ibmvnic: Updated reset handling

The ibmvnic driver has multiple handlers for resetting the driver
depending on the reason the reset is needed (failover, lpm,
fatal erors,...). All of the reset handlers do essentially the same
thing, this patch moves this work to a common reset handler.

By doing this we also allow the driver to better handle situations
where we can get a reset while handling a reset.

The updated reset handling works by adding a reset work item to the
list of resets and then scheduling work to perform the reset. This
step is necessary because we can receive a reset in interrupt context
and we want to handle the reset out of interrupt context.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/ibm/ibmvnic.c

@@ -194,7 +194,8 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
 	if (!ltb->buff)
 		return;
 
-	if (!adapter->failover)
+	if (adapter->reset_reason != VNIC_RESET_FAILOVER &&
+	    adapter->reset_reason != VNIC_RESET_MOBILITY)
 		send_request_unmap(adapter, ltb->map_id);
 	dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
 }
@@ -292,9 +293,6 @@ static void replenish_pools(struct ibmvnic_adapter *adapter)
 {
 	int i;
 
-	if (adapter->migrated)
-		return;
-
 	adapter->replenish_task_cycles++;
 	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
 	     i++) {
@@ -569,11 +567,6 @@ static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state)
 	bool resend;
 	int rc;
 
-	if (adapter->logical_link_state == link_state) {
-		netdev_dbg(netdev, "Link state already %d\n", link_state);
-		return 0;
-	}
-
 	netdev_err(netdev, "setting link state %d\n", link_state);
 	memset(&crq, 0, sizeof(crq));
 	crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
@@ -664,27 +657,13 @@ static int init_resources(struct ibmvnic_adapter *adapter)
 	return rc;
 }
 
-static int ibmvnic_open(struct net_device *netdev)
+static int __ibmvnic_open(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	enum vnic_state prev_state = adapter->state;
 	int i, rc;
 
 	adapter->state = VNIC_OPENING;
-
-	if (adapter->state == VNIC_CLOSED) {
-		rc = ibmvnic_init(adapter);
-		if (rc)
-			return rc;
-	}
-
-	rc = ibmvnic_login(netdev);
-	if (rc)
-		return rc;
-
-	rc = init_resources(adapter);
-	if (rc)
-		return rc;
-
 	replenish_pools(adapter);
 
 	for (i = 0; i < adapter->req_rx_queues; i++)
@@ -693,22 +672,65 @@ static int ibmvnic_open(struct net_device *netdev)
 	/* We're ready to receive frames, enable the sub-crq interrupts and
 	 * set the logical link state to up
 	 */
-	for (i = 0; i < adapter->req_rx_queues; i++)
+	for (i = 0; i < adapter->req_rx_queues; i++) {
+		if (prev_state == VNIC_CLOSED)
+			enable_irq(adapter->rx_scrq[i]->irq);
+		else
 			enable_scrq_irq(adapter, adapter->rx_scrq[i]);
+	}
 
-	for (i = 0; i < adapter->req_tx_queues; i++)
+	for (i = 0; i < adapter->req_tx_queues; i++) {
+		if (prev_state == VNIC_CLOSED)
+			enable_irq(adapter->tx_scrq[i]->irq);
+		else
 			enable_scrq_irq(adapter, adapter->tx_scrq[i]);
+	}
 
 	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
 	if (rc) {
 		for (i = 0; i < adapter->req_rx_queues; i++)
 			napi_disable(&adapter->napi[i]);
 		release_resources(adapter);
-	} else {
+		return rc;
+	}
+
 	netif_tx_start_all_queues(netdev);
+
+	if (prev_state == VNIC_CLOSED) {
+		for (i = 0; i < adapter->req_rx_queues; i++)
+			napi_schedule(&adapter->napi[i]);
+	}
+
 	adapter->state = VNIC_OPEN;
+	return rc;
+}
+
+static int ibmvnic_open(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	int rc;
+
+	mutex_lock(&adapter->reset_lock);
+
+	if (adapter->state != VNIC_CLOSED) {
+		rc = ibmvnic_login(netdev);
+		if (rc) {
+			mutex_unlock(&adapter->reset_lock);
+			return rc;
 		}
 
