7 files changed, 43 insertions, 12 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index bbfb86eb2d24..bc2b9e038439 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/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);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index e426b990c1dd..6ad0d46ab879 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/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) {
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index b3203afa3b1d..347fe18b1a41 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/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);
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index fbe7198a715a..bedd5fba33b0 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -198,7 +198,7 @@ int node_affinity_init(void)
 		while ((dev = pci_get_device(ids->vendor, ids->device, dev))) {
 			node = pcibus_to_node(dev->bus);
 			if (node < 0)
-				node = numa_node_id();
+				goto out;
 
 			hfi1_per_node_cntr[node]++;
 		}
@@ -206,6 +206,18 @@ int node_affinity_init(void)
 	}
 
 	return 0;
+
+out:
+	/*
+	 * Invalid PCI NUMA node information found, note it, and populate
+	 * our database 1:1.
+	 */
+	pr_err("HFI: Invalid PCI NUMA node. Performance may be affected\n");
+	pr_err("HFI: System BIOS may need to be upgraded\n");
+	for (node = 0; node < node_affinity.num_possible_nodes; node++)
+		hfi1_per_node_cntr[node] = 1;
+
+	return 0;
 }
 
 static void node_affinity_destroy(struct hfi1_affinity_node *entry)
@@ -622,8 +634,14 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 	int curr_cpu, possible, i, ret;
 	bool new_entry = false;
 
-	if (node < 0)
-		node = numa_node_id();
+	/*
+	 * If the BIOS does not have the NUMA node information set, select
+	 * NUMA 0 so we get consistent performance.
+	 */
+	if (node < 0) {
+		dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
+		node = 0;
+	}
 	dd->node = node;
 
 	local_mask = cpumask_of_node(dd->node);
diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
index 70aceefe14d5..e1c7996c018e 100644
--- a/drivers/infiniband/hw/hfi1/mmu_rb.c
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -67,9 +67,9 @@ struct mmu_rb_handler {
 
 static unsigned long mmu_node_start(struct mmu_rb_node *);
 static unsigned long mmu_node_last(struct mmu_rb_node *);
-static void mmu_notifier_range_start(struct mmu_notifier *,
+static int mmu_notifier_range_start(struct mmu_notifier *,
 				     struct mm_struct *,
-				     unsigned long, unsigned long);
+				     unsigned long, unsigned long, bool);
 static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *,
 					   unsigned long, unsigned long);
 static void do_remove(struct mmu_rb_handler *handler,
@@ -284,10 +284,11 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler,
 	handler->ops->remove(handler->ops_arg, node);
 }
 
-static void mmu_notifier_range_start(struct mmu_notifier *mn,
+static int mmu_notifier_range_start(struct mmu_notifier *mn,
 				     struct mm_struct *mm,
 				     unsigned long start,
-				     unsigned long end)
+				     unsigned long end,
+				     bool blockable)
 {
 	struct mmu_rb_handler *handler =
 		container_of(mn, struct mmu_rb_handler, mn);
@@ -313,6 +314,8 @@ static void mmu_notifier_range_start(struct mmu_notifier *mn,
 
 	if (added)
 		queue_work(handler->wq, &handler->del_work);
+
+	return 0;
 }
 
 /*
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index ca0f1ee26091..0bbeaaae47e0 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/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;
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index f1a87a690a4c..d216e0d2921d 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -488,7 +488,7 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
 
 	down_read(&ctx->umem_rwsem);
 	rbt_ib_umem_for_each_in_range(&ctx->umem_tree, 0, ULLONG_MAX,
-				      mr_leaf_free, imr);
+				      mr_leaf_free, true, imr);
 	up_read(&ctx->umem_rwsem);
 
 	wait_event(imr->q_leaf_free, !atomic_read(&imr->num_leaf_free));