From: Yuchung Cheng ycheng@google.com
stable inclusion from stable-5.10.51 commit f9c67c179e3b2e4daefa5fb208ddcb13b5728864 bugzilla: 175263 https://gitee.com/openeuler/kernel/issues/I4DT6F
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit a29cb6914681a55667436a9eb7a42e28da8cf387 ]
This patch aims to improve the situation when reordering and loss are ocurring in the same flight of packets.
Previously the reordering would first induce a spurious recovery, then the subsequent ACK may undo the cwnd (based on the timestamps e.g.). However the current loss recovery does not proceed to invoke RACK to install a reordering timer. If some packets are also lost, this may lead to a long RTO-based recovery. An example is https://groups.google.com/g/bbr-dev/c/OFHADvJbTEI
The solution is to after reverting the recovery, always invoke RACK to either mount the RACK timer to fast retransmit after the reordering window, or restarts the recovery if new loss is identified. Hence it is possible the sender may go from Recovery to Disorder/Open to Recovery again in one ACK.
Reported-by: mingkun bian bianmingkun@gmail.com Signed-off-by: Yuchung Cheng ycheng@google.com Signed-off-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: Sasha Levin sashal@kernel.org Signed-off-by: Chen Jun chenjun102@huawei.com Acked-by: Weilong Chen chenweilong@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- net/ipv4/tcp_input.c | 45 +++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fac5c1469cee..4d4b641c204d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2802,8 +2802,17 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, *rexmit = REXMIT_LOST; }
+static bool tcp_force_fast_retransmit(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + return after(tcp_highest_sack_seq(tp), + tp->snd_una + tp->reordering * tp->mss_cache); +} + /* Undo during fast recovery after partial ACK. */ -static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) +static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, + bool *do_lost) { struct tcp_sock *tp = tcp_sk(sk);
@@ -2828,7 +2837,9 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) tcp_undo_cwnd_reduction(sk, true); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); - return true; + } else { + /* Partial ACK arrived. Force fast retransmit. */ + *do_lost = tcp_force_fast_retransmit(sk); } return false; } @@ -2852,14 +2863,6 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) } }
-static bool tcp_force_fast_retransmit(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - return after(tcp_highest_sack_seq(tp), - tp->snd_una + tp->reordering * tp->mss_cache); -} - /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2929,17 +2932,21 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp)) tcp_add_reno_sack(sk, num_dupack, ece_ack); - } else { - if (tcp_try_undo_partial(sk, prior_snd_una)) - return; - /* Partial ACK arrived. Force fast retransmit. */ - do_lost = tcp_force_fast_retransmit(sk); - } - if (tcp_try_undo_dsack(sk)) { - tcp_try_keep_open(sk); + } else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost)) return; - } + + if (tcp_try_undo_dsack(sk)) + tcp_try_keep_open(sk); + tcp_identify_packet_loss(sk, ack_flag); + if (icsk->icsk_ca_state != TCP_CA_Recovery) { + if (!tcp_time_to_recover(sk, flag)) + return; + /* Undo reverts the recovery state. If loss is evident, + * starts a new recovery (e.g. reordering then loss); + */ + tcp_enter_recovery(sk, ece_ack); + } break; case TCP_CA_Loss: tcp_process_loss(sk, flag, num_dupack, rexmit);