io_uring: don't iopoll from io_ring_ctx_wait_and_kill()

We should not be completing requests from a task context that has already
undergone io_uring cancellations, i.e. __io_uring_cancel(), as there are
some assumptions, e.g. around cached task refs draining. Remove
iopolling from io_ring_ctx_wait_and_kill() as it can be called later
after PF_EXITING is set with the last task_work run.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7c03cc91455c4a1af49c6b9cbda4e57ea467aa11.1665891182.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Pavel Begunkov 2022-10-16 21:30:51 +01:00 committed by Jens Axboe
parent 34f0bc427e
commit 02bac94bd8
1 changed files with 5 additions and 8 deletions

View File

@ -2804,15 +2804,12 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
io_poll_remove_all(ctx, NULL, true);
mutex_unlock(&ctx->uring_lock);
/* failed during ring init, it couldn't have issued any requests */
if (ctx->rings) {
/*
* If we failed setting up the ctx, we might not have any rings
* and therefore did not submit any requests
*/
if (ctx->rings)
io_kill_timeouts(ctx, NULL, true);
/* if we failed setting up the ctx, we might not have any rings */
io_iopoll_try_reap_events(ctx);
/* drop cached put refs after potentially doing completions */
if (current->io_uring)
io_uring_drop_tctx_refs(current);
}
INIT_WORK(&ctx->exit_work, io_ring_exit_work);
/*