diff options
| author | Jens Axboe <axboe@kernel.dk> | 2023-08-13 19:05:36 +0200 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2023-08-16 21:40:28 +0200 |
| commit | ebdfefc09c6de7897962769bd3e63a2ff443ebf5 (patch) | |
| tree | a70556ba92be56e756410d5e9871c24f1fe1ea24 /io_uring/io-wq.h | |
| parent | io_uring: simplify io_run_task_work_sig return (diff) | |
| download | linux-ebdfefc09c6de7897962769bd3e63a2ff443ebf5.tar.xz linux-ebdfefc09c6de7897962769bd3e63a2ff443ebf5.zip | |
io_uring/sqpoll: fix io-wq affinity when IORING_SETUP_SQPOLL is used
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>
Diffstat (limited to 'io_uring/io-wq.h')
| -rw-r--r-- | io_uring/io-wq.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h index 31228426d192..06d9ca90c577 100644 --- a/io_uring/io-wq.h +++ b/io_uring/io-wq.h @@ -50,7 +50,7 @@ void io_wq_put_and_exit(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_hash_work(struct io_wq_work *work, void *val); -int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); +int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask); int io_wq_max_workers(struct io_wq *wq, int *new_count); static inline bool io_wq_is_hashed(struct io_wq_work *work) |