Commit f4dae54e authored Mar 11, 2021 by Eric Dumazet Committed by David S. Miller Mar 11, 2021

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 1f3279ae ("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 <edumazet@google.com>
Reported-by: Neil Spring <ntspring@fb.com>
Reported-by: Jakub Kicinski <kuba@kernel.org>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

parent 8176f8c0

include/linux/skbuff.h

+1 −1

Original line number	Diff line number	Diff line
		@@ -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;
		}

		/**

net/ipv4/tcp_output.c

+8 −4

Original line number	Diff line number	Diff line
		@@ -2775,14 +2775,18 @@ 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))) {
		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;
		}