4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <edumazet@xxxxxxxxxx>
[ Upstream commit 0f9fa831aecfc297b7b45d4f046759bcefcf87f0 ]
When using TCP FastOpen for an active session, we send one wakeup event
from tcp_finish_connect(), right before the data eventually contained in
the received SYNACK is queued to sk->sk_receive_queue.
This means that depending on machine load or luck, poll() users
might receive POLLOUT events instead of POLLIN|POLLOUT
To fix this, we need to move the call to sk->sk_state_change()
after the (optional) call to tcp_rcv_fastopen_synack()
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Acked-by: Yuchung Cheng <ycheng@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
net/ipv4/tcp_input.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5464,10 +5464,6 @@ void tcp_finish_connect(struct sock *sk,
else
tp->pred_flags = 0;
- if (!sock_flag(sk, SOCK_DEAD)) {
- sk->sk_state_change(sk);
- sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
- }
}
static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
@@ -5531,6 +5527,7 @@ static int tcp_rcv_synsent_state_process
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_cookie foc = { .len = -1 };
int saved_clamp = tp->rx_opt.mss_clamp;
+ bool fastopen_fail;
tcp_parse_options(skb, &tp->rx_opt, 0, &foc);
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
@@ -5633,10 +5630,15 @@ static int tcp_rcv_synsent_state_process
tcp_finish_connect(sk, skb);
- if ((tp->syn_fastopen || tp->syn_data) &&
- tcp_rcv_fastopen_synack(sk, skb, &foc))
- return -1;
+ fastopen_fail = (tp->syn_fastopen || tp->syn_data) &&
+ tcp_rcv_fastopen_synack(sk, skb, &foc);
+ if (!sock_flag(sk, SOCK_DEAD)) {
+ sk->sk_state_change(sk);
+ sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
+ }
+ if (fastopen_fail)
+ return -1;
if (sk->sk_write_pending ||
icsk->icsk_accept_queue.rskq_defer_accept ||
icsk->icsk_ack.pingpong) {