[TCPv4]: Improve BH latency in /proc/net/tcp

Currently the code for /proc/net/tcp disable BH while iterating
over the entire established hash table. Even though we call
cond_resched_softirq for each entry, we still won't process
softirq's as regularly as we would otherwise do which results
in poor performance when the system is loaded near capacity.

This anomaly comes from the 2.4 code where this was all in a
single function and the local_bh_disable might have made sense
as a small optimisation.

The cost of each local_bh_disable is so small when compared
against the increased latency in keeping it disabled over a
large but mostly empty TCP established hash table that we
should just move it to the individual read_lock/read_unlock
calls as we do in inet_diag.

Signed-off-by: Herbert Xu <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

net/ipv4/tcp_ipv4.c

···
 		struct hlist_node *node;
 		struct inet_timewait_sock *tw;
 
-		/* We can reschedule _before_ having picked the target: */
-		cond_resched_softirq();
-
-		read_lock(&tcp_hashinfo.ehash[st->bucket].lock);
+		read_lock_bh(&tcp_hashinfo.ehash[st->bucket].lock);
 		sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
 			if (sk->sk_family != st->family) {
 				continue;
···
 			rc = tw;
 			goto out;
 		}
-		read_unlock(&tcp_hashinfo.ehash[st->bucket].lock);
+		read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock);
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 	}
 out:
···
 			cur = tw;
 			goto out;
 		}
-		read_unlock(&tcp_hashinfo.ehash[st->bucket].lock);
+		read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock);
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 
-		/* We can reschedule between buckets: */
-		cond_resched_softirq();
-
 		if (++st->bucket < tcp_hashinfo.ehash_size) {
-			read_lock(&tcp_hashinfo.ehash[st->bucket].lock);
+			read_lock_bh(&tcp_hashinfo.ehash[st->bucket].lock);
 			sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain);
 		} else {
 			cur = NULL;
···
 
 	if (!rc) {
 		inet_listen_unlock(&tcp_hashinfo);
-		local_bh_disable();
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		rc	  = established_get_idx(seq, pos);
 	}
···
 		rc = listening_get_next(seq, v);
 		if (!rc) {
 			inet_listen_unlock(&tcp_hashinfo);
-			local_bh_disable();
 			st->state = TCP_SEQ_STATE_ESTABLISHED;
 			rc	  = established_get_first(seq);
 		}
···
 	case TCP_SEQ_STATE_TIME_WAIT:
 	case TCP_SEQ_STATE_ESTABLISHED:
 		if (v)
-			read_unlock(&tcp_hashinfo.ehash[st->bucket].lock);
-		local_bh_enable();
+			read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock);
 		break;
 	}
 }