From ab92d68fc22f9afab480153bd82a20f6e2533769 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:51 +0000 Subject: net: core: add generic lockdep keys Some interface types could be nested. (VLAN, BONDING, TEAM, MACSEC, MACVLAN, IPVLAN, VIRT_WIFI, VXLAN, etc..) These interface types should set lockdep class because, without lockdep class key, lockdep always warn about unexisting circular locking. In the current code, these interfaces have their own lockdep class keys and these manage itself. So that there are so many duplicate code around the /driver/net and /net/. This patch adds new generic lockdep keys and some helper functions for it. This patch does below changes. a) Add lockdep class keys in struct net_device - qdisc_running, xmit, addr_list, qdisc_busylock - these keys are used as dynamic lockdep key. b) When net_device is being allocated, lockdep keys are registered. - alloc_netdev_mqs() c) When net_device is being free'd llockdep keys are unregistered. - free_netdev() d) Add generic lockdep key helper function - netdev_register_lockdep_key() - netdev_unregister_lockdep_key() - netdev_update_lockdep_key() e) Remove unnecessary generic lockdep macro and functions f) Remove unnecessary lockdep code of each interfaces. After this patch, each interface modules don't need to maintain their lockdep keys. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/net/bonding') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 21d8fcc83c9c..ac1b09b56c77 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4769,7 +4769,6 @@ static int bond_init(struct net_device *bond_dev) return -ENOMEM; bond->nest_level = SINGLE_DEPTH_NESTING; - netdev_lockdep_set_classes(bond_dev); list_add_tail(&bond->bond_list, &bn->dev_list); -- cgit v1.2.3 From 65de65d9033750d2cf1b336c9d6e9da3a8b5cc6e Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:52 +0000 Subject: bonding: fix unexpected IFF_BONDING bit unset The IFF_BONDING means bonding master or bonding slave device. ->ndo_add_slave() sets IFF_BONDING flag and ->ndo_del_slave() unsets IFF_BONDING flag. bond0<--bond1 Both bond0 and bond1 are bonding device and these should keep having IFF_BONDING flag until they are removed. But bond1 would lose IFF_BONDING at ->ndo_del_slave() because that routine do not check whether the slave device is the bonding type or not. This patch adds the interface type check routine before removing IFF_BONDING flag. Test commands: ip link add bond0 type bond ip link add bond1 type bond ip link set bond1 master bond0 ip link set bond1 nomaster ip link del bond1 type bond ip link add bond1 type bond Splat looks like: [ 226.665555] proc_dir_entry 'bonding/bond1' already registered [ 226.666440] WARNING: CPU: 0 PID: 737 at fs/proc/generic.c:361 proc_register+0x2a9/0x3e0 [ 226.667571] Modules linked in: bonding af_packet sch_fq_codel ip_tables x_tables unix [ 226.668662] CPU: 0 PID: 737 Comm: ip Not tainted 5.4.0-rc3+ #96 [ 226.669508] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 226.670652] RIP: 0010:proc_register+0x2a9/0x3e0 [ 226.671612] Code: 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 39 01 00 00 48 8b 04 24 48 89 ea 48 c7 c7 a0 0b 14 9f 48 8b b0 e 0 00 00 00 e8 07 e7 88 ff <0f> 0b 48 c7 c7 40 2d a5 9f e8 59 d6 23 01 48 8b 4c 24 10 48 b8 00 [ 226.675007] RSP: 0018:ffff888050e17078 EFLAGS: 00010282 [ 226.675761] RAX: dffffc0000000008 RBX: ffff88805fdd0f10 RCX: ffffffff9dd344e2 [ 226.676757] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff88806c9f6b8c [ 226.677751] RBP: ffff8880507160f3 R08: ffffed100d940019 R09: ffffed100d940019 [ 226.678761] R10: 0000000000000001 R11: ffffed100d940018 R12: ffff888050716008 [ 226.679757] R13: ffff8880507160f2 R14: dffffc0000000000 R15: ffffed100a0e2c1e [ 226.680758] FS: 00007fdc217cc0c0(0000) GS:ffff88806c800000(0000) knlGS:0000000000000000 [ 226.681886] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 226.682719] CR2: 00007f49313424d0 CR3: 