[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 1 Feb 2016 21:03:08 -0800
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>
Cc: netdev <netdev@...r.kernel.org>,
Eric Dumazet <edumazet@...gle.com>,
Sara Dickinson <sara@...odun.com>,
Yuchung Cheng <ycheng@...gle.com>,
Neal Cardwell <ncardwell@...gle.com>
Subject: [PATCH net-next 2/2] tcp: do not enqueue skb with SYN flag
If we remove the SYN flag from the skbs that tcp_fastopen_add_skb()
places in socket receive queue, then we can remove the test that
tcp_recvmsg() has to perform in fast path.
All we have to do is to adjust SEQ in the slow path.
For the moment, we place an unlikely() and output a message
if we find an skb having SYN flag set.
Goal would be to get rid of the test completely.
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
Signed-off-by: Yuchung Cheng <ycheng@...gle.com>
Signed-off-by: Neal Cardwell <ncardwell@...gle.com>
---
net/ipv4/tcp.c | 8 ++++++--
net/ipv4/tcp_fastopen.c | 3 +++
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 19746b3fcbbe..c5075779e017 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1466,8 +1466,10 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
offset = seq - TCP_SKB_CB(skb)->seq;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
+ }
if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
*off = offset;
return skb;
@@ -1657,8 +1659,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
break;
offset = *seq - TCP_SKB_CB(skb)->seq;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
+ }
if (offset < skb->len)
goto found_ok_skb;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 467d3e985411..6a6e11e54bae 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -143,6 +143,9 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
__skb_pull(skb, tcp_hdrlen(skb));
skb_set_owner_r(skb, sk);
+ TCP_SKB_CB(skb)->seq++;
+ TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
__skb_queue_tail(&sk->sk_receive_queue, skb);
tp->syn_data_acked = 1;
--
2.7.0.rc3.207.g0ac5344
Powered by blists - more mailing lists