+		rc = init_resources(adapter);
+		if (rc) {
+			netdev_err(netdev, "failed to initialize resources\n");
+			release_resources(adapter);
+			mutex_unlock(&adapter->reset_lock);
+			return rc;
+		}
+	}
+
+	rc = __ibmvnic_open(netdev);
+	mutex_unlock(&adapter->reset_lock);
+
 	return rc;
 }
 
@@ -729,13 +751,14 @@ static void disable_sub_crqs(struct ibmvnic_adapter *adapter)
 	}
 }
 
-static int ibmvnic_close(struct net_device *netdev)
+static int __ibmvnic_close(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	int rc = 0;
 	int i;
 
 	adapter->state = VNIC_CLOSING;
+	netif_tx_stop_all_queues(netdev);
 	disable_sub_crqs(adapter);
 
 	if (adapter->napi) {
@@ -743,17 +766,24 @@ static int ibmvnic_close(struct net_device *netdev)
 			napi_disable(&adapter->napi[i]);
 	}
 
-	if (!adapter->failover)
-		netif_tx_stop_all_queues(netdev);
-
 	rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_DN);
 
-	release_resources(adapter);
-
 	adapter->state = VNIC_CLOSED;
 	return rc;
 }
 
+static int ibmvnic_close(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	int rc;
+
+	mutex_lock(&adapter->reset_lock);
+	rc = __ibmvnic_close(netdev);
+	mutex_unlock(&adapter->reset_lock);
+
+	return rc;
+}
+
 /**
  * build_hdr_data - creates L2/L3/L4 header data buffer
  * @hdr_field - bitfield determining needed headers
@@ -915,7 +945,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
 				   be32_to_cpu(adapter->login_rsp_buf->
 					       off_txsubm_subcrqs));
-	if (adapter->migrated) {
+	if (adapter->resetting) {
 		if (!netif_subqueue_stopped(netdev, skb))
 			netif_stop_subqueue(netdev, queue_num);
 		dev_kfree_skb_any(skb);
@@ -1107,18 +1137,185 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p)
 	return 0;
 }
 
-static void ibmvnic_tx_timeout(struct net_device *dev)
+/**
+ * do_reset returns zero if we are able to keep processing reset events, or
+ * non-zero if we hit a fatal error and must halt.
+ */
+static int do_reset(struct ibmvnic_adapter *adapter,
+		    struct ibmvnic_rwi *rwi, u32 reset_state)
 {
-	struct ibmvnic_adapter *adapter = netdev_priv(dev);
-	int rc;
+	struct net_device *netdev = adapter->netdev;
+	int i, rc;
+
+	netif_carrier_off(netdev);
+	adapter->reset_reason = rwi->reset_reason;
 
