net: change addr_list_lock back to static key

The dynamic key update for addr_list_lock still causes troubles,
for example the following race condition still exists:

CPU 0:				CPU 1:
(RCU read lock)			(RTNL lock)
dev_mc_seq_show()		netdev_update_lockdep_key()
				  -> lockdep_unregister_key()
 -> netif_addr_lock_bh()

because lockdep doesn't provide an API to update it atomically.
Therefore, we have to move it back to static keys and use subclass
for nest locking like before.

In commit 1a33e10e ("net: partially revert dynamic lockdep key
changes"), I already reverted most parts of commit ab92d68f
("net: core: add generic lockdep keys").

This patch reverts the rest and also part of commit f3b0a18b
("net: remove unnecessary variables and callback"). After this
patch, addr_list_lock changes back to using static keys and
subclasses to satisfy lockdep. Thanks to dev->lower_level, we do
not have to change back to ->ndo_get_lock_subclass().

And hopefully this reduces some syzbot lockdep noises too.

Reported-by: syzbot+f3a0e80c34b3fc28ac5e@syzkaller.appspotmail.com
Cc: Taehee Yoo <ap420073@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/bonding/bond_main.c

@@ -3687,8 +3687,6 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
 		res = bond_release(bond_dev, slave_dev);
-		if (!res)
-			netdev_update_lockdep_key(slave_dev);
 		break;
 	case BOND_SETHWADDR_OLD:
 	case SIOCBONDSETHWADDR:

drivers/net/bonding/bond_options.c

@@ -1398,8 +1398,6 @@ static int bond_option_slaves_set(struct bonding *bond,
 	case '-':
 		slave_dbg(bond->dev, dev, "Releasing interface\n");
 		ret = bond_release(bond->dev, dev);
-		if (!ret)
-			netdev_update_lockdep_key(dev);
 		break;
 
 	default:

drivers/net/hamradio/bpqether.c

@@ -113,6 +113,7 @@ static LIST_HEAD(bpq_devices);
  * off into a separate class since they always nest.
  */
 static struct lock_class_key bpq_netdev_xmit_lock_key;
+static struct lock_class_key bpq_netdev_addr_lock_key;
 
 static void bpq_set_lockdep_class_one(struct net_device *dev,
 				      struct netdev_queue *txq,
@@ -123,6 +124,7 @@ static void bpq_set_lockdep_class_one(struct net_device *dev,
 
 static void bpq_set_lockdep_class(struct net_device *dev)
 {
+	lockdep_set_class(&dev->addr_list_lock, &bpq_netdev_addr_lock_key);
 	netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL);
 }
 

drivers/net/macsec.c

@@ -3999,6 +3999,8 @@ static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 	return 0;
 }
 
+static struct lock_class_key macsec_netdev_addr_lock_key;
+
 static int macsec_newlink(struct net *net, struct net_device *dev,
 			  struct nlattr *tb[], struct nlattr *data[],
 			  struct netlink_ext_ack *extack)
@@ -4050,6 +4052,9 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 		return err;
 
 	netdev_lockdep_set_classes(dev);
+	lockdep_set_class_and_subclass(&dev->addr_list_lock,
+				       &macsec_netdev_addr_lock_key,
+				       dev->lower_level);
 
 	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err < 0)

drivers/net/macvlan.c

@@ -860,6 +860,8 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
  * "super class" of normal network devices; split their locks off into a
  * separate class since they always nest.
  */
+static struct lock_class_key macvlan_netdev_addr_lock_key;
+
 #define ALWAYS_ON_OFFLOADS \
 	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \
 	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL)
@@ -875,6 +877,14 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 #define MACVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
+static void macvlan_set_lockdep_class(struct net_device *dev)
+{
+	netdev_lockdep_set_classes(dev);
+	lockdep_set_class_and_subclass(&dev->addr_list_lock,
+				       &macvlan_netdev_addr_lock_key,
+				       dev->lower_level);
+}
+
 static int macvlan_init(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
@@ -892,8 +902,7 @@ static int macvlan_init(struct net_device *dev)
 	dev->gso_max_size	= lowerdev->gso_max_size;
 	dev->gso_max_segs	= lowerdev->gso_max_segs;
 	dev->hard_header_len	= lowerdev->hard_header_len;
-
-	netdev_lockdep_set_classes(dev);
+	macvlan_set_lockdep_class(dev);
 
 	vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan->pcpu_stats)

drivers/net/vxlan.c

@@ -4245,10 +4245,8 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 		mod_timer(&vxlan->age_timer, jiffies);
 
 	netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev);
-	if (lowerdev && lowerdev != dst->remote_dev) {
+	if (lowerdev && lowerdev != dst->remote_dev)
 		dst->remote_dev = lowerdev;
-		netdev_update_lockdep_key(lowerdev);
-	}
 	vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true);
 	return 0;
 }

