From: Pavel Begunkov <asml.silence@xxxxxxxxx> commit 28090c133869b461c5366195a856d73469ab87d9 upstream. After closing an SQPOLL ring, io_ring_exit_work() kicks in and starts doing cancellations via io_uring_try_cancel_requests(). It will go through io_uring_try_cancel_iowq(), which uses ctx->tctx_list, but as SQPOLL task don't have a ctx note, its io-wq won't be reachable and so is left not cancelled. It will eventually cancelled when one of the tasks dies, but if a thread group survives for long and changes rings, it will spawn lots of unreclaimed resources and live locked works. Cancel SQPOLL task's io-wq separately in io_ring_exit_work(). Cc: stable@xxxxxxxxxxxxxxx Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx> Link: https://lore.kernel.org/r/a71a7fe345135d684025bb529d5cb1d8d6b46e10.1619389911.git.asml.silence@xxxxxxxxx Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- fs/io_uring.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8571,6 +8571,13 @@ static void io_tctx_exit_cb(struct callb complete(&work->completion); } +static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + return req->ctx == data; +} + static void io_ring_exit_work(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); @@ -8587,6 +8594,17 @@ static void io_ring_exit_work(struct wor */ do { io_uring_try_cancel_requests(ctx, NULL, NULL); + if (ctx->sq_data) { + struct io_sq_data *sqd = ctx->sq_data; + struct task_struct *tsk; + + io_sq_thread_park(sqd); + tsk = sqd->thread; + if (tsk && tsk->io_uring && tsk->io_uring->io_wq) + io_wq_cancel_cb(tsk->io_uring->io_wq, + io_cancel_ctx_cb, ctx, true); + io_sq_thread_unpark(sqd); + } WARN_ON_ONCE(time_after(jiffies, timeout)); } while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20)); @@ -8731,13 +8749,6 @@ static bool io_cancel_defer_files(struct return true; } -static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - - return req->ctx == data; -} - static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) { struct io_tctx_node *node;
