From 064ff66e2bef84f1153087612032b5b9eab005bd Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sat, 15 Feb 2020 10:50:08 +0000 Subject: bonding: add missing netdev_update_lockdep_key() After bond_release(), netdev_update_lockdep_key() should be called. But both ioctl path and attribute path don't call netdev_update_lockdep_key(). This patch adds missing netdev_update_lockdep_key(). Test commands: ip link add bond0 type bond ip link add bond1 type bond ifenslave bond0 bond1 ifenslave -d bond0 bond1 ifenslave bond1 bond0 Splat looks like: [ 29.501182][ T1046] WARNING: possible circular locking dependency detected [ 29.501945][ T1039] hardirqs last disabled at (1962): [] handle_mm_fault+0x13f/0x700 [ 29.503442][ T1046] 5.5.0+ #322 Not tainted [ 29.503447][ T1046] ------------------------------------------------------ [ 29.504277][ T1039] softirqs last enabled at (1180): [] __do_softirq+0x678/0x981 [ 29.505443][ T1046] ifenslave/1046 is trying to acquire lock: [ 29.505886][ T1039] softirqs last disabled at (1169): [] irq_exit+0x17a/0x1a0 [ 29.509997][ T1046] ffff88805d5da280 (&dev->addr_list_lock_key#3){+...}, at: dev_mc_sync_multiple+0x95/0x120 [ 29.511243][ T1046] [ 29.511243][ T1046] but task is already holding lock: [ 29.512192][ T1046] ffff8880460f2280 (&dev->addr_list_lock_key#4){+...}, at: bond_enslave+0x4482/0x47b0 [bonding] [ 29.514124][ T1046] [ 29.514124][ T1046] which lock already depends on the new lock. [ 29.514124][ T1046] [ 29.517297][ T1046] [ 29.517297][ T1046] the existing dependency chain (in reverse order) is: [ 29.518231][ T1046] [ 29.518231][ T1046] -> #1 (&dev->addr_list_lock_key#4){+...}: [ 29.519076][ T1046] _raw_spin_lock+0x30/0x70 [ 29.519588][ T1046] dev_mc_sync_multiple+0x95/0x120 [ 29.520208][ T1046] bond_enslave+0x448d/0x47b0 [bonding] [ 29.520862][ T1046] bond_option_slaves_set+0x1a3/0x370 [bonding] [ 29.521640][ T1046] __bond_opt_set+0x1ff/0xbb0 [bonding] [ 29.522438][ T1046] __bond_opt_set_notify+0x2b/0xf0 [bonding] [ 29.523251][ T1046] bond_opt_tryset_rtnl+0x92/0xf0 [bonding] [ 29.524082][ T1046] bonding_sysfs_store_option+0x8a/0xf0 [bonding] [ 29.524959][ T1046] kernfs_fop_write+0x276/0x410 [ 29.525620][ T1046] vfs_write+0x197/0x4a0 [ 29.526218][ T1046] ksys_write+0x141/0x1d0 [ 29.526818][ T1046] do_syscall_64+0x99/0x4f0 [ 29.527430][ T1046] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 29.528265][ T1046] [ 29.528265][ T1046] -> #0 (&dev->addr_list_lock_key#3){+...}: [ 29.529272][ T1046] __lock_acquire+0x2d8d/0x3de0 [ 29.529935][ T1046] lock_acquire+0x164/0x3b0 [ 29.530638][ T1046] _raw_spin_lock+0x30/0x70 [ 29.531187][ T1046] dev_mc_sync_multiple+0x95/0x120 [ 29.531790][ T1046] bond_enslave+0x448d/0x47b0 [bonding] [ 29.532451][ T1046] bond_option_slaves_set+0x1a3/0x370 [bonding] [ 29.533163][ T1046] __bond_opt_set+0x1ff/0xbb0 [bonding] [ 29.533789][ T1046] __bond_opt_set_notify+0x2b/0xf0 [bonding] [ 29.534595][ T1046] bond_opt_tryset_rtnl+0x92/0xf0 [bonding] [ 29.535500][ T1046] bonding_sysfs_store_option+0x8a/0xf0 [bonding] [ 29.536379][ T1046] kernfs_fop_write+0x276/0x410 [ 29.537057][ T1046] vfs_write+0x197/0x4a0 [ 29.537640][ T1046] ksys_write+0x141/0x1d0 [ 29.538251][ T1046] do_syscall_64+0x99/0x4f0 [ 29.538870][ T1046] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 29.539659][ T1046] [ 29.539659][ T1046] other info that might help us debug this: [ 29.539659][ T1046] [ 29.540953][ T1046] Possible unsafe locking scenario: [ 29.540953][ T1046] [ 29.541883][ T1046] CPU0 CPU1 [ 29.542540][ T1046] ---- ---- [ 29.543209][ T1046] lock(&dev->addr_list_lock_key#4); [ 29.543880][ T1046] lock(&dev->addr_list_lock_key#3); [ 29.544873][ T1046] lock(&dev->addr_list_lock_key#4); [ 29.545863][ T1046] lock(&dev->addr_list_lock_key#3); [ 29.546525][ T1046] [ 29.546525][ T1046] *** DEADLOCK *** [ 29.546525][ T1046] [ 29.547542][ T1046] 5 locks held by ifenslave/1046: [ 29.548196][ T1046] #0: ffff88806044c478 (sb_writers#5){.