Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma fixes from Jason Gunthorpe:
 "A few regression and bug fixes for the patches merged in the last
  cycle:

   - hns fixes a subtle crash from the ib core SGL rework

   - hfi1 fixes various error handling, oops and protocol errors

   - bnxt_re fixes a regression where nvmeof doesn't work on some
     configurations

   - mlx5 fixes a serious 'use after free' bug in how MR caching is
     handled

   - some edge case crashers in the new statistic core code

   - more siw static checker fixups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  IB/mlx5: Fix RSS Toeplitz setup to be aligned with the HW specification
  IB/counters: Always initialize the port counter object
  IB/core: Fix querying total rdma stats
  IB/mlx5: Prevent concurrent MR updates during invalidation
  IB/mlx5: Fix clean_mr() to work in the expected order
  IB/mlx5: Move MRs to a kernel PD when freeing them to the MR cache
  IB/mlx5: Use direct mkey destroy command upon UMR unreg failure
  IB/mlx5: Fix unreg_umr to ignore the mkey state
  RDMA/siw: Remove set but not used variables 'rv'
  IB/mlx5: Replace kfree with kvfree
  RDMA/bnxt_re: Honor vlan_id in GID entry comparison
  IB/hfi1: Drop all TID RDMA READ RESP packets after r_next_psn
  IB/hfi1: Field not zero-ed when allocating TID flow memory
  IB/hfi1: Unreserve a flushed OPFN request
  IB/hfi1: Check for error on call to alloc_rsm_map_table
  RDMA/hns: Fix sg offset non-zero issue
  RDMA/siw: Fix error return code in siw_init_module()

17 files changed, 89 insertions, 93 deletions

diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index 01faef7bc061..45d5164e9574 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -393,6 +393,9 @@ u64 rdma_counter_get_hwstat_value(struct ib_device *dev, u8 port, u32 index)
 	u64 sum;
 
 	port_counter = &dev->port_data[port].port_counter;
+	if (!port_counter->hstats)
+		return 0;
+
 	sum = get_running_counters_hwstat_sum(dev, port, index);
 	sum += port_counter->hstats->value[index];
 
@@ -594,7 +597,7 @@ void rdma_counter_init(struct ib_device *dev)
 	struct rdma_port_counter *port_counter;
 	u32 port;
 
-	if (!dev->ops.alloc_hw_stats || !dev->port_data)
+	if (!dev->port_data)
 		return;
 
 	rdma_for_each_port(dev, port) {
@@ -602,6 +605,9 @@ void rdma_counter_init(struct ib_device *dev)
 		port_counter->mode.mode = RDMA_COUNTER_MODE_NONE;
 		mutex_init(&port_counter->lock);
 
+		if (!dev->ops.alloc_hw_stats)
+			continue;
+
 		port_counter->hstats = dev->ops.alloc_hw_stats(dev, port);
 		if (!port_counter->hstats)
 			goto fail;
@@ -624,9 +630,6 @@ void rdma_counter_release(struct ib_device *dev)
 	struct rdma_port_counter *port_counter;
 	u32 port;
 
-	if (!dev->ops.alloc_hw_stats)
-		return;
-
 	rdma_for_each_port(dev, port) {
 		port_counter = &dev->port_data[port].port_counter;
 		kfree(port_counter->hstats);
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index a91653aabf38..098ab883733e 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -308,6 +308,7 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context)
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(attr->device, ibdev);
 	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
 	struct bnxt_qplib_gid *gid_to_del;
+	u16 vlan_id = 0xFFFF;
 
