4.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mahesh Bandewar <maheshb@xxxxxxxxxx>
[ Upstream commit d4859d749aa7090ffb743d15648adb962a1baeae ]
Syzkaller reported this on a slightly older kernel but it's still
applicable to the current kernel -
======================================================
WARNING: possible circular locking dependency detected
4.18.0-next-20180823+ #46 Not tainted
------------------------------------------------------
syz-executor4/26841 is trying to acquire lock:
00000000dd41ef48 ((wq_completion)bond_dev->name){+.+.}, at: flush_workqueue+0x2db/0x1e10 kernel/workqueue.c:2652
but task is already holding lock:
00000000768ab431 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:77 [inline]
00000000768ab431 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x412/0xc30 net/core/rtnetlink.c:4708
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (rtnl_mutex){+.+.}:
__mutex_lock_common kernel/locking/mutex.c:925 [inline]
__mutex_lock+0x171/0x1700 kernel/locking/mutex.c:1073
mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:1088
rtnl_lock+0x17/0x20 net/core/rtnetlink.c:77
bond_netdev_notify drivers/net/bonding/bond_main.c:1310 [inline]
bond_netdev_notify_work+0x44/0xd0 drivers/net/bonding/bond_main.c:1320
process_one_work+0xc73/0x1aa0 kernel/workqueue.c:2153
worker_thread+0x189/0x13c0 kernel/workqueue.c:2296
kthread+0x35a/0x420 kernel/kthread.c:246
ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:415
-> #1 ((work_completion)(&(&nnw->work)->work)){+.+.}:
process_one_work+0xc0b/0x1aa0 kernel/workqueue.c:2129
worker_thread+0x189/0x13c0 kernel/workqueue.c:2296
kthread+0x35a/0x420 kernel/kthread.c:246
ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:415
-> #0 ((wq_completion)bond_dev->name){+.+.}:
lock_acquire+0x1e4/0x4f0 kernel/locking/lockdep.c:3901
flush_workqueue+0x30a/0x1e10 kernel/workqueue.c:2655
drain_workqueue+0x2a9/0x640 kernel/workqueue.c:2820
destroy_workqueue+0xc6/0x9d0 kernel/workqueue.c:4155
__alloc_workqueue_key+0xef9/0x1190 kernel/workqueue.c:4138
bond_init+0x269/0x940 drivers/net/bonding/bond_main.c:4734
register_netdevice+0x337/0x1100 net/core/dev.c:8410
bond_newlink+0x49/0xa0 drivers/net/bonding/bond_netlink.c:453
rtnl_newlink+0xef4/0x1d50 net/core/rtnetlink.c:3099
rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4711
netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2454
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4729
netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline]
netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343
netlink_sendmsg+0xa18/0xfc0 net/netlink/af_netlink.c:1908
sock_sendmsg_nosec net/socket.c:622 [inline]
sock_sendmsg+0xd5/0x120 net/socket.c:632
___sys_sendmsg+0x7fd/0x930 net/socket.c:2115
__sys_sendmsg+0x11d/0x290 net/socket.c:2153
__do_sys_sendmsg net/socket.c:2162 [inline]
__se_sys_sendmsg net/socket.c:2160 [inline]
__x64_sys_sendmsg+0x78/0xb0 net/socket.c:2160
do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
other info that might help us debug this:
Chain exists of:
(wq_completion)bond_dev->name --> (work_completion)(&(&nnw->work)->work) --> rtnl_mutex
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(rtnl_mutex);
lock((work_completion)(&(&nnw->work)->work));
lock(rtnl_mutex);
lock((wq_completion)bond_dev->name);
*** DEADLOCK ***
1 lock held by syz-executor4/26841:
stack backtrace:
CPU: 1 PID: 26841 Comm: syz-executor4 Not tainted 4.18.0-next-20180823+ #46
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
print_circular_bug.isra.34.cold.55+0x1bd/0x27d kernel/locking/lockdep.c:1222
check_prev_add kernel/locking/lockdep.c:1862 [inline]
check_prevs_add kernel/locking/lockdep.c:1975 [inline]
validate_chain kernel/locking/lockdep.c:2416 [inline]
__lock_acquire+0x3449/0x5020 kernel/locking/lockdep.c:3412
lock_acquire+0x1e4/0x4f0 kernel/locking/lockdep.c:3901
flush_workqueue+0x30a/0x1e10 kernel/workqueue.c:2655
drain_workqueue+0x2a9/0x640 kernel/workqueue.c:2820
destroy_workqueue+0xc6/0x9d0 kernel/workqueue.c:4155
__alloc_workqueue_key+0xef9/0x1190 kernel/workqueue.c:4138
bond_init+0x269/0x940 drivers/net/bonding/bond_main.c:4734
register_netdevice+0x337/0x1100 net/core/dev.c:8410
bond_newlink+0x49/0xa0 drivers/net/bonding/bond_netlink.c:453
