netdev - Spurious TCP retransmissions on ack vs kfree

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <20210225152515.2072b5a7@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
Date:   Thu, 25 Feb 2021 15:25:15 -0800
From:   Jakub Kicinski <kuba@...nel.org>
To:     "netdev@...r.kernel.org" <netdev@...r.kernel.org>
Cc:     Eric Dumazet <edumazet@...gle.com>,
        Soheil Hassas Yeganeh <soheil@...gle.com>,
        Neal Cardwell <ncardwell@...gle.com>,
        Yuchung Cheng <ycheng@...gle.com>
Subject: Spurious TCP retransmissions on ack vs kfree_skb reordering

Hi!

We see large (4-8x) increase of what looks like TCP RTOs after rising 
the Tx coalescing above Rx coalescing timeout.

Quick tracing of the events seems to indicate that the data has already
been acked when we enter tcp:tcp_retransmit_skb:

sk_state:      1
icsk_ca_state: 4

bytes_in:      0
bytes_out:   742
bytes_acked: 742

Is this a known condition? Is the recommendation to filter such events
out in tracing infra?