8 files changed, 150 insertions, 242 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f431c32774f3..7aeca5db7916 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -120,8 +120,12 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 	int ret;
 
 	ret = nvme_reset_ctrl(ctrl);
-	if (!ret)
+	if (!ret) {
 		flush_work(&ctrl->reset_work);
+		if (ctrl->state != NVME_CTRL_LIVE)
+			ret = -ENETRESET;
+	}
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);
@@ -265,7 +269,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_ADMIN_ONLY:
 		switch (old_state) {
-		case NVME_CTRL_RECONNECTING:
+		case NVME_CTRL_CONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -276,7 +280,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
-		case NVME_CTRL_RECONNECTING:
+		case NVME_CTRL_CONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -294,9 +298,9 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 			break;
 		}
 		break;
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		switch (old_state) {
-		case NVME_CTRL_LIVE:
+		case NVME_CTRL_NEW:
 		case NVME_CTRL_RESETTING:
 			changed = true;
 			/* FALLTHRU */
@@ -309,7 +313,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_ADMIN_ONLY:
 		case NVME_CTRL_RESETTING:
-		case NVME_CTRL_RECONNECTING:
+		case NVME_CTRL_CONNECTING:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -518,9 +522,11 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
 		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
 
-		range[n].cattr = cpu_to_le32(0);
-		range[n].nlb = cpu_to_le32(nlb);
-		range[n].slba = cpu_to_le64(slba);
+		if (n < segments) {
+			range[n].cattr = cpu_to_le32(0);
+			range[n].nlb = cpu_to_le32(nlb);
+			range[n].slba = cpu_to_le64(slba);
+		}
 		n++;
 	}
 
@@ -794,13 +800,9 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 
 static int nvme_keep_alive(struct nvme_ctrl *ctrl)
 {
-	struct nvme_command c;
 	struct request *rq;
 
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = nvme_admin_keep_alive;
-
-	rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED,
+	rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED,
 			NVME_QID_ANY);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
@@ -832,6 +834,8 @@ void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 		return;
 
 	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
+	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 EXPORT_SYMBOL_GPL(nvme_start_keep_alive);
@@ -1117,14 +1121,19 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns;
+	struct nvme_ns *ns, *next;
+	LIST_HEAD(rm_list);
 
 	mutex_lock(&ctrl->namespaces_mutex);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->disk && nvme_revalidate_disk(ns->disk))
-			nvme_ns_remove(ns);
+		if (ns->disk && nvme_revalidate_disk(ns->disk)) {
+			list_move_tail(&ns->list, &rm_list);
+		}
 	}
 	mutex_unlock(&ctrl->namespaces_mutex);
+
+	list_for_each_entry_safe(ns, next, &rm_list, list)
+		nvme_ns_remove(ns);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -2687,7 +2696,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 		[NVME_CTRL_LIVE]	= "live",
 		[NVME_CTRL_ADMIN_ONLY]	= "only-admin",
 		[NVME_CTRL_RESETTING]	= "resetting",
-		[NVME_CTRL_RECONNECTING]= "reconnecting",
+		[NVME_CTRL_CONNECTING]	= "connecting",
 		[NVME_CTRL_DELETING]	= "deleting",
 		[NVME_CTRL_DEAD]	= "dead",
 	};
@@ -2835,7 +2844,7 @@ out:
 }
 
 static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
-		struct nvme_id_ns *id, bool *new)
+		struct nvme_id_ns *id)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	bool is_shared = id->nmic & (1 << 0);
@@ -2851,8 +2860,6 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 			ret = PTR_ERR(head);
 			goto out_unlock;
 		}
-
-		*new = true;
 	} else {
 		struct nvme_ns_ids ids;
 
@@ -2864,8 +2871,6 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 			ret = -EINVAL;
 			goto out_unlock;
 		}
-
-		*new = false;
 	}
 
 	list_add_tail(&ns->siblings, &head->list);
@@ -2936,7 +2941,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	struct nvme_id_ns *id;
 	char disk_name[DISK_NAME_LEN];
 	int node = dev_to_node(ctrl->dev), flags = GENHD_FL_EXT_DEVT;
-	bool new = true;
 
 	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
@@ -2962,7 +2966,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (id->ncap == 0)
 		goto out_free_id;
 
