Re: [PATCH 5.12] io_uring: do ctx sqd ejection in a clear context

[Jens Axboe <axboe@kernel.dk>]

On 3/23/21 4:52 AM, Pavel Begunkov wrote:
> WARNING: CPU: 1 PID: 27907 at fs/io_uring.c:7147 io_sq_thread_park+0xb5/0xd0 fs/io_uring.c:7147
> CPU: 1 PID: 27907 Comm: iou-sqp-27905 Not tainted 5.12.0-rc4-syzkaller #0
> RIP: 0010:io_sq_thread_park+0xb5/0xd0 fs/io_uring.c:7147
> Call Trace:
>  io_ring_ctx_wait_and_kill+0x214/0x700 fs/io_uring.c:8619
>  io_uring_release+0x3e/0x50 fs/io_uring.c:8646
>  __fput+0x288/0x920 fs/file_table.c:280
>  task_work_run+0xdd/0x1a0 kernel/task_work.c:140
>  io_run_task_work fs/io_uring.c:2238 [inline]
>  io_run_task_work fs/io_uring.c:2228 [inline]
>  io_uring_try_cancel_requests+0x8ec/0xc60 fs/io_uring.c:8770
>  io_uring_cancel_sqpoll+0x1cf/0x290 fs/io_uring.c:8974
>  io_sqpoll_cancel_cb+0x87/0xb0 fs/io_uring.c:8907
>  io_run_task_work_head+0x58/0xb0 fs/io_uring.c:1961
>  io_sq_thread+0x3e2/0x18d0 fs/io_uring.c:6763
>  ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294
> 
> May happen that last ctx ref is killed in io_uring_cancel_sqpoll(), so
> fput callback (i.e. io_uring_release()) is enqueued through task_work,
> and run by same cancellation. As it's deeply nested we can't do parking
> or taking sqd->lock there, because its state is unclear. So avoid
> ctx ejection from sqd list from io_ring_ctx_wait_and_kill() and do it
> in a clear context in io_ring_exit_work().

Applied, thanks.

-- 
Jens Axboe