io_uring: defer all io_req_complete_failed

Browse source

All failures happen under lock now, and can be deferred. To be consistent
when the failure has happened after some multishot cqe has been
deferred (and keep ordering), always defer failures.

To make this obvious at the caller (and to help prevent a future bug)
rename io_req_complete_failed to io_req_defer_failed.

Signed-off-by: Dylan Yudaken <dylany@meta.com>
Link: https://lore.kernel.org/r/20221124093559.3780686-4-dylany@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

...

This commit is contained in:

Dylan Yudaken 2022-11-24 01:35:53 -08:00 • committed by Jens Axboe

parent c06c6c5d27

commit 973fc83f3a

3 changed files with 10 additions and 11 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

17

io_uring/io_uring.c

View file

2

io_uring/io_uring.h

View file

2

io_uring/poll.c

View file