1 files changed, 94 insertions, 29 deletions

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5c7371dc8384..c809e8fe648f 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -108,6 +108,7 @@ static int init_crq_queue(struct ibmvnic_adapter *adapter);
 static int send_query_phys_parms(struct ibmvnic_adapter *adapter);
 static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 					 struct ibmvnic_sub_crq_queue *tx_scrq);
+static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter);
 
 struct ibmvnic_stat {
 	char name[ETH_GSTRING_LEN];
@@ -1245,10 +1246,19 @@ static int __ibmvnic_open(struct net_device *netdev)
 	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
 	if (rc) {
 		ibmvnic_napi_disable(adapter);
-		release_resources(adapter);
+		ibmvnic_disable_irqs(adapter);
 		return rc;
 	}
 
+	adapter->tx_queues_active = true;
+
+	/* Since queues were stopped until now, there shouldn't be any
+	 * one in ibmvnic_complete_tx() or ibmvnic_xmit() so maybe we
+	 * don't need the synchronize_rcu()? Leaving it for consistency
+	 * with setting ->tx_queues_active = false.
+	 */
+	synchronize_rcu();
+
 	netif_tx_start_all_queues(netdev);
 
 	if (prev_state == VNIC_CLOSED) {
@@ -1295,7 +1305,6 @@ static int ibmvnic_open(struct net_device *netdev)
 		rc = init_resources(adapter);
 		if (rc) {
 			netdev_err(netdev, "failed to initialize resources\n");
-			release_resources(adapter);
 			goto out;
 		}
 	}
@@ -1312,6 +1321,11 @@ out:
 		adapter->state = VNIC_OPEN;
 		rc = 0;
 	}
+
+	if (rc) {
+		release_resources(adapter);
+	}
+
 	return rc;
 }
 
@@ -1417,6 +1431,14 @@ static void ibmvnic_cleanup(struct net_device *netdev)
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 
 	/* ensure that transmissions are stopped if called by do_reset */
+
+	adapter->tx_queues_active = false;
+
+	/* Ensure complete_tx() and ibmvnic_xmit() see ->tx_queues_active
+	 * update so they don't restart a queue after we stop it below.
+	 */
+	synchronize_rcu();
+
 	if (test_bit(0, &adapter->resetting))
 		netif_tx_disable(netdev);
 	else
@@ -1657,14 +1679,21 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 		tx_buff->skb = NULL;
 		adapter->netdev->stats.tx_dropped++;
 	}
+
 	ind_bufp->index = 0;
+
 	if (atomic_sub_return(entries, &tx_scrq->used) <=
 	    (adapter->req_tx_entries_per_subcrq / 2) &&
-	    __netif_subqueue_stopped(adapter->netdev, queue_num) &&
-	    !test_bit(0, &adapter->resetting)) {
-		netif_wake_subqueue(adapter->netdev, queue_num);
-		netdev_dbg(adapter->netdev, "Started queue %d\n",
-			   queue_num);
+	    __netif_subqueue_stopped(adapter->netdev, queue_num)) {
+		rcu_read_lock();
+
+		if (adapter->tx_queues_active) {
+			netif_wake_subqueue(adapter->netdev, queue_num);
+			netdev_dbg(adapter->netdev, "Started queue %d\n",
+				   queue_num);
+		}
+
+		rcu_read_unlock();
 	}
 }
 
@@ -1719,11 +1748,12 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int index = 0;
 	u8 proto = 0;
 
-	tx_scrq = adapter->tx_scrq[queue_num];
-	txq = netdev_get_tx_queue(netdev, queue_num);
-	ind_bufp = &tx_scrq->ind_buf;
-
-	if (test_bit(0, &adapter->resetting)) {
+	/* If a reset is in progress, drop the packet since
+	 * the scrqs may get torn down. Otherwise use the
+	 * rcu to ensure reset waits for us to complete.
+	 */
+	rcu_read_lock();
+	if (!adapter->tx_queues_active) {
 		dev_kfree_skb_any(skb);
 
 		tx_send_failed++;
@@ -1732,6 +1762,10 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		goto out;
 	}
 
+	tx_scrq = adapter->tx_scrq[queue_num];
+	txq = netdev_get_tx_queue(netdev, queue_num);
+	ind_bufp = &tx_scrq->ind_buf;
+
 	if (ibmvnic_xmit_workarounds(skb, netdev)) {
 		tx_dropped++;
 		tx_send_failed++;
@@ -1739,6 +1773,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
 		goto out;
 	}
+
 	if (skb_is_gso(skb))
 		tx_pool = &adapter->tso_pool[queue_num];
 	else
@@ -1893,6 +1928,7 @@ tx_err:
 		netif_carrier_off(netdev);
 	}
 out:
+	rcu_read_unlock();
 	netdev->stats.tx_dropped += tx_dropped;
 	netdev->stats.tx_bytes += tx_bytes;
 	netdev->stats.tx_packets += tx_packets;
@@ -2552,12 +2588,23 @@ static void __ibmvnic_delayed_reset(struct work_struct *work)
 	__ibmvnic_reset(&adapter->ibmvnic_reset);
 }
 
