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

Pull rdma fixes from Jason Gunthorpe:
 "This fixes one major regression with NFS and mlx4 due to the max_sg
  rework in this merge window, tidies a few minor error_path
  regressions, and various small fixes.

  The HFI1 driver is broken this cycle due to a regression caused by a
  PCI change, it is looking like Bjorn will merge a fix for this. Also,
  the lingering ipoib issue I mentioned earlier still remains unfixed.

  Summary:

   - Fix possible FD type confusion crash

   - Fix a user trigger-able crash in cxgb4

   - Fix bad handling of IOMMU resources causing user controlled leaking
     in bnxt

   - Add missing locking in ipoib to fix a rare 'stuck tx' situation

   - Add missing locking in cma

   - Add two missing missing uverbs cleanups on failure paths,
     regressions from this merge window

   - Fix a regression from this merge window that caused RDMA NFS to not
     work with the mlx4 driver due to the max_sg changes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/mlx4: Ensure that maximal send/receive SGE less than supported by HW
  RDMA/cma: Protect cma dev list with lock
  RDMA/uverbs: Fix error cleanup path of ib_uverbs_add_one()
  bnxt_re: Fix couple of memory leaks that could lead to IOMMU call traces
  IB/ipoib: Avoid a race condition between start_xmit and cm_rep_handler
  iw_cxgb4: only allow 1 flush on user qps
  IB/core: Release object lock if destroy failed
  RDMA/ucma: check fd type in ucma_migrate_id()

Author: torvalds

drivers/infiniband/core/cma.c

@@ -724,6 +724,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 	dgid = (union ib_gid *) &addr->sib_addr;
 	pkey = ntohs(addr->sib_pkey);
 
+	mutex_lock(&lock);
 	list_for_each_entry(cur_dev, &dev_list, list) {
 		for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) {
 			if (!rdma_cap_af_ib(cur_dev->device, p))
@@ -750,18 +751,19 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 					cma_dev = cur_dev;
 					sgid = gid;
 					id_priv->id.port_num = p;
+					goto found;
 				}
 			}
 		}
 	}
-
-	if (!cma_dev)
-		return -ENODEV;
+	mutex_unlock(&lock);
+	return -ENODEV;
 
 found:
 	cma_attach_to_dev(id_priv, cma_dev);
-	addr = (struct sockaddr_ib *) cma_src_addr(id_priv);
-	memcpy(&addr->sib_addr, &sgid, sizeof sgid);
+	mutex_unlock(&lock);
+	addr = (struct sockaddr_ib *)cma_src_addr(id_priv);
+	memcpy(&addr->sib_addr, &sgid, sizeof(sgid));
 	cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr);
 	return 0;
 }

drivers/infiniband/core/rdma_core.c

@@ -882,6 +882,8 @@ static int __uverbs_cleanup_ufile(struct ib_uverbs_file *ufile,
 		WARN_ON(uverbs_try_lock_object(obj, UVERBS_LOOKUP_WRITE));
 		if (!uverbs_destroy_uobject(obj, reason))
 			ret = 0;
+		else
+			atomic_set(&obj->usecnt, 0);
 	}
 	return ret;
 }

drivers/infiniband/core/ucma.c

@@ -124,6 +124,8 @@ static DEFINE_MUTEX(mut);
 static DEFINE_IDR(ctx_idr);
 static DEFINE_IDR(multicast_idr);
 
+static const struct file_operations ucma_fops;
+
 static inline struct ucma_context *_ucma_find_context(int id,
 						      struct ucma_file *file)
 {
@@ -1581,6 +1583,10 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file,
 	f = fdget(cmd.fd);
 	if (!f.file)
 		return -ENOENT;
+	if (f.file->f_op != &ucma_fops) {
+		ret = -EINVAL;
+		goto file_put;
+	}
 
