Merge branch 's390-qeth-fixes-2021-09-21'

Julian Wiedmann says:

====================
s390/qeth: fixes 2021-09-21

This brings two fixes for deadlocks when a device is removed while it
has certain types of async work pending. And one additional fix for a
missing NULL check in an error case.
====================

Link: https://lore.kernel.org/r/20210921145217.1584654-1-jwi@linux.ibm.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

arch/s390/include/asm/ccwgroup.h

@@ -55,7 +55,7 @@ int ccwgroup_create_dev(struct device *root, struct ccwgroup_driver *gdrv,
 			int num_devices, const char *buf);
 
 extern int ccwgroup_set_online(struct ccwgroup_device *gdev);
-extern int ccwgroup_set_offline(struct ccwgroup_device *gdev);
+int ccwgroup_set_offline(struct ccwgroup_device *gdev, bool call_gdrv);
 
 extern int ccwgroup_probe_ccwdev(struct ccw_device *cdev);
 extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev);

drivers/s390/cio/ccwgroup.c

@@ -77,12 +77,13 @@ EXPORT_SYMBOL(ccwgroup_set_online);
 /**
  * ccwgroup_set_offline() - disable a ccwgroup device
  * @gdev: target ccwgroup device
+ * @call_gdrv: Call the registered gdrv set_offline function
  *
  * This function attempts to put the ccwgroup device into the offline state.
  * Returns:
  *  %0 on success and a negative error value on failure.
  */
-int ccwgroup_set_offline(struct ccwgroup_device *gdev)
+int ccwgroup_set_offline(struct ccwgroup_device *gdev, bool call_gdrv)
 {
 	struct ccwgroup_driver *gdrv = to_ccwgroupdrv(gdev->dev.driver);
 	int ret = -EINVAL;
@@ -91,11 +92,16 @@ int ccwgroup_set_offline(struct ccwgroup_device *gdev)
 		return -EAGAIN;
 	if (gdev->state == CCWGROUP_OFFLINE)
 		goto out;
+	if (!call_gdrv) {
+		ret = 0;
+		goto offline;
+	}
 	if (gdrv->set_offline)
 		ret = gdrv->set_offline(gdev);
 	if (ret)
 		goto out;
 
+offline:
 	gdev->state = CCWGROUP_OFFLINE;
 out:
 	atomic_set(&gdev->onoff, 0);
@@ -124,7 +130,7 @@ static ssize_t ccwgroup_online_store(struct device *dev,
 	if (value == 1)
 		ret = ccwgroup_set_online(gdev);
 	else if (value == 0)
-		ret = ccwgroup_set_offline(gdev);
+		ret = ccwgroup_set_offline(gdev, true);
 	else
 		ret = -EINVAL;
 out:

drivers/s390/net/qeth_core.h

@@ -858,7 +858,6 @@ struct qeth_card {
 	struct napi_struct napi;
 	struct qeth_rx rx;
 	struct delayed_work buffer_reclaim_work;
-	struct work_struct close_dev_work;
 };
 
 static inline bool qeth_card_hw_is_reachable(struct qeth_card *card)

drivers/s390/net/qeth_core_main.c

@@ -70,15 +70,6 @@ static void qeth_issue_next_read_cb(struct qeth_card *card,
 static int qeth_qdio_establish(struct qeth_card *);
 static void qeth_free_qdio_queues(struct qeth_card *card);
 
-static void qeth_close_dev_handler(struct work_struct *work)
-{
-	struct qeth_card *card;
-
-	card = container_of(work, struct qeth_card, close_dev_work);
-	QETH_CARD_TEXT(card, 2, "cldevhdl");
-	ccwgroup_set_offline(card->gdev);
-}
-
 static const char *qeth_get_cardname(struct qeth_card *card)
 {
 	if (IS_VM_NIC(card)) {
@@ -202,6 +193,9 @@ static void qeth_clear_working_pool_list(struct qeth_card *card)
 				 &card->qdio.in_buf_pool.entry_list, list)
 		list_del(&pool_entry->list);
 
+	if (!queue)
+		return;
+
 	for (i = 0; i < ARRAY_SIZE(queue->bufs); i++)
 		queue->bufs[i].pool_entry = NULL;
 }
@@ -792,10 +786,12 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 	case IPA_CMD_STOPLAN:
 		if (cmd->hdr.return_code == IPA_RC_VEPA_TO_VEB_TRANSITION) {
 			dev_err(&card->gdev->dev,
-				"Interface %s is down because the adjacent port is no longer in reflective relay mode\n",
+				"Adjacent port of interface %s is no longer in reflective relay mode, trigger recovery\n",
 				netdev_name(card->dev));
-			schedule_work(&card->close_dev_work);
+			/* Set offline, then probably fail to set online: */
+			qeth_schedule_recovery(card);
 		} else {
+			/* stay online for subsequent STARTLAN */
 			dev_warn(&card->gdev->dev,
 				 "The link for interface %s on CHPID 0x%X failed\n",
 				 netdev_name(card->dev), card->info.chpid);
@@ -1537,7 +1533,6 @@ static void qeth_setup_card(struct qeth_card *card)
 	INIT_LIST_HEAD(&card->ipato.entries);
 	qeth_init_qdio_info(card);
 	INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
-	INIT_WORK(&card->close_dev_work, qeth_close_dev_handler);
 	hash_init(card->rx_mode_addrs);
 	hash_init(card->local_addrs4);
 	hash_init(card->local_addrs6);
@@ -5519,7 +5514,8 @@ static int qeth_do_reset(void *data)
 		dev_info(&card->gdev->dev,
 			 "Device successfully recovered!\n");
 	} else {
-		ccwgroup_set_offline(card->gdev);
+		qeth_set_offline(card, disc, true);
+		ccwgroup_set_offline(card->gdev, false);
 		dev_warn(&card->gdev->dev,
 			 "The qeth device driver failed to recover an error on the device\n");
 	}

drivers/s390/net/qeth_l2_main.c

@@ -2307,7 +2307,6 @@ static void qeth_l2_remove_device(struct ccwgroup_device *gdev)
 	if (gdev->state == CCWGROUP_ONLINE)
 		qeth_set_offline(card, card->discipline, false);
 
-	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED) {
 		priv = netdev_priv(card->dev);
 		if (priv->brport_features & BR_LEARNING_SYNC) {

drivers/s390/net/qeth_l3_main.c

@@ -1969,7 +1969,6 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 	if (cgdev->state == CCWGROUP_ONLINE)
 		qeth_set_offline(card, card->discipline, false);
 
-	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(card->dev);