IPoIB uninit

index e255a7e5a4c3..9eebb705d994 100644
@@ -95,7 +95,6 @@ enum {
 	IPOIB_NEIGH_TBL_FLUSH	  = 12,
 	IPOIB_FLAG_DEV_ADDR_SET	  = 13,
 	IPOIB_FLAG_DEV_ADDR_CTRL  = 14,
-	IPOIB_FLAG_GOING_DOWN	  = 15,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 

index 8b44f33c7ae0..83fa402e5d03 100644
@@ -1516,9 +1516,6 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 	int ret;
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 
-	if (test_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags))
-		return -EPERM;
-
 	if (!mutex_trylock(&priv->sysfs_mutex))
 		return restart_syscall();
 

@@ -1527,6 +1524,12 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 		return restart_syscall();
 	}
 
+	if (dev->reg_state != NETREG_REGISTERED) {
+		rtnl_unlock();
+		mutex_unlock(&priv->sysfs_mutex);
+		return -EPERM;
+	}
+
 	ret = ipoib_set_mode(dev, buf);
 
 	/* The assumption is that the function ipoib_set_mode returned

index 82f0e3869b04..7ca9013bf05c 100644
@@ -2406,9 +2406,6 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 		ib_unregister_event_handler(&priv->event_handler);
 		flush_workqueue(ipoib_workqueue);
 
-		/* mark interface in the middle of destruction */
-		set_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags);
-
 		rtnl_lock();
 		dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
 		rtnl_unlock();

index b067ad5e4c7e..1b7bfd500893 100644
@@ -127,9 +127,6 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 
 	ppriv = ipoib_priv(pdev);
 
-	if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
-		return -EPERM;
-
 	snprintf(intf_name, sizeof(intf_name), "%s.%04x",
 		 ppriv->dev->name, pkey);
 

@@ -141,6 +138,12 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 		return restart_syscall();
 	}
 
+	if (pdev->reg_state != NETREG_REGISTERED) {
+		rtnl_unlock();
+		mutex_unlock(&ppriv->sysfs_mutex);
+		return -EPERM;
+	}
+
 	if (!down_write_trylock(&ppriv->vlan_rwsem)) {
 		rtnl_unlock();
 		mutex_unlock(&ppriv->sysfs_mutex);

@@ -199,9 +202,6 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 
 	ppriv = ipoib_priv(pdev);
 
-	if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
-		return -EPERM;
-
 	if (!mutex_trylock(&ppriv->sysfs_mutex))
 		return restart_syscall();
 

@@ -210,6 +210,12 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 		return restart_syscall();
 	}
 
+	if (pdev->reg_state != NETREG_REGISTERED) {
+		rtnl_unlock();
+		mutex_unlock(&ppriv->sysfs_mutex);
+		return -EPERM;
+	}
+
 	if (!down_write_trylock(&ppriv->vlan_rwsem)) {
 		rtnl_unlock();
 		mutex_unlock(&ppriv->sysfs_mutex);

index 7ca9013bf05c..7cd42619deb2 100644
@@ -1661,7 +1661,7 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev)
 	/* Stop GC if called at init fail need to cancel work */
 	stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	if (!stopped)
-		cancel_delayed_work(&priv->neigh_reap_task);
+		cancel_delayed_work_sync(&priv->neigh_reap_task);
 
 	ipoib_flush_neighs(priv);
 

@@ -1837,7 +1837,7 @@ void ipoib_dev_cleanup(struct net_device *dev)
 	list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
 		/* Stop GC on child */
 		set_bit(IPOIB_STOP_NEIGH_GC, &cpriv->flags);
-		cancel_delayed_work(&cpriv->neigh_reap_task);
+		cancel_delayed_work_sync(&cpriv->neigh_reap_task);
 		unregister_netdevice_queue(cpriv->dev, &head);
 	}
 	unregister_netdevice_many(&head);

@@ -2346,7 +2346,7 @@ static struct net_device *ipoib_add_port(const char *format,
 	flush_workqueue(ipoib_workqueue);
 	/* Stop GC if started before flush */
 	set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
-	cancel_delayed_work(&priv->neigh_reap_task);
+	cancel_delayed_work_sync(&priv->neigh_reap_task);
 	flush_workqueue(priv->wq);
 	ipoib_dev_cleanup(priv->dev);
 

@@ -2412,7 +2412,7 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 
 		/* Stop GC */
 		set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
-		cancel_delayed_work(&priv->neigh_reap_task);
+		cancel_delayed_work_sync(&priv->neigh_reap_task);
 		flush_workqueue(priv->wq);
 
