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

Pull rdma fixes from Jason Gunthorpe:
 "Nothing very exciting here, it has been a quiet cycle overall. Usual
  collection of small bug fixes:

   - irdma issues with CQ entries, VLAN completions and a mutex deadlock

   - Incorrect DCT packets in mlx5

   - Userspace triggered overflows in qib

   - Locking error in hfi

   - Typo in errno value in qib/hfi1

   - Double free in qedr

   - Leak of random kernel memory to userspace with a netlink callback"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/sa_query: Use strscpy_pad instead of memcpy to copy a string
  RDMA/irdma: Do not hold qos mutex twice on QP resume
  RDMA/irdma: Set VLAN in UD work completion correctly
  RDMA/mlx5: Initialize the ODP xarray when creating an ODP MR
  rdma/qedr: Fix crash due to redundant release of device's qp memory
  RDMA/rdmavt: Fix error code in rvt_create_qp()
  IB/hfi1: Fix abba locking issue with sc_disable()
  IB/qib: Protect from buffer overflow in struct qib_user_sdma_pkt fields
  RDMA/mlx5: Set user priority for DCT
  RDMA/irdma: Process extended CQ entries correctly

drivers/infiniband/core/sa_query.c

@@ -706,8 +706,9 @@ static void ib_nl_set_path_rec_attrs(struct sk_buff *skb,
 
 	/* Construct the family header first */
 	header = skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
-	memcpy(header->device_name, dev_name(&query->port->agent->device->dev),
-	       LS_DEVICE_NAME_MAX);
+	strscpy_pad(header->device_name,
+		    dev_name(&query->port->agent->device->dev),
+		    LS_DEVICE_NAME_MAX);
 	header->port_num = query->port->port_num;
 
 	if ((comp_mask & IB_SA_PATH_REC_REVERSIBLE) &&

drivers/infiniband/hw/hfi1/pio.c

@@ -878,6 +878,7 @@ void sc_disable(struct send_context *sc)
 {
 	u64 reg;
 	struct pio_buf *pbuf;
+	LIST_HEAD(wake_list);
 
 	if (!sc)
 		return;
@@ -912,19 +913,21 @@ void sc_disable(struct send_context *sc)
 	spin_unlock(&sc->release_lock);
 
 	write_seqlock(&sc->waitlock);
-	while (!list_empty(&sc->piowait)) {
+	if (!list_empty(&sc->piowait))
+		list_move(&sc->piowait, &wake_list);
+	write_sequnlock(&sc->waitlock);
+	while (!list_empty(&wake_list)) {
 		struct iowait *wait;
 		struct rvt_qp *qp;
 		struct hfi1_qp_priv *priv;
 
-		wait = list_first_entry(&sc->piowait, struct iowait, list);
+		wait = list_first_entry(&wake_list, struct iowait, list);
 		qp = iowait_to_qp(wait);
 		priv = qp->priv;
 		list_del_init(&priv->s_iowait.list);
 		priv->s_iowait.lock = NULL;
 		hfi1_qp_wakeup(qp, RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN);
 	}
-	write_sequnlock(&sc->waitlock);
 
 	spin_unlock_irq(&sc->alloc_lock);
 }

drivers/infiniband/hw/irdma/uk.c

@@ -1092,12 +1092,12 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info)
 		if (cq->avoid_mem_cflct) {
 			ext_cqe = (__le64 *)((u8 *)cqe + 32);
 			get_64bit_val(ext_cqe, 24, &qword7);
-			polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+			polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7);
 		} else {
 			peek_head = (cq->cq_ring.head + 1) % cq->cq_ring.size;
 			ext_cqe = cq->cq_base[peek_head].buf;
 			get_64bit_val(ext_cqe, 24, &qword7);
-			polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+			polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7);
 			if (!peek_head)
 				polarity ^= 1;
 		}