0000000050e46001 CR4: 00000000000606f0 [ 226.683727] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 226.684725] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 226.685681] Call Trace: [ 226.687089] proc_create_seq_private+0xb3/0xf0 [ 226.687778] bond_create_proc_entry+0x1b3/0x3f0 [bonding] [ 226.691458] bond_netdev_event+0x433/0x970 [bonding] [ 226.692139] ? __module_text_address+0x13/0x140 [ 226.692779] notifier_call_chain+0x90/0x160 [ 226.693401] register_netdevice+0x9b3/0xd80 [ 226.694010] ? alloc_netdev_mqs+0x854/0xc10 [ 226.694629] ? netdev_change_features+0xa0/0xa0 [ 226.695278] ? rtnl_create_link+0x2ed/0xad0 [ 226.695849] bond_newlink+0x2a/0x60 [bonding] [ 226.696422] __rtnl_newlink+0xb9f/0x11b0 [ 226.696968] ? rtnl_link_unregister+0x220/0x220 [ ... ] Fixes: 0b680e753724 ("[PATCH] bonding: Add priv_flag to avoid event mishandling") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/bonding') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ac1b09b56c77..92713b93f66f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1816,7 +1816,8 @@ err_detach: slave_disable_netpoll(new_slave); err_close: - slave_dev->priv_flags &= ~IFF_BONDING; + if (!netif_is_bond_master(slave_dev)) + slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_restore_mac: @@ -2017,7 +2018,8 @@ static int __bond_release_one(struct net_device *bond_dev, else dev_set_mtu(slave_dev, slave->original_mtu); - slave_dev->priv_flags &= ~IFF_BONDING; + if (!netif_is_bond_master(slave_dev)) + slave_dev->priv_flags &= ~IFF_BONDING; bond_free_slave(slave); -- cgit v1.2.3 From 089bca2caed0d0dea7da235ce1fe245808f5ec02 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:53 +0000 Subject: bonding: use dynamic lockdep key instead of subclass All bonding device has same lockdep key and subclass is initialized with nest_level. But actual nest_level value can be changed when a lower device is attached. And at this moment, the subclass should be updated but it seems to be unsafe. So this patch makes bonding use dynamic lockdep key instead of the subclass. Test commands: ip link add bond0 type bond for i in {1..5} do let A=$i-1 ip link add bond$i type bond ip link set bond$i master bond$A done ip link set bond5 master bond0 Splat looks like: [ 307.992912] WARNING: possible recursive locking detected [ 307.993656] 5.4.0-rc3+ #96 Tainted: G W [ 307.994367] -------------------------------------------- [ 307.995092] ip/761 is trying to acquire lock: [ 307.995710] ffff8880513aac60 (&(&bond->stats_lock)->rlock#2/2){+.+.}, at: bond_get_stats+0xb8/0x500 [bonding] [ 307.997045] but task is already holding lock: [ 307.997923] ffff88805fcbac60 (&(&bond->stats_lock)->rlock#2/2){+.+.}, at: bond_get_stats+0xb8/0x500 [bonding] [ 307.999215] other info that might help us debug this: [ 308.000251] Possible unsafe locking scenario: [ 308.001137] CPU0 [ 308.001533] ---- [ 308.001915] lock(&(&bond->stats_lock)->rlock#2/2); [ 308.002609] lock(&(&bond->stats_lock)->rlock#2/2); [ 308.003302] *** DEADLOCK *** [ 308.004310] May be due to missing lock nesting notation [ 308.005319] 3 locks held by ip/761: [ 308.005830] #0: ffffffff9fcc42b0 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x466/0x8a0 [ 308.006894] #1: ffff88805fcbac60 (&(&bond->stats_lock)->rlock#2/2){+.+.}, at: bond_get_stats+0xb8/0x500 [bonding] [ 308.008243] #2: ffffffff9f9219c0 (rcu_read_lock){....