-	if (nvme_init_ns_head(ns, nsid, id, &new))
+	if (nvme_init_ns_head(ns, nsid, id))
 		goto out_free_id;
 	nvme_setup_streams_ns(ctrl, ns);
 	
@@ -3028,9 +3032,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
 			ns->disk->disk_name);
 
-	if (new)
-		nvme_mpath_add_disk(ns->head);
-	nvme_mpath_add_disk_links(ns);
+	nvme_mpath_add_disk(ns->head);
 	return;
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
@@ -3050,7 +3052,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		return;
 
 	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
-		nvme_mpath_remove_disk_links(ns);
 		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_id_attr_group);
 		if (ns->ndev)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 5dd4ceefed8f..8f0f34d06d46 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -493,7 +493,7 @@ EXPORT_SYMBOL_GPL(nvmf_should_reconnect);
  */
 int nvmf_register_transport(struct nvmf_transport_ops *ops)
 {
-	if (!ops->create_ctrl || !ops->module)
+	if (!ops->create_ctrl)
 		return -EINVAL;
 
 	down_write(&nvmf_transports_rwsem);
@@ -650,6 +650,11 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				ret = -EINVAL;
 				goto out;
 			}
+			if (opts->discovery_nqn) {
+				pr_debug("Ignoring nr_io_queues value for discovery controller\n");
+				break;
+			}
+
 			opts->nr_io_queues = min_t(unsigned int,
 					num_online_cpus(), token);
 			break;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 25b19f722f5b..a3145d90c1d2 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -171,13 +171,14 @@ static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl,
 	    cmd->common.opcode != nvme_fabrics_command ||
 	    cmd->fabrics.fctype != nvme_fabrics_type_connect) {
 		/*
-		 * Reconnecting state means transport disruption, which can take
-		 * a long time and even might fail permanently, fail fast to
-		 * give upper layers a chance to failover.
+		 * Connecting state means transport disruption or initial
+		 * establishment, which can take a long time and even might
+		 * fail permanently, fail fast to give upper layers a chance
+		 * to failover.
 		 * Deleting state means that the ctrl will never accept commands
 		 * again, fail it permanently.
 		 */
-		if (ctrl->state == NVME_CTRL_RECONNECTING ||
+		if (ctrl->state == NVME_CTRL_CONNECTING ||
 		    ctrl->state == NVME_CTRL_DELETING) {
 			nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 			return BLK_STS_IOERR;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index b856d7c919d2..1dc1387b7134 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -55,9 +55,7 @@ struct nvme_fc_queue {
 
 enum nvme_fcop_flags {
 	FCOP_FLAGS_TERMIO	= (1 << 0),
-	FCOP_FLAGS_RELEASED	= (1 << 1),
-	FCOP_FLAGS_COMPLETE	= (1 << 2),
-	FCOP_FLAGS_AEN		= (1 << 3),
+	FCOP_FLAGS_AEN		= (1 << 1),
 };
 
 struct nvmefc_ls_req_op {
@@ -532,7 +530,7 @@ nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl)
 {
 	switch (ctrl->ctrl.state) {
 	case NVME_CTRL_NEW:
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		/*
 		 * As all reconnects were suppressed, schedule a
 		 * connect.
@@ -777,7 +775,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		}
 		break;
 
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		/*
 		 * The association has already been terminated and the
 		 * controller is attempting reconnects.  No need to do anything
@@ -1208,7 +1206,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
 				sizeof(struct fcnvme_lsdesc_cr_assoc_cmd));
 
 	assoc_rqst->assoc_cmd.ersp_ratio = cpu_to_be16(ersp_ratio);
-	assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize);
+	assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize - 1);
 	/* Linux supports only Dynamic controllers */
 	assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff);
 	uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id);
@@ -1323,7 +1321,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 				sizeof(struct fcnvme_lsdesc_cr_conn_cmd));
 	conn_rqst->connect_cmd.ersp_ratio = cpu_to_be16(ersp_ratio);
 	conn_rqst->connect_cmd.qid  = cpu_to_be16(queue->qnum);
-	conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize);
+	conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize - 1);
 
 	lsop->queue = queue;
 	lsreq->rqstaddr = conn_rqst;
@@ -1470,7 +1468,6 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
 
