nvme fixes for Linux 5.13

- fix a memory leak in nvme_cdev_add (Guoqing Jiang)
  - fix inline data size comparison in nvmet_tcp_queue_response (Hou Pu)
  - fix false keep-alive timeout when a controller is torn down
    (Sagi Grimberg)
  - fix a nvme-tcp Kconfig dependency (Sagi Grimberg)
  - short-circuit reconnect retries for FC (Hannes Reinecke)
  - decode host pathing error for connect (Hannes Reinecke)
 -----BEGIN PGP SIGNATURE-----
 
 iQI/BAABCgApFiEEgdbnc3r/njty3Iq9D55TZVIEUYMFAmCviQcLHGhjaEBsc3Qu
 ZGUACgkQD55TZVIEUYOl2BAAsFnUbt+2oYKzNldYHGewAv+v33uwtN88zCChbEXu
 6Saj0M5B4s9LbpyXdz2l8cb8CtmvSnFRjbHpdKny0E0qXGKp1YHbcTlefBiMeDPp
 YME543oAZ1rACafiLFwr/7Ys50Frtel9hNWty2Fgv8Q2eiyQRJnQvJHfwQ/Fk9g2
 swtVLbO83RwAef+kcLZaJojLeBlvW55vl/Srj5qj6tMPNl5DUgjUmioPTnFdo0ty
 6iEyAurXpcdbMIjYdgulbAypyQIvKyzcXgi0BVuxAbCV9DBKdrwP0ob/HDyYsNBX
 8sRUQnIfLketBKsIvuwhVcLr27HYHyDAHiGc70iG1ndrvdfkEKDP5BEwZxkNOA7d
 TbjvFanQIlvxkz419KIZo3SIdrG88DcYz5Ai0MxA8RuiKPJUE+Iksp8aCds/3dLR
 urfXHyHvj/O5US+xej0j5K63oVW7KPri3mbnFgfSHhmpg1KXBTmVk9a2Gz7ZyKIO
 XVHaq1kQHhvE0Kp1juZNqJ/ojd17wQP7bFIBGEHo6IPJtDILa0IQOw1S2aPX+/+q
 45dJqFxndco8oCyl81ynax9n+T3nA4DJs20a6j7fYbQnJpwKBiSKQsUbVWPybKzM
 rq+/7PlsGbjSsQwf1dTvhF04j/5HqTT5A+LUsLR6Jm7sPPYkws36PC7Cqr9sUxPX
 RYo=
 =JT0/
 -----END PGP SIGNATURE-----

Merge tag 'nvme-5.13-2021-05-27' of git://git.infradead.org/nvme into block-5.13

Pull NVMe fixes from Christoph:

"nvme fixes for Linux 5.13

 - fix a memory leak in nvme_cdev_add (Guoqing Jiang)
 - fix inline data size comparison in nvmet_tcp_queue_response (Hou Pu)
 - fix false keep-alive timeout when a controller is torn down
   (Sagi Grimberg)
 - fix a nvme-tcp Kconfig dependency (Sagi Grimberg)
 - short-circuit reconnect retries for FC (Hannes Reinecke)
 - decode host pathing error for connect (Hannes Reinecke)"

* tag 'nvme-5.13-2021-05-27' of git://git.infradead.org/nvme:
  nvmet: fix false keep-alive timeout when a controller is torn down
  nvmet-tcp: fix inline data size comparison in nvmet_tcp_queue_response
  nvme-tcp: remove incorrect Kconfig dep in BLK_DEV_NVME
  nvme-fabrics: decode host pathing error for connect
  nvme-fc: short-circuit reconnect retries
  nvme: fix potential memory leaks in nvme_cdev_add

drivers/nvme/host/Kconfig

@@ -71,7 +71,8 @@ config NVME_FC
 config NVME_TCP
 	tristate "NVM Express over Fabrics TCP host driver"
 	depends on INET
-	depends on BLK_DEV_NVME
+	depends on BLOCK
+	select NVME_CORE
 	select NVME_FABRICS
 	select CRYPTO
 	select CRYPTO_CRC32C

drivers/nvme/host/core.c

@@ -3485,8 +3485,10 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
 	cdev_init(cdev, fops);
 	cdev->owner = owner;
 	ret = cdev_device_add(cdev, cdev_device);
-	if (ret)
+	if (ret) {
+		put_device(cdev_device);
 		ida_simple_remove(&nvme_ns_chr_minor_ida, minor);
+	}
 	return ret;
 }
 

drivers/nvme/host/fabrics.c

@@ -336,6 +336,11 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
 			cmd->connect.recfmt);
 		break;
 
