Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 86b3bfe9 authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller
Browse files

pkt_sched: fq: remove useless TIME_WAIT check 



TIME_WAIT sockets are not owning any skb.

ip_send_unicast_reply() and tcp_v6_send_response() both use
regular sockets.

We can safely remove a test in sch_fq and save one cache line miss,
as sk_state is far away from sk_pacing_rate.

Tested at Google for about one year.

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 2dbce096

net/sched/sch_fq.c

+2 −2
Original line number Diff line number Diff line 
/*

 * net/sched/sch_fq.c Fair Queue Packet Scheduler (per flow pacing)

 *

 *  Copyright (C) 2013 Eric Dumazet <edumazet@google.com>

 *  Copyright (C) 2013-2015 Eric Dumazet <edumazet@google.com>

 *

 *	This program is free software; you can redistribute it and/or

 *	modify it under the terms of the GNU General Public License
@@ -471,7 +471,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) 
		goto out;



	rate = q->flow_max_rate;

	if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT)

	if (skb->sk)

		rate = min(skb->sk->sk_pacing_rate, rate);



	if (rate != ~0U) {