 /* *********************** NVME Ctrl Routines **************************** */
 
-static void __nvme_fc_final_op_cleanup(struct request *rq);
 static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg);
 
 static int
@@ -1512,13 +1509,19 @@ nvme_fc_exit_request(struct blk_mq_tag_set *set, struct request *rq,
 static int
 __nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op)
 {
-	int state;
+	unsigned long flags;
+	int opstate;
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	opstate = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
+	if (opstate != FCPOP_STATE_ACTIVE)
+		atomic_set(&op->state, opstate);
+	else if (ctrl->flags & FCCTRL_TERMIO)
+		ctrl->iocnt++;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
-	state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
-	if (state != FCPOP_STATE_ACTIVE) {
-		atomic_set(&op->state, state);
+	if (opstate != FCPOP_STATE_ACTIVE)
 		return -ECANCELED;
-	}
 
 	ctrl->lport->ops->fcp_abort(&ctrl->lport->localport,
 					&ctrl->rport->remoteport,
@@ -1532,60 +1535,26 @@ static void
 nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl)
 {
 	struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops;
-	unsigned long flags;
-	int i, ret;
-
-	for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) {
-		if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE)
-			continue;
-
-		spin_lock_irqsave(&ctrl->lock, flags);
-		if (ctrl->flags & FCCTRL_TERMIO) {
-			ctrl->iocnt++;
-			aen_op->flags |= FCOP_FLAGS_TERMIO;
-		}
-		spin_unlock_irqrestore(&ctrl->lock, flags);
-
-		ret = __nvme_fc_abort_op(ctrl, aen_op);
-		if (ret) {
-			/*
-			 * if __nvme_fc_abort_op failed the io wasn't
-			 * active. Thus this call path is running in
-			 * parallel to the io complete. Treat as non-error.
-			 */
+	int i;
 
-			/* back out the flags/counters */
-			spin_lock_irqsave(&ctrl->lock, flags);
-			if (ctrl->flags & FCCTRL_TERMIO)
-				ctrl->iocnt--;
-			aen_op->flags &= ~FCOP_FLAGS_TERMIO;
-			spin_unlock_irqrestore(&ctrl->lock, flags);
-			return;
-		}
-	}
+	for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++)
+		__nvme_fc_abort_op(ctrl, aen_op);
 }
 
-static inline int
+static inline void
 __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl,
-		struct nvme_fc_fcp_op *op)
+		struct nvme_fc_fcp_op *op, int opstate)
 {
 	unsigned long flags;
-	bool complete_rq = false;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
+	if (opstate == FCPOP_STATE_ABORTED) {
+		spin_lock_irqsave(&ctrl->lock, flags);
 		if (ctrl->flags & FCCTRL_TERMIO) {
 			if (!--ctrl->iocnt)
 				wake_up(&ctrl->ioabort_wait);
 		}
+		spin_unlock_irqrestore(&ctrl->lock, flags);
 	}
-	if (op->flags & FCOP_FLAGS_RELEASED)
-		complete_rq = true;
-	else
-		op->flags |= FCOP_FLAGS_COMPLETE;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	return complete_rq;
 }
 
 static void
@@ -1601,6 +1570,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	__le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1);
 	union nvme_result result;
 	bool terminate_assoc = true;
+	int opstate;
 
 	/*
 	 * WARNING:
@@ -1639,11 +1609,12 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	 * association to be terminated.
 	 */
 
+	opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE);
+
 	fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma,
 				sizeof(op->rsp_iu), DMA_FROM_DEVICE);
 
-	if (atomic_read(&op->state) == FCPOP_STATE_ABORTED ||
-			op->flags & FCOP_FLAGS_TERMIO)
+	if (opstate == FCPOP_STATE_ABORTED)
 		status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
 	else if (freq->status)
 		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
@@ -1708,7 +1679,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 done:
 	if (op->flags & FCOP_FLAGS_AEN) {
 		nvme_complete_async_event(&queue->ctrl->ctrl, status, &result);
-		__nvme_fc_fcpop_chk_teardowns(ctrl, op);
+		__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
 		atomic_set(&op->state, FCPOP_STATE_IDLE);
 		op->flags = FCOP_FLAGS_AEN;	/* clear other flags */
 		nvme_fc_ctrl_put(ctrl);
@@ -1722,13 +1693,11 @@ done:
 	if (status &&
 	    (blk_queue_dying(rq->q) ||
 	     ctrl->ctrl.state == NVME_CTRL_NEW ||
-	     ctrl->ctrl.state == NVME_CTRL_RECONNECTING))
+	     ctrl->ctrl.state == NVME_CTRL_CONNECTING))
 		status |= cpu_to_le16(NVME_SC_DNR << 1);
 
