team interface could be nested and it's lock variable could be nested too. But this lock uses static lockdep key and there is no nested locking handling code such as mutex_lock_nested() and so on. so the Lockdep would warn about the circular locking scenario that couldn't happen. In order to fix, this patch makes the team module to use dynamic lock key instead of static key. Test commands: ip link add team0 type team ip link add team1 type team ip link set team0 master team1 ip link set team0 nomaster ip link set team1 master team0 ip link set team1 nomaster Splat that looks like: [ 40.364352] WARNING: possible recursive locking detected [ 40.364964] 5.4.0-rc3+ #96 Not tainted [ 40.365405] -------------------------------------------- [ 40.365973] ip/750 is trying to acquire lock: [ 40.366542] ffff888060b34c40 (&team->lock){+.+.}, at: team_set_mac_address+0x151/0x290 [team] [ 40.367689] but task is already holding lock: [ 40.368729] ffff888051201c40 (&team->lock){+.+.}, at: team_del_slave+0x29/0x60 [team] [ 40.370280] other info that might help us debug this: [ 40.371159] Possible unsafe locking scenario: [ 40.371942] CPU0 [ 40.372338] ---- [ 40.372673] lock(&team->lock); [ 40.373115] lock(&team->lock); [ 40.373549] *** DEADLOCK *** [ 40.374432] May be due to missing lock nesting notation [ 40.375338] 2 locks held by ip/750: [ 40.375851] #0: ffffffffabcc42b0 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x466/0x8a0 [ 40.376927] #1: ffff888051201c40 (&team->lock){+.+.}, at: team_del_slave+0x29/0x60 [team] [ 40.377989] stack backtrace: [ 40.378650] CPU: 0 PID: 750 Comm: ip Not tainted 5.4.0-rc3+ #96 [ 40.379368] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 40.380574] Call Trace: [ 40.381208] dump_stack+0x7c/0xbb [ 40.381959] __lock_acquire+0x269d/0x3de0 [ 40.382817] ? register_lock_class+0x14d0/0x14d0 [ 40.383784] ? check_chain_key+0x236/0x5d0 [ 40.384518] lock_acquire+0x164/0x3b0 [ 40.385074] ? team_set_mac_address+0x151/0x290 [team] [ 40.385805] __mutex_lock+0x14d/0x14c0 [ 40.386371] ? team_set_mac_address+0x151/0x290 [team] [ 40.387038] ? team_set_mac_address+0x151/0x290 [team] [ 40.387632] ? mutex_lock_io_nested+0x1380/0x1380 [ 40.388245] ? team_del_slave+0x60/0x60 [team] [ 40.388752] ? rcu_read_lock_sched_held+0x90/0xc0 [ 40.389304] ? rcu_read_lock_bh_held+0xa0/0xa0 [ 40.389819] ? lock_acquire+0x164/0x3b0 [ 40.390285] ? lockdep_rtnl_is_held+0x16/0x20 [ 40.390797] ? team_port_get_rtnl+0x90/0xe0 [team] [ 40.391353] ? __module_text_address+0x13/0x140 [ 40.391886] ? team_set_mac_address+0x151/0x290 [team] [ 40.392547] team_set_mac_address+0x151/0x290 [team] [ 40.393111] dev_set_mac_address+0x1f0/0x3f0 [ ... ]
Unified · Split
| @@ -1615,7 +1615,6 @@ static int team_init(struct net_device *dev) · 1614 unmodified lines | ||
| 1615 | 1615 | int err; |
| 1616 | 1616 | |
| 1617 | 1617 | team->dev = dev; |
| 1618 | − mutex_init(&team->lock); | |
| 1619 | 1618 | team_set_no_mode(team); |
| 1620 | 1619 | |
| 1621 | 1620 | team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); |
| @@ -1642,6 +1641,9 @@ static int team_init(struct net_device *dev) · 20 unmodified lines | ||
| 1642 | 1641 | goto err_options_register; |
| 1643 | 1642 | netif_carrier_off(dev); |
| 1644 | 1643 | |
| 1644 | + lockdep_register_key(&team->team_lock_key); | |
| 1645 | + __mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key); | |
| 1646 | + | |
| 1645 | 1647 | return 0; |
| 1646 | 1648 | |
| 1647 | 1649 | err_options_register: |
| @@ -1671,6 +1673,7 @@ static void team_uninit(struct net_device *dev) · 23 unmodified lines | ||
| 1671 | 1673 | team_queue_override_fini(team); |
| 1672 | 1674 | mutex_unlock(&team->lock); |
| 1673 | 1675 | netdev_change_features(dev); |
| 1676 | + lockdep_unregister_key(&team->team_lock_key); | |
| 1674 | 1677 | } |
| 1675 | 1678 | |
| 1676 | 1679 | static void team_destructor(struct net_device *dev) |
| @@ -1974,8 +1977,15 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev) · 297 unmodified lines | ||
| 1974 | 1977 | err = team_port_del(team, port_dev); |
| 1975 | 1978 | mutex_unlock(&team->lock); |
| 1976 | 1979 | |
| 1977 | − if (!err) | |
| 1978 | − netdev_change_features(dev); | |
| 1980 | + if (err) | |
| 1981 | + return err; | |
| 1982 | + | |
| 1983 | + if (netif_is_team_master(port_dev)) { | |
| 1984 | + lockdep_unregister_key(&team->team_lock_key); | |
| 1985 | + lockdep_register_key(&team->team_lock_key); | |
| 1986 | + lockdep_set_class(&team->lock, &team->team_lock_key); | |
| 1987 | + } | |
| 1988 | + netdev_change_features(dev); | |
| 1979 | 1989 | |
| 1980 | 1990 | return err; |
| 1981 | 1991 | } |
| @@ -223,6 +223,7 @@ struct team { · 222 unmodified lines | ||
| 223 | 223 | atomic_t count_pending; |
| 224 | 224 | struct delayed_work dw; |
| 225 | 225 | } mcast_rejoin; |
| 226 | + struct lock_class_key team_lock_key; | |
| 226 | 227 | long mode_priv[TEAM_MODE_PRIV_LONGS]; |
| 227 | 228 | }; |
| 228 | 229 | |