leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

tcp: defer sacked assignment

Browse Source 
While chasing tcp_xmit_retransmit_queue() kasan issue, I found
that we could avoid reading sacked field of skb that we wont send,
possibly removing one cache line miss.

Very minor change in slow path, but why not ? ;)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet
2016-08-17 07:48:36 -07:00
committed by David S. Miller
parent 53e43f3905
commit dca0aaf847
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
net/ipv4/tcp_output.c
View File

@@ -2776,7 +2776,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk)); max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk));
tcp_for_write_queue_from(skb, sk) { tcp_for_write_queue_from(skb, sk) {
__u8 sacked = TCP_SKB_CB(skb)->sacked; __u8 sacked;
int segs; int segs;
if (skb == tcp_send_head(sk)) if (skb == tcp_send_head(sk))
@@ -2788,6 +2788,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
segs = tp->snd_cwnd - tcp_packets_in_flight(tp); segs = tp->snd_cwnd - tcp_packets_in_flight(tp);
if (segs <= 0) if (segs <= 0)
return; return;
sacked = TCP_SKB_CB(skb)->sacked;
/* In case tcp_shift_skb_data() have aggregated large skbs, /* In case tcp_shift_skb_data() have aggregated large skbs,
* we need to make sure not sending too bigs TSO packets * we need to make sure not sending too bigs TSO packets
*/ */