-	if (__nvme_fc_fcpop_chk_teardowns(ctrl, op))
-		__nvme_fc_final_op_cleanup(rq);
-	else
-		nvme_end_request(rq, status, result);
+	__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
+	nvme_end_request(rq, status, result);
 
 check_error:
 	if (terminate_assoc)
@@ -2415,46 +2384,16 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg)
 }
 
 static void
-__nvme_fc_final_op_cleanup(struct request *rq)
+nvme_fc_complete_rq(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
 
 	atomic_set(&op->state, FCPOP_STATE_IDLE);
-	op->flags &= ~(FCOP_FLAGS_TERMIO | FCOP_FLAGS_RELEASED |
-			FCOP_FLAGS_COMPLETE);
 
 	nvme_fc_unmap_data(ctrl, rq, op);
 	nvme_complete_rq(rq);
 	nvme_fc_ctrl_put(ctrl);
-
-}
-
-static void
-nvme_fc_complete_rq(struct request *rq)
-{
-	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
-	struct nvme_fc_ctrl *ctrl = op->ctrl;
-	unsigned long flags;
-	bool completed = false;
-
-	/*
-	 * the core layer, on controller resets after calling
-	 * nvme_shutdown_ctrl(), calls complete_rq without our
-	 * calling blk_mq_complete_request(), thus there may still
-	 * be live i/o outstanding with the LLDD. Means transport has
-	 * to track complete calls vs fcpio_done calls to know what
-	 * path to take on completes and dones.
-	 */
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (op->flags & FCOP_FLAGS_COMPLETE)
-		completed = true;
-	else
-		op->flags |= FCOP_FLAGS_RELEASED;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	if (completed)
-		__nvme_fc_final_op_cleanup(rq);
 }
 
 /*
@@ -2476,35 +2415,11 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
 	struct nvme_ctrl *nctrl = data;
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
-	unsigned long flags;
-	int status;
 
 	if (!blk_mq_request_started(req))
 		return;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (ctrl->flags & FCCTRL_TERMIO) {
-		ctrl->iocnt++;
-		op->flags |= FCOP_FLAGS_TERMIO;
-	}
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	status = __nvme_fc_abort_op(ctrl, op);
-	if (status) {
-		/*
-		 * if __nvme_fc_abort_op failed the io wasn't
-		 * active. Thus this call path is running in
-		 * parallel to the io complete. Treat as non-error.
-		 */
-
-		/* back out the flags/counters */
-		spin_lock_irqsave(&ctrl->lock, flags);
-		if (ctrl->flags & FCCTRL_TERMIO)
-			ctrl->iocnt--;
-		op->flags &= ~FCOP_FLAGS_TERMIO;
-		spin_unlock_irqrestore(&ctrl->lock, flags);
-		return;
-	}
+	__nvme_fc_abort_op(ctrl, op);
 }
 
 
@@ -2566,11 +2481,11 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 		goto out_free_tag_set;
 	}
 
-	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_cleanup_blk_queue;
 
-	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_delete_hw_queues;
 
@@ -2617,11 +2532,11 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (ret)
 		goto out_free_io_queues;
 
-	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_free_io_queues;
 
-	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+	ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1);
 	if (ret)
 		goto out_delete_hw_queues;
 
@@ -2717,13 +2632,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	nvme_fc_init_queue(ctrl, 0);
 
 	ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
-				NVME_AQ_BLK_MQ_DEPTH);
+				NVME_AQ_DEPTH);
 	if (ret)
 		goto out_free_queue;
 
 	ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0],
-				NVME_AQ_BLK_MQ_DEPTH,
-				(NVME_AQ_BLK_MQ_DEPTH / 4));
+				NVME_AQ_DEPTH, (NVME_AQ_DEPTH / 4));
 	if (ret)
 		goto out_delete_hw_queue;
 
@@ -2751,7 +2665,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	}
 
 	ctrl->ctrl.sqsize =
-		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap) + 1, ctrl->ctrl.sqsize);
+		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
 
