2 files changed, 44 insertions, 16 deletions

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index db1a25fbe..26c66685a 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -33,6 +33,7 @@ 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",
@@ -1056,13 +1057,26 @@ 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,
+						enum ib_cm_state old_state)
+{
+	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 -> %d, refcnt=%d\n", __func__,
+	       cm_id, old_state, 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;
+	enum ib_cm_state old_state;
 	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);
+	old_state = cm_id->state;
 retest:
 	switch (cm_id->state) {
 	case IB_CM_LISTEN:
@@ -1171,7 +1185,14 @@ 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, old_state);
+	} while (!ret);
+
 	while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
 		cm_free_work(work);
 
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 3c29fd04b..94c3bad72 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1686,7 +1686,7 @@ static int assign_client_id(struct ib_client *client)
 {
 	int ret;
 
-	down_write(&clients_rwsem);
+	lockdep_assert_held(&clients_rwsem);
 	/*
 	 * The add/remove callbacks must be called in FIFO/LIFO order. To
 	 * achieve this we assign client_ids so they are sorted in
@@ -1695,14 +1695,11 @@ static int assign_client_id(struct ib_client *client)
 	client->client_id = highest_client_id;
 	ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL);
 	if (ret)
-		goto out;
+		return ret;
 
 	highest_client_id++;
 	xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED);
-
-out:
-	up_write(&clients_rwsem);
-	return ret;
+	return 0;
 }
 
 static void remove_client_id(struct ib_client *client)
@@ -1732,25 +1729,35 @@ int ib_register_client(struct ib_client *client)
 {
 	struct ib_device *device;
 	unsigned long index;
+	bool need_unreg = false;
 	int ret;
 
 	refcount_set(&client->uses, 1);
 	init_completion(&client->uses_zero);
+
+	/*
+	 * The devices_rwsem is held in write mode to ensure that a racing
+	 * ib_register_device() sees a consisent view of clients and devices.
+	 */
+	down_write(&devices_rwsem);
+	down_write(&clients_rwsem);
 	ret = assign_client_id(client);
 	if (ret)
-		return ret;
+		goto out;
 
-	down_read(&devices_rwsem);
+	need_unreg = true;
 	xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) {
 		ret = add_client_context(device, client);
-		if (ret) {
-			up_read(&devices_rwsem);
-			ib_unregister_client(client);
-			return ret;
-		}
+		if (ret)
+			goto out;
 	}
-	up_read(&devices_rwsem);
-	return 0;
+	ret = 0;
+out:
+	up_write(&clients_rwsem);
+	up_write(&devices_rwsem);
+	if (need_unreg && ret)
+		ib_unregister_client(client);
+	return ret;
 }
 EXPORT_SYMBOL(ib_register_client);