All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: io-uring <io-uring@vger.kernel.org>
Subject: [GIT PULL] io_uring updates for 5.14-rc1
Date: Tue, 29 Jun 2021 14:43:29 -0600	[thread overview]
Message-ID: <c9a79f27-02e9-b0d6-78ae-2e777eed8fe0@kernel.dk> (raw)

Hi Linus,

This pull request contains the io_uring updates for the 5.14-rc1 merge
window. In detail:

- Support for mkdirat, symlinkat, and linkat for io_uring (Dmitry)

- Multi-queue iopoll improvement (Fam)

- Allow configurable io-wq CPU masks (me)

- renameat/linkat tightening (me)

- poll re-arm improvement (Olivier)

- SQPOLL race fix (Olivier)

- Cancelation unification (Pavel)

- SQPOLL cleanups (Pavel)

- Enable file backed buffers for shmem/memfd (Pavel)

- A ton of cleanups and performance improvements (Pavel)

- Followup and misc fixes (Colin, Fam, Hao, Olivier)

Please pull!


The following changes since commit 009c9aa5be652675a06d5211e1640e02bbb1c33d:

  Linux 5.13-rc6 (2021-06-13 14:43:10 -0700)

are available in the Git repository at:

  git://git.kernel.dk/linux-block.git tags/for-5.14/io_uring-2021-06-29

for you to fetch changes up to bdfe4dc5bfddf8f3b4080ac4a11a4c5843cbe928:

  io_uring: code clean for kiocb_done() (2021-06-27 16:22:42 -0600)

----------------------------------------------------------------
for-5.14/io_uring-2021-06-29

----------------------------------------------------------------
Colin Ian King (2):
      io_uring: Fix incorrect sizeof operator for copy_from_user call
      io-wq: remove redundant initialization of variable ret

Dmitry Kadashev (9):
      fs: make do_mkdirat() take struct filename
      io_uring: add support for IORING_OP_MKDIRAT
      fs: make do_mknodat() take struct filename
      fs: make do_symlinkat() take struct filename
      namei: add getname_uflags()
      fs: make do_linkat() take struct filename
      fs: update do_*() helpers to return ints
      io_uring: add support for IORING_OP_SYMLINKAT
      io_uring: add support for IORING_OP_LINKAT

Fam Zheng (1):
      io_uring: Fix comment of io_get_sqe

Hao Xu (2):
      io_uring: spin in iopoll() only when reqs are in a single queue
      io_uring: code clean for kiocb_done()

Jens Axboe (4):
      io-wq: use private CPU mask
      io_uring: allow user configurable IO thread CPU affinity
      io_uring: add IOPOLL and reserved field checks to IORING_OP_RENAMEAT
      io_uring: add IOPOLL and reserved field checks to IORING_OP_UNLINKAT

Olivier Langlois (6):
      io_uring: Add to traces the req pointer when available
      io_uring: minor clean up in trace events definition
      io-wq: remove header files not needed anymore
      io_uring: Fix race condition when sqp thread goes to sleep
      io_uring: Create define to modify a SQPOLL parameter
      io_uring: reduce latency by reissueing the operation

