@@ -4393,6 +4393,16 @@ static inline void netif_addr_unlock_bh(struct net_device *dev)
spin_unlock_bh(&dev->addr_list_lock);
}
+static inline void netif_lists_lock(struct net *net)
+{
+ mutex_lock(&net->netif_lists_lock);
+}
+
+static inline void netif_lists_unlock(struct net *net)
+{
+ mutex_unlock(&net->netif_lists_lock);
+}
+
/*
* dev_addrs walker. Should be used only for read access. Call with
* rcu_read_lock held.
@@ -183,6 +183,12 @@ struct net {
struct sock *crypto_nlsk;
#endif
struct sock *diag_nlsk;
+
+ /* Serializes writers to @dev_base_head, @dev_name_head and
+ * @dev_index_head. It does _not_ protect the netif adjacency lists
+ * (struct net_device::adj_list).
+ */
+ struct mutex netif_lists_lock;
} __randomize_layout;
#include <linux/seq_file_net.h>
@@ -175,13 +175,16 @@ static struct napi_struct *napi_by_id(unsigned int napi_id);
*
* Pure readers should hold rcu_read_lock() which should protect them against
* concurrent changes to the interface lists made by the writers. Pure writers
- * must serialize by holding the RTNL mutex while they loop through the list
- * and make changes to it.
+ * must serialize by holding the @net->netif_lists_lock mutex while they loop
+ * through the list and make changes to it.
+ *
+ * It is possible to hold the RTNL mutex for serializing the writers too, but
+ * this should be avoided in new code due to lock contention.
*
* It is also possible to hold the global rwlock_t @dev_base_lock for
* protection (holding its read side as an alternative to rcu_read_lock, and
- * its write side as an alternative to the RTNL mutex), however this should not
- * be done in new code, since it is deprecated and pending removal.
+ * its write side as an alternative to @net->netif_lists_lock), however this
+ * should not be done in new code, since it is deprecated and pending removal.
*
* One other role of @dev_base_lock is to protect against changes in the
* operational state of a network interface.
@@ -360,12 +363,14 @@ static void list_netdevice(struct net_device *dev)
ASSERT_RTNL();
+ netif_lists_lock(net);
write_lock_bh(&dev_base_lock);
list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
netdev_name_node_add(net, dev->name_node);
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
+ netif_lists_unlock(net);
dev_base_seq_inc(net);
}
@@ -375,16 +380,20 @@ static void list_netdevice(struct net_device *dev)
*/
static void unlist_netdevice(struct net_device *dev)
{
+ struct net *net = dev_net(dev);
+
ASSERT_RTNL();
/* Unlink dev from the device chain */
+ netif_lists_lock(net);
write_lock_bh(&dev_base_lock);
list_del_rcu(&dev->dev_list);
netdev_name_node_del(dev->name_node);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
+ netif_lists_unlock(net);
- dev_base_seq_inc(dev_net(dev));
+ dev_base_seq_inc(net);
}
/*
@@ -850,11 +859,11 @@ EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
* @net: the applicable net namespace
* @name: name to find
*
- * Find an interface by name. Must be called under RTNL semaphore
- * or @dev_base_lock. If the name is found a pointer to the device
- * is returned. If the name is not found then %NULL is returned. The
- * reference counters are not incremented so the caller must be
- * careful with locks.
+ * Find an interface by name. Must be called under RTNL semaphore,
+ * @net->netif_lists_lock or @dev_base_lock. If the name is found,
+ * a pointer to the device is returned. If the name is not found then
+ * %NULL is returned. The reference counters are not incremented so the
+ * caller must be careful with locks.
*/
struct net_device *__dev_get_by_name(struct net *net, const char *name)
@@ -920,8 +929,8 @@ EXPORT_SYMBOL(dev_get_by_name);
* Search for an interface by index. Returns %NULL if the device
* is not found or a pointer to the device. The device has not
* had its reference counter increased so the caller must be careful
- * about locking. The caller must hold either the RTNL semaphore
- * or @dev_base_lock.
+ * about locking. The caller must hold either the RTNL semaphore,
+ * @net->netif_lists_lock or @dev_base_lock.
*/
struct net_device *__dev_get_by_index(struct net *net, int ifindex)
@@ -1330,15 +1339,19 @@ int dev_change_name(struct net_device *dev, const char *newname)
netdev_adjacent_rename_links(dev, oldname);
+ netif_lists_lock(net);
write_lock_bh(&dev_base_lock);
netdev_name_node_del(dev->name_node);
write_unlock_bh(&dev_base_lock);
+ netif_lists_unlock(net);
synchronize_rcu();
+ netif_lists_lock(net);
write_lock_bh(&dev_base_lock);
netdev_name_node_add(net, dev->name_node);
write_unlock_bh(&dev_base_lock);
+ netif_lists_unlock(net);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
ret = notifier_to_errno(ret);
@@ -9415,8 +9428,9 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
* @net: the applicable net namespace
*
* Returns a suitable unique value for a new device interface
- * number. The caller must hold the rtnl semaphore or the
- * dev_base_lock to be sure it remains unique.
+ * number.
+ * The caller must hold the rtnl semaphore, @net->netif_lists_lock or the
+ * @dev_base_lock to be sure it remains unique.
*/
static int dev_new_index(struct net *net)
{
@@ -10999,6 +11013,8 @@ static int __net_init netdev_init(struct net *net)
if (net->dev_index_head == NULL)
goto err_idx;
+ mutex_init(&net->netif_lists_lock);
+
RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
return 0;