netdev - Re: [net,v3] tcp: correct handling of extreme memory squeeze

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

Message-ID: <20250128161825.339f95ea@elisabeth>
Date: Tue, 28 Jan 2025 16:18:25 +0100
From: Stefano Brivio <sbrivio@...hat.com>
To: Eric Dumazet <edumazet@...gle.com>
Cc: jmaloy@...hat.com, netdev@...r.kernel.org, davem@...emloft.net,
 kuba@...nel.org, passt-dev@...st.top, lvivier@...hat.com,
 dgibson@...hat.com, memnglong8.dong@...il.com, kerneljasonxing@...il.com,
 ncardwell@...gle.com, eric.dumazet@...il.com
Subject: Re: [net,v3] tcp: correct handling of extreme memory squeeze

On Tue, 28 Jan 2025 16:04:35 +0100
Eric Dumazet <edumazet@...gle.com> wrote:

> This so-called 'deadlock' only occurs if a remote TCP stack is unable
> to send win0 probes.
> 
> In this case, sending some ACK will not help reliably if these ACK get lost.
> 
> I find the description tries very hard to hide a bug in another stack,
> for some reason.

Side note: that was fixed meanwhile. Back then, at a first analysis, we
thought it was a workaround, but it's the actual fix as we *must* send
zero-window probes in that situation, and this commit triggers them:

  https://passt.top/passt/commit/?id=a740e16fd1b9bdca8d259aa6d37f942a3874425c

-- 
Stefano