kernel/linux.git/io_uring/sqpoll.h, branch v6.6.131Linux kernel stable tree (mirror)https://git.radix-linux.su/kernel/linux.git/atom?h=v6.6.1312023-08-16T19:40:28+00:00io_uring/sqpoll: fix io-wq affinity when IORING_SETUP_SQPOLL is used2023-08-16T19:40:28+00:00Jens Axboeaxboe@kernel.dk2023-08-13T17:05:36+00:00urn:sha1:ebdfefc09c6de7897962769bd3e63a2ff443ebf5
If we setup the ring with SQPOLL, then that polling thread has its
own io-wq setup. This means that if the application uses
IORING_REGISTER_IOWQ_AFF to set the io-wq affinity, we should not be
setting it for the invoking task, but rather the sqpoll task.
Add an sqpoll helper that parks the thread and updates the affinity,
and use that one if we're using SQPOLL.
Fixes: fe76421d1da1 ("io_uring: allow user configurable IO thread CPU affinity")
Cc: stable@vger.kernel.org # 5.10+
Link: https://github.com/axboe/liburing/discussions/884
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring: make io_sqpoll_wait_sq return void2023-01-29T22:17:40+00:00Quanfa Fuquanfafu@gmail.com2023-01-15T07:15:19+00:00urn:sha1:88b80534f60f5ddf5f42218b280e0370f95eae78
Change the return type to void since it always return 0, and no need
to do the checking in syscall io_uring_enter.
Signed-off-by: Quanfa Fu <quanfafu@gmail.com>
Link: https://lore.kernel.org/r/20230115071519.554282-1-quanfafu@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring: move SQPOLL related handling into its own file2022-07-25T00:39:12+00:00Jens Axboeaxboe@kernel.dk2022-05-25T15:13:39+00:00urn:sha1:17437f311490d873a5157f65a84317d16270fd38
Signed-off-by: Jens Axboe <axboe@kernel.dk>