+.+}, at: vfs_write+0x3bb/0x4a0 [ 29.549248][ T1046] #1: ffff88805af00890 (&of->mutex){+.+.}, at: kernfs_fop_write+0x1cf/0x410 [ 29.550343][ T1046] #2: ffff88805b8b54b0 (kn->count#157){.+.+}, at: kernfs_fop_write+0x1f2/0x410 [ 29.551575][ T1046] #3: ffffffffaecf4cf0 (rtnl_mutex){+.+.}, at: bond_opt_tryset_rtnl+0x5f/0xf0 [bonding] [ 29.552819][ T1046] #4: ffff8880460f2280 (&dev->addr_list_lock_key#4){+...}, at: bond_enslave+0x4482/0x47b0 [bonding] [ 29.554175][ T1046] [ 29.554175][ T1046] stack backtrace: [ 29.554907][ T1046] CPU: 0 PID: 1046 Comm: ifenslave Not tainted 5.5.0+ #322 [ 29.555854][ T1046] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 29.557064][ T1046] Call Trace: [ 29.557504][ T1046] dump_stack+0x96/0xdb [ 29.558054][ T1046] check_noncircular+0x371/0x450 [ 29.558723][ T1046] ? print_circular_bug.isra.35+0x310/0x310 [ 29.559486][ T1046] ? hlock_class+0x130/0x130 [ 29.560100][ T1046] ? __lock_acquire+0x2d8d/0x3de0 [ 29.560761][ T1046] __lock_acquire+0x2d8d/0x3de0 [ 29.561366][ T1046] ? register_lock_class+0x14d0/0x14d0 [ 29.562045][ T1046] ? find_held_lock+0x39/0x1d0 [ 29.562641][ T1046] lock_acquire+0x164/0x3b0 [ 29.563199][ T1046] ? dev_mc_sync_multiple+0x95/0x120 [ 29.563872][ T1046] _raw_spin_lock+0x30/0x70 [ 29.564464][ T1046] ? dev_mc_sync_multiple+0x95/0x120 [ 29.565146][ T1046] dev_mc_sync_multiple+0x95/0x120 [ 29.565793][ T1046] bond_enslave+0x448d/0x47b0 [bonding] [ 29.566487][ T1046] ? bond_update_slave_arr+0x940/0x940 [bonding] [ 29.567279][ T1046] ? bstr_printf+0xc20/0xc20 [ 29.567857][ T1046] ? stack_trace_consume_entry+0x160/0x160 [ 29.568614][ T1046] ? deactivate_slab.isra.77+0x2c5/0x800 [ 29.569320][ T1046] ? check_chain_key+0x236/0x5d0 [ 29.569939][ T1046] ? sscanf+0x93/0xc0 [ 29.570442][ T1046] ? vsscanf+0x1e20/0x1e20 [ 29.571003][ T1046] bond_option_slaves_set+0x1a3/0x370 [bonding] [ ... ] Fixes: ab92d68fc22f ("net: core: add generic lockdep keys") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 ++ drivers/net/bonding/bond_options.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'drivers/net/bonding') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 48d5ec770b94..1e9d5d35fc78 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3640,6 +3640,8 @@ 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: diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index ddb3916d3506..215c10923289 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1398,6 +1398,8 @@ 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: -- cgit v1.2.3-59-g8ed1b From b3e80d44f5b1b470dd9e2dbc6816e63a5c519709 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sat, 15 Feb 2020 10:50:40 +0000 Subject: bonding: fix lockdep warning in bond_get_stats() In the "struct bonding", there is stats_lock. This lock protects "bond_stats" in the "struct bonding". bond_stats is updated in the bond_get_stats() and this function would be executed concurrently. So, the lock is needed. Bonding interfaces would be nested. So, either stats_lock should use dynamic lockdep class key or stats_lock should be used by spin_lock_nested(). In the current code, stats_lock is using a dynamic lockdep class key. But there is no updating stats_lock_key routine So, lockdep warning will occur. Test commands: ip link add bond0 type bond ip link add bond1 type bond ip link set bond0 master bond1 ip link set bond0 nomaster ip link set bond1 master bond0 Splat looks like: [ 38.420603][ T957] 5.5.0+ #394 Not tainted [ 38.421074][ T957] ------------------------------------------------------ [ 38.421837][ T957] ip/957 is trying to acquire lock: [ 38.422399][ T957] ffff888063262cd8 (&bond->stats_lock_key#2){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding] [ 38.423528][ T957] [ 38.423528][ T957] but task is already holding lock: [ 38.424526][ T957] ffff888065fd2cd8 (&bond->stats_lock_key){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding] [ 38.426075][ T957] [ 38.426075][ T957] which lock already depends on the new lock. [ 38.426075][ T957] [ 38.428536][ T957] [ 38.428536][ T957] the existing dependency chain (in reverse order) is: [ 38.429475][ T957] [ 38.429475][ T957] -> #1 (&bond->stats_lock_key){+.+.}: [ 38.430273][ T957] _raw_spin_lock+0x30/0x70 [ 38.430812][ T957] bond_get_stats+0x90/0x4d0 [bonding] [ 38.431451][ T957] dev_get_stats+0x1ec/0x270 [ 38.432088][ T957] bond_get_stats+0x1a5/0x4d0 [bonding] [ 38.432767][ T957] dev_get_stats+0x1ec/0x270 [ 38.433322][ T957] rtnl_fill_stats+0x44/0xbe0 [ 38.433866][ T957] rtnl_fill_ifinfo+0xeb2/0x3720 [ 38.434474][ T957] rtmsg_ifinfo_build_skb+0xca/0x170 [ 38.435081][ T957] rtmsg_ifinfo_event.part.33+0x1b/0xb0 [ 38.436848][ T957] rtnetlink_event+0xcd/0x120 [ 38.437455][ T957] notifier_call_chain+0x90/0x160 [ 38.438067][ T957] netdev_change_features+0x74/0xa0 [ 38.438708][ T957] bond_compute_features.isra.45+0x4e6/0x6f0 [bonding] [ 38.439522][ T957] bond_enslave+0x3639/0x47b0 [bonding] [ 38.440225][ T957] do_setlink+0xaab/0x2ef0 [ 38.440786][ T957] __rtnl_newlink+0x9c5/0x1270 [ 38.441463][ T957] rtnl_newlink+0x65/0x90 [ 38.442075][ T957] rtnetlink_rcv_msg+0x4a8/0x890 [ 38.442774][ T957] netlink_rcv_skb+0x121/0x350 [ 38.443451][ T957] netlink_unicast+0x42e/0x610 [ 38.444282][ T957] netlink_sendmsg+0x65a/0xb90 [ 38.444992][ T957] ____sys_sendmsg+0x5ce/0x7a0 [ 38.445679][ T957] ___sys_sendmsg+0x10f/0x1b0 [ 38.446365][ T957] __sys_sendmsg+0xc6/0x150 [ 38.447007][ T957] do_syscall_64+0x99/0x4f0 [ 38.447668][ T957] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 38.448538][ T957] [ 38.448538][ T957] -> #0 (&bond->stats_lock_key#2){+.+.}: [ 38.449554][ T957] __lock_acquire+0x2d8d/0x3de0 [ 38.450148][ T957] lock_acquire+0x164/0x3b0 [ 38.450711][ T957] _raw_spin_lock+0x30/0x70 [ 38.451292][ T957] bond_get_stats+0x90/0x4d0 [bonding] [ 38.451950][ T957] dev_get_stats+0x1ec/0x270 [ 38.452425][ T957] bond_get_stats+0x1a5/0x4d0 [bonding] [ 38.453362][ T957] dev_get_stats+0x1ec/0x270 [ 38.453825][ T957] rtnl_fill_stats+0x44/0xbe0 [ 38.454390][ T957] rtnl_fill_ifinfo+0xeb2/0x3720 [ 38.456257][ T957] rtmsg_ifinfo_build_skb+0xca/0x170 [ 38.456998][ T957] rtmsg_ifinfo_event.part.33+0x1b/0xb0 [ 38.459351][ T957] rtnetlink_event+0xcd/0x120 [ 38.460086][ T957] notifier_call_chain+0x90/0x160 [ 38.460829][ T957] netdev_change_features+0x74/0xa0 [ 38.461752][ T957] bond_compute_features.isra.45+0x4e6/0x6f0 [bonding] [ 38.462705][ T957] bond_enslave+0x3639/0x47b0 [bonding] [ 38.463476][ T957] do_setlink+0xaab/0x2ef0 [ 38.464141][ T957] __rtnl_newlink+0x9c5/0x1270 [ 38.464897][ T957] rtnl_newlink+0x65/0x90 [ 38.465522][ T957] rtnetlink_rcv_msg+0x4a8/0x890 [ 38.466215][ T957] netlink_rcv_skb+0x121/0x350 [ 38.466895][ T957] netlink_unicast+0x42e/0x610 [ 38.467583][ T957] netlink_sendmsg+0x65a/0xb90 [ 38.468285][ T957] ____sys_sendmsg+0x5ce/0x7a0 [ 38.469202][ T957] ___sys_sendmsg+0x10f/0x1b0 [ 38.469884][ T957] __sys_sendmsg+0xc6/0x150 [ 38.470587][ T957] do_syscall_64+0x99/0x4f0 [ 38.471245][ T957] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 38.472093][ T957] [ 38.472093][ T957] other info that might help us debug this: [ 38.472093][ T957] [ 38.473438][ T957] Possible unsafe locking scenario: [ 38.473438][ T957] [ 38.474898][ T957] CPU0 CPU1 [ 38.476234][ T957] ---- ---- [ 38.480171][ T957] lock(&bond->stats_lock_key); [ 38.480808][ T957] lock(&bond->stats_lock_key#2); [ 38.481791][ T957] lock(&bond->stats_lock_key); [ 38.482754][ T957] lock(&bond->stats_lock_key#2); [ 38.483416][ T957] [ 38.483416][ T957] *** DEADLOCK *** [ 38.483416][ T957] [ 38.484505][ T957] 3 locks held by ip/957: [ 38.485048][ T957] #0: ffffffffbccf6230 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x457/0x890 [ 38.486198][ T957] #1: ffff888065fd2cd8 (&bond->stats_lock_key){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding] [ 38.487625][ T957] #2: ffffffffbc9254c0 (rcu_read_lock){....