 	/* Delete the entry from the hardware */
 	ctx = *context;
@@ -317,7 +318,8 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context)
 	if (sgid_tbl && sgid_tbl->active) {
 		if (ctx->idx >= sgid_tbl->max)
 			return -EINVAL;
-		gid_to_del = &sgid_tbl->tbl[ctx->idx];
+		gid_to_del = &sgid_tbl->tbl[ctx->idx].gid;
+		vlan_id = sgid_tbl->tbl[ctx->idx].vlan_id;
 		/* DEL_GID is called in WQ context(netdevice_event_work_handler)
 		 * or via the ib_unregister_device path. In the former case QP1
 		 * may not be destroyed yet, in which case just return as FW
@@ -335,7 +337,8 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context)
 		}
 		ctx->refcnt--;
 		if (!ctx->refcnt) {
-			rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true);
+			rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del,
+						 vlan_id,  true);
 			if (rc) {
 				dev_err(rdev_to_dev(rdev),
 					"Failed to remove GID: %#x", rc);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 37928b1111df..bdbde8e22420 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -488,7 +488,7 @@ static int bnxt_qplib_alloc_sgid_tbl(struct bnxt_qplib_res *res,
 				     struct bnxt_qplib_sgid_tbl *sgid_tbl,
 				     u16 max)
 {
-	sgid_tbl->tbl = kcalloc(max, sizeof(struct bnxt_qplib_gid), GFP_KERNEL);
+	sgid_tbl->tbl = kcalloc(max, sizeof(*sgid_tbl->tbl), GFP_KERNEL);
 	if (!sgid_tbl->tbl)
 		return -ENOMEM;
 
@@ -526,9 +526,10 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res,
 	for (i = 0; i < sgid_tbl->max; i++) {
 		if (memcmp(&sgid_tbl->tbl[i], &bnxt_qplib_gid_zero,
 			   sizeof(bnxt_qplib_gid_zero)))
-			bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i], true);
+			bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i].gid,
+					    sgid_tbl->tbl[i].vlan_id, true);
 	}
-	memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max);
+	memset(sgid_tbl->tbl, 0, sizeof(*sgid_tbl->tbl) * sgid_tbl->max);
 	memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
 	memset(sgid_tbl->vlan, 0, sizeof(u8) * sgid_tbl->max);
 	sgid_tbl->active = 0;
@@ -537,7 +538,11 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res,
 static void bnxt_qplib_init_sgid_tbl(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 				     struct net_device *netdev)
 {
-	memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max);
+	u32 i;
+
+	for (i = 0; i < sgid_tbl->max; i++)
+		sgid_tbl->tbl[i].vlan_id = 0xffff;
+
 	memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
 }
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 30c42c92fac7..fbda11a7ab1a 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -111,7 +111,7 @@ struct bnxt_qplib_pd_tbl {
 };
 
 struct bnxt_qplib_sgid_tbl {
-	struct bnxt_qplib_gid		*tbl;
+	struct bnxt_qplib_gid_info	*tbl;
 	u16				*hw_id;
 	u16				max;
 	u16				active;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 48793d3512ac..40296b97d21e 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -213,12 +213,12 @@ int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res,
 			index, sgid_tbl->max);
 		return -EINVAL;
 	}
-	memcpy(gid, &sgid_tbl->tbl[index], sizeof(*gid));
+	memcpy(gid, &sgid_tbl->tbl[index].gid, sizeof(*gid));
 	return 0;
 }
 
