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

tcp: fill shinfo->gso_type at last moment

Browse Source 
Our goal is to touch skb_shinfo(skb) only when absolutely needed,
to avoid two cache line misses in TCP output path for last skb
that is considered but not sent because of various conditions
(cwnd, tso defer, receiver window, TSQ...)

A packet is GSO only when skb_shinfo(skb)->gso_size is not zero.

We can set skb_shinfo(skb)->gso_type to sk->sk_gso_type even for
non GSO packets.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet
2015-06-11 09:15:16 -07:00
committed by David S. Miller
parent a7eea416cb
commit 51466a7545
2 changed files with 3 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
net/ipv4/tcp_output.c
View File

@@ -412,7 +412,6 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
tcp_skb_pcount_set(skb, 1);
shinfo->gso_size = 0;
shinfo->gso_type = 0;
TCP_SKB_CB(skb)->seq = seq;
if (flags & (TCPHDR_SYN | TCPHDR_FIN))
@@ -1003,6 +1002,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
}
tcp_options_write((__be32 *)(th + 1), tp, &opts);
skb_shinfo(skb)->gso_type = sk->sk_gso_type;
if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0))
tcp_ecn_send(sk, skb, tcp_header_size);
@@ -1080,11 +1080,9 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
*/
tcp_skb_pcount_set(skb, 1);
shinfo->gso_size = 0;
shinfo->gso_type = 0;
} else {
tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now));
shinfo->gso_size = mss_now;
shinfo->gso_type = sk->sk_gso_type;
}
}