netdev - Re: bnxt_en: NETDEV WATCHDOG in 6.13-rc7

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: <CALs4sv2pjRKKLUK8sFDkAGxK_6gkPO5zDX5gDsHw6FF99eKK7g@mail.gmail.com>
Date: Fri, 17 Jan 2025 19:21:58 +0530
From: Pavan Chebbi <pavan.chebbi@...adcom.com>
To: Breno Leitao <leitao@...ian.org>
Cc: michael.chan@...adcom.com, netdev@...r.kernel.org, kuba@...nel.org, 
	kernel-team@...a.com
Subject: Re: bnxt_en: NETDEV WATCHDOG in 6.13-rc7

On Fri, Jan 17, 2025 at 5:38 PM Breno Leitao <leitao@...ian.org> wrote:
>
> Hello,
>
> I am deploying 6.13-rc7 at commit 619f0b6fad52 ("Merge tag 'seccomp-v6.13-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux")
> in a machine with Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb and
> the machine's network is down, with some error messages and NETDEV
> WATCHDOG kicking in.
>
> Are you guys familiar with something similar ?

It appears that by the time netconsole selftest completes, bnxt stops
receiving transmit completions and triggers a reset. The subsequent
hwrm_ring_free (part of the reset) completions are also not received.
I also see nvme driver reporting timeouts. Maybe all because CPUs are
blocked. It is not clear to me as to what could have led to this
situation.
Michael may share his thoughts. Do we need to investigate the 4 locks
held by bnxt?

Download attachment "smime.p7s" of type "application/pkcs7-signature" (4209 bytes)