 int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
-			struct bnxt_qplib_gid *gid, bool update)
+			struct bnxt_qplib_gid *gid, u16 vlan_id, bool update)
 {
 	struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl,
 						   struct bnxt_qplib_res,
@@ -236,7 +236,8 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 		return -ENOMEM;
 	}
 	for (index = 0; index < sgid_tbl->max; index++) {
-		if (!memcmp(&sgid_tbl->tbl[index], gid, sizeof(*gid)))
+		if (!memcmp(&sgid_tbl->tbl[index].gid, gid, sizeof(*gid)) &&
+		    vlan_id == sgid_tbl->tbl[index].vlan_id)
 			break;
 	}
 	if (index == sgid_tbl->max) {
@@ -262,8 +263,9 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 		if (rc)
 			return rc;
 	}
-	memcpy(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero,
+	memcpy(&sgid_tbl->tbl[index].gid, &bnxt_qplib_gid_zero,
 	       sizeof(bnxt_qplib_gid_zero));
+	sgid_tbl->tbl[index].vlan_id = 0xFFFF;
 	sgid_tbl->vlan[index] = 0;
 	sgid_tbl->active--;
 	dev_dbg(&res->pdev->dev,
@@ -296,7 +298,8 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 	}
 	free_idx = sgid_tbl->max;
 	for (i = 0; i < sgid_tbl->max; i++) {
-		if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid))) {
+		if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid)) &&
+		    sgid_tbl->tbl[i].vlan_id == vlan_id) {
 			dev_dbg(&res->pdev->dev,
 				"SGID entry already exist in entry %d!\n", i);
 			*index = i;
@@ -351,6 +354,7 @@ 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->tbl[free_idx].vlan_id = vlan_id;
 	sgid_tbl->active++;
 	if (vlan_id != 0xFFFF)
 		sgid_tbl->vlan[free_idx] = 1;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index 0ec3b12b0bcd..13d9432d5ce2 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -84,6 +84,11 @@ struct bnxt_qplib_gid {
 	u8				data[16];
 };
 
+struct bnxt_qplib_gid_info {
+	struct bnxt_qplib_gid gid;
+	u16 vlan_id;
+};
+
 struct bnxt_qplib_ah {
 	struct bnxt_qplib_gid		dgid;
 	struct bnxt_qplib_pd		*pd;
@@ -221,7 +226,7 @@ int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res,
 			struct bnxt_qplib_sgid_tbl *sgid_tbl, int index,
 			struct bnxt_qplib_gid *gid);
 int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
-			struct bnxt_qplib_gid *gid, bool update);
+			struct bnxt_qplib_gid *gid, u16 vlan_id, bool update);
 int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 			struct bnxt_qplib_gid *gid, u8 *mac, u16 vlan_id,
 			bool update, u32 *index);
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index d5b643a1d9fd..67052dc3100c 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -14452,7 +14452,7 @@ void hfi1_deinit_vnic_rsm(struct hfi1_devdata *dd)
 		clear_rcvctrl(dd, RCV_CTRL_RCV_RSM_ENABLE_SMASK);
 }
 
-static void init_rxe(struct hfi1_devdata *dd)
+static int init_rxe(struct hfi1_devdata *dd)
 {
 	struct rsm_map_table *rmt;
 	u64 val;
@@ -14461,6 +14461,9 @@ static void init_rxe(struct hfi1_devdata *dd)
 	write_csr(dd, RCV_ERR_MASK, ~0ull);
 
 	rmt = alloc_rsm_map_table(dd);
+	if (!rmt)
+		return -ENOMEM;
+
 	/* set up QOS, including the QPN map table */
 	init_qos(dd, rmt);
 	init_fecn_handling(dd, rmt);
@@ -14487,6 +14490,7 @@ static void init_rxe(struct hfi1_devdata *dd)
 	val |= ((4ull & RCV_BYPASS_HDR_SIZE_MASK) <<
 		RCV_BYPASS_HDR_SIZE_SHIFT);
 	write_csr(dd, RCV_BYPASS, val);
+	return 0;
 }
 
 static void init_other(struct hfi1_devdata *dd)
@@ -15024,7 +15028,10 @@ int hfi1_init_dd(struct hfi1_devdata *dd)
 		goto bail_cleanup;
 
