io_uring: utilize the io batching infrastructure for more efficient polled IO

Wire up using an io_comp_batch for f_op->iopoll(). If the lower stack
supports it, we can handle high rates of polled IO more efficiently.

This raises the single core efficiency on my system from ~6.1M IOPS to
~6.6M IOPS running a random read workload at depth 128 on two gen2
Optane drives.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -2458,6 +2458,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 {
 	struct io_kiocb *req, *tmp;
 	unsigned int poll_flags = BLK_POLL_NOSLEEP;
+	DEFINE_IO_COMP_BATCH(iob);
 	LIST_HEAD(done);
 
 	/*
@@ -2483,17 +2484,20 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		if (!list_empty(&done))
 			break;
 
-		ret = kiocb->ki_filp->f_op->iopoll(kiocb, NULL, poll_flags);
+		ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags);
 		if (unlikely(ret < 0))
 			return ret;
 		else if (ret)
 			poll_flags |= BLK_POLL_ONESHOT;
 
 		/* iopoll may have completed current req */
-		if (READ_ONCE(req->iopoll_completed))
+		if (!rq_list_empty(iob.req_list) ||
+		    READ_ONCE(req->iopoll_completed))
 			list_move_tail(&req->inflight_entry, &done);
 	}
 
+	if (!rq_list_empty(iob.req_list))
+		iob.complete(&iob);
 	if (!list_empty(&done))
 		io_iopoll_complete(ctx, nr_events, &done);