drivers/net/wireless/intersil/hostap/hostap_hw.c

@@ -3048,6 +3048,7 @@ static void prism2_clear_set_tim_queue(local_info_t *local)
  * This is a natural nesting, which needs a split lock type.
  */
 static struct lock_class_key hostap_netdev_xmit_lock_key;
+static struct lock_class_key hostap_netdev_addr_lock_key;
 
 static void prism2_set_lockdep_class_one(struct net_device *dev,
 					 struct netdev_queue *txq,
@@ -3059,6 +3060,8 @@ static void prism2_set_lockdep_class_one(struct net_device *dev,
 
 static void prism2_set_lockdep_class(struct net_device *dev)
 {
+	lockdep_set_class(&dev->addr_list_lock,
+			  &hostap_netdev_addr_lock_key);
 	netdev_for_each_tx_queue(dev, prism2_set_lockdep_class_one, NULL);
 }
 

include/linux/netdevice.h

@@ -1821,8 +1821,6 @@ enum netdev_priv_flags {
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
  *
- *	@addr_list_lock_key:	lockdep class annotating
- *				net_device->addr_list_lock spinlock
  *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
  *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
  *
@@ -2125,7 +2123,6 @@ struct net_device {
 #endif
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
-	struct lock_class_key	addr_list_lock_key;
 	struct lock_class_key	*qdisc_tx_busylock;
 	struct lock_class_key	*qdisc_running_key;
 	bool			proto_down;
@@ -2217,10 +2214,13 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 	static struct lock_class_key qdisc_tx_busylock_key;	\
 	static struct lock_class_key qdisc_running_key;		\
 	static struct lock_class_key qdisc_xmit_lock_key;	\
+	static struct lock_class_key dev_addr_list_lock_key;	\
 	unsigned int i;						\
 								\
 	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
 	(dev)->qdisc_running_key = &qdisc_running_key;		\
+	lockdep_set_class(&(dev)->addr_list_lock,		\
+			  &dev_addr_list_lock_key);		\
 	for (i = 0; i < (dev)->num_tx_queues; i++)		\
 		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
 				  &qdisc_xmit_lock_key);	\
@@ -3253,7 +3253,6 @@ static inline void netif_stop_queue(struct net_device *dev)
 }
 
 void netif_tx_stop_all_queues(struct net_device *dev);
-void netdev_update_lockdep_key(struct net_device *dev);
 
 static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
 {
@@ -4239,6 +4238,11 @@ static inline void netif_addr_lock(struct net_device *dev)
 	spin_lock(&dev->addr_list_lock);
 }
 
+static inline void netif_addr_lock_nested(struct net_device *dev)
+{
+	spin_lock_nested(&dev->addr_list_lock, dev->lower_level);
+}
+
 static inline void netif_addr_lock_bh(struct net_device *dev)
 {
 	spin_lock_bh(&dev->addr_list_lock);

net/8021q/vlan_dev.c

@@ -494,6 +494,7 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
  * separate class since they always nest.
  */
 static struct lock_class_key vlan_netdev_xmit_lock_key;
+static struct lock_class_key vlan_netdev_addr_lock_key;
 
 static void vlan_dev_set_lockdep_one(struct net_device *dev,
 				     struct netdev_queue *txq,
@@ -502,8 +503,11 @@ static void vlan_dev_set_lockdep_one(struct net_device *dev,
 	lockdep_set_class(&txq->_xmit_lock, &vlan_netdev_xmit_lock_key);
 }
 
-static void vlan_dev_set_lockdep_class(struct net_device *dev)
+static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
 {
+	lockdep_set_class_and_subclass(&dev->addr_list_lock,
+				       &vlan_netdev_addr_lock_key,
+				       subclass);
 	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL);
 }
 
@@ -597,7 +601,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-	vlan_dev_set_lockdep_class(dev);
+	vlan_dev_set_lockdep_class(dev, dev->lower_level);
 
 	vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan->vlan_pcpu_stats)

net/batman-adv/soft-interface.c

@@ -745,6 +745,7 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto,
  * separate class since they always nest.
  */
 static struct lock_class_key batadv_netdev_xmit_lock_key;
+static struct lock_class_key batadv_netdev_addr_lock_key;
 
 /**
  * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue
@@ -765,6 +766,7 @@ static void batadv_set_lockdep_class_one(struct net_device *dev,
  */
 static void batadv_set_lockdep_class(struct net_device *dev)
 {
+	lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key);
 	netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL);
 }
 

net/bridge/br_device.c

@@ -105,6 +105,13 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static struct lock_class_key bridge_netdev_addr_lock_key;
+
+static void br_set_lockdep_class(struct net_device *dev)
+{
+	lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
+}
+
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -143,6 +150,7 @@ static int br_dev_init(struct net_device *dev)
 		br_fdb_hash_fini(br);
 	}
 