 	/* set initial RXE CSRs */
-	init_rxe(dd);
+	ret = init_rxe(dd);
+	if (ret)
+		goto bail_cleanup;
+
 	/* set initial TXE CSRs */
 	init_txe(dd);
 	/* set initial non-RXE, non-TXE CSRs */
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 0477c14633ab..024a7c2b6124 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -1835,7 +1835,6 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah)
 		    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) <= 0)
 			break;
 		trdma_clean_swqe(qp, wqe);
-		rvt_qp_wqe_unreserve(qp, wqe);
 		trace_hfi1_qp_send_completion(qp, wqe, qp->s_last);
 		rvt_qp_complete_swqe(qp,
 				     wqe,
@@ -1882,7 +1881,6 @@ struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 	if (cmp_psn(wqe->lpsn, qp->s_sending_psn) < 0 ||
 	    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) {
 		trdma_clean_swqe(qp, wqe);
-		rvt_qp_wqe_unreserve(qp, wqe);
 		trace_hfi1_qp_send_completion(qp, wqe, qp->s_last);
 		rvt_qp_complete_swqe(qp,
 				     wqe,
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index 92acccaaaa86..996fc298207e 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -1620,6 +1620,7 @@ static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req,
 		flows[i].req = req;
 		flows[i].npagesets = 0;
 		flows[i].pagesets[0].mapped =  0;
+		flows[i].resync_npkts = 0;
 	}
 	req->flows = flows;
 	return 0;
@@ -1673,34 +1674,6 @@ static struct tid_rdma_flow *find_flow_ib(struct tid_rdma_request *req,
 	return NULL;
 }
 
-static struct tid_rdma_flow *
-__find_flow_ranged(struct tid_rdma_request *req, u16 head, u16 tail,
-		   u32 psn, u16 *fidx)
-{
-	for ( ; CIRC_CNT(head, tail, MAX_FLOWS);
-	      tail = CIRC_NEXT(tail, MAX_FLOWS)) {
-		struct tid_rdma_flow *flow = &req->flows[tail];
-		u32 spsn, lpsn;
-
-		spsn = full_flow_psn(flow, flow->flow_state.spsn);
-		lpsn = full_flow_psn(flow, flow->flow_state.lpsn);
-
-		if (cmp_psn(psn, spsn) >= 0 && cmp_psn(psn, lpsn) <= 0) {
-			if (fidx)
-				*fidx = tail;
-			return flow;
-		}
-	}
-	return NULL;
-}
-
-static struct tid_rdma_flow *find_flow(struct tid_rdma_request *req,
-				       u32 psn, u16 *fidx)
-{
-	return __find_flow_ranged(req, req->setup_head, req->clear_tail, psn,
-				  fidx);
-}
-
 /* TID RDMA READ functions */
 u32 hfi1_build_tid_rdma_read_packet(struct rvt_swqe *wqe,
 				    struct ib_other_headers *ohdr, u32 *bth1,
@@ -2788,19 +2761,7 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd,
 			 * to prevent continuous Flow Sequence errors for any
 			 * packets that could be still in the fabric.
 			 */
-			flow = find_flow(req, psn, NULL);
-			if (!flow) {
-				/*
-				 * We can't find the IB PSN matching the
-				 * received KDETH PSN. The only thing we can
-				 * do at this point is report the error to
-				 * the QP.
-				 */
-				hfi1_kern_read_tid_flow_free(qp);
-				spin_unlock(&qp->s_lock);
-				rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
-				return ret;
-			}
+			flow = &req->flows[req->clear_tail];
 			if (priv->s_flags & HFI1_R_TID_SW_PSN) {
 				diff = cmp_psn(psn,
 					       flow->flow_state.r_next_psn);
diff --git a/drivers/infiniband/hw/hns/hns_roce_db.c b/drivers/infiniband/hw/hns/hns_roce_db.c
index 627aa46ef683..c00714c2f16a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_db.c
+++ b/drivers/infiniband/hw/hns/hns_roce_db.c
@@ -12,13 +12,15 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context,
 			 struct ib_udata *udata, unsigned long virt,
 			 struct hns_roce_db *db)
 {
+	unsigned long page_addr = virt & PAGE_MASK;
 	struct hns_roce_user_db_page *page;
+	unsigned int offset;
 	int ret = 0;
 
 	mutex_lock(&context->page_mutex);
 
 	list_for_each_entry(page, &context->page_list, list)
-		if (page->user_virt == (virt & PAGE_MASK))
+		if (page->user_virt == page_addr)
 			goto found;
 
