netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@nvidia.com>
To: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Leon Romanovsky <leon@kernel.org>,
	Majd Dibbiny <majd@mellanox.com>,
	Doug Ledford <dledford@redhat.com>,
	Yuval Shaia <yshaia@marvell.com>,
	Matan Barak <matanb@mellanox.com>,
	Bernard Metzler <bernard.metzler@linux.dev>,
	OFED mailing list <linux-rdma@vger.kernel.org>,
	Network Development <netdev@vger.kernel.org>
Subject: Re: [not-yet-signed PATCH] RDMA/core: flush gid_cache_wq WQ from disable_device()
Date: Tue, 16 Dec 2025 10:05:12 -0400	[thread overview]
Message-ID: <20251216140512.GC6079@nvidia.com> (raw)
In-Reply-To: <ace1ebe4-4fdb-49f4-a3fa-bbf11e1b40ed@I-love.SAKURA.ne.jp>

On Tue, Dec 16, 2025 at 10:29:29PM +0900, Tetsuo Handa wrote:
> Hmm, I misinterpreted that commit. Since ib_register_device() was doing
> 
> 	down_write(&lists_rwsem);
> 	list_add_tail(&device->core_list, &device_list);
> 	up_write(&lists_rwsem);
> 
> , it was
> 
> 	down_write(&lists_rwsem);
> 	list_del(&device->core_list);
> 
> in ib_unregister_device() that makes ib_enum_all_roce_netdevs() no longer
> call ib_enum_roce_netdev().
> 
> Then, calling ib_enum_all_roce_netdevs() asynchronously was always racy
> since commit 03db3a2d81e6 ("IB/core: Add RoCE GID table management") was added?

Yes, probably, it may need to grab the registration lock in the WQ.

Jason

  reply	other threads:[~2025-12-16 14:05 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-25 14:31 [rdma/siw] unregister_netdevice: waiting for bond0 to become free. Usage count = 3 Tetsuo Handa
2025-12-05 14:20 ` Tetsuo Handa
2025-12-11 13:24   ` [not-yet-signed PATCH] RDMA/core: flush gid_cache_wq WQ from disable_device() Tetsuo Handa
2025-12-15 14:09     ` Tetsuo Handa
2025-12-16 11:28       ` Tetsuo Handa
2025-12-16 13:29         ` Tetsuo Handa
2025-12-16 14:05           ` Jason Gunthorpe [this message]
2025-12-16 14:38             ` [PATCH] " Tetsuo Handa
2025-12-18  9:53               ` Tetsuo Handa
2025-12-19 15:09                 ` Tetsuo Handa
2025-12-20  2:11                   ` [PATCH] RDMA/core: always drop device refcount in ib_del_sub_device_and_put() Tetsuo Handa
2025-12-21  6:17                     ` Parav Pandit
2025-12-21 11:45                     ` Leon Romanovsky

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=20251216140512.GC6079@nvidia.com \
    --to=jgg@nvidia.com \
    --cc=bernard.metzler@linux.dev \
    --cc=dledford@redhat.com \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=majd@mellanox.com \
    --cc=matanb@mellanox.com \
    --cc=netdev@vger.kernel.org \
    --cc=penguin-kernel@i-love.sakura.ne.jp \
    --cc=yshaia@marvell.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).