[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 <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 5 insertions, 14 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 354721d67f6..3f5f7423b95 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2045,10 +2045,7 @@ static void *established_get_first(struct seq_file *seq)
 		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;
@@ -2065,7 +2062,7 @@ static void *established_get_first(struct seq_file *seq)
 			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:
@@ -2092,14 +2089,11 @@ get_tw:
 			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;
@@ -2144,7 +2138,6 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
 
 	if (!rc) {
 		inet_listen_unlock(&tcp_hashinfo);
-		local_bh_disable();
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		rc	  = established_get_idx(seq, pos);
 	}
@@ -2177,7 +2170,6 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *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);
 		}
@@ -2209,8 +2201,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 	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;
 	}
 }