rtnl_newlink+0xef4/0x1d50 net/core/rtnetlink.c:3099
rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4711
netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2454
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4729
netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline]
netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343
netlink_sendmsg+0xa18/0xfc0 net/netlink/af_netlink.c:1908
sock_sendmsg_nosec net/socket.c:622 [inline]
sock_sendmsg+0xd5/0x120 net/socket.c:632
___sys_sendmsg+0x7fd/0x930 net/socket.c:2115
__sys_sendmsg+0x11d/0x290 net/socket.c:2153
__do_sys_sendmsg net/socket.c:2162 [inline]
__se_sys_sendmsg net/socket.c:2160 [inline]
__x64_sys_sendmsg+0x78/0xb0 net/socket.c:2160
do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457089
Code: fd b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f2df20a5c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f2df20a66d4 RCX: 0000000000457089
RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003
RBP: 0000000000930140 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000004d40b8 R14: 00000000004c8ad8 R15: 0000000000000001
Signed-off-by: Mahesh Bandewar <maheshb@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/net/bonding/bond_main.c | 43 +++++++++++++++-------------------------
include/net/bonding.h | 7 ------
2 files changed, 18 insertions(+), 32 deletions(-)
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -210,6 +210,7 @@ static void bond_get_stats(struct net_de
static void bond_slave_arr_handler(struct work_struct *work);
static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
int mod);
+static void bond_netdev_notify_work(struct work_struct *work);
/*---------------------------- General routines -----------------------------*/
@@ -1276,6 +1277,8 @@ static struct slave *bond_alloc_slave(st
return NULL;
}
}
+ INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work);
+
return slave;
}
@@ -1283,6 +1286,7 @@ static void bond_free_slave(struct slave
{
struct bonding *bond = bond_get_bond_by_slave(slave);
+ cancel_delayed_work_sync(&slave->notify_work);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
kfree(SLAVE_AD_INFO(slave));
@@ -1304,39 +1308,26 @@ static void bond_fill_ifslave(struct sla
info->link_failure_count = slave->link_failure_count;
}
-static void bond_netdev_notify(struct net_device *dev,
- struct netdev_bonding_info *info)
-{
- rtnl_lock();
- netdev_bonding_info_change(dev, info);
- rtnl_unlock();
-}
-
static void bond_netdev_notify_work(struct work_struct *_work)
{
- struct netdev_notify_work *w =
- container_of(_work, struct netdev_notify_work, work.work);
+ struct slave *slave = container_of(_work, struct slave,
+ notify_work.work);
+
+ if (rtnl_trylock()) {
+ struct netdev_bonding_info binfo;
- bond_netdev_notify(w->dev, &w->bonding_info);
- dev_put(w->dev);
- kfree(w);
+ bond_fill_ifslave(slave, &binfo.slave);
+ bond_fill_ifbond(slave->bond, &binfo.master);
+ netdev_bonding_info_change(slave->dev, &binfo);
+ rtnl_unlock();
+ } else {
+ queue_delayed_work(slave->bond->wq, &slave->notify_work, 1);
+ }
}
void bond_queue_slave_event(struct slave *slave)
{
- struct bonding *bond = slave->bond;
- struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC);
-
- if (!nnw)
- return;
-
- dev_hold(slave->dev);
- nnw->dev = slave->dev;
- bond_fill_ifslave(slave, &nnw->bonding_info.slave);
- bond_fill_ifbond(bond, &nnw->bonding_info.master);
- INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work);
-
- queue_delayed_work(slave->bond->wq, &nnw->work, 0);
+ queue_delayed_work(slave->bond->wq, &slave->notify_work, 0);
}
void bond_lower_state_changed(struct slave *slave)
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -139,12 +139,6 @@ struct bond_parm_tbl {
int mode;
};
-struct netdev_notify_work {
- struct delayed_work work;
- struct net_device *dev;
- struct netdev_bonding_info bonding_info;
-};
-
struct slave {
struct net_device *dev; /* first - useful for panic debug */
struct bonding *bond; /* our master */
@@ -172,6 +166,7 @@ struct slave {
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *np;
#endif
+ struct delayed_work notify_work;
struct kobject kobj;
struct rtnl_link_stats64 slave_stats;
};
