io_uring: don't fail submit with overflow backlog
authorPavel Begunkov <asml.silence@gmail.com>
Thu, 15 Apr 2021 12:40:50 +0000 (13:40 +0100)
committerJens Axboe <axboe@kernel.dk>
Sun, 18 Apr 2021 01:19:41 +0000 (19:19 -0600)
commitc82d5bc703825a47af5c600e82e1e0c1db49e036
tree36862811bfb7a988dcbe6a81fe1814b0b4e5dcb7
parenta7be7c23cfdd2cb57609fd2d607923a9cb2a305d
io_uring: don't fail submit with overflow backlog

Don't fail submission attempts if there are CQEs in the overflow
backlog, but give away the decision making to the userspace. It
might be very inconvenient to the userspace, especially if
submission and completion are done by different threads.

We can remove it because of recent changes, where requests
are now not locked by the backlog, backlog entries are allocated
separately, so they take less space and cgroup accounted.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
fs/io_uring.c