}, at: bond_get_stats+0x5/0x4d0 [bonding] [ 38.488897][ T957] [ 38.488897][ T957] stack backtrace: [ 38.489646][ T957] CPU: 1 PID: 957 Comm: ip Not tainted 5.5.0+ #394 [ 38.490497][ T957] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 38.492810][ T957] Call Trace: [ 38.493219][ T957] dump_stack+0x96/0xdb [ 38.493709][ T957] check_noncircular+0x371/0x450 [ 38.494344][ T957] ? lookup_address+0x60/0x60 [ 38.494923][ T957] ? print_circular_bug.isra.35+0x310/0x310 [ 38.495699][ T957] ? hlock_class+0x130/0x130 [ 38.496334][ T957] ? __lock_acquire+0x2d8d/0x3de0 [ 38.496979][ T957] __lock_acquire+0x2d8d/0x3de0 [ 38.497607][ T957] ? register_lock_class+0x14d0/0x14d0 [ 38.498333][ T957] ? check_chain_key+0x236/0x5d0 [ 38.499003][ T957] lock_acquire+0x164/0x3b0 [ 38.499800][ T957] ? bond_get_stats+0x90/0x4d0 [bonding] [ 38.500706][ T957] _raw_spin_lock+0x30/0x70 [ 38.501435][ T957] ? bond_get_stats+0x90/0x4d0 [bonding] [ 38.502311][ T957] bond_get_stats+0x90/0x4d0 [bonding] [ ... ] But, there is another problem. The dynamic lockdep class key is protected by RTNL, but bond_get_stats() would be called outside of RTNL. So, it would use an invalid dynamic lockdep class key. In order to fix this issue, stats_lock uses spin_lock_nested() instead of a dynamic lockdep key. The bond_get_stats() calls bond_get_lowest_level_rcu() to get the correct nest level value, which will be used by spin_lock_nested(). The "dev->lower_level" indicates lower nest level value, but this value is invalid outside of RTNL. So, bond_get_lowest_level_rcu() returns valid lower nest level value in the RCU critical section. bond_get_lowest_level_rcu() will be work only when LOCKDEP is enabled. 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 | 53 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 50 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 1e9d5d35fc78..d10805e5e623 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3526,6 +3526,47 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +#ifdef CONFIG_LOCKDEP +static int bond_get_lowest_level_rcu(struct net_device *dev) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int cur = 0, max = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + if (max <= cur) + max = cur; + break; + } + + if (!next) { + if (!cur) + return max; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return max; +} +#endif + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3533,11 +3574,17 @@ static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; + int nest_level = 0; - spin_lock(&bond->stats_lock); - memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); +#ifdef CONFIG_LOCKDEP + nest_level = bond_get_lowest_level_rcu(bond_dev); +#endif + + spin_lock_nested(&bond->stats_lock, nest_level); + memcpy(stats, &bond->bond_stats, sizeof(*stats)); + bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); @@ -3547,10 +3594,10 @@ static void bond_get_stats(struct net_device *bond_dev, /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } - rcu_read_unlock(); memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); + rcu_read_unlock(); } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) -- cgit v1.2.3-59-g8ed1b