From: Moshe Shemesh <moshe@nvidia.com>
To: Jakub Kicinski <kuba@kernel.org>,
Tariq Toukan <tariqt@nvidia.com>,
"Simon Horman" <horms@kernel.org>
Cc: Alexandre Cassen <acassen@corp.free.fr>,
Saeed Mahameed <saeedm@nvidia.com>,
Leon Romanovsky <leon@kernel.org>, Mark Bloch <mbloch@nvidia.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@kernel.org>,
Paolo Abeni <pabeni@redhat.com>,
Yevgeny Kliteynik <kliteyn@nvidia.com>, <netdev@vger.kernel.org>,
<linux-rdma@vger.kernel.org>
Subject: Re: [PATCH net v2 0/2] net/mlx5: HWS, fix pool creation races
Date: Tue, 20 Oct 2026 13:10:54 +0300 [thread overview]
Message-ID: <8255a276-f13e-4aa9-b5e2-d814103f9368@nvidia.com> (raw)
In-Reply-To: <20261019185104.7a2135c3@kernel.org>
On 10/20/2026 4:51 AM, Jakub Kicinski wrote:
> On Mon, 19 Oct 2026 14:25:38 +0300 Tariq Toukan wrote:
>> Acked-by: Tariq Toukan <tariqt@nvidia.com>
>
> Clashiko keeps saying that the problem solved by patch 1 doesn't
> actually exist, could one of the reviewers of this series pls
> confirm that the AI analysis is wrong? The commit msg says
> the problem itself was found by AI, so is it not a hallucination?
There is a race here.
mlx5_cmd_hws_packet_reformat_alloc() doesn't take a lock while calling
mlx5_fs_get_pr_encap_pool(), so it can run concurrently for the same
size. Reformats can come from independent flows as TC and RDMA flows.
Note that the race did not create any leak or UAF. As the commit message
says "Two callers allocating the first reformat of a size at once both
create one and the second fails with -EBUSY.". After the fix the second
won't fail but get the pool the first caller allocated.
next prev parent reply other threads:[~2026-10-20 10:11 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-12 10:05 [PATCH net v2 0/2] net/mlx5: HWS, fix pool creation races Alexandre Cassen
2026-10-12 10:05 ` [PATCH net v2 1/2] net/mlx5: HWS, fix reformat pool creation race Alexandre Cassen
2026-10-13 10:25 ` netdev-bot+sashiko
2026-10-18 14:18 ` Simon Horman
2026-10-12 10:05 ` [PATCH net v2 2/2] net/mlx5: HWS, fix modify header " Alexandre Cassen
2026-10-12 18:03 ` Moshe Shemesh
2026-10-18 14:18 ` Simon Horman
2026-10-19 11:25 ` [PATCH net v2 0/2] net/mlx5: HWS, fix pool creation races Tariq Toukan
2026-10-20 1:51 ` Jakub Kicinski
2026-10-20 10:10 ` Moshe Shemesh [this message]
2026-10-20 11:10 ` patchwork-bot+netdevbpf
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=8255a276-f13e-4aa9-b5e2-d814103f9368@nvidia.com \
--to=moshe@nvidia.com \
--cc=acassen@corp.free.fr \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=edumazet@kernel.org \
--cc=horms@kernel.org \
--cc=kliteyn@nvidia.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mbloch@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=saeedm@nvidia.com \
--cc=tariqt@nvidia.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