Merge branch 'per-netns-notifier'

Jiri Pirko says:

====================
net: introduce per-netns netdevice notifiers and use them in mlxsw

Some drivers, like mlxsw, are not interested in notifications coming in
for netdevices from other network namespaces. So introduce per-netns
notifiers and allow to reduce overhead by listening only for
notifications from the same netns.

This is also a preparation for upcoming patchset "devlink: allow devlink
instances to change network namespace". This resolves deadlock during
reload mlxsw into initial netns made possible by
328fbe747a ("net: Close race between {un, }register_netdevice_notifier() and setup_net()/cleanup_net()").
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -4864,7 +4864,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	 * respin.
 	 */
 	mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event;
-	err = register_netdevice_notifier(&mlxsw_sp->netdevice_nb);
+	err = register_netdevice_notifier_net(&init_net,
+					      &mlxsw_sp->netdevice_nb);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to register netdev notifier\n");
 		goto err_netdev_notifier;
@@ -4887,7 +4888,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 err_ports_create:
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
 err_dpipe_init:
-	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
+	unregister_netdevice_notifier_net(&init_net,
+					  &mlxsw_sp->netdevice_nb);
 err_netdev_notifier:
 	if (mlxsw_sp->clock)
 		mlxsw_sp->ptp_ops->fini(mlxsw_sp->ptp_state);
@@ -4973,7 +4975,8 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 
 	mlxsw_sp_ports_remove(mlxsw_sp);
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
-	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
+	unregister_netdevice_notifier_net(&init_net,
+					  &mlxsw_sp->netdevice_nb);
 	if (mlxsw_sp->clock) {
 		mlxsw_sp->ptp_ops->fini(mlxsw_sp->ptp_state);
 		mlxsw_sp->ptp_ops->clock_fini(mlxsw_sp->clock);

include/linux/netdevice.h

@@ -2504,6 +2504,9 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd);
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
+int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb);
+int unregister_netdevice_notifier_net(struct net *net,
+				      struct notifier_block *nb);
 
 struct netdev_notifier_info {
 	struct net_device	*dev;
@@ -2574,6 +2577,9 @@ extern rwlock_t				dev_base_lock;		/* Device list lock */
 		list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list)
 #define for_each_netdev_continue(net, d)		\
 		list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list)
+#define for_each_netdev_continue_reverse(net, d)		\
+		list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \
+						     dev_list)
 #define for_each_netdev_continue_rcu(net, d)		\
 	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
 #define for_each_netdev_in_bond_rcu(bond, slave)	\

include/net/net_namespace.h

@@ -36,6 +36,7 @@
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 #include <linux/skbuff.h>
+#include <linux/notifier.h>
 
 struct user_namespace;
 struct proc_dir_entry;
@@ -96,6 +97,8 @@ struct net {
 	struct list_head 	dev_base_head;
 	struct hlist_head 	*dev_name_head;
 	struct hlist_head	*dev_index_head;
+	struct raw_notifier_head	netdev_chain;
+
 	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
 	int			ifindex;
 	unsigned int		dev_unreg_count;
@@ -317,7 +320,8 @@ static inline struct net *read_pnet(const possible_net_t *pnet)
 /* Protected by net_rwsem */
 #define for_each_net(VAR)				\
 	list_for_each_entry(VAR, &net_namespace_list, list)
-
+#define for_each_net_continue_reverse(VAR)		\
+	list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list)
 #define for_each_net_rcu(VAR)				\
 	list_for_each_entry_rcu(VAR, &net_namespace_list, list)
 

net/core/dev.c

@@ -1725,6 +1725,62 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
 	return nb->notifier_call(nb, val, &info);
 }
 
+static int call_netdevice_register_notifiers(struct notifier_block *nb,
+					     struct net_device *dev)
+{
+	int err;
+
+	err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
+	err = notifier_to_errno(err);
+	if (err)
+		return err;
+
+	if (!(dev->flags & IFF_UP))
+		return 0;
+
+	call_netdevice_notifier(nb, NETDEV_UP, dev);
+	return 0;
+}
+
+static void call_netdevice_unregister_notifiers(struct notifier_block *nb,
+						struct net_device *dev)
+{
+	if (dev->flags & IFF_UP) {
+		call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+					dev);
+		call_netdevice_notifier(nb, NETDEV_DOWN, dev);
+	}
+	call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
+}
+
+static int call_netdevice_register_net_notifiers(struct notifier_block *nb,
+						 struct net *net)
+{
+	struct net_device *dev;
+	int err;
+
+	for_each_netdev(net, dev) {
+		err = call_netdevice_register_notifiers(nb, dev);
+		if (err)
+			goto rollback;
+	}
+	return 0;
+
+rollback:
+	for_each_netdev_continue_reverse(net, dev)
+		call_netdevice_unregister_notifiers(nb, dev);
+	return err;
+}
+
+static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb,
+						    struct net *net)
+{
+	struct net_device *dev;
+
+	for_each_netdev(net, dev)
+		call_netdevice_unregister_notifiers(nb, dev);
+}
+
 static int dev_boot_phase = 1;
 
