From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 From: Fabian Ebner Date: Wed, 28 Jul 2021 08:55:31 +0200 Subject: [PATCH] io_uring: don't block level reissue off completion path Some setups, like SCSI, can throw spurious -EAGAIN off the softirq completion path. Normally we expect this to happen inline as part of submission, but apparently SCSI has a weird corner case where it can happen as part of normal completions. This should be solved by having the -EAGAIN bubble back up the stack as part of submission, but previous attempts at this failed and we're not just quite there yet. Instead we currently use REQ_F_REISSUE to handle this case. For now, catch it in io_rw_should_reissue() and prevent a reissue from a bogus path. Upstream mail: https://lore.kernel.org/io-uring/20210727165811.284510-3-axboe@kernel.dk/T/#u Originally-by: Jens Axboe [backport] Signed-off-by: Fabian Ebner --- fs/io_uring.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index a0d42aea3aa1..ce5cf51a5667 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2731,6 +2731,13 @@ static bool io_rw_reissue(struct io_kiocb *req, long res) if (percpu_ref_is_dying(&req->ctx->refs)) return false; + /* + * Play it safe and assume not safe to re-import and reissue if we're + * not in the original thread group (or in task context). + */ + if (!same_thread_group(req->task, current) || !in_task()) + return false; + lockdep_assert_held(&req->ctx->uring_lock); ret = io_sq_thread_acquire_mm_files(req->ctx, req);