+	br_set_lockdep_class(dev);
 	return err;
 }
 

net/core/dev.c

@@ -439,6 +439,7 @@ static const char *const netdev_lock_name[] = {
 	"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
 
 static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
+static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
 
 static inline unsigned short netdev_lock_pos(unsigned short dev_type)
 {
@@ -460,11 +461,25 @@ static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
 	lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
 				   netdev_lock_name[i]);
 }
+
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
+{
+	int i;
+
+	i = netdev_lock_pos(dev->type);
+	lockdep_set_class_and_name(&dev->addr_list_lock,
+				   &netdev_addr_lock_key[i],
+				   netdev_lock_name[i]);
+}
 #else
 static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
 						 unsigned short dev_type)
 {
 }
+
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
+{
+}
 #endif
 
 /*******************************************************************************
@@ -9373,15 +9388,6 @@ void netif_tx_stop_all_queues(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_tx_stop_all_queues);
 
-void netdev_update_lockdep_key(struct net_device *dev)
-{
-	lockdep_unregister_key(&dev->addr_list_lock_key);
-	lockdep_register_key(&dev->addr_list_lock_key);
-
-	lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
-}
-EXPORT_SYMBOL(netdev_update_lockdep_key);
-
 /**
  *	register_netdevice	- register a network device
  *	@dev: device to register
@@ -9420,7 +9426,7 @@ int register_netdevice(struct net_device *dev)
 		return ret;
 
 	spin_lock_init(&dev->addr_list_lock);
-	lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
+	netdev_set_addr_lockdep_class(dev);
 
 	ret = dev_get_valid_name(net, dev, dev->name);
 	if (ret < 0)
@@ -9939,8 +9945,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev_net_set(dev, &init_net);
 
-	lockdep_register_key(&dev->addr_list_lock_key);
-
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
 	dev->upper_level = 1;
@@ -10028,8 +10032,6 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->xdp_bulkq);
 	dev->xdp_bulkq = NULL;
 
-	lockdep_unregister_key(&dev->addr_list_lock_key);
-
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		netdev_freemem(dev);

net/core/dev_addr_lists.c

@@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
 		return;
 
 	netif_addr_lock_bh(from);
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
 	__dev_set_rx_mode(to);
 	netif_addr_unlock(to);
@@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
 		return;
 
 	netif_addr_lock_bh(from);
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
 	__dev_set_rx_mode(to);
 	netif_addr_unlock(to);

net/core/rtnetlink.c

@@ -2462,7 +2462,6 @@ static int do_set_master(struct net_device *dev, int ifindex,
 			err = ops->ndo_del_slave(upper_dev, dev);
 			if (err)
 				return err;
-			netdev_update_lockdep_key(dev);
 		} else {
 			return -EOPNOTSUPP;
 		}

net/dsa/master.c

@@ -327,6 +327,8 @@ static void dsa_master_reset_mtu(struct net_device *dev)
 	rtnl_unlock();
 }
 
+static struct lock_class_key dsa_master_addr_list_lock_key;
+
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	int ret;
@@ -345,6 +347,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	wmb();
 
 	dev->dsa_ptr = cpu_dp;
+	lockdep_set_class(&dev->addr_list_lock,
+			  &dsa_master_addr_list_lock_key);
 	ret = dsa_master_ethtool_setup(dev);
 	if (ret)
 		return ret;

net/netrom/af_netrom.c

@@ -70,6 +70,7 @@ static const struct proto_ops nr_proto_ops;
  * separate class since they always nest.
  */
 static struct lock_class_key nr_netdev_xmit_lock_key;
+static struct lock_class_key nr_netdev_addr_lock_key;
 
 static void nr_set_lockdep_one(struct net_device *dev,
 			       struct netdev_queue *txq,
@@ -80,6 +81,7 @@ static void nr_set_lockdep_one(struct net_device *dev,
 
 static void nr_set_lockdep_key(struct net_device *dev)
 {
+	lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key);
 	netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL);
 }
 

net/rose/af_rose.c

@@ -71,6 +71,7 @@ ax25_address rose_callsign;
  * separate class since they always nest.
  */
 static struct lock_class_key rose_netdev_xmit_lock_key;
+static struct lock_class_key rose_netdev_addr_lock_key;
 
 static void rose_set_lockdep_one(struct net_device *dev,
 				 struct netdev_queue *txq,
@@ -81,6 +82,7 @@ static void rose_set_lockdep_one(struct net_device *dev,
 
 static void rose_set_lockdep_key(struct net_device *dev)
 {
+	lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key);
 	netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL);
 }