 		/* Wrap rtnl_lock/unlock with mutex to protect sysfs calls */

index 9eebb705d994..48e9ea50ca87 100644
@@ -510,7 +510,6 @@ int ipoib_ib_dev_stop_default(struct net_device *dev);
 void ipoib_pkey_dev_check_presence(struct net_device *dev);
 
 int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
-void ipoib_dev_cleanup(struct net_device *dev);
 
 void ipoib_mcast_join_task(struct work_struct *work);
 void ipoib_mcast_carrier_on_task(struct work_struct *work);

106 lines not on this page · raw message

index 1b7bfd500893..b62ab85c8ead 100644
@@ -83,7 +83,7 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 	result = register_netdevice(priv->dev);
 	if (result) {
 		ipoib_warn(priv, "failed to initialize; error %i", result);
-		goto register_failed;
+		goto err;
 	}
 
 	/* RTNL childs don't need proprietary sysfs entries */

@@ -108,9 +108,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 	result = -ENOMEM;
 	unregister_netdevice(priv->dev);
 
-register_failed:
-	ipoib_dev_cleanup(priv->dev);
-
 err:
 	return result;
 }

index 48e9ea50ca87..04fc5ad1b69f 100644
@@ -91,7 +91,6 @@ enum {
 	IPOIB_STOP_REAPER	  = 7,
 	IPOIB_FLAG_ADMIN_CM	  = 9,
 	IPOIB_FLAG_UMCAST	  = 10,
-	IPOIB_STOP_NEIGH_GC	  = 11,
 	IPOIB_NEIGH_TBL_FLUSH	  = 12,
 	IPOIB_FLAG_DEV_ADDR_SET	  = 13,
 	IPOIB_FLAG_DEV_ADDR_CTRL  = 14,

index 4eec2781e83f..d4e9951dc539 100644
@@ -1305,9 +1305,6 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	int i;
 	LIST_HEAD(remove_list);
 
-	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
-		return;
-
 	spin_lock_irqsave(&priv->lock, flags);
 
 	htbl = rcu_dereference_protected(ntbl->htbl,

@@ -1319,9 +1316,6 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	/* neigh is obsolete if it was idle for two GC periods */
 	dt = 2 * arp_tbl.gc_interval;
 	neigh_obsolete = jiffies - dt;
-	/* handle possible race condition */
-	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
-		goto out_unlock;
 
 	for (i = 0; i < htbl->size; i++) {
 		struct ipoib_neigh *neigh;

@@ -1359,9 +1353,8 @@ static void ipoib_reap_neigh(struct work_struct *work)
 
 	__ipoib_reap_neigh(priv);
 
-	if (!test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->neigh_reap_task,
-				   arp_tbl.gc_interval);
+	queue_delayed_work(priv->wq, &priv->neigh_reap_task,
+			   arp_tbl.gc_interval);
 }
 
 

@@ -1523,7 +1516,6 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 	htbl = kzalloc(sizeof(*htbl), GFP_KERNEL);
 	if (!htbl)
 		return -ENOMEM;
-	set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	size = roundup_pow_of_two(arp_tbl.gc_thresh3);
 	buckets = kvcalloc(size, sizeof(*buckets), GFP_KERNEL);
 	if (!buckets) {

@@ -1538,7 +1530,6 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 	atomic_set(&ntbl->entries, 0);
 
 	/* start garbage collection */
-	clear_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	queue_delayed_work(priv->wq, &priv->neigh_reap_task,
 			   arp_tbl.gc_interval);
 

@@ -1648,15 +1639,11 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
 static void ipoib_neigh_hash_uninit(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-	int stopped;
 
 	ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n");
 	init_completion(&priv->ntbl.deleted);
 
-	/* Stop GC if called at init fail need to cancel work */
-	stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
-	if (!stopped)
-		cancel_delayed_work_sync(&priv->neigh_reap_task);
+	cancel_delayed_work_sync(&priv->neigh_reap_task);
 
 	ipoib_flush_neighs(priv);
 

@@ -1796,12 +1783,15 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
 		if (ipoib_ib_dev_open(dev)) {
 			pr_warn("%s failed to open device\n", dev->name);
 			ret = -ENODEV;
-			goto out_dev_uninit;
+			goto out_hash_uninit;
 		}
 	}
 
 	return 0;
 
+out_hash_uninit:
+	ipoib_neigh_hash_uninit(dev);
+
 out_dev_uninit:
 	ipoib_ib_dev_cleanup(dev);
 

@@ -1857,7 +1847,6 @@ static void ipoib_ndo_uninit(struct net_device *dev)
 	/* Delete any child interfaces first */
 	list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
 		/* Stop GC on child */
-		set_bit(IPOIB_STOP_NEIGH_GC, &cpriv->flags);
 		cancel_delayed_work_sync(&cpriv->neigh_reap_task);
 		unregister_netdevice_queue(cpriv->dev, &head);
 	}

index 04fc5ad1b69f..02ad1a60dc80 100644
@@ -508,8 +508,6 @@ void ipoib_ib_dev_down(struct net_device *dev);
 int ipoib_ib_dev_stop_default(struct net_device *dev);
 void ipoib_pkey_dev_check_presence(struct net_device *dev);
 
-int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
-
 void ipoib_mcast_join_task(struct work_struct *work);
 void ipoib_mcast_carrier_on_task(struct work_struct *work);
 void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);

@@ -597,7 +595,6 @@ void ipoib_pkey_open(struct ipoib_dev_priv *priv);
 void ipoib_drain_cq(struct net_device *dev);
 
 void ipoib_set_ethtool_ops(struct net_device *dev);
-void ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca);
 
 #define IPOIB_FLAGS_RC		0x80
 #define IPOIB_FLAGS_UC		0x40

260 lines not on this page · raw message

index 3e44087935ae..a86928a80c08 100644
@@ -125,12 +125,6 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
 	if (child_pkey == 0 || child_pkey == 0x8000)
 		return -EINVAL;
 
-	/*
-	 * Set the full membership bit, so that we join the right
-	 * broadcast group, etc.
-	 */
-	child_pkey |= 0x8000;
-
 	err = __ipoib_vlan_add(ppriv, ipoib_priv(dev),
 			       child_pkey, IPOIB_RTNL_CHILD);
 

index b62ab85c8ead..3103729a73fd 100644
@@ -55,35 +55,14 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 {
 	int result;
 
-	priv->max_ib_mtu = ppriv->max_ib_mtu;
-	/* MTU will be reset when mcast join happens */
-	priv->dev->mtu   = IPOIB_UD_MTU(priv->max_ib_mtu);
-	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
 	priv->parent = ppriv->dev;
-	set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
-
-	ipoib_set_dev_features(priv, ppriv->ca);
-
 	priv->pkey = pkey;
-
-	memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
-	memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid));
-	set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
-	priv->dev->broadcast[8] = pkey >> 8;
-	priv->dev->broadcast[9] = pkey & 0xff;
-
-	result = ipoib_dev_init(priv->dev, ppriv->ca, ppriv->port);
-	if (result < 0) {
-		ipoib_warn(ppriv, "failed to initialize subinterface: "
-			   "device %s, port %d",
-			   ppriv->ca->name, ppriv->port);
-		goto err;
-	}
+	priv->child_type = type;
 
 	result = register_netdevice(priv->dev);
 	if (result) {
 		ipoib_warn(priv, "failed to initialize; error %i", result);
-		goto err;
+		return result;
 	}
 
 	/* RTNL childs don't need proprietary sysfs entries */

@@ -99,17 +78,13 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 			goto sysfs_failed;
 	}
 
-	priv->child_type  = type;
 	list_add_tail(&priv->list, &ppriv->child_intfs);
 
 	return 0;
 
 sysfs_failed:
-	result = -ENOMEM;
 	unregister_netdevice(priv->dev);
-
-err:
-	return result;
+	return -ENOMEM;
 }
 
 int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)

index a93ef6367d38..9011187ca081 100644
@@ -5157,11 +5157,6 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 	return num_counters;
 }
 
-static void mlx5_ib_free_rdma_netdev(struct net_device *netdev)
-{
-	return mlx5_rdma_netdev_free(netdev);
-}
-
 static struct net_device*
 mlx5_ib_alloc_rdma_netdev(struct ib_device *hca,
 			  u8 port_num,

