tipc: wait and exit until all work queues are done

On some host, a crash could be triggered simply by repeating these
commands several times:

  # modprobe tipc
  # tipc bearer enable media udp name UDP1 localip 127.0.0.1
  # rmmod tipc

  [] BUG: unable to handle kernel paging request at ffffffffc096bb00
  [] Workqueue: events 0xffffffffc096bb00
  [] Call Trace:
  []  ? process_one_work+0x1a7/0x360
  []  ? worker_thread+0x30/0x390
  []  ? create_worker+0x1a0/0x1a0
  []  ? kthread+0x116/0x130
  []  ? kthread_flush_work_fn+0x10/0x10
  []  ? ret_from_fork+0x35/0x40

When removing the TIPC module, the UDP tunnel sock will be delayed to
release in a work queue as sock_release() can't be done in rtnl_lock().
If the work queue is schedule to run after the TIPC module is removed,
kernel will crash as the work queue function cleanup_beareri() code no
longer exists when trying to invoke it.

To fix it, this patch introduce a member wq_count in tipc_net to track
the numbers of work queues in schedule, and  wait and exit until all
work queues are done in tipc_exit_net().

Fixes: d0f91938be ("tipc: add ip/udp media type")
Reported-by: Shuang Li <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Xin Long 2021-05-17 02:28:58 +08:00 committed by David S. Miller
parent 020ef930b8
commit 04c26faa51
3 changed files with 6 additions and 0 deletions

View File

@ -119,6 +119,8 @@ static void __net_exit tipc_exit_net(struct net *net)
#ifdef CONFIG_TIPC_CRYPTO
tipc_crypto_stop(&tipc_net(net)->crypto_tx);
#endif
while (atomic_read(&tn->wq_count))
cond_resched();
}
static void __net_exit tipc_pernet_pre_exit(struct net *net)

View File

@ -149,6 +149,8 @@ struct tipc_net {
#endif
/* Work item for net finalize */
struct tipc_net_work final_work;
/* The numbers of work queues in schedule */
atomic_t wq_count;
};
static inline struct tipc_net *tipc_net(struct net *net)

View File

@ -814,6 +814,7 @@ static void cleanup_bearer(struct work_struct *work)
kfree_rcu(rcast, rcu);
}
atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count);
dst_cache_destroy(&ub->rcast.dst_cache);
udp_tunnel_sock_release(ub->ubsock);
synchronize_net();
@ -834,6 +835,7 @@ static void tipc_udp_disable(struct tipc_bearer *b)
RCU_INIT_POINTER(ub->bearer, NULL);
/* sock_release need to be done outside of rtnl lock */
atomic_inc(&tipc_net(sock_net(ub->ubsock->sk))->wq_count);
INIT_WORK(&ub->work, cleanup_bearer);
schedule_work(&ub->work);
}