-	/* Adapter timed out, resetting it */
+	if (rwi->reset_reason == VNIC_RESET_MOBILITY) {
+		rc = ibmvnic_reenable_crq_queue(adapter);
+		if (rc)
+			return 0;
+	}
+
+	rc = __ibmvnic_close(netdev);
+	if (rc)
+		return rc;
+
+	/* remove the closed state so when we call open it appears
+	 * we are coming from the probed state.
+	 */
+	adapter->state = VNIC_PROBED;
+
+	release_resources(adapter);
 	release_sub_crqs(adapter);
-	rc = ibmvnic_reset_crq(adapter);
+	release_crq_queue(adapter);
+
+	rc = ibmvnic_init(adapter);
 	if (rc)
-		dev_err(&adapter->vdev->dev, "Adapter timeout, reset failed\n");
+		return 0;
+
+	/* If the adapter was in PROBE state prior to the reset, exit here. */
+	if (reset_state == VNIC_PROBED)
+		return 0;
+
+	rc = ibmvnic_login(netdev);
+	if (rc) {
+		adapter->state = VNIC_PROBED;
+		return 0;
+	}
+
+	rtnl_lock();
+	rc = init_resources(adapter);
+	rtnl_unlock();
+	if (rc)
+		return rc;
+
+	if (reset_state == VNIC_CLOSED)
+		return 0;
+
+	rc = __ibmvnic_open(netdev);
+	if (rc) {
+		if (list_empty(&adapter->rwi_list))
+			adapter->state = VNIC_CLOSED;
 		else
-		ibmvnic_send_crq_init(adapter);
+			adapter->state = reset_state;
+
+		return 0;
+	}
+
+	netif_carrier_on(netdev);
+
+	/* kick napi */
+	for (i = 0; i < adapter->req_rx_queues; i++)
+		napi_schedule(&adapter->napi[i]);
+
+	return 0;
+}
+
+static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_rwi *rwi;
+
+	mutex_lock(&adapter->rwi_lock);
+
+	if (!list_empty(&adapter->rwi_list)) {
+		rwi = list_first_entry(&adapter->rwi_list, struct ibmvnic_rwi,
+				       list);
+		list_del(&rwi->list);
+	} else {
+		rwi = NULL;
+	}
+
+	mutex_unlock(&adapter->rwi_lock);
+	return rwi;
+}
+
+static void free_all_rwi(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_rwi *rwi;
+
+	rwi = get_next_rwi(adapter);
+	while (rwi) {
+		kfree(rwi);
+		rwi = get_next_rwi(adapter);
+	}
+}
+
+static void __ibmvnic_reset(struct work_struct *work)
+{
+	struct ibmvnic_rwi *rwi;
+	struct ibmvnic_adapter *adapter;
+	struct net_device *netdev;
+	u32 reset_state;
+	int rc;
+
+	adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset);
+	netdev = adapter->netdev;
+
+	mutex_lock(&adapter->reset_lock);
+	adapter->resetting = true;
+	reset_state = adapter->state;
+
+	rwi = get_next_rwi(adapter);
+	while (rwi) {
+		rc = do_reset(adapter, rwi, reset_state);
+		kfree(rwi);
+		if (rc)
+			break;
+
+		rwi = get_next_rwi(adapter);
+	}
+
+	if (rc) {
+		free_all_rwi(adapter);
+		return;
+	}
+
+	adapter->resetting = false;
+	mutex_unlock(&adapter->reset_lock);
+}
+
+static void ibmvnic_reset(struct ibmvnic_adapter *adapter,
+			  enum ibmvnic_reset_reason reason)
+{
+	struct ibmvnic_rwi *rwi, *tmp;
+	struct net_device *netdev = adapter->netdev;
+	struct list_head *entry;
+
+	if (adapter->state == VNIC_REMOVING ||
+	    adapter->state == VNIC_REMOVED) {
+		netdev_dbg(netdev, "Adapter removing, skipping reset\n");
+		return;
+	}
+
+	mutex_lock(&adapter->rwi_lock);
+
+	list_for_each(entry, &adapter->rwi_list) {
+		tmp = list_entry(entry, struct ibmvnic_rwi, list);
+		if (tmp->reset_reason == reason) {
+			netdev_err(netdev, "Matching reset found, skipping\n");
+			mutex_unlock(&adapter->rwi_lock);
+			return;
+		}
+	}
+
+	rwi = kzalloc(sizeof(*rwi), GFP_KERNEL);
+	if (!rwi) {
+		mutex_unlock(&adapter->rwi_lock);
+		ibmvnic_close(netdev);
+		return;
+	}
+
+	rwi->reset_reason = reason;
+	list_add_tail(&rwi->list, &adapter->rwi_list);
+	mutex_unlock(&adapter->rwi_lock);
+	schedule_work(&adapter->ibmvnic_reset);
+}
+
+static void ibmvnic_tx_timeout(struct net_device *dev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(dev);
+
+	ibmvnic_reset(adapter, VNIC_RESET_TIMEOUT);
 }
 
 static void remove_buff_from_pool(struct ibmvnic_adapter *adapter,
@@ -2000,18 +2197,6 @@ static int ibmvnic_send_crq_init(struct ibmvnic_adapter *adapter)
 	return ibmvnic_send_crq(adapter, &crq);
 }
 
