Hi Linus,
Nothing major, just a few minor tweaks:
- Teak for the TCP zero-copy io_uring self test (Pavel)
- Rather than use our internal cached value of number of CQ events
available, use what the user can see (Dylan)
- Fix a typo in a comment, added in this release (me)
- Don't allow wrapping while adding provided buffers (me)
- Fix a double poll race, and add a lockdep assertion for it too (Pavel)
Please pull!
The following changes since commit b3026767e15b488860d4bbf1649d69612bab2c25:
io_uring: unlock if __io_run_local_work locked inside (2022-10-27 09:52:12 -0600)
are available in the Git repository at:
git://git.kernel.dk/linux.git tags/io_uring-6.1-2022-11-11
for you to fetch changes up to 5576035f15dfcc6cb1cec236db40c2c0733b0ba4:
io_uring/poll: lockdep annote io_poll_req_insert_locked (2022-11-11 09:59:27 -0700)
----------------------------------------------------------------
io_uring-6.1-2022-11-11
----------------------------------------------------------------
Dylan Yudaken (1):
io_uring: calculate CQEs from the user visible value
Jens Axboe (2):
io_uring: fix typo in io_uring.h comment
io_uring: check for rollover of buffer ID when providing buffers
Pavel Begunkov (3):
selftests/net: don't tests batched TCP io_uring zc
io_uring/poll: fix double poll req->flags races
io_uring/poll: lockdep annote io_poll_req_insert_locked
include/uapi/linux/io_uring.h | 2 +-
io_uring/io_uring.c | 10 +++++--
io_uring/kbuf.c | 2 ++
io_uring/poll.c | 31 +++++++++++++---------
.../testing/selftests/net/io_uring_zerocopy_tx.sh | 2 +-
5 files changed, 31 insertions(+), 16 deletions(-)
--
Jens Axboe
