4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yuchung Cheng ycheng@google.com
[ Upstream commit 27cde44a259c380a3c09066fc4b42de7dde9b1ad ]
Currently when a DCTCP receiver delays an ACK and receive a data packet with a different CE mark from the previous one's, it sends two immediate ACKs acking previous and latest sequences respectly (for ECN accounting).
Previously sending the first ACK may mark off the delayed ACK timer (tcp_event_ack_sent). This may subsequently prevent sending the second ACK to acknowledge the latest sequence (tcp_ack_snd_check). The culprit is that tcp_send_ack() assumes it always acknowleges the latest sequence, which is not true for the first special ACK.
The fix is to not make the assumption in tcp_send_ack and check the actual ack sequence before cancelling the delayed ACK. Further it's safer to pass the ack sequence number as a local variable into tcp_send_ack routine, instead of intercepting tp->rcv_nxt to avoid future bugs like this.
Reported-by: Neal Cardwell ncardwell@google.com Signed-off-by: Yuchung Cheng ycheng@google.com Acked-by: Neal Cardwell ncardwell@google.com Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/tcp.h | 1 + net/ipv4/tcp_dctcp.c | 34 ++++------------------------------ net/ipv4/tcp_output.c | 11 ++++++++--- 3 files changed, 13 insertions(+), 33 deletions(-)
--- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -553,6 +553,7 @@ void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -135,21 +135,8 @@ static void dctcp_ce_state_0_to_1(struct * ACK has not sent yet. */ if (!ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=0. */ - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; - } + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt);
ca->prior_rcv_nxt = tp->rcv_nxt; ca->ce_state = 1; @@ -166,21 +153,8 @@ static void dctcp_ce_state_1_to_0(struct * ACK has not sent yet. */ if (ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=1. */ - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; - } + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt);
ca->prior_rcv_nxt = tp->rcv_nxt; ca->ce_state = 0; --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -174,8 +174,13 @@ static void tcp_event_data_sent(struct t }
/* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) +static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, + u32 rcv_nxt) { + struct tcp_sock *tp = tcp_sk(sk); + + if (unlikely(rcv_nxt != tp->rcv_nxt)) + return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1010,7 +1015,7 @@ static int __tcp_transmit_skb(struct soc icsk->icsk_af_ops->send_check(sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -3529,12 +3534,12 @@ void __tcp_send_ack(struct sock *sk, u32 skb_mstamp_get(&buff->skb_mstamp); __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); } +EXPORT_SYMBOL_GPL(__tcp_send_ack);
void tcp_send_ack(struct sock *sk) { __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } -EXPORT_SYMBOL_GPL(tcp_send_ack);
/* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it.