+	case NVME_SC_HOST_PATH_ERROR:
+		dev_err(ctrl->device,
+			"Connect command failed: host path error\n");
+		break;
+
 	default:
 		dev_err(ctrl->device,
 			"Connect command failed, error wo/DNR bit: %d\n",

drivers/nvme/host/fc.c

@@ -3107,6 +3107,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (ctrl->ctrl.icdoff) {
 		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
 				ctrl->ctrl.icdoff);
+		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto out_disconnect_admin_queue;
 	}
 
@@ -3114,6 +3115,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) {
 		dev_err(ctrl->ctrl.device,
 			"Mandatory sgls are not supported!\n");
+		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto out_disconnect_admin_queue;
 	}
 
@@ -3280,11 +3282,13 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING)
 		return;
 
-	if (portptr->port_state == FC_OBJSTATE_ONLINE)
+	if (portptr->port_state == FC_OBJSTATE_ONLINE) {
 		dev_info(ctrl->ctrl.device,
 			"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
 			ctrl->cnum, status);
-	else if (time_after_eq(jiffies, rport->dev_loss_end))
+		if (status > 0 && (status & NVME_SC_DNR))
+			recon = false;
+	} else if (time_after_eq(jiffies, rport->dev_loss_end))
 		recon = false;
 
 	if (recon && nvmf_should_reconnect(&ctrl->ctrl)) {
@@ -3298,12 +3302,17 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 
 		queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay);
 	} else {
-		if (portptr->port_state == FC_OBJSTATE_ONLINE)
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Max reconnect attempts (%d) "
-				"reached.\n",
-				ctrl->cnum, ctrl->ctrl.nr_reconnects);
-		else
+		if (portptr->port_state == FC_OBJSTATE_ONLINE) {
+			if (status > 0 && (status & NVME_SC_DNR))
+				dev_warn(ctrl->ctrl.device,
+					 "NVME-FC{%d}: reconnect failure\n",
+					 ctrl->cnum);
+			else
+				dev_warn(ctrl->ctrl.device,
+					 "NVME-FC{%d}: Max reconnect attempts "
+					 "(%d) reached.\n",
+					 ctrl->cnum, ctrl->ctrl.nr_reconnects);
+		} else
 			dev_warn(ctrl->ctrl.device,
 				"NVME-FC{%d}: dev_loss_tmo (%d) expired "
 				"while waiting for remoteport connectivity.\n",

drivers/nvme/target/core.c

@@ -388,10 +388,10 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 {
 	struct nvmet_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvmet_ctrl, ka_work);
-	bool cmd_seen = ctrl->cmd_seen;
+	bool reset_tbkas = ctrl->reset_tbkas;
 
-	ctrl->cmd_seen = false;
-	if (cmd_seen) {
+	ctrl->reset_tbkas = false;
+	if (reset_tbkas) {
 		pr_debug("ctrl %d reschedule traffic based keep-alive timer\n",
 			ctrl->cntlid);
 		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
@@ -804,6 +804,13 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
 	percpu_ref_exit(&sq->ref);
 
 	if (ctrl) {
+		/*
+		 * The teardown flow may take some time, and the host may not
+		 * send us keep-alive during this period, hence reset the
+		 * traffic based keep-alive timer so we don't trigger a
+		 * controller teardown as a result of a keep-alive expiration.
+		 */
+		ctrl->reset_tbkas = true;
 		nvmet_ctrl_put(ctrl);
 		sq->ctrl = NULL; /* allows reusing the queue later */
 	}
@@ -952,7 +959,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	}
 
 	if (sq->ctrl)
-		sq->ctrl->cmd_seen = true;
+		sq->ctrl->reset_tbkas = true;
 
 	return true;
 

drivers/nvme/target/nvmet.h

@@ -167,7 +167,7 @@ struct nvmet_ctrl {
 	struct nvmet_subsys	*subsys;
 	struct nvmet_sq		**sqs;
 
-	bool			cmd_seen;
+	bool			reset_tbkas;
 
 	struct mutex		lock;
 	u64			cap;

drivers/nvme/target/tcp.c

@@ -550,7 +550,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 		 * nvmet_req_init is completed.
 		 */
 		if (queue->rcv_state == NVMET_TCP_RECV_PDU &&
-		    len && len < cmd->req.port->inline_data_size &&
+		    len && len <= cmd->req.port->inline_data_size &&
 		    nvme_is_write(cmd->req.cmd))
 			return;
 	}