Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit e480bfcf authored by Eric Dumazet's avatar Eric Dumazet Committed by Greg Kroah-Hartman
Browse files

tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb 

commit f921a4a5bffa8a0005b190fb9421a7fc1fd716b6 upstream.

In commit 75eefc6c ("tcp: tsq: add a shortcut in tcp_small_queue_check()")
we allowed to send an skb regardless of TSQ limits being hit if rtx queue
was empty or had a single skb, in order to better fill the pipe
when/if TX completions were slow.

Then later, commit 75c119af ("tcp: implement rb-tree based
retransmit queue") accidentally removed the special case for
one skb in rtx queue.

Stefan Wahren reported a regression in single TCP flow throughput
using a 100Mbit fec link, starting from commit 65466904b015 ("tcp: adjust
TSO packet sizes based on min_rtt"). This last commit only made the
regression more visible, because it locked the TCP flow on a particular
behavior where TSQ prevented two skbs being pushed downstream,
adding silences on the wire between each TSO packet.

Many thanks to Stefan for his invaluable help !

Fixes: 75c119af ("tcp: implement rb-tree based retransmit queue")
Link: https://lore.kernel.org/netdev/7f31ddc8-9971-495e-a1f6-819df542e0af@gmx.net/


Reported-by: default avatarStefan Wahren <wahrenst@gmx.net>
Tested-by: default avatarStefan Wahren <wahrenst@gmx.net>
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20231017124526.4060202-1-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent 6d022a7a

net/ipv4/tcp_output.c

+14 −2
Original line number Diff line number Diff line
@@ -2220,6 +2220,18 @@ static int tcp_mtu_probe(struct sock *sk) 
	return -1;

}



static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk)

{

	const struct rb_node *node = sk->tcp_rtx_queue.rb_node;



	/* No skb in the rtx queue. */

	if (!node)

		return true;



	/* Only one skb in rtx queue. */

	return !node->rb_left && !node->rb_right;

}



/* TCP Small Queues :

 * Control number of packets in qdisc/devices to two packets / or ~1 ms.

 * (These limits are doubled for retransmits)
@@ -2242,12 +2254,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, 
	limit <<= factor;



	if (refcount_read(&sk->sk_wmem_alloc) > limit) {

		/* Always send skb if rtx queue is empty.

		/* Always send skb if rtx queue is empty or has one skb.

		 * No need to wait for TX completion to call us back,

		 * after softirq/tasklet schedule.

		 * This helps when TX completions are delayed too much.

		 */

		if (tcp_rtx_queue_empty(sk))

		if (tcp_rtx_queue_empty_or_single_skb(sk))

			return false;



		set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);