[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <48b9a876-0e3b-4c89-9aa3-b48f502868c3@samsung.com>
Date: Mon, 31 Mar 2025 12:16:58 +0530
From: Kanchan Joshi <joshi.k@...sung.com>
To: Caleb Sander Mateos <csander@...estorage.com>, Keith Busch
<kbusch@...nel.org>, Jens Axboe <axboe@...nel.dk>, Christoph Hellwig
<hch@....de>, Sagi Grimberg <sagi@...mberg.me>, Pavel Begunkov
<asml.silence@...il.com>
Cc: Chaitanya Kulkarni <kch@...dia.com>, linux-nvme@...ts.infradead.org,
io-uring@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v4 3/3] nvme/ioctl: move fixed buffer lookup to
nvme_uring_cmd_io()
On 3/28/2025 9:16 PM, Caleb Sander Mateos wrote:
> For NVMe passthru operations with fixed buffers, the fixed buffer lookup
> happens in io_uring_cmd_import_fixed(). But nvme_uring_cmd_io() can
> return -EAGAIN first from nvme_alloc_user_request() if all tags in the
> tag set are in use. This ordering difference is observable when using
> UBLK_U_IO_{,UN}REGISTER_IO_BUF SQEs to modify the fixed buffer table. If
> the NVMe passthru operation is followed by UBLK_U_IO_UNREGISTER_IO_BUF
> to unregister the fixed buffer and the NVMe passthru goes async, the
> fixed buffer lookup will fail because it happens after the unregister.
while the patch looks fine, I wonder what setup is required to
trigger/test this. Given that io_uring NVMe passthru is on the char
device node, and ublk does not take char device as the backing file.
Care to explain?
Powered by blists - more mailing lists