@@ -5171,17 +5166,12 @@ mlx5_ib_alloc_rdma_netdev(struct ib_device *hca,
 			  void (*setup)(struct net_device *))
 {
 	struct net_device *netdev;
-	struct rdma_netdev *rn;
 
 	if (type != RDMA_NETDEV_IPOIB)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	netdev = mlx5_rdma_netdev_alloc(to_mdev(hca)->mdev, hca,
 					name, setup);
-	if (likely(!IS_ERR_OR_NULL(netdev))) {
-		rn = netdev_priv(netdev);
-		rn->free_rdma_netdev = mlx5_ib_free_rdma_netdev;
-	}
 	return netdev;
 }
 

index 02ad1a60dc80..d2cb0a8500e3 100644
@@ -323,6 +323,7 @@ struct ipoib_dev_priv {
 	spinlock_t lock;
 
 	struct net_device *dev;
+	void (*next_priv_destructor)(struct net_device *dev);
 
 	struct napi_struct send_napi;
 	struct napi_struct recv_napi;

@@ -481,6 +482,7 @@ static inline void ipoib_put_ah(struct ipoib_ah *ah)
 	kref_put(&ah->ref, ipoib_free_ah);
 }
 int ipoib_open(struct net_device *dev);
+void ipoib_intf_free(struct net_device *dev);
 int ipoib_add_pkey_attr(struct net_device *dev);
 int ipoib_add_umcast_attr(struct net_device *dev);
 

175 lines not on this page · raw message

123 lines not on this page · raw message

index af3bb2f7a504..b8d150d2fd72 100644
@@ -580,6 +580,22 @@ static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev)
 	return 0;
 }
 
+static void mlx5_rdma_netdev_free(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5i_priv *ipriv = priv->ppriv;
+	const struct mlx5e_profile *profile = priv->profile;
+
+	mlx5e_detach_netdev(priv);
+	profile->cleanup(priv);
+	destroy_workqueue(priv->wq);
+
+	if (!ipriv->sub_interface) {
+		mlx5i_pkey_qpn_ht_cleanup(netdev);
+		mlx5e_destroy_mdev_resources(priv->mdev);
+	}
+}
+
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  struct ib_device *ibdev,
 					  const char *name,

@@ -653,6 +669,9 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 	rn->detach_mcast = mlx5i_detach_mcast;
 	rn->set_id = mlx5i_set_pkey_index;
 
+	netdev->priv_destructor = mlx5_rdma_netdev_free;
+	netdev->needs_free_netdev = 1;
+
 	return netdev;
 
 destroy_ht:

@@ -665,21 +684,3 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 	return NULL;
 }
 EXPORT_SYMBOL(mlx5_rdma_netdev_alloc);
-
-void mlx5_rdma_netdev_free(struct net_device *netdev)
-{
-	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
-	struct mlx5i_priv *ipriv = priv->ppriv;
-	const struct mlx5e_profile *profile = priv->profile;
-
-	mlx5e_detach_netdev(priv);
-	profile->cleanup(priv);
-	destroy_workqueue(priv->wq);
-
-	if (!ipriv->sub_interface) {
-		mlx5i_pkey_qpn_ht_cleanup(netdev);
-		mlx5e_destroy_mdev_resources(priv->mdev);
-	}
-	free_netdev(netdev);
-}
-EXPORT_SYMBOL(mlx5_rdma_netdev_free);

index 0c1beb14837b..789489e3aa76 100644
@@ -1218,14 +1218,11 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-
-static inline void mlx5_rdma_netdev_free(struct net_device *netdev) {}
 #else
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  struct ib_device *ibdev,
 					  const char *name,
 					  void (*setup)(struct net_device *));
-void mlx5_rdma_netdev_free(struct net_device *netdev);
 #endif /* CONFIG_MLX5_CORE_IPOIB */
 
 struct mlx5_profile {

index 42cbf8eabe9d..73c780c99482 100644
@@ -2202,7 +2202,11 @@ struct rdma_netdev {
 	struct ib_device  *hca;
 	u8                 port_num;
 
-	/* cleanup function must be specified */
+	/*
+	 * cleanup function must be specified.
+	 * FIXME: This is only used for OPA_VNIC and that usage should be
+	 * removed too.
+	 */
 	void (*free_rdma_netdev)(struct net_device *netdev);
 
 	/* control functions */

index d2cb0a8500e3..804cb4bee57d 100644
@@ -332,7 +332,6 @@ struct ipoib_dev_priv {
 
 	struct rw_semaphore vlan_rwsem;
 	struct mutex mcast_mutex;
-	struct mutex sysfs_mutex;
 
 	struct rb_root  path_tree;
 	struct list_head path_list;

index 83fa402e5d03..04785d3f8195 100644
@@ -1514,19 +1514,13 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 {
 	struct net_device *dev = to_net_dev(d);
 	int ret;
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-
-	if (!mutex_trylock(&priv->sysfs_mutex))
-		return restart_syscall();
 
 	if (!rtnl_trylock()) {
-		mutex_unlock(&priv->sysfs_mutex);
 		return restart_syscall();
 	}
 
 	if (dev->reg_state != NETREG_REGISTERED) {
 		rtnl_unlock();
-		mutex_unlock(&priv->sysfs_mutex);
 		return -EPERM;
 	}
 