 	page = kmalloc(sizeof(*page), GFP_KERNEL);
@@ -28,8 +30,8 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context,
 	}
 
 	refcount_set(&page->refcount, 1);
-	page->user_virt = (virt & PAGE_MASK);
-	page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0, 0);
+	page->user_virt = page_addr;
+	page->umem = ib_umem_get(udata, page_addr, PAGE_SIZE, 0, 0);
 	if (IS_ERR(page->umem)) {
 		ret = PTR_ERR(page->umem);
 		kfree(page);
@@ -39,10 +41,9 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context,
 	list_add(&page->list, &context->page_list);
 
 found:
-	db->dma = sg_dma_address(page->umem->sg_head.sgl) +
-		  (virt & ~PAGE_MASK);
-	page->umem->sg_head.sgl->offset = virt & ~PAGE_MASK;
-	db->virt_addr = sg_virt(page->umem->sg_head.sgl);
+	offset = virt - page_addr;
+	db->dma = sg_dma_address(page->umem->sg_head.sgl) + offset;
+	db->virt_addr = sg_virt(page->umem->sg_head.sgl) + offset;
 	db->u.user_page = page;
 	refcount_inc(&page->refcount);
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index c482f19958b3..f6a53455bf8b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -481,6 +481,7 @@ struct mlx5_umr_wr {
 	u64				length;
 	int				access_flags;
 	u32				mkey;
+	u8				ignore_free_state:1;
 };
 
 static inline const struct mlx5_umr_wr *umr_wr(const struct ib_send_wr *wr)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 20ece6e0b2fc..2c77456f359f 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -545,13 +545,16 @@ void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		return;
 
 	c = order2idx(dev, mr->order);
-	if (c < 0 || c >= MAX_MR_CACHE_ENTRIES) {
-		mlx5_ib_warn(dev, "order %d, cache index %d\n", mr->order, c);
-		return;
-	}
+	WARN_ON(c < 0 || c >= MAX_MR_CACHE_ENTRIES);
 
-	if (unreg_umr(dev, mr))
+	if (unreg_umr(dev, mr)) {
+		mr->allocated_from_cache = false;
+		destroy_mkey(dev, mr);
+		ent = &cache->ent[c];
+		if (ent->cur < ent->limit)
+			queue_work(cache->wq, &ent->work);
 		return;
+	}
 
 	ent = &cache->ent[c];
 	spin_lock_irq(&ent->lock);
@@ -1373,9 +1376,11 @@ static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		return 0;
 
 	umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR |
-			      MLX5_IB_SEND_UMR_FAIL_IF_FREE;
+			      MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS;
 	umrwr.wr.opcode = MLX5_IB_WR_UMR;
+	umrwr.pd = dev->umrc.pd;
 	umrwr.mkey = mr->mmkey.key;
+	umrwr.ignore_free_state = 1;
 
 	return mlx5_ib_post_send_wait(dev, &umrwr);
 }
@@ -1577,10 +1582,10 @@ static void clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		mr->sig = NULL;
 	}
 
-	mlx5_free_priv_descs(mr);
-
-	if (!allocated_from_cache)
+	if (!allocated_from_cache) {
 		destroy_mkey(dev, mr);
+		mlx5_free_priv_descs(mr);
+	}
 }
 
 static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 5b642d81e617..81da82050d05 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -246,7 +246,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 	 * overwrite the same MTTs.  Concurent invalidations might race us,
 	 * but they will write 0s as well, so no difference in the end result.
 	 */
-
+	mutex_lock(&umem_odp->umem_mutex);
 	for (addr = start; addr < end; addr += BIT(umem_odp->page_shift)) {
 		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
 		/*
@@ -278,6 +278,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 				   idx - blk_start_idx + 1, 0,
 				   MLX5_IB_UPD_XLT_ZAP |
 				   MLX5_IB_UPD_XLT_ATOMIC);
+	mutex_unlock(&umem_odp->umem_mutex);
 	/*
 	 * We are now sure that the device will not access the
 	 * memory. We can safely unmap it, and mark it as dirty if
@@ -1771,7 +1772,7 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *work)
 
 	num_pending_prefetch_dec(to_mdev(w->pd->device), w->sg_list,
 				 w->num_sge, 0);
-	kfree(w);
+	kvfree(w);
 }
 
 int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
@@ -1813,7 +1814,7 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 	if (valid_req)
 		queue_work(system_unbound_wq, &work->work);
 	else
-		kfree(work);
+		kvfree(work);
 
 	srcu_read_unlock(&dev->mr_srcu, srcu_key);
 