drivers/infiniband/hw/irdma/verbs.c

@@ -3399,9 +3399,13 @@ static void irdma_process_cqe(struct ib_wc *entry,
 		}
 
 		if (cq_poll_info->ud_vlan_valid) {
-			entry->vlan_id = cq_poll_info->ud_vlan & VLAN_VID_MASK;
-			entry->wc_flags |= IB_WC_WITH_VLAN;
+			u16 vlan = cq_poll_info->ud_vlan & VLAN_VID_MASK;
+
 			entry->sl = cq_poll_info->ud_vlan >> VLAN_PRIO_SHIFT;
+			if (vlan) {
+				entry->vlan_id = vlan;
+				entry->wc_flags |= IB_WC_WITH_VLAN;
+			}
 		} else {
 			entry->sl = 0;
 		}

drivers/infiniband/hw/irdma/ws.c

@@ -330,8 +330,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri)
 
 		tc_node->enable = true;
 		ret = irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_MODIFY_NODE);
-		if (ret)
+		if (ret) {
+			vsi->unregister_qset(vsi, tc_node);
 			goto reg_err;
+		}
 	}
 	ibdev_dbg(to_ibdev(vsi->dev),
 		  "WS: Using node %d which represents VSI %d TC %d\n",
@@ -350,6 +352,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri)
 	}
 	goto exit;
 
+reg_err:
+	irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_DELETE_NODE);
+	list_del(&tc_node->siblings);
+	irdma_free_node(vsi, tc_node);
 leaf_add_err:
 	if (list_empty(&vsi_node->child_list_head)) {
 		if (irdma_ws_cqp_cmd(vsi, vsi_node, IRDMA_OP_WS_DELETE_NODE))
@@ -369,11 +375,6 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri)
 exit:
 	mutex_unlock(&vsi->dev->ws_mutex);
 	return ret;
-
-reg_err:
-	mutex_unlock(&vsi->dev->ws_mutex);
-	irdma_ws_remove(vsi, user_pri);
-	return ret;
 }
 
 /**

drivers/infiniband/hw/mlx5/mr.c

@@ -1339,7 +1339,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
 		goto err_2;
 	}
 	mr->mmkey.type = MLX5_MKEY_MR;
-	mr->desc_size = sizeof(struct mlx5_mtt);
 	mr->umem = umem;
 	set_mr_fields(dev, mr, umem->length, access_flags);
 	kvfree(in);
@@ -1533,6 +1532,7 @@ static struct ib_mr *create_user_odp_mr(struct ib_pd *pd, u64 start, u64 length,
 		ib_umem_release(&odp->umem);
 		return ERR_CAST(mr);
 	}
+	xa_init(&mr->implicit_children);
 
 	odp->private = mr;
 	err = mlx5r_store_odp_mkey(dev, &mr->mmkey);

drivers/infiniband/hw/mlx5/qp.c

@@ -4458,6 +4458,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		MLX5_SET(dctc, dctc, mtu, attr->path_mtu);
 		MLX5_SET(dctc, dctc, my_addr_index, attr->ah_attr.grh.sgid_index);
 		MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit);
+		if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE)
+			MLX5_SET(dctc, dctc, eth_prio, attr->ah_attr.sl & 0x7);
 
 		err = mlx5_core_create_dct(dev, &qp->dct.mdct, qp->dct.in,
 					   MLX5_ST_SZ_BYTES(create_dct_in), out,

drivers/infiniband/hw/qedr/qedr.h

@@ -455,6 +455,7 @@ struct qedr_qp {
 	/* synchronization objects used with iwarp ep */
 	struct kref refcnt;
 	struct completion iwarp_cm_comp;
+	struct completion qp_rel_comp;
 	unsigned long iwarp_cm_flags; /* enum iwarp_cm_flags */
 };
 

drivers/infiniband/hw/qedr/qedr_iw_cm.c

@@ -83,7 +83,7 @@ static void qedr_iw_free_qp(struct kref *ref)
 {
 	struct qedr_qp *qp = container_of(ref, struct qedr_qp, refcnt);
 
-	kfree(qp);
+	complete(&qp->qp_rel_comp);
 }
 
 static void

drivers/infiniband/hw/qedr/verbs.c

@@ -1357,6 +1357,7 @@ static void qedr_set_common_qp_params(struct qedr_dev *dev,
 	if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
 		kref_init(&qp->refcnt);
 		init_completion(&qp->iwarp_cm_comp);
+		init_completion(&qp->qp_rel_comp);
 	}
 
 	qp->pd = pd;
@@ -2857,8 +2858,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 
 	qedr_free_qp_resources(dev, qp, udata);
 
