On 2016-08-31 12:15:53 [-0400], Steven Rostedt wrote: > > @@ -689,10 +691,13 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) > > offsetof(struct inet_timewait_sock, tw_bound_dev_if)); > > > > arg.tos = ip_hdr(skb)->tos; > > + > > + local_lock(tcp_sk_lock); > > Interesting that I noticed in mainline, they have: > > local_bh_disable(); > > here. > > I'm surprised we don't have a local_lock_bh() or something to that > effect. Turning local_bh_disable() into local_lock_bh(). One side effect would be that the network driver will be flushed out / waited for completion during socket write (due to the spin_lock_bh()). Not sure how much fun all this will bring. We could try this… > -- Steve Sebastian -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