 	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
 	if (ret)
@@ -2784,6 +2698,14 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		opts->queue_size = ctrl->ctrl.maxcmd;
 	}
 
+	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
+		/* warn if sqsize is lower than queue_size */
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl sqsize %u, clamping down\n",
+			opts->queue_size, ctrl->ctrl.sqsize + 1);
+		opts->queue_size = ctrl->ctrl.sqsize + 1;
+	}
+
 	ret = nvme_fc_init_aen_ops(ctrl);
 	if (ret)
 		goto out_term_aen_ops;
@@ -2943,7 +2865,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 	unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ;
 	bool recon = true;
 
-	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING)
+	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING)
 		return;
 
 	if (portptr->port_state == FC_OBJSTATE_ONLINE)
@@ -2991,10 +2913,10 @@ nvme_fc_reset_ctrl_work(struct work_struct *work)
 	/* will block will waiting for io to terminate */
 	nvme_fc_delete_association(ctrl);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		dev_err(ctrl->ctrl.device,
 			"NVME-FC{%d}: error_recovery: Couldn't change state "
-			"to RECONNECTING\n", ctrl->cnum);
+			"to CONNECTING\n", ctrl->cnum);
 		return;
 	}
 
@@ -3195,7 +3117,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	 * transport errors (frame drop, LS failure) inherently must kill
 	 * the association. The transport is coded so that any command used
 	 * to create the association (prior to a LIVE state transition
-	 * while NEW or RECONNECTING) will fail if it completes in error or
+	 * while NEW or CONNECTING) will fail if it completes in error or
 	 * times out.
 	 *
 	 * As such: as the connect request was mostly likely due to a
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 3b211d9e58b8..060f69e03427 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -198,30 +198,16 @@ void nvme_mpath_add_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	device_add_disk(&head->subsys->dev, head->disk);
-	if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
-			&nvme_ns_id_attr_group))
-		pr_warn("%s: failed to create sysfs group for identification\n",
-			head->disk->disk_name);
-}
-
-void nvme_mpath_add_disk_links(struct nvme_ns *ns)
-{
-	struct kobject *slave_disk_kobj, *holder_disk_kobj;
-
-	if (!ns->head->disk)
-		return;
-
-	slave_disk_kobj = &disk_to_dev(ns->disk)->kobj;
-	if (sysfs_create_link(ns->head->disk->slave_dir, slave_disk_kobj,
-			kobject_name(slave_disk_kobj)))
-		return;
 
-	holder_disk_kobj = &disk_to_dev(ns->head->disk)->kobj;
-	if (sysfs_create_link(ns->disk->part0.holder_dir, holder_disk_kobj,
-			kobject_name(holder_disk_kobj)))
-		sysfs_remove_link(ns->head->disk->slave_dir,
-			kobject_name(slave_disk_kobj));
+	mutex_lock(&head->subsys->lock);
+	if (!(head->disk->flags & GENHD_FL_UP)) {
+		device_add_disk(&head->subsys->dev, head->disk);
+		if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
+				&nvme_ns_id_attr_group))
+			pr_warn("%s: failed to create sysfs group for identification\n",
+				head->disk->disk_name);
+	}
+	mutex_unlock(&head->subsys->lock);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -238,14 +224,3 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	blk_cleanup_queue(head->disk->queue);
 	put_disk(head->disk);
 }
-
-void nvme_mpath_remove_disk_links(struct nvme_ns *ns)
-{
-	if (!ns->head->disk)
-		return;
-
-	sysfs_remove_link(ns->disk->part0.holder_dir,
-			kobject_name(&disk_to_dev(ns->head->disk)->kobj));
-	sysfs_remove_link(ns->head->disk->slave_dir,
-			kobject_name(&disk_to_dev(ns->disk)->kobj));
-}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 8e4550fa08f8..d733b14ede9d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -123,7 +123,7 @@ enum nvme_ctrl_state {
 	NVME_CTRL_LIVE,
 	NVME_CTRL_ADMIN_ONLY,    /* Only admin queue live */
 	NVME_CTRL_RESETTING,
-	NVME_CTRL_RECONNECTING,
+	NVME_CTRL_CONNECTING,
 	NVME_CTRL_DELETING,
 	NVME_CTRL_DEAD,
 };
@@ -183,6 +183,7 @@ struct nvme_ctrl {
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
+	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
 
