nvme-pci: Unblock reset_work on IO failure

The reset_work waits for queued IO to complete before setting the
controller to live. If any of these times out and requeues, we won't be
able to restart the controller because the reset_work is already running.

Flush all entered requests to a failed completion if a timeout occurs
in the connecting state, and ensure the controller can't transition to
the live state after we've unblocked it from waiting for completions.

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <keith.busch@intel.com>

drivers/nvme/host/pci.c

@@ -1257,7 +1257,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *abort_req;
 	struct nvme_command cmd;
-	bool shutdown = false;
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 	/* If PCI error recovery process is happening, we cannot reset or
@@ -1294,14 +1293,14 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * shutdown, so we return BLK_EH_DONE.
 	 */
 	switch (dev->ctrl.state) {
-	case NVME_CTRL_DELETING:
-		shutdown = true;
-		/* fall through */
 	case NVME_CTRL_CONNECTING:
+		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
+		/* fall through */
+	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
-		nvme_dev_disable(dev, shutdown);
+		nvme_dev_disable(dev, true);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_DONE;
 	case NVME_CTRL_RESETTING: