		npages = 1 + (entries * sizeof(struct pvrdma_cqe) +
 			      PAGE_SIZE - 1) / PAGE_SIZE;
@@ -178,8 +177,8 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev,
 	else
 		pvrdma_page_dir_insert_umem(&cq->pdir, cq->umem, 0);
 
-	atomic_set(&cq->refcnt, 1);
-	init_waitqueue_head(&cq->wait);
+	refcount_set(&cq->refcnt, 1);
+	init_completion(&cq->free);
 	spin_lock_init(&cq->cq_lock);
 
 	memset(cmd, 0, sizeof(*cmd));
@@ -202,7 +201,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev,
 	dev->cq_tbl[cq->cq_handle % dev->dsr->caps.max_cq] = cq;
 	spin_unlock_irqrestore(&dev->cq_tbl_lock, flags);
 
-	if (context) {
+	if (!cq->is_kernel) {
 		cq->uar = &(to_vucontext(context)->uar);
 
 		/* Copy udata back. */
@@ -219,7 +218,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev,
 err_page_dir:
 	pvrdma_page_dir_cleanup(dev, &cq->pdir);
 err_umem:
-	if (context)
+	if (!cq->is_kernel)
 		ib_umem_release(cq->umem);
 err_cq:
 	atomic_dec(&dev->num_cqs);
@@ -230,8 +229,9 @@ err_cq:
 
 static void pvrdma_free_cq(struct pvrdma_dev *dev, struct pvrdma_cq *cq)
 {
-	atomic_dec(&cq->refcnt);
-	wait_event(cq->wait, !atomic_read(&cq->refcnt));
+	if (refcount_dec_and_test(&cq->refcnt))
+		complete(&cq->free);
+	wait_for_completion(&cq->free);
 
 	if (!cq->is_kernel)
 		ib_umem_release(cq->umem);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 1f4e18717a00..939ac2f7bf0f 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -243,13 +243,13 @@ static int pvrdma_register_device(struct pvrdma_dev *dev)
 	mutex_init(&dev->port_mutex);
 	spin_lock_init(&dev->desc_lock);
 
-	dev->cq_tbl = kcalloc(dev->dsr->caps.max_cq, sizeof(void *),
+	dev->cq_tbl = kcalloc(dev->dsr->caps.max_cq, sizeof(struct pvrdma_cq *),
 			      GFP_KERNEL);
 	if (!dev->cq_tbl)
 		return ret;
 	spin_lock_init(&dev->cq_tbl_lock);
 
-	dev->qp_tbl = kcalloc(dev->dsr->caps.max_qp, sizeof(void *),
+	dev->qp_tbl = kcalloc(dev->dsr->caps.max_qp, sizeof(struct pvrdma_qp *),
 			      GFP_KERNEL);
 	if (!dev->qp_tbl)
 		goto err_cq_free;
@@ -333,7 +333,7 @@ static void pvrdma_qp_event(struct pvrdma_dev *dev, u32 qpn, int type)
 	spin_lock_irqsave(&dev->qp_tbl_lock, flags);
 	qp = dev->qp_tbl[qpn % dev->dsr->caps.max_qp];
 	if (qp)
-		atomic_inc(&qp->refcnt);
+		refcount_inc(&qp->refcnt);
 	spin_unlock_irqrestore(&dev->qp_tbl_lock, flags);
 
 	if (qp && qp->ibqp.event_handler) {
@@ -346,9 +346,8 @@ static void pvrdma_qp_event(struct pvrdma_dev *dev, u32 qpn, int type)
 		ibqp->event_handler(&e, ibqp->qp_context);
 	}
 	if (qp) {
-		atomic_dec(&qp->refcnt);
-		if (atomic_read(&qp->refcnt) == 0)
-			wake_up(&qp->wait);
+		if (refcount_dec_and_test(&qp->refcnt))
+			complete(&qp->free);
 	}
 }
 
@@ -360,7 +359,7 @@ static void pvrdma_cq_event(struct pvrdma_dev *dev, u32 cqn, int type)
 	spin_lock_irqsave(&dev->cq_tbl_lock, flags);
 	cq = dev->cq_tbl[cqn % dev->dsr->caps.max_cq];
 	if (cq)
-		atomic_inc(&cq->refcnt);
+		refcount_inc(&cq->refcnt);
 	spin_unlock_irqrestore(&dev->cq_tbl_lock, flags);
 
 	if (cq && cq->ibcq.event_handler) {
@@ -373,9 +372,8 @@ static void pvrdma_cq_event(struct pvrdma_dev *dev, u32 cqn, int type)
 		ibcq->event_handler(&e, ibcq->cq_context);
 	}
 	if (cq) {
-		atomic_dec(&cq->refcnt);
-		if (atomic_read(&cq->refcnt) == 0)
-			wake_up(&cq->wait);
+		if (refcount_dec_and_test(&cq->refcnt))
+			complete(&cq->free);
 	}
 }
 
@@ -404,7 +402,7 @@ static void pvrdma_srq_event(struct pvrdma_dev *dev, u32 srqn, int type)
 	}
 	if (srq) {
 		if (refcount_dec_and_test(&srq->refcnt))
-			wake_up(&srq->wait);
+			complete(&srq->free);
 	}
 }
 
@@ -533,15 +531,14 @@ static irqreturn_t pvrdma_intrx_handler(int irq, void *dev_id)
 		spin_lock_irqsave(&dev->cq_tbl_lock, flags);
 		cq = dev->cq_tbl[cqne->info % dev->dsr->caps.max_cq];
 		if (cq)
-			atomic_inc(&cq->refcnt);
+			refcount_inc(&cq->refcnt);
 		spin_unlock_irqrestore(&dev->cq_tbl_lock, flags);
 
 		if (cq && cq->ibcq.comp_handler)
 			cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
 		if (cq) {
-			atomic_dec(&cq->refcnt);
-			if (atomic_read(&cq->refcnt))
-				wake_up(&cq->wait);
+			if (refcount_dec_and_test(&cq->refcnt))
+				complete(&cq->free);
 		}
 		pvrdma_idx_ring_inc(&ring->cons_head, ring_slots);
 	}
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index 10420a18d02f..7bf518bdbf21 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -245,12 +245,13 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 		spin_lock_init(&qp->sq.lock);
 		spin_lock_init(&qp->rq.lock);
 		mutex_init(&qp->mutex);
-		atomic_set(&qp->refcnt, 1);
-		init_waitqueue_head(&qp->wait);
+		refcount_set(&qp->refcnt, 1);
+		init_completion(&qp->free);
 
 		qp->state = IB_QPS_RESET;
+		qp->is_kernel = !(pd->uobject && udata);
 
-		if (pd->uobject && udata) {
+		if (!qp->is_kernel) {
 			dev_dbg(&dev->pdev->dev,
 				"create queuepair from user space\n");
 
@@ -291,8 +292,6 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 				qp->npages_recv = 0;
 			qp->npages = qp->npages_send + qp->npages_recv;
 		} else {
-			qp->is_kernel = true;
-
 			ret = pvrdma_set_sq_size(to_vdev(pd->device),
 						 &init_attr->cap, qp);
 			if (ret)
@@ -394,7 +393,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 err_pdir:
 	pvrdma_page_dir_cleanup(dev, &qp->pdir);
 err_umem:
-	if (pd->uobject && udata) {
+	if (!qp->is_kernel) {
 		if (qp->rumem)
 			ib_umem_release(qp->rumem);
 		if (qp->sumem)
@@ -428,8 +427,16 @@ static void pvrdma_free_qp(struct pvrdma_qp *qp)
 
 	pvrdma_unlock_cqs(scq, rcq, &scq_flags, &rcq_flags);
 
-	atomic_dec(&qp->refcnt);
-	wait_event(qp->wait, !atomic_read(&qp->refcnt));
+	if (refcount_dec_and_test(&qp->refcnt))
+		complete(&qp->free);
+	wait_for_completion(&qp->free);
+
+	if (!qp->is_kernel) {
+		if (qp->rumem)
+			ib_umem_release(qp->rumem);
+		if (qp->sumem)
+			ib_umem_release(qp->sumem);
+	}
 
 	pvrdma_page_dir_cleanup(dev, &qp->pdir);
 
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
index 826ccb864596..5acebb1ef631 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
@@ -149,7 +149,7 @@ struct ib_srq *pvrdma_create_srq(struct ib_pd *pd,
 
 	spin_lock_init(&srq->lock);
 	refcount_set(&srq->refcnt, 1);
-	init_waitqueue_head(&srq->wait);
+	init_completion(&srq->free);
 
 	dev_dbg(&dev->pdev->dev,
 		"create shared receive queue from user space\n");
@@ -236,8 +236,9 @@ static void pvrdma_free_srq(struct pvrdma_dev *dev, struct pvrdma_srq *srq)
 	dev->srq_tbl[srq->srq_handle] = NULL;
 	spin_unlock_irqrestore(&dev->srq_tbl_lock, flags);
 
-	refcount_dec(&srq->refcnt);
-	wait_event(srq->wait, !refcount_read(&srq->refcnt));
+	if (refcount_dec_and_test(&srq->refcnt))
+		complete(&srq->free);
+	wait_for_completion(&srq->free);
 
 	/* There is no support for kernel clients, so this is safe. */
 	ib_umem_release(srq->umem);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index c0a596e4c258..d45b0f2aa987 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1145,6 +1145,7 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
 	noio_flag = memalloc_noio_save();
 	p->tx_ring = vzalloc(ipoib_sendq_size * sizeof(*p->tx_ring));
 	if (!p->tx_ring) {
+		memalloc_noio_restore(noio_flag);
 		ret = -ENOMEM;
 		goto err_tx;
 	}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index b9fa21790da9..a8760d40dfa6 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -1235,13 +1235,10 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 		ipoib_ib_dev_down(dev);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
-		rtnl_lock();
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 			ipoib_ib_dev_stop(dev);
 
-		result = ipoib_ib_dev_open(dev);
-		rtnl_unlock();
-		if (result)
+		if (ipoib_ib_dev_open(dev))
 			return;
 
 		if (netif_queue_stopped(dev))
@@ -1281,7 +1278,9 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_heavy);
 
+	rtnl_lock();
 	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
+	rtnl_unlock();
 }
 
 void ipoib_ib_dev_cleanup(struct net_device *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index f26f97fe4666..582b2f18010a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -137,6 +137,17 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag);
 
+static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
+				       bool reset, void *out, int out_size)
+{
+	u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { };
+
+	MLX5_SET(query_cong_statistics_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
+	MLX5_SET(query_cong_statistics_in, in, clear, reset);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
+}
+
 static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev)
 {
 	return dev->priv.lag;
@@ -633,3 +644,48 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	/* If bonded, we do not add an IB device for PF1. */
 	return false;
 }
+
+int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
+				 u64 *values,
+				 int num_counters,
+				 size_t *offsets)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
+	struct mlx5_core_dev *mdev[MLX5_MAX_PORTS];
+	struct mlx5_lag *ldev;
+	int num_ports;
+	int ret, i, j;
+	void *out;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	memset(values, 0, sizeof(*values) * num_counters);
+
+	mutex_lock(&lag_mutex);
+	ldev = mlx5_lag_dev_get(dev);
+	if (ldev && mlx5_lag_is_bonded(ldev)) {
+		num_ports = MLX5_MAX_PORTS;
+		mdev[0] = ldev->pf[0].dev;
+		mdev[1] = ldev->pf[1].dev;
+	} else {
+		num_ports = 1;
+		mdev[0] = dev;
+	}
+
+	for (i = 0; i < num_ports; ++i) {
+		ret = mlx5_cmd_query_cong_counter(mdev[i], false, out, outlen);
+		if (ret)
+			goto unlock;
+
+		for (j = 0; j < num_counters; ++j)
+			values[j] += be64_to_cpup((__be64 *)(out + offsets[j]));
+	}
+
+unlock:
+	mutex_unlock(&lag_mutex);
+	kvfree(out);
+	return ret;
+}
+EXPORT_SYMBOL(mlx5_lag_query_cong_counters);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index a886b51511ab..8846919356ca 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1164,6 +1164,10 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
 int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev);
+int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
+				 u64 *values,
+				 int num_counters,
+				 size_t *offsets);
 struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
 void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
 
diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h
index aaa352f2f110..02ca0d0f1eb7 100644
--- a/include/uapi/rdma/vmw_pvrdma-abi.h
+++ b/include/uapi/rdma/vmw_pvrdma-abi.h
@@ -52,12 +52,14 @@
 #define PVRDMA_UVERBS_ABI_VERSION	3		/* ABI Version. */
 #define PVRDMA_UAR_HANDLE_MASK		0x00FFFFFF	/* Bottom 24 bits. */
 #define PVRDMA_UAR_QP_OFFSET		0		/* QP doorbell. */
-#define PVRDMA_UAR_QP_SEND		BIT(30)		/* Send bit. */
-#define PVRDMA_UAR_QP_RECV		BIT(31)		/* Recv bit. */
+#define PVRDMA_UAR_QP_SEND		(1 << 30)	/* Send bit. */
+#define PVRDMA_UAR_QP_RECV		(1 << 31)	/* Recv bit. */
 #define PVRDMA_UAR_CQ_OFFSET		4		/* CQ doorbell. */
-#define PVRDMA_UAR_CQ_ARM_SOL		BIT(29)		/* Arm solicited bit. */
-#define PVRDMA_UAR_CQ_ARM		BIT(30)		/* Arm bit. */
-#define PVRDMA_UAR_CQ_POLL		BIT(31)		/* Poll bit. */
+#define PVRDMA_UAR_CQ_ARM_SOL		(1 << 29)	/* Arm solicited bit. */
+#define PVRDMA_UAR_CQ_ARM		(1 << 30)	/* Arm bit. */
+#define PVRDMA_UAR_CQ_POLL		(1 << 31)	/* Poll bit. */
+#define PVRDMA_UAR_SRQ_OFFSET		8		/* SRQ doorbell. */
+#define PVRDMA_UAR_SRQ_RECV		(1 << 30)	/* Recv bit. */
 
 enum pvrdma_wr_opcode {
 	PVRDMA_WR_RDMA_WRITE,