-	if (rdma_protocol_iwarp(&dev->ibdev, 1))
+	if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
 		qedr_iw_qp_rem_ref(&qp->ibqp);
+		wait_for_completion(&qp->qp_rel_comp);
+	}
 
 	return 0;
 }

drivers/infiniband/hw/qib/qib_user_sdma.c

@@ -602,7 +602,7 @@ static int qib_user_sdma_coalesce(const struct qib_devdata *dd,
 /*
  * How many pages in this iovec element?
  */
-static int qib_user_sdma_num_pages(const struct iovec *iov)
+static size_t qib_user_sdma_num_pages(const struct iovec *iov)
 {
 	const unsigned long addr  = (unsigned long) iov->iov_base;
 	const unsigned long  len  = iov->iov_len;
@@ -658,7 +658,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
 static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 				   struct qib_user_sdma_queue *pq,
 				   struct qib_user_sdma_pkt *pkt,
-				   unsigned long addr, int tlen, int npages)
+				   unsigned long addr, int tlen, size_t npages)
 {
 	struct page *pages[8];
 	int i, j;
@@ -722,7 +722,7 @@ static int qib_user_sdma_pin_pkt(const struct qib_devdata *dd,
 	unsigned long idx;
 
 	for (idx = 0; idx < niov; idx++) {
-		const int npages = qib_user_sdma_num_pages(iov + idx);
+		const size_t npages = qib_user_sdma_num_pages(iov + idx);
 		const unsigned long addr = (unsigned long) iov[idx].iov_base;
 
 		ret = qib_user_sdma_pin_pages(dd, pq, pkt, addr,
@@ -824,8 +824,8 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
 		unsigned pktnw;
 		unsigned pktnwc;
 		int nfrags = 0;
-		int npages = 0;
-		int bytes_togo = 0;
+		size_t npages = 0;
+		size_t bytes_togo = 0;
 		int tiddma = 0;
 		int cfur;
 
@@ -885,7 +885,11 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
 
 			npages += qib_user_sdma_num_pages(&iov[idx]);
 
-			bytes_togo += slen;
+			if (check_add_overflow(bytes_togo, slen, &bytes_togo) ||
+			    bytes_togo > type_max(typeof(pkt->bytes_togo))) {
+				ret = -EINVAL;
+				goto free_pbc;
+			}
 			pktnwc += slen >> 2;
 			idx++;
 			nfrags++;
@@ -904,8 +908,7 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
 		}
 
 		if (frag_size) {
-			int tidsmsize, n;
-			size_t pktsize;
+			size_t tidsmsize, n, pktsize, sz, addrlimit;
 
 			n = npages*((2*PAGE_SIZE/frag_size)+1);
 			pktsize = struct_size(pkt, addr, n);
@@ -923,14 +926,24 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
 			else
 				tidsmsize = 0;
 
-			pkt = kmalloc(pktsize+tidsmsize, GFP_KERNEL);
+			if (check_add_overflow(pktsize, tidsmsize, &sz)) {
+				ret = -EINVAL;
+				goto free_pbc;
+			}
+			pkt = kmalloc(sz, GFP_KERNEL);
 			if (!pkt) {
 				ret = -ENOMEM;
 				goto free_pbc;
 			}
 			pkt->largepkt = 1;
 			pkt->frag_size = frag_size;
-			pkt->addrlimit = n + ARRAY_SIZE(pkt->addr);
+			if (check_add_overflow(n, ARRAY_SIZE(pkt->addr),
+					       &addrlimit) ||
+			    addrlimit > type_max(typeof(pkt->addrlimit))) {
+				ret = -EINVAL;
+				goto free_pbc;
+			}
+			pkt->addrlimit = addrlimit;
 
 			if (tiddma) {
 				char *tidsm = (char *)pkt + pktsize;

drivers/infiniband/sw/rdmavt/qp.c

@@ -1223,7 +1223,7 @@ int rvt_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
 	spin_lock(&rdi->n_qps_lock);
 	if (rdi->n_qps_allocated == rdi->dparms.props.max_qp) {
 		spin_unlock(&rdi->n_qps_lock);
-		ret = ENOMEM;
+		ret = -ENOMEM;
 		goto bail_ip;
 	}