From c60eb049f4a19ddddcd3ee97a9c79ab8066a6a03 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 8 Apr 2021 01:54:42 +0100 Subject: io-wq: cancel unbounded works on io-wq destroy WARNING: CPU: 5 PID: 227 at fs/io_uring.c:8578 io_ring_exit_work+0xe6/0x470 RIP: 0010:io_ring_exit_work+0xe6/0x470 Call Trace: process_one_work+0x206/0x400 worker_thread+0x4a/0x3d0 kthread+0x129/0x170 ret_from_fork+0x22/0x30 INFO: task lfs-openat:2359 blocked for more than 245 seconds. task:lfs-openat state:D stack: 0 pid: 2359 ppid: 1 flags:0x00000004 Call Trace: ... wait_for_completion+0x8b/0xf0 io_wq_destroy_manager+0x24/0x60 io_wq_put_and_exit+0x18/0x30 io_uring_clean_tctx+0x76/0xa0 __io_uring_files_cancel+0x1b9/0x2e0 do_exit+0xc0/0xb40 ... Even after io-wq destroy has been issued io-wq worker threads will continue executing all left work items as usual, and may hang waiting for I/O that won't ever complete (aka unbounded). [<0>] pipe_read+0x306/0x450 [<0>] io_iter_do_read+0x1e/0x40 [<0>] io_read+0xd5/0x330 [<0>] io_issue_sqe+0xd21/0x18a0 [<0>] io_wq_submit_work+0x6c/0x140 [<0>] io_worker_handle_work+0x17d/0x400 [<0>] io_wqe_worker+0x2c0/0x330 [<0>] ret_from_fork+0x22/0x30 Cancel all unbounded I/O instead of executing them. This changes the user visible behaviour, but that's inevitable as io-wq is not per task. Suggested-by: Jens Axboe Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/cd4b543154154cba055cf86f351441c2174d7f71.1617842918.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io-wq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/io-wq.c b/fs/io-wq.c index 433c4d3c3c1c..4eba531bea5a 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -415,6 +415,7 @@ static void io_worker_handle_work(struct io_worker *worker) { struct io_wqe *wqe = worker->wqe; struct io_wq *wq = wqe->wq; + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); do { struct io_wq_work *work; @@ -444,6 +445,9 @@ get_next: unsigned int hash = io_get_work_hash(work); next_hashed = wq_next_work(work); + + if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND)) + work->flags |= IO_WQ_WORK_CANCEL; wq->do_work(work); io_assign_current_work(worker, NULL); -- cgit v1.2.3-58-ga151