@@ -1538,7 +1532,6 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 	 */
 	if (ret != -EBUSY)
 		rtnl_unlock();
-	mutex_unlock(&priv->sysfs_mutex);
 
 	return (!ret || ret == -EBUSY) ? count : ret;
 }

index 73d917d57f93..e9f4f261fe20 100644
@@ -2079,7 +2079,6 @@ static void ipoib_build_priv(struct net_device *dev)
 	spin_lock_init(&priv->lock);
 	init_rwsem(&priv->vlan_rwsem);
 	mutex_init(&priv->mcast_mutex);
-	mutex_init(&priv->sysfs_mutex);
 
 	INIT_LIST_HEAD(&priv->path_list);
 	INIT_LIST_HEAD(&priv->child_intfs);

@@ -2476,10 +2475,7 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 	list_for_each_entry_safe(priv, tmp, dev_list, list) {
 		ipoib_parent_unregister_pre(priv->dev);
 
-		/* Wrap rtnl_lock/unlock with mutex to protect sysfs calls */
-		mutex_lock(&priv->sysfs_mutex);
 		unregister_netdev(priv->dev);
-		mutex_unlock(&priv->sysfs_mutex);
 	}
 
 	kfree(dev_list);

@@ -2527,8 +2523,7 @@ static int __init ipoib_init_module(void)
 	 * its private workqueue, and we only queue up flush events
 	 * on our global flush workqueue.  This avoids the deadlocks.
 	 */
-	ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush",
-						  WQ_MEM_RECLAIM);
+	ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush", 0);
 	if (!ipoib_workqueue) {
 		ret = -ENOMEM;
 		goto err_fs;

145 lines not on this page · raw message

index 804cb4bee57d..1abe3c62f106 100644
@@ -330,6 +330,13 @@ struct ipoib_dev_priv {
 
 	unsigned long flags;
 
+	/*
+	 * This protects access to the child_intfs list.
+	 * To READ from child_intfs the RTNL or vlan_rwsem read side must be
+	 * held.  To WRITE RTNL and the vlan_rwsem write side must be held (in
+	 * that order) This lock exists because we have a few contexts where
+	 * we need the child_intfs, but do not want to grab the RTNL.
+	 */
 	struct rw_semaphore vlan_rwsem;
 	struct mutex mcast_mutex;
 

index e9f4f261fe20..b2fe23d60103 100644
@@ -1939,18 +1939,15 @@ static int ipoib_ndo_init(struct net_device *ndev)
 
 static void ipoib_ndo_uninit(struct net_device *dev)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev), *cpriv, *tcpriv;
-	LIST_HEAD(head);
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 
 	ASSERT_RTNL();
 
-	/* Delete any child interfaces first */
-	list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
-		/* Stop GC on child */
-		cancel_delayed_work_sync(&cpriv->neigh_reap_task);
-		unregister_netdevice_queue(cpriv->dev, &head);
-	}
-	unregister_netdevice_many(&head);
+	/*
+	 * ipoib_remove_one guarantees the children are removed before the
+	 * parent, and that is the only place where a parent can be removed.
+	 */
+	WARN_ON(!list_empty(&priv->child_intfs));
 
 	ipoib_neigh_hash_uninit(dev);
 

@@ -2466,16 +2463,25 @@ static void ipoib_add_one(struct ib_device *device)
 
 static void ipoib_remove_one(struct ib_device *device, void *client_data)
 {
-	struct ipoib_dev_priv *priv, *tmp;
+	struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv;
 	struct list_head *dev_list = client_data;
 
 	if (!dev_list)
 		return;
 
 	list_for_each_entry_safe(priv, tmp, dev_list, list) {
+		LIST_HEAD(head);
 		ipoib_parent_unregister_pre(priv->dev);
 
-		unregister_netdev(priv->dev);
+		rtnl_lock();
+
+		list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs,
+					 list)
+			unregister_netdevice_queue(cpriv->dev, &head);
+		unregister_netdevice_queue(priv->dev, &head);
+		unregister_netdevice_many(&head);
+
+		rtnl_unlock();
 	}
 
 	kfree(dev_list);

index 891c5b40018a..fa4dfcee2644 100644
@@ -67,6 +67,12 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 
 	ASSERT_RTNL();
 
