Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 70 insertions, 14 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 35e9c8a330..963e936da5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -351,10 +351,12 @@ struct ipoib_dev_priv {
 	struct workqueue_struct *wq;
 	struct delayed_work mcast_task;
 	struct work_struct carrier_on_task;
+	struct work_struct reschedule_napi_work;
 	struct work_struct flush_light;
 	struct work_struct flush_normal;
 	struct work_struct flush_heavy;
 	struct work_struct restart_task;
+	struct work_struct tx_timeout_work;
 	struct delayed_work ah_reap_task;
 	struct delayed_work neigh_reap_task;
 	struct ib_device *ca;
@@ -499,6 +501,7 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	       struct ib_ah *address, u32 dqpn);
 void ipoib_reap_ah(struct work_struct *work);
 
+void ipoib_napi_schedule_work(struct work_struct *work);
 struct ipoib_path *__path_find(struct net_device *dev, void *gid);
 void ipoib_mark_paths_invalid(struct net_device *dev);
 void ipoib_flush_paths(struct net_device *dev);
@@ -510,6 +513,7 @@ void ipoib_ib_tx_timer_func(struct timer_list *t);
 void ipoib_ib_dev_flush_light(struct work_struct *work);
 void ipoib_ib_dev_flush_normal(struct work_struct *work);
 void ipoib_ib_dev_flush_heavy(struct work_struct *work);
+void ipoib_ib_tx_timeout_work(struct work_struct *work);
 void ipoib_pkey_event(struct work_struct *work);
 void ipoib_ib_dev_cleanup(struct net_device *dev);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 7f84d9866c..5cde275daa 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -531,11 +531,35 @@ void ipoib_ib_rx_completion(struct ib_cq *cq, void *ctx_ptr)
 	napi_schedule(&priv->recv_napi);
 }
 
+/* The function will force napi_schedule */
+void ipoib_napi_schedule_work(struct work_struct *work)
+{
+	struct ipoib_dev_priv *priv =
+		container_of(work, struct ipoib_dev_priv, reschedule_napi_work);
+	bool ret;
+
+	do {
+		ret = napi_schedule(&priv->send_napi);
+		if (!ret)
+			msleep(3);
+	} while (!ret && netif_queue_stopped(priv->dev) &&
+		 test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags));
+}
+
 void ipoib_ib_tx_completion(struct ib_cq *cq, void *ctx_ptr)
 {
 	struct ipoib_dev_priv *priv = ctx_ptr;
+	bool ret;
 
-	napi_schedule(&priv->send_napi);
+	ret = napi_schedule(&priv->send_napi);
+	/*
+	 * if the queue is closed the driver must be able to schedule napi,
+	 * otherwise we can end with closed queue forever, because no new
+	 * packets to send and napi callback might not get new event after
+	 * its re-arm of the napi.
+	 */
+	if (!ret && netif_queue_stopped(priv->dev))
+		schedule_work(&priv->reschedule_napi_work);
 }
 
 static inline int post_send(struct ipoib_dev_priv *priv,
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 967004ccad..7a5be705d7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1200,7 +1200,34 @@ static void ipoib_timeout(struct net_device *dev, unsigned int txqueue)
 		   netif_queue_stopped(dev), priv->tx_head, priv->tx_tail,
 		   priv->global_tx_head, priv->global_tx_tail);
 
-	/* XXX reset QP, etc. */
+
+	schedule_work(&priv->tx_timeout_work);
+}
+
+void ipoib_ib_tx_timeout_work(struct work_struct *work)
+{
+	struct ipoib_dev_priv *priv = container_of(work,
+						   struct ipoib_dev_priv,
+						   tx_timeout_work);
+	int err;
+
+	rtnl_lock();
+
+	if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+		goto unlock;
+
+	ipoib_stop(priv->dev);
+	err = ipoib_open(priv->dev);
+	if (err) {
+		ipoib_warn(priv, "ipoib_open failed recovering from a tx_timeout, err(%d).\n",
+				err);
+		goto unlock;
+	}
+
+	netif_tx_wake_all_queues(priv->dev);
+unlock:
+	rtnl_unlock();
+
 }
 
 static int ipoib_hard_header(struct sk_buff *skb,
@@ -2112,7 +2139,7 @@ void ipoib_setup_common(struct net_device *dev)
 
 	ipoib_set_ethtool_ops(dev);
 