-static int ibmvnic_send_crq_init_complete(struct ibmvnic_adapter *adapter)
-{
-	union ibmvnic_crq crq;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.generic.first = IBMVNIC_CRQ_INIT_CMD;
-	crq.generic.cmd = IBMVNIC_CRQ_INIT_COMPLETE;
-	netdev_dbg(adapter->netdev, "Sending CRQ init complete\n");
-
-	return ibmvnic_send_crq(adapter, &crq);
-}
-
 static int send_version_xchg(struct ibmvnic_adapter *adapter)
 {
 	union ibmvnic_crq crq;
@@ -2509,6 +2694,9 @@ static void handle_error_indication(union ibmvnic_crq *crq,
 
 	if (be32_to_cpu(crq->error_indication.error_id))
 		request_error_information(adapter, crq);
+
+	if (crq->error_indication.flags & IBMVNIC_FATAL_ERROR)
+		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
 }
 
 static void handle_change_mac_rsp(union ibmvnic_crq *crq,
@@ -2897,26 +3085,6 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 	}
 }
 
-static void ibmvnic_xport_event(struct work_struct *work)
-{
-	struct ibmvnic_adapter *adapter = container_of(work,
-						       struct ibmvnic_adapter,
-						       ibmvnic_xport);
-	struct device *dev = &adapter->vdev->dev;
-	long rc;
-
-	release_sub_crqs(adapter);
-	if (adapter->migrated) {
-		rc = ibmvnic_reenable_crq_queue(adapter);
-		if (rc)
-			dev_err(dev, "Error after enable rc=%ld\n", rc);
-		adapter->migrated = false;
-		rc = ibmvnic_send_crq_init(adapter);
-		if (rc)
-			dev_err(dev, "Error sending init rc=%ld\n", rc);
-	}
-}
-
 static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			       struct ibmvnic_adapter *adapter)
 {
@@ -2934,12 +3102,6 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		switch (gen_crq->cmd) {
 		case IBMVNIC_CRQ_INIT:
 			dev_info(dev, "Partner initialized\n");
-			/* Send back a response */
-			rc = ibmvnic_send_crq_init_complete(adapter);
-			if (!rc)
-				schedule_work(&adapter->vnic_crq_init);
-			else
-				dev_err(dev, "Can't send initrsp rc=%ld\n", rc);
 			break;
 		case IBMVNIC_CRQ_INIT_COMPLETE:
 			dev_info(dev, "Partner initialization complete\n");
@@ -2950,19 +3112,18 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		}
 		return;
 	case IBMVNIC_CRQ_XPORT_EVENT:
+		netif_carrier_off(netdev);
 		if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) {
-			dev_info(dev, "Re-enabling adapter\n");
-			adapter->migrated = true;
-			schedule_work(&adapter->ibmvnic_xport);
+			dev_info(dev, "Migrated, re-enabling adapter\n");
+			ibmvnic_reset(adapter, VNIC_RESET_MOBILITY);
 		} else if (gen_crq->cmd == IBMVNIC_DEVICE_FAILOVER) {
 			dev_info(dev, "Backing device failover detected\n");
-			netif_carrier_off(netdev);
-			adapter->failover = true;
+			ibmvnic_reset(adapter, VNIC_RESET_FAILOVER);
 		} else {
 			/* The adapter lost the connection */
 			dev_err(dev, "Virtual Adapter failed (rc=%d)\n",
 				gen_crq->cmd);
-			schedule_work(&adapter->ibmvnic_xport);
+			ibmvnic_reset(adapter, VNIC_RESET_FATAL);
 		}
 		return;
 	case IBMVNIC_CRQ_CMD_RSP:
@@ -3243,64 +3404,6 @@ static int init_crq_queue(struct ibmvnic_adapter *adapter)
 	return retrc;
 }
 