+static void flush_reset_queue(struct ibmvnic_adapter *adapter)
+{
+	struct list_head *entry, *tmp_entry;
+
+	if (!list_empty(&adapter->rwi_list)) {
+		list_for_each_safe(entry, tmp_entry, &adapter->rwi_list) {
+			list_del(entry);
+			kfree(list_entry(entry, struct ibmvnic_rwi, list));
+		}
+	}
+}
+
 static int ibmvnic_reset(struct ibmvnic_adapter *adapter,
 			 enum ibmvnic_reset_reason reason)
 {
-	struct list_head *entry, *tmp_entry;
-	struct ibmvnic_rwi *rwi, *tmp;
 	struct net_device *netdev = adapter->netdev;
+	struct ibmvnic_rwi *rwi, *tmp;
 	unsigned long flags;
 	int ret;
 
@@ -2600,10 +2647,9 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter,
 	/* if we just received a transport event,
 	 * flush reset queue and process this reset
 	 */
-	if (adapter->force_reset_recovery && !list_empty(&adapter->rwi_list)) {
-		list_for_each_safe(entry, tmp_entry, &adapter->rwi_list)
-			list_del(entry);
-	}
+	if (adapter->force_reset_recovery)
+		flush_reset_queue(adapter);
+
 	rwi->reset_reason = reason;
 	list_add_tail(&rwi->list, &adapter->rwi_list);
 	netdev_dbg(adapter->netdev, "Scheduling reset (reason %s)\n",
@@ -3467,9 +3513,15 @@ restart_loop:
 		    (adapter->req_tx_entries_per_subcrq / 2) &&
 		    __netif_subqueue_stopped(adapter->netdev,
 					     scrq->pool_index)) {
-			netif_wake_subqueue(adapter->netdev, scrq->pool_index);
-			netdev_dbg(adapter->netdev, "Started queue %d\n",
-				   scrq->pool_index);
+			rcu_read_lock();
+			if (adapter->tx_queues_active) {
+				netif_wake_subqueue(adapter->netdev,
+						    scrq->pool_index);
+				netdev_dbg(adapter->netdev,
+					   "Started queue %d\n",
+					   scrq->pool_index);
+			}
+			rcu_read_unlock();
 		}
 	}
 
@@ -5138,9 +5190,9 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			}
 
 			if (!completion_done(&adapter->init_done)) {
-				complete(&adapter->init_done);
 				if (!adapter->init_done_rc)
 					adapter->init_done_rc = -EAGAIN;
+				complete(&adapter->init_done);
 			}
 
 			break;
@@ -5163,6 +5215,13 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			adapter->fw_done_rc = -EIO;
 			complete(&adapter->fw_done);
 		}
+
+		/* if we got here during crq-init, retry crq-init */
+		if (!completion_done(&adapter->init_done)) {
+			adapter->init_done_rc = -EAGAIN;
+			complete(&adapter->init_done);
+		}
+
 		if (!completion_done(&adapter->stats_done))
 			complete(&adapter->stats_done);
 		if (test_bit(0, &adapter->resetting))
@@ -5627,12 +5686,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		goto ibmvnic_dev_file_err;
 
 	netif_carrier_off(netdev);
-	rc = register_netdev(netdev);
-	if (rc) {
-		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
-		goto ibmvnic_register_fail;
-	}
-	dev_info(&dev->dev, "ibmvnic registered\n");
 
 	if (init_success) {
 		adapter->state = VNIC_PROBED;
@@ -5645,6 +5698,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	adapter->wait_for_reset = false;
 	adapter->last_reset_time = jiffies;
+
+	rc = register_netdev(netdev);
+	if (rc) {
+		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
+		goto ibmvnic_register_fail;
+	}
+	dev_info(&dev->dev, "ibmvnic registered\n");
+
 	return 0;
 
 ibmvnic_register_fail:
@@ -5733,10 +5794,14 @@ static ssize_t failover_store(struct device *dev, struct device_attribute *attr,
 		   be64_to_cpu(session_token));
 	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
 				H_SESSION_ERR_DETECTED, session_token, 0, 0);
-	if (rc)
+	if (rc) {
 		netdev_err(netdev,
 			   "H_VIOCTL initiated failover failed, rc %ld\n",
 			   rc);
+		goto last_resort;
+	}
+
+	return count;
 
 last_resort:
 	netdev_dbg(netdev, "Trying to send CRQ_CMD, the last resort\n");