From f4dae54e486d528d4dd98df116e7a522bbf12667 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 Mar 2021 12:35:04 -0800 Subject: [PATCH] tcp: plug skb_still_in_host_queue() to TSQ Jakub and Neil reported an increase of RTO timers whenever TX completions are delayed a bit more (by increasing NIC TX coalescing parameters) Main issue is that TCP stack has a logic preventing a packet being retransmit if the prior clone has not yet been orphaned or freed. This logic came with commit 1f3279ae0c13 ("tcp: avoid retransmits of TCP packets hanging in host queues") Thankfully, in the case skb_still_in_host_queue() detects the initial clone is still in flight, it can use TSQ logic that will eventually retry later, at the moment the clone is freed or orphaned. Signed-off-by: Eric Dumazet Reported-by: Neil Spring Reported-by: Jakub Kicinski Cc: Neal Cardwell Cc: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/ipv4/tcp_output.c | 12 ++++++++---- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0503c91..483e893 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1140,7 +1140,7 @@ static inline bool skb_fclone_busy(const struct sock *sk, return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && - fclones->skb2.sk == sk; + READ_ONCE(fclones->skb2.sk) == sk; } /** diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fbf140a..0dbf208 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2775,13 +2775,17 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! */ -static bool skb_still_in_host_queue(const struct sock *sk, +static bool skb_still_in_host_queue(struct sock *sk, const struct sk_buff *skb) { if (unlikely(skb_fclone_busy(sk, skb))) { - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); - return true; + set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); + smp_mb__after_atomic(); + if (skb_fclone_busy(sk, skb)) { + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + return true; + } } return false; } -- 2.7.4