[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <20201006.061258.2191845903557820470.davem@davemloft.net>
Date: Tue, 06 Oct 2020 06:12:58 -0700 (PDT)
From: David Miller <davem@...emloft.net>
To: eric.dumazet@...il.com
Cc: netdev@...r.kernel.org, soheil@...gle.com, ncardwell@...gle.com,
ycheng@...gle.com, edumazet@...gle.com,
alexandre.ferrieux@...nge.com
Subject: Re: [PATCH net] tcp: fix receive window update in tcp_add_backlog()
From: Eric Dumazet <eric.dumazet@...il.com>
Date: Mon, 5 Oct 2020 06:48:13 -0700
> From: Eric Dumazet <edumazet@...gle.com>
>
> We got reports from GKE customers flows being reset by netfilter
> conntrack unless nf_conntrack_tcp_be_liberal is set to 1.
>
> Traces seemed to suggest ACK packet being dropped by the
> packet capture, or more likely that ACK were received in the
> wrong order.
>
> wscale=7, SYN and SYNACK not shown here.
>
> This ACK allows the sender to send 1871*128 bytes from seq 51359321 :
> New right edge of the window -> 51359321+1871*128=51598809
...
> Now imagine ACK were delivered out of order and tcp_add_backlog() sets window based on wrong packet.
> New right edge of the window -> 51521241+859*128=51631193
>
> Normally TCP stack handles OOO packets just fine, but it
> turns out tcp_add_backlog() does not. It can update the window
> field of the aggregated packet even if the ACK sequence
> of the last received packet is too old.
>
> Many thanks to Alexandre Ferrieux for independently reporting the issue
> and suggesting a fix.
>
> Fixes: 4f693b55c3d2 ("tcp: implement coalescing on backlog queue")
> Signed-off-by: Eric Dumazet <edumazet@...gle.com>
> Reported-by: Alexandre Ferrieux <alexandre.ferrieux@...nge.com>
Applied and queued up for -stable, thank you.
Powered by blists - more mailing lists