}, at: bond_get_stats+0x9f/0x500 [bonding] [ 308.009422] stack backtrace: [ 308.010124] CPU: 0 PID: 761 Comm: ip Tainted: G W 5.4.0-rc3+ #96 [ 308.011097] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 308.012179] Call Trace: [ 308.012601] dump_stack+0x7c/0xbb [ 308.013089] __lock_acquire+0x269d/0x3de0 [ 308.013669] ? register_lock_class+0x14d0/0x14d0 [ 308.014318] lock_acquire+0x164/0x3b0 [ 308.014858] ? bond_get_stats+0xb8/0x500 [bonding] [ 308.015520] _raw_spin_lock_nested+0x2e/0x60 [ 308.016129] ? bond_get_stats+0xb8/0x500 [bonding] [ 308.017215] bond_get_stats+0xb8/0x500 [bonding] [ 308.018454] ? bond_arp_rcv+0xf10/0xf10 [bonding] [ 308.019710] ? rcu_read_lock_held+0x90/0xa0 [ 308.020605] ? rcu_read_lock_sched_held+0xc0/0xc0 [ 308.021286] ? bond_get_stats+0x9f/0x500 [bonding] [ 308.021953] dev_get_stats+0x1ec/0x270 [ 308.022508] bond_get_stats+0x1d1/0x500 [bonding] Fixes: d3fff6c443fe ("net: add netdev_lockdep_set_classes() helper") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 10 +++++++--- include/net/bonding.h | 1 + 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'drivers/net/bonding') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 92713b93f66f..6a6273590288 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3459,7 +3459,7 @@ static void bond_get_stats(struct net_device *bond_dev, struct list_head *iter; struct slave *slave; - spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev)); + spin_lock(&bond->stats_lock); memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); @@ -4297,8 +4297,6 @@ void bond_setup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - spin_lock_init(&bond->mode_lock); - spin_lock_init(&bond->stats_lock); bond->params = bonding_defaults; /* Initialize pointers */ @@ -4367,6 +4365,7 @@ static void bond_uninit(struct net_device *bond_dev) list_del(&bond->bond_list); + lockdep_unregister_key(&bond->stats_lock_key); bond_debug_unregister(bond); } @@ -4772,6 +4771,11 @@ static int bond_init(struct net_device *bond_dev) bond->nest_level = SINGLE_DEPTH_NESTING; + spin_lock_init(&bond->mode_lock); + spin_lock_init(&bond->stats_lock); + lockdep_register_key(&bond->stats_lock_key); + lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key); + list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); diff --git a/include/net/bonding.h b/include/net/bonding.h index f7fe45689142..334909feb2bb 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -239,6 +239,7 @@ struct bonding { struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; + struct lock_class_key stats_lock_key; }; #define bond_slave_get_rcu(dev) \ -- cgit v1.2.3 From f3b0a18bb6cb07a9abb75e21b1f08eeaefa78e81 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:58 +0000 Subject: net: remove unnecessary variables and callback This patch removes variables and callback these are related to the nested device structure. devices that can be nested have their own nest_level variable that represents the depth of nested devices. In the previous patch, new {lower/upper}_level variables are added and they replace old private nest_level variable. So, this patch removes all 'nest_level' variables. In order to avoid lockdep warning, ->ndo_get_lock_subclass() was added to get lockdep subclass value, which is actually lower nested depth value. But now, they use the dynamic lockdep key to avoid lockdep warning instead of the subclass. So, this patch removes ->ndo_get_lock_subclass() callback. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_alb.c | 2 +- drivers/net/bonding/bond_main.c | 15 --------------- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/macsec.c | 9 --------- drivers/net/macvlan.c | 7 ------- include/linux/if_macvlan.h | 1 - include/linux/if_vlan.h | 11 ----------- include/linux/netdevice.h | 12 ------------ include/net/bonding.h | 1 - net/8021q/vlan.c | 1 - net/8021q/vlan_dev.c | 6 ------ net/core/dev.c | 19 ------------------- net/core/dev_addr_lists.c | 12 ++++++------ net/smc/smc_core.c | 2 +- net/smc/smc_pnet.c | 2 +- 15 files changed, 10 insertions(+), 92 deletions(-) (limited to 'drivers/net/bonding') diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 8c79bad2a9a5..4f2e6910c623 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -952,7 +952,7 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data) struct bond_vlan_tag *tags; if (is_vlan_dev(upper) && - bond->nest_level == vlan_get_encap_level(upper) - 1) { + bond->dev->lower_level == upper->lower_level - 1) { if (upper->addr_assign_type == NET_ADDR_STOLEN) { alb_send_lp_vid(slave, mac_addr, vlan_dev_vlan_proto(upper), diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 6a6273590288..a48950b81434 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1733,8 +1733,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_upper_unlink; } - bond->nest_level = dev_get_nest_level(bond_dev) + 1; - /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ @@ -1957,9 +1955,6 @@ static int __bond_release_one(struct net_device *bond_dev, if (!bond_has_slaves(bond)) { bond_set_carrier(bond); eth_hw_addr_random(bond_dev); - bond->nest_level = SINGLE_DEPTH_NESTING; - } else { - bond->nest_level = dev_get_nest_level(bond_dev) + 1; } unblock_netpoll_tx(); @@ -3444,13 +3439,6 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } -static int bond_get_nest_level(struct net_device *bond_dev) -{ - struct bonding *bond = netdev_priv(bond_dev); - - return bond->nest_level; -} - static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -4270,7 +4258,6 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, - .ndo_get_lock_subclass = bond_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, @@ -4769,8 +4756,6 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; - bond->nest_level = SINGLE_DEPTH_NESTING; - spin_lock_init(&bond->mode_lock); spin_lock_init(&bond->stats_lock); lockdep_register_key(&bond->stats_lock_key); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3e78a727f3e6..c4c59d2e676e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3160,7 +3160,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr, u32 *action) { - int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev); + int nest_level = attr->parse_attr->filter_dev->lower_level; struct flow_action_entry vlan_act = { .id = FLOW_ACTION_VLAN_POP, }; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9e97b66b26d3..afd8b2a08245 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -267,7 +267,6 @@ struct macsec_dev { struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; - unsigned int nest_level; }; /** @@ -2957,11 +2956,6 @@ static int macsec_get_iflink(const struct net_device *dev) return macsec_priv(dev)->real_dev->ifindex; } -static int macsec_get_nest_level(struct net_device *dev) -{ - return macsec_priv(dev)->nest_level; -} - static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, @@ -2975,7 +2969,6 @@ static const struct net_device_ops macsec_netdev_ops = { .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, - .ndo_get_lock_subclass = macsec_get_nest_level, }; static const struct device_type macsec_type = { @@ -3258,8 +3251,6 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (err < 0) return err; - macsec->nest_level = dev_get_nest_level(real_dev) + 1; - err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 0354e9be2ca5..34fc59bd1e20 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -867,11 +867,6 @@ 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 int macvlan_get_nest_level(struct net_device *dev) -{ - return ((struct macvlan_dev *)netdev_priv(dev))->nest_level; -} - static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -1149,7 +1144,6 @@ static const struct net_device_ops macvlan_netdev_ops = { .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, - .ndo_get_lock_subclass = macvlan_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macvlan_dev_poll_controller, .ndo_netpoll_setup = macvlan_dev_netpoll_setup, @@ -1433,7 +1427,6 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; - vlan->nest_level = dev_get_nest_level(lowerdev) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 2e55e4cdbd8a..a367ead4bf4b 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -29,7 +29,6 @@ struct macvlan_dev { netdev_features_t set_features; enum macvlan_mode mode; u16 flags; - int nest_level; unsigned int macaddr_count; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 244278d5c222..b05e855f1ddd 