Commit 6a6b83ca authored by Kangmin Park's avatar Kangmin Park Committed by David S. Miller
Browse files

mpls: defer ttl decrement in mpls_forward() 



Defer ttl decrement to optimize in tx_err case. There is no need
to decrease ttl in the case of goto tx_err.

Signed-off-by: default avatarKangmin Park <l4stpr0gr4m@gmail.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 8cc236db

net/mpls/af_mpls.c

+1 −1
Original line number Diff line number Diff line
@@ -407,7 +407,6 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, 
	/* Verify ttl is valid */

	if (dec.ttl <= 1)

		goto err;

	dec.ttl -= 1;



	/* Find the output device */

	out_dev = rcu_dereference(nh->nh_dev);
@@ -431,6 +430,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, 
	skb->dev = out_dev;

	skb->protocol = htons(ETH_P_MPLS_UC);



	dec.ttl -= 1;

	if (unlikely(!new_header_size && dec.bos)) {

		/* Penultimate hop popping */

		if (!mpls_egress(dev_net(out_dev), rt, skb, dec))