From: Jens Axboe <axboe@kernel.dk>
To: "Alexander V. Buev" <a.buev@yadro.com>, linux-block@vger.kernel.org
Cc: Christoph Hellwig <hch@lst.de>,
"Martin K . Petersen" <martin.petersen@oracle.com>,
Mikhail Malygin <m.malygin@yadro.com>,
linux@yadro.com
Subject: Re: [PATCH 0/3] implement direct IO with integrity
Date: Thu, 28 Oct 2021 09:13:07 -0600 [thread overview]
Message-ID: <bc336e90-378e-6016-ea1c-d519290dce5f@kernel.dk> (raw)
In-Reply-To: <20211028112406.101314-1-a.buev@yadro.com>
On 10/28/21 5:24 AM, Alexander V. Buev wrote:
> This series of patches makes possible to do direct block IO
> with integrity payload using io uring kernel interface.
> Userspace app can utilize READV/WRITEV operation with a new
> (unused before) flag in sqe struct to mark IO request as
> "request with integrity payload".
> When this flag is set, the last of provided iovecs
> must contain pointer and length of this integrity payload.
>
> Alexander V. Buev (3):
> block: bio-integrity: add PI iovec to bio
> block: io_uring: add IO_WITH_PI flag to SQE
> block: fops: handle IOCB_USE_PI in direct IO
>
> block/bio-integrity.c | 124 +++++++++++++++++++++++++++++++++-
> block/fops.c | 71 +++++++++++++++++++
> fs/io_uring.c | 32 ++++++++-
> include/linux/bio.h | 8 +++
> include/linux/fs.h | 1 +
> include/uapi/linux/io_uring.h | 3 +
> 6 files changed, 235 insertions(+), 4 deletions(-)
A couple of suggestions on this:
1) Don't think we need an IOSQE flag, those are mostly reserved for
modifiers that apply to (mostly) all kinds of requests
2) I think this would be cleaner as a separate command, rather than
need odd adjustments and iov assumptions. That also gets it out
of the fast path.
I'd add IORING_OP_READV_PI and IORING_OP_WRITEV_PI for this, I think
you'd end up with a much cleaner implementation that way.
--
Jens Axboe
next prev parent reply other threads:[~2021-10-28 15:13 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-28 11:24 [PATCH 0/3] implement direct IO with integrity Alexander V. Buev
2021-10-28 11:24 ` [PATCH 1/3] block: bio-integrity: add PI iovec to bio Alexander V. Buev
2021-10-28 15:16 ` Christoph Hellwig
2021-10-29 0:11 ` Chaitanya Kulkarni
2021-10-29 4:27 ` Martin K. Petersen
2021-10-29 10:59 ` Alexander V. Buev
2021-10-29 8:40 ` kernel test robot
2021-10-29 8:53 ` kernel test robot
2021-10-29 9:48 ` kernel test robot
2021-10-28 11:24 ` [PATCH 2/3] block: io_uring: add IO_WITH_PI flag to SQE Alexander V. Buev
2021-10-28 11:24 ` [PATCH 3/3] block: fops: handle IOCB_USE_PI in direct IO Alexander V. Buev
2021-10-28 15:17 ` Christoph Hellwig
2021-10-29 9:04 ` kernel test robot
2021-10-28 15:13 ` Jens Axboe [this message]
2021-10-28 15:18 ` [PATCH 0/3] implement direct IO with integrity Christoph Hellwig
2021-10-28 15:20 ` Jens Axboe
2021-10-28 15:44 ` Mikhail Malygin
2021-10-28 15:50 ` Jens Axboe
2021-10-28 15:56 ` Pavel Begunkov
2021-10-28 16:22 ` Jens Axboe
2021-10-28 17:11 ` Pavel Begunkov
2021-10-28 17:45 ` Jens Axboe
2021-10-29 3:39 ` Martin K. Petersen
2021-10-28 15:25 ` Jens Axboe
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=bc336e90-378e-6016-ea1c-d519290dce5f@kernel.dk \
--to=axboe@kernel.dk \
--cc=a.buev@yadro.com \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux@yadro.com \
--cc=m.malygin@yadro.com \
--cc=martin.petersen@oracle.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).