-static void handle_crq_init_rsp(struct work_struct *work)
-{
-	struct ibmvnic_adapter *adapter = container_of(work,
-						       struct ibmvnic_adapter,
-						       vnic_crq_init);
-	struct device *dev = &adapter->vdev->dev;
-	struct net_device *netdev = adapter->netdev;
-	unsigned long timeout = msecs_to_jiffies(30000);
-	bool restart = false;
-	int rc;
-
-	if (adapter->failover) {
-		release_sub_crqs(adapter);
-		if (netif_running(netdev)) {
-			netif_tx_disable(netdev);
-			ibmvnic_close(netdev);
-			restart = true;
-		}
-	}
-
-	reinit_completion(&adapter->init_done);
-	send_version_xchg(adapter);
-	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
-		dev_err(dev, "Passive init timeout\n");
-		goto task_failed;
-	}
-
-	netdev->mtu = adapter->req_mtu - ETH_HLEN;
-
-	if (adapter->failover) {
-		adapter->failover = false;
-		if (restart) {
-			rc = ibmvnic_open(netdev);
-			if (rc)
-				goto restart_failed;
-		}
-		netif_carrier_on(netdev);
-		return;
-	}
-
-	rc = register_netdev(netdev);
-	if (rc) {
-		dev_err(dev,
-			"failed to register netdev rc=%d\n", rc);
-		goto register_failed;
-	}
-	dev_info(dev, "ibmvnic registered\n");
-
-	return;
-
-restart_failed:
-	dev_err(dev, "Failed to restart ibmvnic, rc=%d\n", rc);
-register_failed:
-	release_sub_crqs(adapter);
-task_failed:
-	dev_err(dev, "Passive initialization was not successful\n");
-}
-
 static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
@@ -3359,7 +3462,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	dev_set_drvdata(&dev->dev, netdev);
 	adapter->vdev = dev;
 	adapter->netdev = netdev;
-	adapter->failover = false;
 
 	ether_addr_copy(adapter->mac_addr, mac_addr_p);
 	ether_addr_copy(netdev->dev_addr, adapter->mac_addr);
@@ -3368,14 +3470,17 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	netdev->ethtool_ops = &ibmvnic_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
 
-	INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp);
-	INIT_WORK(&adapter->ibmvnic_xport, ibmvnic_xport_event);
-
 	spin_lock_init(&adapter->stats_lock);
 
 	INIT_LIST_HEAD(&adapter->errors);
 	spin_lock_init(&adapter->error_list_lock);
 
+	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
+	INIT_LIST_HEAD(&adapter->rwi_list);
+	mutex_init(&adapter->reset_lock);
+	mutex_init(&adapter->rwi_lock);
+	adapter->resetting = false;
+
 	rc = ibmvnic_init(adapter);
 	if (rc) {
 		free_netdev(netdev);
@@ -3403,6 +3508,7 @@ static int ibmvnic_remove(struct vio_dev *dev)
 
 	adapter->state = VNIC_REMOVING;
 	unregister_netdev(netdev);
+	mutex_lock(&adapter->reset_lock);
 
 	release_resources(adapter);
 	release_sub_crqs(adapter);
@@ -3410,6 +3516,7 @@ static int ibmvnic_remove(struct vio_dev *dev)
 
 	adapter->state = VNIC_REMOVED;
 
+	mutex_unlock(&adapter->reset_lock);
 	free_netdev(netdev);
 	dev_set_drvdata(&dev->dev, NULL);
 

drivers/net/ethernet/ibm/ibmvnic.h

@@ -922,6 +922,16 @@ enum vnic_state {VNIC_PROBING = 1,
 		 VNIC_REMOVING,
 		 VNIC_REMOVED};
 
+enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1,
+			   VNIC_RESET_MOBILITY,
+			   VNIC_RESET_FATAL,
+			   VNIC_RESET_TIMEOUT};
+
+struct ibmvnic_rwi {
+	enum ibmvnic_reset_reason reset_reason;
+	struct list_head list;
+};
+
 struct ibmvnic_adapter {
 	struct vio_dev *vdev;
 	struct net_device *netdev;
@@ -931,7 +941,6 @@ struct ibmvnic_adapter {
 	dma_addr_t ip_offload_tok;
 	struct ibmvnic_control_ip_offload_buffer ip_offload_ctrl;
 	dma_addr_t ip_offload_ctrl_tok;
-	bool migrated;
 	u32 msg_enable;
 
 	/* Statistics */
@@ -1015,9 +1024,11 @@ struct ibmvnic_adapter {
 	__be64 tx_rx_desc_req;
 	u8 map_id;
 
-	struct work_struct vnic_crq_init;
-	struct work_struct ibmvnic_xport;
 	struct tasklet_struct tasklet;
-	bool failover;
 	enum vnic_state state;
+	enum ibmvnic_reset_reason reset_reason;
+	struct mutex reset_lock, rwi_lock;
+	struct list_head rwi_list;
+	struct work_struct ibmvnic_reset;
+	bool resetting;
 };