 	/* Validate current fd and prevent destruction of id. */
 	ctx = ucma_get_ctx(f.file->private_data, cmd.id);

drivers/infiniband/core/uverbs_main.c

@@ -1050,7 +1050,7 @@ static void ib_uverbs_add_one(struct ib_device *device)
 	uverbs_dev->num_comp_vectors = device->num_comp_vectors;
 
 	if (ib_uverbs_create_uapi(device, uverbs_dev))
-		goto err;
+		goto err_uapi;
 
 	cdev_init(&uverbs_dev->cdev, NULL);
 	uverbs_dev->cdev.owner = THIS_MODULE;
@@ -1077,11 +1077,10 @@ static void ib_uverbs_add_one(struct ib_device *device)
 
 err_class:
 	device_destroy(uverbs_class, uverbs_dev->cdev.dev);
-
 err_cdev:
 	cdev_del(&uverbs_dev->cdev);
+err_uapi:
 	clear_bit(devnum, dev_map);
-
 err:
 	if (atomic_dec_and_test(&uverbs_dev->refcount))
 		ib_uverbs_comp_dev(uverbs_dev);

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -833,6 +833,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp)
 				"Failed to destroy Shadow QP");
 			return rc;
 		}
+		bnxt_qplib_free_qp_res(&rdev->qplib_res,
+				       &rdev->qp1_sqp->qplib_qp);
 		mutex_lock(&rdev->qp_lock);
 		list_del(&rdev->qp1_sqp->list);
 		atomic_dec(&rdev->qp_count);

drivers/infiniband/hw/bnxt_re/qplib_fp.c

@@ -196,7 +196,7 @@ static int bnxt_qplib_alloc_qp_hdr_buf(struct bnxt_qplib_res *res,
 				       struct bnxt_qplib_qp *qp)
 {
 	struct bnxt_qplib_q *rq = &qp->rq;
-	struct bnxt_qplib_q *sq = &qp->rq;
+	struct bnxt_qplib_q *sq = &qp->sq;
 	int rc = 0;
 
 	if (qp->sq_hdr_buf_size && sq->hwq.max_elements) {

drivers/infiniband/hw/cxgb4/qp.c

@@ -1685,6 +1685,12 @@ static void flush_qp(struct c4iw_qp *qhp)
 	schp = to_c4iw_cq(qhp->ibqp.send_cq);
 
 	if (qhp->ibqp.uobject) {
+
+		/* for user qps, qhp->wq.flushed is protected by qhp->mutex */
+		if (qhp->wq.flushed)
+			return;
+
+		qhp->wq.flushed = 1;
 		t4_set_wq_in_error(&qhp->wq, 0);
 		t4_set_cq_in_error(&rchp->cq);
 		spin_lock_irqsave(&rchp->comp_handler_lock, flag);

drivers/infiniband/hw/mlx4/main.c

@@ -517,9 +517,11 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->page_size_cap	   = dev->dev->caps.page_size_cap;
 	props->max_qp		   = dev->dev->quotas.qp;
 	props->max_qp_wr	   = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
-	props->max_send_sge	   = dev->dev->caps.max_sq_sg;
-	props->max_recv_sge	   = dev->dev->caps.max_rq_sg;
-	props->max_sge_rd	   = MLX4_MAX_SGE_RD;
+	props->max_send_sge =
+		min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg);
+	props->max_recv_sge =
+		min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg);
+	props->max_sge_rd = MLX4_MAX_SGE_RD;
 	props->max_cq		   = dev->dev->quotas.cq;
 	props->max_cqe		   = dev->dev->caps.max_cqes;
 	props->max_mr		   = dev->dev->quotas.mpt;

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -1027,12 +1027,14 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id,
 
 	skb_queue_head_init(&skqueue);
 
+	netif_tx_lock_bh(p->dev);
 	spin_lock_irq(&priv->lock);
 	set_bit(IPOIB_FLAG_OPER_UP, &p->flags);
 	if (p->neigh)
 		while ((skb = __skb_dequeue(&p->neigh->queue)))
 			__skb_queue_tail(&skqueue, skb);
 	spin_unlock_irq(&priv->lock);
+	netif_tx_unlock_bh(p->dev);
 
 	while ((skb = __skb_dequeue(&skqueue))) {
 		skb->dev = p->dev;