public inbox for [email protected]
 help / color / mirror / Atom feed
From: Keith Busch <[email protected]>
To: <[email protected]>, <[email protected]>,
	<[email protected]>, <[email protected]>,
	<[email protected]>
Cc: <[email protected]>, <[email protected]>,
	Keith Busch <[email protected]>
Subject: [PATCHv8 0/6] ublk zero copy support
Date: Thu, 27 Feb 2025 14:39:10 -0800	[thread overview]
Message-ID: <[email protected]> (raw)

From: Keith Busch <[email protected]>

This one completed liburing 'make runtests' successfully.

Changes from v7:

  Prep patch, mostly from Jens, that removes the "do_import" parameter
  from the generic rw prep.

  Added check for kernel buffers in rw's loop submit. This file
  operation requires __user pointers, so can't use it there (Pavel)

  Added a bool, is_kbuf, so that we don't use the existence of the
  "release" callback to distinguish user vs kernel buffers. And had user
  buffers define its own release function so that we can remove a branch
  check on free.

  The io node and imu caching is moved from the table to ring ctx. This
  is the simplest solution to situations where the node outlives the
  table it came from.

  Fixed missing (parens) logical error checking for ublk flags.

  Minor cleanups to reduce diff churn.

Keith Busch (5):
  io_uring/rw: move buffer_select outside generic prep
  io_uring/rw: move fixed buffer import to issue path
  io_uring: add support for kernel registered bvecs
  ublk: zc register/unregister bvec
  io_uring: cache nodes and mapped buffers

Xinyu Zhang (1):
  nvme: map uring_cmd data even if address is 0

 drivers/block/ublk_drv.c       |  59 ++++++++--
 drivers/nvme/host/ioctl.c      |   2 +-
 include/linux/io_uring/cmd.h   |   7 ++
 include/linux/io_uring_types.h |   2 +
 include/uapi/linux/ublk_cmd.h  |   4 +
 io_uring/filetable.c           |   2 +-
 io_uring/io_uring.c            |   5 +
 io_uring/opdef.c               |   4 +-
 io_uring/rsrc.c                | 189 +++++++++++++++++++++++++++++----
 io_uring/rsrc.h                |  13 ++-
 io_uring/rw.c                  |  85 ++++++++++-----
 io_uring/rw.h                  |   2 +
 12 files changed, 318 insertions(+), 56 deletions(-)

-- 
2.43.5


             reply	other threads:[~2025-02-27 22:39 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-27 22:39 Keith Busch [this message]
2025-02-27 22:39 ` [PATCHv8 1/6] io_uring/rw: move buffer_select outside generic prep Keith Busch
2025-02-28  8:10   ` Ming Lei
2025-02-27 22:39 ` [PATCHv8 2/6] io_uring/rw: move fixed buffer import to issue path Keith Busch
2025-02-28  8:11   ` Ming Lei
2025-02-27 22:39 ` [PATCHv8 3/6] nvme: map uring_cmd data even if address is 0 Keith Busch
2025-02-27 22:39 ` [PATCHv8 4/6] io_uring: add support for kernel registered bvecs Keith Busch
2025-02-28  8:13   ` Ming Lei
2025-02-27 22:39 ` [PATCHv8 5/6] ublk: zc register/unregister bvec Keith Busch
2025-02-28  8:14   ` Ming Lei
2025-02-27 22:39 ` [PATCHv8 6/6] io_uring: cache nodes and mapped buffers Keith Busch
2025-02-27 23:50   ` Jens Axboe
2025-02-28 14:06 ` [PATCHv8 0/6] ublk zero copy support 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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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