-	dev->watchdog_timeo	 = HZ;
+	dev->watchdog_timeo	 = 10 * HZ;
 
 	dev->flags		|= IFF_BROADCAST | IFF_MULTICAST;
 
@@ -2150,10 +2177,12 @@ static void ipoib_build_priv(struct net_device *dev)
 
 	INIT_DELAYED_WORK(&priv->mcast_task,   ipoib_mcast_join_task);
 	INIT_WORK(&priv->carrier_on_task, ipoib_mcast_carrier_on_task);
+	INIT_WORK(&priv->reschedule_napi_work, ipoib_napi_schedule_work);
 	INIT_WORK(&priv->flush_light,   ipoib_ib_dev_flush_light);
 	INIT_WORK(&priv->flush_normal,   ipoib_ib_dev_flush_normal);
 	INIT_WORK(&priv->flush_heavy,   ipoib_ib_dev_flush_heavy);
 	INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task);
+	INIT_WORK(&priv->tx_timeout_work, ipoib_ib_tx_timeout_work);
 	INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah);
 	INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh);
 }
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index d967d55324..68429a5f79 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -182,7 +182,7 @@ enum iser_data_dir {
  *
  * @sg:           pointer to the sg list
  * @size:         num entries of this sg
- * @data_len:     total beffer byte len
+ * @data_len:     total buffer byte len
  * @dma_nents:    returned by dma_map_sg
  */
 struct iser_data_buf {
@@ -299,7 +299,6 @@ struct ib_conn;
  *
  * @ib_device:     RDMA device
  * @pd:            Protection Domain for this device
- * @mr:            Global DMA memory region
  * @event_handler: IB events handle routine
  * @ig_list:	   entry in devices list
  * @refcount:      Reference counter, dominated by open iser connections
@@ -387,7 +386,7 @@ struct ib_conn {
  *                    to max number of post recvs
  * @max_cmds:         maximum cmds allowed for this connection
  * @name:             connection peer portal
- * @release_work:     deffered work for release job
+ * @release_work:     deferred work for release job
  * @state_mutex:      protects iser onnection state
  * @stop_completion:  conn_stop completion
  * @ib_completion:    RDMA cleanup completion
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 7f3167ce29..88106cf5ce 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1391,9 +1391,9 @@ static int alloc_path_reqs(struct rtrs_clt_path *clt_path)
 				      clt_path->max_pages_per_mr);
 		if (IS_ERR(req->mr)) {
 			err = PTR_ERR(req->mr);
+			pr_err("Failed to alloc clt_path->max_pages_per_mr %d: %pe\n",
+			       clt_path->max_pages_per_mr, req->mr);
 			req->mr = NULL;
-			pr_err("Failed to alloc clt_path->max_pages_per_mr %d\n",
-			       clt_path->max_pages_per_mr);
 			goto out;
 		}
 
@@ -2025,6 +2025,8 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id,
 		/*
 		 * Device removal is a special case.  Queue close and return 0.
 		 */
+		rtrs_wrn_rl(s, "CM event: %s, status: %d\n", rdma_event_msg(ev->event),
+			    ev->status);
 		rtrs_clt_close_conns(clt_path, false);
 		return 0;
 	default:
@@ -2058,10 +2060,8 @@ static int create_cm(struct rtrs_clt_con *con)
 			       clt_path->s.dst_addr.ss_family == AF_IB ?
 			       RDMA_PS_IB : RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(cm_id)) {
-		err = PTR_ERR(cm_id);
-		rtrs_err(s, "Failed to create CM ID, err: %d\n", err);
-
-		return err;
+		rtrs_err(s, "Failed to create CM ID, err: %pe\n", cm_id);
+		return PTR_ERR(cm_id);
 	}
 	con->c.cm_id = cm_id;
 	con->cm_err = 0;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c
index d80edfffd2..4e17d546d4 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs.c
@@ -242,8 +242,8 @@ static int create_cq(struct rtrs_con *con, int cq_vector, int nr_cqe,
 		cq = ib_cq_pool_get(cm_id->device, nr_cqe, cq_vector, poll_ctx);
 
 	if (IS_ERR(cq)) {
-		rtrs_err(con->path, "Creating completion queue failed, errno: %ld\n",
-			  PTR_ERR(cq));
+		rtrs_err(con->path, "Creating completion queue failed, errno: %pe\n",
+			  cq);
 		return PTR_ERR(cq);
 	}
 	con->cq = cq;