From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
To: Alessandro Decina <alessandro.d@gmail.com>
Cc: "Loktionov, Aleksandr" <aleksandr.loktionov@intel.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"David S. Miller" <davem@davemloft.net>,
Alexei Starovoitov <ast@kernel.org>,
Andrew Lunn <andrew+netdev@lunn.ch>,
Daniel Borkmann <daniel@iogearbox.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>,
"Jesper Dangaard Brouer" <hawk@kernel.org>,
John Fastabend <john.fastabend@gmail.com>,
"Paolo Abeni" <pabeni@redhat.com>,
"Kitszel, Przemyslaw" <przemyslaw.kitszel@intel.com>,
Stanislav Fomichev <sdf@fomichev.me>,
"Sarkar, Tirthendu" <tirthendu.sarkar@intel.com>,
"Nguyen, Anthony L" <anthony.l.nguyen@intel.com>,
"bpf@vger.kernel.org" <bpf@vger.kernel.org>,
"intel-wired-lan@lists.osuosl.org"
<intel-wired-lan@lists.osuosl.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [Intel-wired-lan] [PATCH net v4 1/1] i40e: xsk: advance next_to_clean on status descriptors
Date: Wed, 19 Nov 2025 17:11:25 +0100 [thread overview]
Message-ID: <aR3sLeEpPGK0iP+3@boxer> (raw)
In-Reply-To: <aR0UKHeilBX5oTg9@lima-default>
On Wed, Nov 19, 2025 at 11:49:44AM +1100, Alessandro Decina wrote:
> On Tue, Nov 18, 2025 at 07:45:24PM +0100, Maciej Fijalkowski wrote:
> > Repro steps would be nice to have, rest would be rather redundant to me.
>
> Yeah unfortunately I don't really know how to _manually_ reproduce.
>
> I don't know why I'm getting these status descriptors, but I'm getting
> them reproducibly every few minutes on ubuntu 24.04 across 3 machines
Might be a HW quirk, I don't remember. Other example I have handy is HW
that is served by ice driver can sometimes produce 0-length descriptors
for jumbo frames and we do handle this in driver.
Describing your setup in commit message would be enough, if you ask me.
> where I've hit this bug/tested the fix. The machines are doing ~300Mbps
> of UDP traffic, some of which is done using AF_XDP. The AF_XDP code is
> TX only, so it's executing the build-skb-in-zc-path all the time as all
> the ingress traffic goes to sockets.
>
> If you have any idea on how to reliably produce the descriptors I'm
> happy to give it a try.
next prev parent reply other threads:[~2025-11-19 16:11 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-18 11:31 [Intel-wired-lan] [PATCH net v4 0/1] i40e: xsk: advance next_to_clean on status descriptors Alessandro Decina
2025-11-18 11:31 ` [Intel-wired-lan] [PATCH net v4 1/1] " Alessandro Decina
2025-11-18 12:13 ` Loktionov, Aleksandr
2025-11-18 18:45 ` Maciej Fijalkowski
2025-11-19 0:49 ` Alessandro Decina
2025-11-19 16:11 ` Maciej Fijalkowski [this message]
2025-11-20 15:41 ` Loktionov, Aleksandr
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aR3sLeEpPGK0iP+3@boxer \
--to=maciej.fijalkowski@intel.com \
--cc=aleksandr.loktionov@intel.com \
--cc=alessandro.d@gmail.com \
--cc=andrew+netdev@lunn.ch \
--cc=anthony.l.nguyen@intel.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=john.fastabend@gmail.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=przemyslaw.kitszel@intel.com \
--cc=sdf@fomichev.me \
--cc=tirthendu.sarkar@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).