diff mbox

[net] tcp: align tcp_xmit_size_goal() on tcp_tso_autosize()

Message ID 1425571386.5130.247.camel@edumazet-glaptop2.roam.corp.google.com
State Accepted, archived
Delegated to: David Miller
Headers show

Commit Message

Eric Dumazet March 5, 2015, 4:03 p.m. UTC 
From: Eric Dumazet <edumazet@google.com>

With some mss values, it is possible tcp_xmit_size_goal() puts
one segment more in TSO packet than tcp_tso_autosize().

We send then one TSO packet followed by one single MSS.

It is not a serious bug, but we can do slightly better, especially
for drivers using netif_set_gso_max_size() to lower gso_max_size.

Using same formula avoids these corner cases and makes
tcp_xmit_size_goal() a bit faster.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 605ad7f184b6 ("tcp: refine TSO autosizing")
---
 net/ipv4/tcp.c |   10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Neal Cardwell March 5, 2015, 4:13 p.m. UTC | #1 
On Thu, Mar 5, 2015 at 11:03 AM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> From: Eric Dumazet <edumazet@google.com>
>
> With some mss values, it is possible tcp_xmit_size_goal() puts
> one segment more in TSO packet than tcp_tso_autosize().
>
> We send then one TSO packet followed by one single MSS.
>
> It is not a serious bug, but we can do slightly better, especially
> for drivers using netif_set_gso_max_size() to lower gso_max_size.
>
> Using same formula avoids these corner cases and makes
> tcp_xmit_size_goal() a bit faster.
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Fixes: 605ad7f184b6 ("tcp: refine TSO autosizing")

Acked-by: Neal Cardwell <ncardwell@google.com>

neal
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
David Miller March 6, 2015, 3:31 a.m. UTC | #2 
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 05 Mar 2015 08:03:06 -0800

> From: Eric Dumazet <edumazet@google.com>
> 
> With some mss values, it is possible tcp_xmit_size_goal() puts
> one segment more in TSO packet than tcp_tso_autosize().
> 
> We send then one TSO packet followed by one single MSS.
> 
> It is not a serious bug, but we can do slightly better, especially
> for drivers using netif_set_gso_max_size() to lower gso_max_size.
> 
> Using same formula avoids these corner cases and makes
> tcp_xmit_size_goal() a bit faster.
> 
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Fixes: 605ad7f184b6 ("tcp: refine TSO autosizing")

Applied, thanks Eric.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9d72a0fcd928..995a2259bcfc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -835,17 +835,13 @@  static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 				       int large_allowed)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 new_size_goal, size_goal, hlen;
+	u32 new_size_goal, size_goal;
 
 	if (!large_allowed || !sk_can_gso(sk))
 		return mss_now;
 
-	/* Maybe we should/could use sk->sk_prot->max_header here ? */
-	hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
-	       inet_csk(sk)->icsk_ext_hdr_len +
-	       tp->tcp_header_len;
-
-	new_size_goal = sk->sk_gso_max_size - 1 - hlen;
+	/* Note : tcp_tso_autosize() will eventually split this later */
+	new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER;
 	new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
 
 	/* We try hard to avoid divides here */