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -182,7 +182,6 @@ struct vlan_dev_priv { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif - unsigned int nest_level; }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) @@ -221,11 +220,6 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG_ON(!is_vlan_dev(dev)); - return vlan_dev_priv(dev)->nest_level; -} #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, @@ -295,11 +289,6 @@ static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG(); - return 0; -} #endif /** diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6c6490e15cd4..c20f190b4c18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1422,7 +1422,6 @@ struct net_device_ops { void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); @@ -4051,16 +4050,6 @@ 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) -{ - int subclass = SINGLE_DEPTH_NESTING; - - if (dev->netdev_ops->ndo_get_lock_subclass) - subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); - - spin_lock_nested(&dev->addr_list_lock, subclass); -} - static inline void netif_addr_lock_bh(struct net_device *dev) { spin_lock_bh(&dev->addr_list_lock); @@ -4345,7 +4334,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, diff --git a/include/net/bonding.h b/include/net/bonding.h index 334909feb2bb..1afc125014da 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -203,7 +203,6 @@ struct bonding { struct slave __rcu *primary_slave; struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ bool force_primary; - u32 nest_level; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 54728d2eda18..d4bcfd8f95bf 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -172,7 +172,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 6e6f26bf6e73..e5bff5cc6f97 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -489,11 +489,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } -static int vlan_dev_get_lock_subclass(struct net_device *dev) -{ - return vlan_dev_priv(dev)->nest_level; -} - static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .parse = eth_header_parse, @@ -785,7 +780,6 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, - .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, .ndo_get_iflink = vlan_dev_get_iflink, }; diff --git a/net/core/dev.c b/net/core/dev.c index 092c094038b6..1482e2ef2d25 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7615,25 +7615,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev) -{ - struct net_device *lower = NULL; - struct list_head *iter; - int max_nest = -1; - int nest; - - ASSERT_RTNL(); - - netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower); - if (max_nest < nest) - max_nest = nest; - } - - return max_nest + 1; -} -EXPORT_SYMBOL(dev_get_nest_level); - /** * netdev_lower_change - Dispatch event about lower device state change * @lower_dev: device diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 6393ba930097..2f949b5a1eb9 100644 --- a/net/core/dev_addr_lists.c +++ b/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_nested(to); + netif_addr_lock(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_nested(to); + netif_addr_lock(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_nested(to); + netif_addr_lock(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_nested(to); + netif_addr_lock(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_nested(to); + netif_addr_lock(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_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 88556f0251ab..2ba97ff325a5 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -561,7 +561,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) } rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index bab2da8cf17a..2920b006f65c 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -718,7 +718,7 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) int i, nest_lvl; rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; -- cgit v1.2.3 From