io-wq: perform both unstarted and started work cancelations in one go

Rather than split these into two separate lookups and matches, combine
them into one loop. This will become important when we can guarantee
that we don't have a window where a pending work item isn't discoverable
in either state.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io-wq.c

@@ -1072,27 +1072,25 @@ enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
 	 * First check pending list, if we're lucky we can just remove it
 	 * from there. CANCEL_OK means that the work is returned as-new,
 	 * no completion will be posted for it.
+	 *
+	 * Then check if a free (going busy) or busy worker has the work
+	 * currently running. If we find it there, we'll return CANCEL_RUNNING
+	 * as an indication that we attempt to signal cancellation. The
+	 * completion will run normally in this case.
+	 *
+	 * Do both of these while holding the wqe->lock, to ensure that
+	 * we'll find a work item regardless of state.
 	 */
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
 
 		raw_spin_lock(&wqe->lock);
 		io_wqe_cancel_pending_work(wqe, &match);
+		if (match.nr_pending && !match.cancel_all) {
 			raw_spin_unlock(&wqe->lock);
-		if (match.nr_pending && !match.cancel_all)
 			return IO_WQ_CANCEL_OK;
 		}
 
-	/*
-	 * Now check if a free (going busy) or busy worker has the work
-	 * currently running. If we find it there, we'll return CANCEL_RUNNING
-	 * as an indication that we attempt to signal cancellation. The
-	 * completion will run normally in this case.
-	 */
-	for_each_node(node) {
-		struct io_wqe *wqe = wq->wqes[node];
-
-		raw_spin_lock(&wqe->lock);
 		io_wqe_cancel_running_work(wqe, &match);
 		raw_spin_unlock(&wqe->lock);
 		if (match.nr_running && !match.cancel_all)