+	/*
+	 * Racing with unregister of the parent must be prevented by the
+	 * caller.
+	 */
+	WARN_ON(ppriv->dev->reg_state != NETREG_REGISTERED);
+
 	priv->parent = ppriv->dev;
 	priv->pkey = pkey;
 	priv->child_type = type;

index b2fe23d60103..e3d28f9ad9c0 100644
@@ -1890,6 +1890,12 @@ static void ipoib_child_init(struct net_device *ndev)
 	struct ipoib_dev_priv *priv = ipoib_priv(ndev);
 	struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
 
+	dev_hold(priv->parent);
+
+	down_write(&ppriv->vlan_rwsem);
+	list_add_tail(&priv->list, &ppriv->child_intfs);
+	up_write(&ppriv->vlan_rwsem);
+
 	priv->max_ib_mtu = ppriv->max_ib_mtu;
 	set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
 	memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);

@@ -1959,6 +1965,16 @@ static void ipoib_ndo_uninit(struct net_device *dev)
 		destroy_workqueue(priv->wq);
 		priv->wq = NULL;
 	}
+
+	if (priv->parent) {
+		struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
+
+		down_write(&ppriv->vlan_rwsem);
+		list_del(&priv->list);
+		up_write(&ppriv->vlan_rwsem);
+
+		dev_put(priv->parent);
+	}
 }
 
 static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state)

index a86928a80c08..7e093b7aad8f 100644
@@ -133,19 +133,6 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
 	return err;
 }
 
-static void ipoib_unregister_child_dev(struct net_device *dev, struct list_head *head)
-{
-	struct ipoib_dev_priv *priv, *ppriv;
-
-	priv = ipoib_priv(dev);
-	ppriv = ipoib_priv(priv->parent);
-
-	down_write(&ppriv->vlan_rwsem);
-	unregister_netdevice_queue(dev, head);
-	list_del(&priv->list);
-	up_write(&ppriv->vlan_rwsem);
-}
-
 static size_t ipoib_get_size(const struct net_device *dev)
 {
 	return nla_total_size(2) +	/* IFLA_IPOIB_PKEY   */

@@ -161,7 +148,6 @@ static struct rtnl_link_ops ipoib_link_ops __read_mostly = {
 	.setup		= ipoib_setup_common,
 	.newlink	= ipoib_new_child_link,
 	.changelink	= ipoib_changelink,
-	.dellink	= ipoib_unregister_child_dev,
 	.get_size	= ipoib_get_size,
 	.fill_info	= ipoib_fill_info,
 };

index fa4dfcee2644..ca3a7f6c0998 100644
@@ -106,8 +106,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 			goto sysfs_failed;
 	}
 
-	list_add_tail(&priv->list, &ppriv->child_intfs);
-
 	return 0;
 
 sysfs_failed:

@@ -139,11 +137,6 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 		return -EPERM;
 	}
 
-	if (!down_write_trylock(&ppriv->vlan_rwsem)) {
-		rtnl_unlock();
-		return restart_syscall();
-	}
-
 	/*
 	 * First ensure this isn't a duplicate. We check the parent device and
 	 * then all of the legacy child interfaces to make sure the Pkey

@@ -175,7 +168,6 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 		free_netdev(ndev);
 
 out:
-	up_write(&ppriv->vlan_rwsem);
 	rtnl_unlock();
 
 	return result;

@@ -209,10 +201,6 @@ static void ipoib_vlan_delete_task(struct work_struct *work)
 		struct ipoib_dev_priv *priv = ipoib_priv(dev);
 		struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
 
-		down_write(&ppriv->vlan_rwsem);
-		list_del(&priv->list);
-		up_write(&ppriv->vlan_rwsem);
-
 		ipoib_dbg(ppriv, "delete child vlan %s\n", dev->name);
 		unregister_netdevice(dev);
 	}

index 7e093b7aad8f..d4d553a51fa9 100644
@@ -122,9 +122,6 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
 	} else
 		child_pkey  = nla_get_u16(data[IFLA_IPOIB_PKEY]);
 
-	if (child_pkey == 0 || child_pkey == 0x8000)
-		return -EINVAL;
-
 	err = __ipoib_vlan_add(ppriv, ipoib_priv(dev),
 			       child_pkey, IPOIB_RTNL_CHILD);
 

123 lines not on this page · raw message