 /**
@@ -1743,8 +1799,6 @@ static int dev_boot_phase = 1;
 
 int register_netdevice_notifier(struct notifier_block *nb)
 {
-	struct net_device *dev;
-	struct net_device *last;
 	struct net *net;
 	int err;
 
@@ -1757,17 +1811,9 @@ int register_netdevice_notifier(struct notifier_block *nb)
 	if (dev_boot_phase)
 		goto unlock;
 	for_each_net(net) {
-		for_each_netdev(net, dev) {
-			err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
-			err = notifier_to_errno(err);
+		err = call_netdevice_register_net_notifiers(nb, net);
 		if (err)
 			goto rollback;
-
-			if (!(dev->flags & IFF_UP))
-				continue;
-
-			call_netdevice_notifier(nb, NETDEV_UP, dev);
-		}
 	}
 
 unlock:
@@ -1776,22 +1822,9 @@ unlock:
 	return err;
 
 rollback:
-	last = dev;
-	for_each_net(net) {
-		for_each_netdev(net, dev) {
-			if (dev == last)
-				goto outroll;
+	for_each_net_continue_reverse(net)
+		call_netdevice_unregister_net_notifiers(nb, net);
 
-			if (dev->flags & IFF_UP) {
-				call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
-							dev);
-				call_netdevice_notifier(nb, NETDEV_DOWN, dev);
-			}
-			call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
-		}
-	}
-
-outroll:
 	raw_notifier_chain_unregister(&netdev_chain, nb);
 	goto unlock;
 }
@@ -1841,6 +1874,80 @@ unlock:
 }
 EXPORT_SYMBOL(unregister_netdevice_notifier);
 
+/**
+ * register_netdevice_notifier_net - register a per-netns network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Register a notifier to be called when network device events occur.
+ * The notifier passed is linked into the kernel structures and must
+ * not be reused until it has been unregistered. A negative errno code
+ * is returned on a failure.
+ *
+ * When registered all registration and up events are replayed
+ * to the new notifier to allow device to have a race free
+ * view of the network device list.
+ */
+
+int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb)
+{
+	int err;
+
+	rtnl_lock();
+	err = raw_notifier_chain_register(&net->netdev_chain, nb);
+	if (err)
+		goto unlock;
+	if (dev_boot_phase)
+		goto unlock;
+
+	err = call_netdevice_register_net_notifiers(nb, net);
+	if (err)
+		goto chain_unregister;
+
+unlock:
+	rtnl_unlock();
+	return err;
+
+chain_unregister:
+	raw_notifier_chain_unregister(&netdev_chain, nb);
+	goto unlock;
+}
+EXPORT_SYMBOL(register_netdevice_notifier_net);
+
+/**
+ * unregister_netdevice_notifier_net - unregister a per-netns
+ *                                     network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Unregister a notifier previously registered by
+ * register_netdevice_notifier(). The notifier is unlinked into the
+ * kernel structures and may then be reused. A negative errno code
+ * is returned on a failure.
+ *
+ * After unregistering unregister and down device events are synthesized
+ * for all devices on the device list to the removed notifier to remove
+ * the need for special case cleanup code.
+ */
+
+int unregister_netdevice_notifier_net(struct net *net,
+				      struct notifier_block *nb)
+{
+	int err;
+
+	rtnl_lock();
+	err = raw_notifier_chain_unregister(&net->netdev_chain, nb);
+	if (err)
+		goto unlock;
+
+	call_netdevice_unregister_net_notifiers(nb, net);
+
+unlock:
+	rtnl_unlock();
+	return err;
+}
+EXPORT_SYMBOL(unregister_netdevice_notifier_net);
+
 /**
  *	call_netdevice_notifiers_info - call all network notifier blocks
  *	@val: value passed unmodified to notifier function
@@ -1853,7 +1960,18 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
 static int call_netdevice_notifiers_info(unsigned long val,
 					 struct netdev_notifier_info *info)
 {
+	struct net *net = dev_net(info->dev);
+	int ret;
+
 	ASSERT_RTNL();
+
+	/* Run per-netns notifier block chain first, then run the global one.
+	 * Hopefully, one day, the global one is going to be removed after
+	 * all notifier block registrators get converted to be per-netns.
+	 */
+	ret = raw_notifier_call_chain(&net->netdev_chain, val, info);
+	if (ret & NOTIFY_STOP_MASK)
+		return ret;
 	return raw_notifier_call_chain(&netdev_chain, val, info);
 }
 
@@ -9752,6 +9870,8 @@ static int __net_init netdev_init(struct net *net)
 	if (net->dev_index_head == NULL)
 		goto err_idx;
 
+	RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
+
 	return 0;
 
 err_idx: