diff mbox series

[net] tipc: wait and exit until all work queues are done

Message ID 5db04a37335895e04e98bdf53aff3c8ecb6774db.1621189738.git.lucien.xin@gmail.com
State New
Headers show
Series [net] tipc: wait and exit until all work queues are done | expand

Commit Message

Xin Long May 16, 2021, 6:28 p.m. UTC
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: d0f91938bede ("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>
---
 net/tipc/core.c      | 2 ++
 net/tipc/core.h      | 2 ++
 net/tipc/udp_media.c | 2 ++
 3 files changed, 6 insertions(+)

Comments

patchwork-bot+netdevbpf@kernel.org May 17, 2021, 9:20 p.m. UTC | #1
Hello:

This patch was applied to netdev/net.git (refs/heads/master):

On Mon, 17 May 2021 02:28:58 +0800 you wrote:
> 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

> 

> [...]


Here is the summary with links:
  - [net] tipc: wait and exit until all work queues are done
    https://git.kernel.org/netdev/net/c/04c26faa51d1

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
diff mbox series

Patch

diff --git a/net/tipc/core.c b/net/tipc/core.c
index 5cc1f03..72f3ac7 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -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)
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 03de7b2..5741ae4 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -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)
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index e556d2c..c2bb818 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -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);
 }