ad9bd8daf2f9938572b0604e1280fefa8f338581 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Tue, 29 Oct 2019 09:12:32 +0000 Subject: bonding: fix using uninitialized mode_lock When a bonding interface is being created, it setups its mode and options. At that moment, it uses mode_lock so mode_lock should be initialized before that moment. rtnl_newlink() rtnl_create_link() alloc_netdev_mqs() ->setup() //bond_setup() ->newlink //bond_newlink bond_changelink() register_netdevice() ->ndo_init() //bond_init() After commit 089bca2caed0 ("bonding: use dynamic lockdep key instead of subclass"), mode_lock is initialized in bond_init(). So in the bond_changelink(), un-initialized mode_lock can be used. mode_lock should be initialized in bond_setup(). This patch partially reverts commit 089bca2caed0 ("bonding: use dynamic lockdep key instead of subclass") Test command: ip link add bond0 type bond mode 802.3ad lacp_rate 0 Splat looks like: [ 60.615127] INFO: trying to register non-static key. [ 60.615900] the code is fine but needs lockdep annotation. [ 60.616697] turning off the locking correctness validator. [ 60.617490] CPU: 1 PID: 957 Comm: ip Not tainted 5.4.0-rc3+ #109 [ 60.618350] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 60.619481] Call Trace: [ 60.619918] dump_stack+0x7c/0xbb [ 60.620453] register_lock_class+0x1215/0x14d0 [ 60.621131] ? alloc_netdev_mqs+0x7b3/0xcc0 [ 60.621771] ? is_bpf_text_address+0x86/0xf0 [ 60.622416] ? is_dynamic_key+0x230/0x230 [ 60.623032] ? unwind_get_return_address+0x5f/0xa0 [ 60.623757] ? create_prof_cpu_mask+0x20/0x20 [ 60.624408] ? arch_stack_walk+0x83/0xb0 [ 60.625023] __lock_acquire+0xd8/0x3de0 [ 60.625616] ? stack_trace_save+0x82/0xb0 [ 60.626225] ? stack_trace_consume_entry+0x160/0x160 [ 60.626957] ? deactivate_slab.isra.80+0x2c5/0x800 [ 60.627668] ? register_lock_class+0x14d0/0x14d0 [ 60.628380] ? alloc_netdev_mqs+0x7b3/0xcc0 [ 60.629020] ? save_stack+0x69/0x80 [ 60.629574] ? save_stack+0x19/0x80 [ 60.630121] ? __kasan_kmalloc.constprop.4+0xa0/0xd0 [ 60.630859] ? __kmalloc_node+0x16f/0x480 [ 60.631472] ? alloc_netdev_mqs+0x7b3/0xcc0 [ 60.632121] ? rtnl_create_link+0x2ed/0xad0 [ 60.634388] ? __rtnl_newlink+0xad4/0x11b0 [ 60.635024] lock_acquire+0x164/0x3b0 [ 60.635608] ? bond_3ad_update_lacp_rate+0x91/0x200 [bonding] [ 60.636463] _raw_spin_lock_bh+0x38/0x70 [ 60.637084] ? bond_3ad_update_lacp_rate+0x91/0x200 [bonding] [ 60.637930] bond_3ad_update_lacp_rate+0x91/0x200 [bonding] [ 60.638753] ? bond_3ad_lacpdu_recv+0xb30/0xb30 [bonding] [ 60.639552] ? bond_opt_get_val+0x180/0x180 [bonding] [ 60.640307] ? ___slab_alloc+0x5aa/0x610 [ 60.640925] bond_option_lacp_rate_set+0x71/0x140 [bonding] [ 60.641751] __bond_opt_set+0x1ff/0xbb0 [bonding] [ 60.643217] ? kasan_unpoison_shadow+0x30/0x40 [ 60.643924] bond_changelink+0x9a4/0x1700 [bonding] [ 60.644653] ? memset+0x1f/0x40 [ 60.742941] ? bond_slave_changelink+0x1a0/0x1a0 [bonding] [ 60.752694] ? alloc_netdev_mqs+0x8ea/0xcc0 [ 60.753330] ? rtnl_create_link+0x2ed/0xad0 [ 60.753964] bond_newlink+0x1e/0x60 [bonding] [ 60.754612] __rtnl_newlink+0xb9f/0x11b0 [ ... ] Reported-by: syzbot+8da67f407bcba2c72e6e@syzkaller.appspotmail.com Reported-by: syzbot+0d083911ab18b710da71@syzkaller.appspotmail.com Fixes: 089bca2caed0 ("bonding: use dynamic lockdep key instead of subclass") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/bonding') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a48950b81434..480f9459b402 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4284,6 +4284,7 @@ void bond_setup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + spin_lock_init(&bond->mode_lock); bond->params = bonding_defaults; /* Initialize pointers */ @@ -4756,7 +4757,6 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; - spin_lock_init(&bond->mode_lock); spin_lock_init(&bond->stats_lock); lockdep_register_key(&bond->stats_lock_key); lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key); -- cgit v1.2.3