Pavel Begunkov (68):
      io_uring: improve sqpoll event/state handling
      io_uring: improve sq_thread waiting check
      io_uring: remove unused park_task_work
      io_uring: simplify waking sqo_sq_wait
      io_uring: get rid of files in exit cancel
      io_uring: make fail flag not link specific
      io_uring: shuffle rarely used ctx fields
      io_uring: better locality for rsrc fields
      io_uring: remove dependency on ring->sq/cq_entries
      io_uring: deduce cq_mask from cq_entries
      io_uring: kill cached_cq_overflow
      io_uring: rename io_get_cqring
      io_uring: don't bounce submit_state cachelines
      io_uring: enable shmem/memfd memory registration
      io_uring: fix blocking inline submission
      io-wq: embed wqe ptr array into struct io_wq
      io-wq: remove unused io-wq refcounting
      io_uring: refactor io_iopoll_req_issued
      io_uring: rename function *task_file
      io-wq: don't repeat IO_WQ_BIT_EXIT check by worker
      io-wq: simplify worker exiting
      io_uring: hide rsrc tag copy into generic helpers
      io_uring: remove rsrc put work irq save/restore
      io_uring: add helpers for 2 level table alloc
      io_uring: don't vmalloc rsrc tags
      io_uring: cache task struct refs
      io_uring: unify SQPOLL and user task cancellations
      io_uring: inline io_iter_do_read()
      io_uring: keep SQ pointers in a single cacheline
      io_uring: move ctx->flags from SQ cacheline
      io_uring: shuffle more fields into SQ ctx section
      io_uring: refactor io_get_sqe()
      io_uring: don't cache number of dropped SQEs
      io_uring: optimise completion timeout flushing
      io_uring: small io_submit_sqe() optimisation
      io_uring: clean up check_overflow flag
      io_uring: wait heads renaming
      io_uring: move uring_lock location
      io_uring: refactor io_req_defer()
      io_uring: optimise non-drain path
      io_uring: fix min types mismatch in table alloc
      io_uring: switch !DRAIN fast path when possible
      io_uring: shove more drain bits out of hot path
      io_uring: optimise io_commit_cqring()
      io_uring: fix false WARN_ONCE
      io_uring: refactor io_submit_flush_completions()
      io_uring: move creds from io-wq work to io_kiocb
      io_uring: track request creds with a flag
      io_uring: simplify iovec freeing in io_clean_op()
      io_uring: clean all flags in io_clean_op() at once
      io_uring: refactor io_get_sequence()
      io_uring: inline __tctx_task_work()
      io_uring: optimise task_work submit flushing
      io_uring: refactor tctx task_work list splicing
      io_uring: don't resched with empty task_list
      io_uring: improve in tctx_task_work() resubmission
      io_uring: don't change sqpoll creds if not needed
      io_uring: refactor io_sq_thread()
      io_uring: fix code style problems
      io_uring: update sqe layout build checks
      io_uring: simplify struct io_uring_sqe layout
      io_uring: refactor io_openat2()
      io_uring: refactor io_arm_poll_handler()
      io_uring: mainstream sqpoll task_work running
      io_uring: remove not needed PF_EXITING check
      io_uring: optimise hot path restricted checks
      io_uring: refactor io_submit_flush_completions
      io_uring: pre-initialise some of req fields

 fs/exec.c                       |    8 +-
 fs/internal.h                   |    8 +-
 fs/io-wq.c                      |  103 ++-
 fs/io-wq.h                      |    3 +-
 fs/io_uring.c                   | 1524 +++++++++++++++++++++++----------------
 fs/namei.c                      |  137 ++--
 include/linux/fs.h              |    1 +
 include/trace/events/io_uring.h |  106 ++-
 include/uapi/linux/io_uring.h   |   32 +-
 9 files changed, 1177 insertions(+), 745 deletions(-)

-- 
Jens Axboe


             reply	other threads:[~2021-06-29 20:43 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-29 20:43 Jens Axboe [this message]
2021-06-30 20:05 ` [GIT PULL] io_uring updates for 5.14-rc1 Linus Torvalds
2021-06-30 20:14   ` Jens Axboe
2021-06-30 20:18     ` Linus Torvalds
2021-06-30 20:21       ` Jens Axboe
2021-07-02 11:32   ` Dmitry Kadashev
2021-07-02 18:33     ` Linus Torvalds
2021-07-03 15:26       ` Dmitry Kadashev
2021-07-05 21:40         ` Linus Torvalds
2021-07-06 12:06           ` Dmitry Kadashev
  -- strict thread matches above, loose matches on Subject: below --
2021-07-01 15:24 Jens Axboe
2021-07-01 19:20 ` pr-tracker-bot

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=c9a79f27-02e9-b0d6-78ae-2e777eed8fe0@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.