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

Pull rdma updates from Jason Gunthorpe:
 "Very small update this cycle:

   - Minor code improvements in fi, rxe, ipoib, mana, cxgb4, mlx5,
     irdma, rxe, rtrs, mana

   - Simplify the hns hem mechanism

   - Fix EFA's MSI-X allocation in resource constrained configurations

   - Fix a KASN splat in srpt

   - Narrow hns's congestion control selection to QPs granularity and
     allow userspace to select it

   - Solve a parallel module loading race between the CM module and a
     driver module

   - Flexible array cleanup

   - Dump hns's SCC Conext to 'rdma res' for debugging

   - Make mana build page lists for HW objects that require a 0 offset
     correctly

   - Stuck CM ID debugging"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (29 commits)
  RDMA/cm: add timeout to cm_destroy_id wait
  RDMA/mana_ib: Use virtual address in dma regions for MRs
  RDMA/mana_ib: Fix bug in creation of dma regions
  RDMA/hns: Append SCC context to the raw dump of QPC
  RDMA/uverbs: Avoid -Wflex-array-member-not-at-end warnings
  RDMA/hns: Support userspace configuring congestion control algorithm with QP granularity
  RDMA/rtrs-clt: Check strnlen return len in sysfs mpath_policy_store()
  RDMA/uverbs: Remove flexible arrays from struct *_filter
  RDMA/device: Fix a race between mad_client and cm_client init
  RDMA/hns: Fix mis-modifying default congestion control algorithm
  RDMA/rxe: Remove unused 'iova' parameter from rxe_mr_init_user
  RDMA/srpt: Do not register event handler until srpt device is fully setup
  RDMA/irdma: Remove duplicate assignment
  RDMA/efa: Limit EQs to available MSI-X vectors
  RDMA/mlx5: Delete unused mlx5_ib_copy_pas prototype
  RDMA/cxgb4: Delete unused c4iw_ep_redirect prototype
  RDMA/mana_ib: Introduce mana_ib_install_cq_cb helper function
  RDMA/mana_ib: Introduce mana_ib_get_netdev helper function
  RDMA/mana_ib: Introduce mdev_to_gc helper function
  RDMA/hns: Simplify 'struct hns_roce_hem' allocation
  ...

1 files changed, 19 insertions, 1 deletions

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index ff58058aeadc..bf0df6ee4f78 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -34,6 +34,7 @@ MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("InfiniBand CM");
 MODULE_LICENSE("Dual BSD/GPL");
 
+#define CM_DESTROY_ID_WAIT_TIMEOUT 10000 /* msecs */
 static const char * const ibcm_rej_reason_strs[] = {
 	[IB_CM_REJ_NO_QP]			= "no QP",
 	[IB_CM_REJ_NO_EEC]			= "no EEC",
@@ -1025,10 +1026,20 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv)
 	}
 }
 
+static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id)
+{
+	struct cm_id_private *cm_id_priv;
+
+	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
+	pr_err("%s: cm_id=%p timed out. state=%d refcnt=%d\n", __func__,
+	       cm_id, cm_id->state, refcount_read(&cm_id_priv->refcount));
+}
+
 static void cm_destroy_id(struct ib_cm_id *cm_id, int err)
 {
 	struct cm_id_private *cm_id_priv;
 	struct cm_work *work;
+	int ret;
 
 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
 	spin_lock_irq(&cm_id_priv->lock);
@@ -1135,7 +1146,14 @@ retest:
 
 	xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id));
 	cm_deref_id(cm_id_priv);
-	wait_for_completion(&cm_id_priv->comp);
+	do {
+		ret = wait_for_completion_timeout(&cm_id_priv->comp,
+						  msecs_to_jiffies(
+						  CM_DESTROY_ID_WAIT_TIMEOUT));
+		if (!ret) /* timeout happened */
+			cm_destroy_id_wait_timeout(cm_id);
+	} while (!ret);
+
 	while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
 		cm_free_work(work);