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 2a97619ed603..379328b2598f 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1713,7 +1713,6 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		}
 
 		MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_TOEPLITZ);
-		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
 		memcpy(rss_key, ucmd.rx_hash_key, len);
 		break;
 	}
@@ -4295,10 +4294,14 @@ static int set_reg_umr_segment(struct mlx5_ib_dev *dev,
 
 	memset(umr, 0, sizeof(*umr));
 
-	if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE)
-		umr->flags = MLX5_UMR_CHECK_FREE; /* fail if free */
-	else
-		umr->flags = MLX5_UMR_CHECK_NOT_FREE; /* fail if not free */
+	if (!umrwr->ignore_free_state) {
+		if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE)
+			 /* fail if free */
+			umr->flags = MLX5_UMR_CHECK_FREE;
+		else
+			/* fail if not free */
+			umr->flags = MLX5_UMR_CHECK_NOT_FREE;
+	}
 
 	umr->xlt_octowords = cpu_to_be16(get_xlt_octo(umrwr->xlt_size));
 	if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_XLT) {
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index a7cde98e73e8..9ce8a1b925d2 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -220,13 +220,12 @@ static void siw_put_work(struct siw_cm_work *work)
 static void siw_cep_set_inuse(struct siw_cep *cep)
 {
 	unsigned long flags;
-	int rv;
 retry:
 	spin_lock_irqsave(&cep->lock, flags);
 
 	if (cep->in_use) {
 		spin_unlock_irqrestore(&cep->lock, flags);
-		rv = wait_event_interruptible(cep->waitq, !cep->in_use);
+		wait_event_interruptible(cep->waitq, !cep->in_use);
 		if (signal_pending(current))
 			flush_signals(current);
 		goto retry;
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index f55c4e80aea4..d0f140daf659 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -612,6 +612,7 @@ static __init int siw_init_module(void)
 
 	if (!siw_create_tx_threads()) {
 		pr_info("siw: Could not start any TX thread\n");
+		rv = -ENOMEM;
 		goto out_error;
 	}
 	/*
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 0eeea520a853..e06c77d76463 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -608,7 +608,7 @@ static inline void rvt_qp_wqe_reserve(
 /**
  * rvt_qp_wqe_unreserve - clean reserved operation
  * @qp - the rvt qp
- * @wqe - the send wqe
+ * @flags - send wqe flags
  *
  * This decrements the reserve use count.
  *
@@ -620,11 +620,9 @@ static inline void rvt_qp_wqe_reserve(
  * the compiler does not juggle the order of the s_last
  * ring index and the decrementing of s_reserved_used.
  */
-static inline void rvt_qp_wqe_unreserve(
-	struct rvt_qp *qp,
-	struct rvt_swqe *wqe)
+static inline void rvt_qp_wqe_unreserve(struct rvt_qp *qp, int flags)
 {
-	if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) {
+	if (unlikely(flags & RVT_SEND_RESERVE_USED)) {
 		atomic_dec(&qp->s_reserved_used);
 		/* insure no compiler re-order up to s_last change */
 		smp_mb__after_atomic();
@@ -853,6 +851,7 @@ rvt_qp_complete_swqe(struct rvt_qp *qp,
 	u32 byte_len, last;
 	int flags = wqe->wr.send_flags;
 
+	rvt_qp_wqe_unreserve(qp, flags);
 	rvt_put_qp_swqe(qp, wqe);
 
 	need_completion =