Hi Linus,
Still need a final cancelation fix that isn't quite done done, expected
in the next day or two. That said, this pull request contains:
- Wakeup fix for IOPOLL requests
- SQPOLL split close op handling fix
- Ensure that any use of io_uring fd itself is marked as inflight
- Short non-regular file read fix (Pavel)
- Fix up bad false positive warning (Pavel)
- SQPOLL fixes (Pavel)
- In-flight removal fix (Pavel)
Please pull!
The following changes since commit a8d13dbccb137c46fead2ec1a4f1fbc8cfc9ea91:
io_uring: ensure finish_wait() is always called in __io_uring_task_cancel() (2021-01-15 16:04:23 -0700)
are available in the Git repository at:
git://git.kernel.dk/linux-block.git tags/io_uring-5.11-2021-01-24
for you to fetch changes up to 02a13674fa0e8dd326de8b9f4514b41b03d99003:
io_uring: account io_uring internal files as REQ_F_INFLIGHT (2021-01-24 10:15:33 -0700)
----------------------------------------------------------------
io_uring-5.11-2021-01-24
----------------------------------------------------------------
Jens Axboe (3):
io_uring: iopoll requests should also wake task ->in_idle state
io_uring: fix SQPOLL IORING_OP_CLOSE cancelation state
io_uring: account io_uring internal files as REQ_F_INFLIGHT
Pavel Begunkov (5):
io_uring: fix false positive sqo warning on flush
io_uring: fix uring_flush in exit_files() warning
io_uring: fix skipping disabling sqo on exec
io_uring: fix short read retries for non-reg files
io_uring: fix sleeping under spin in __io_clean_op
fs/io_uring.c | 67 +++++++++++++++++++++++++++++++++++++++++------------------
1 file changed, 47 insertions(+), 20 deletions(-)
--
Jens Axboe
