[PATCH 5.10 105/157] io_uring: dont attempt IO reissue from the ring exit path
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: 2021-03-22 12:50:05
Also in:
lkml
Subsystem:
filesystems (vfs and infrastructure), the rest · Maintainers:
Alexander Viro, Christian Brauner, Linus Torvalds
From: Jens Axboe <axboe@kernel.dk> [ Upstream commit 7c977a58dc83366e488c217fd88b1469d242bee5 ] If we're exiting the ring, just let the IO fail with -EAGAIN as nobody will care anyway. It's not the right context to reissue from. Cc: stable@vger.kernel.org Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Sasha Levin <sashal@kernel.org> --- fs/io_uring.c | 7 +++++++ 1 file changed, 7 insertions(+)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5746998799ab..7625b3e2db2c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c@@ -2617,6 +2617,13 @@ static bool io_rw_reissue(struct io_kiocb *req, long res) return false; if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker()) return false; + /* + * If ref is dying, we might be running poll reap from the exit work. + * Don't attempt to reissue from that path, just let it fail with + * -EAGAIN. + */ + if (percpu_ref_is_dying(&req->ctx->refs)) + return false; ret = io_sq_thread_acquire_mm(req->ctx, req);
--
2.30.1