nvme: move the fabrics queue ready check routines to core

queue_rq() in pci only checks if the dispatched queue (nvmeq) is ready,
e.g. not being suspended. Since nvme_alloc_admin_tags() in reset flow
restarts the admin queue, users are able to submit admin commands to a
controller before reset_work() completes. Commands submitted under this
condition may interfere with commands that performs identify, IO queue
setup in reset_work(), and may result in a hang described in the
following patch.

As seen in the fabrics, user commands are prevented from being executed
under inproper controller states. We may reuse this logic to maintain a
clear admin queue during reset_work().

Signed-off-by: Tao Chiu <taochiu@synology.com>
Signed-off-by: Cody Wong <codywong@synology.com>
Reviewed-by: Leon Chien <leonchien@synology.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 60 insertions, 0 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 61e122cecc2a..522c9b229f80 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -639,6 +639,66 @@ static struct request *nvme_alloc_request_qid(struct request_queue *q,
 	return req;
 }
 
+/*
+ * For something we're not in a state to send to the device the default action
+ * is to busy it and retry it after the controller state is recovered.  However,
+ * if the controller is deleting or if anything is marked for failfast or
+ * nvme multipath it is immediately failed.
+ *
+ * Note: commands used to initialize the controller will be marked for failfast.
+ * Note: nvme cli/ioctl commands are marked for failfast.
+ */
+blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq)
+{
+	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
+	    ctrl->state != NVME_CTRL_DEAD &&
+	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
+	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+		return BLK_STS_RESOURCE;
+	return nvme_host_path_error(rq);
+}
+EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
+
+bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live)
+{
+	struct nvme_request *req = nvme_req(rq);
+
+	/*
+	 * currently we have a problem sending passthru commands
+	 * on the admin_q if the controller is not LIVE because we can't
+	 * make sure that they are going out after the admin connect,
+	 * controller enable and/or other commands in the initialization
+	 * sequence. until the controller will be LIVE, fail with
+	 * BLK_STS_RESOURCE so that they will be rescheduled.
+	 */
+	if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD))
+		return false;
+
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
+		/*
+		 * Only allow commands on a live queue, except for the connect
+		 * command, which is require to set the queue live in the
+		 * appropinquate states.
+		 */
+		switch (ctrl->state) {
+		case NVME_CTRL_CONNECTING:
+			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
+			    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
+				return true;
+			break;
+		default:
+			break;
+		case NVME_CTRL_DEAD:
+			return false;
+		}
+	}
+
+	return queue_live;
+}
+EXPORT_SYMBOL_GPL(__nvme_check_ready);
+
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
 	struct nvme_command c;