 	/* Power saving configuration */
@@ -409,9 +410,7 @@ bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
 void nvme_mpath_add_disk(struct nvme_ns_head *head);
-void nvme_mpath_add_disk_links(struct nvme_ns *ns);
 void nvme_mpath_remove_disk(struct nvme_ns_head *head);
-void nvme_mpath_remove_disk_links(struct nvme_ns *ns);
 
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
@@ -453,12 +452,6 @@ static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
 static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 }
-static inline void nvme_mpath_add_disk_links(struct nvme_ns *ns)
-{
-}
-static inline void nvme_mpath_remove_disk_links(struct nvme_ns *ns)
-{
-}
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 6fe7af00a1f4..b6f43b738f03 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1141,7 +1141,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	/* If there is a reset/reinit ongoing, we shouldn't reset again. */
 	switch (dev->ctrl.state) {
 	case NVME_CTRL_RESETTING:
-	case NVME_CTRL_RECONNECTING:
+	case NVME_CTRL_CONNECTING:
 		return false;
 	default:
 		break;
@@ -1153,12 +1153,6 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	if (!(csts & NVME_CSTS_CFS) && !nssro)
 		return false;
 
-	/* If PCI error recovery process is happening, we cannot reset or
-	 * the recovery mechanism will surely fail.
-	 */
-	if (pci_channel_offline(to_pci_dev(dev->dev)))
-		return false;
-
 	return true;
 }
 
@@ -1189,6 +1183,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_command cmd;
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
+	/* If PCI error recovery process is happening, we cannot reset or
+	 * the recovery mechanism will surely fail.
+	 */
+	mb();
+	if (pci_channel_offline(to_pci_dev(dev->dev)))
+		return BLK_EH_RESET_TIMER;
+
 	/*
 	 * Reset immediately if the controller is failed
 	 */
@@ -1215,13 +1216,17 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * cancellation error. All outstanding requests are completed on
 	 * shutdown, so we return BLK_EH_HANDLED.
 	 */
-	if (dev->ctrl.state == NVME_CTRL_RESETTING) {
+	switch (dev->ctrl.state) {
+	case NVME_CTRL_CONNECTING:
+	case NVME_CTRL_RESETTING:
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_dev_disable(dev, false);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_HANDLED;
+	default:
+		break;
 	}
 
 	/*
@@ -1364,18 +1369,14 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 				int qid, int depth)
 {
-	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
-		unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth),
-						      dev->ctrl.page_size);
-		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
-		nvmeq->sq_cmds_io = dev->cmb + offset;
-	} else {
-		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
-					&nvmeq->sq_dma_addr, GFP_KERNEL);
-		if (!nvmeq->sq_cmds)
-			return -ENOMEM;
-	}
+	/* CMB SQEs will be mapped before creation */
+	if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS))
+		return 0;
 
+	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
+					    &nvmeq->sq_dma_addr, GFP_KERNEL);
+	if (!nvmeq->sq_cmds)
+		return -ENOMEM;
 	return 0;
 }
 
@@ -1449,10 +1450,17 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	struct nvme_dev *dev = nvmeq->dev;
 	int result;
 
+	if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
+		unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
+						      dev->ctrl.page_size);
+		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
+		nvmeq->sq_cmds_io = dev->cmb + offset;
+	}
+
 	nvmeq->cq_vector = qid - 1;
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
-		return result;
+		goto release_vector;
 
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
@@ -1466,9 +1474,12 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	return result;
 
  release_sq:
+	dev->online_queues--;
 	adapter_delete_sq(dev, qid);
  release_cq:
 	adapter_delete_cq(dev, qid);
+ release_vector:
+	nvmeq->cq_vector = -1;
 	return result;
 }
 
@@ -1903,7 +1914,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	int result, nr_io_queues;
 	unsigned long size;
 
-	nr_io_queues = num_present_cpus();
+	nr_io_queues = num_possible_cpus();
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
 	if (result < 0)
 		return result;
@@ -2288,12 +2299,12 @@ static void nvme_reset_work(struct work_struct *work)
 		nvme_dev_disable(dev, false);
 
 	/*
-	 * Introduce RECONNECTING state from nvme-fc/rdma transports to mark the
+	 * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
 	 * initializing procedure here.
 	 */
-	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
 		dev_warn(dev->ctrl.device,
-			"failed to mark controller RECONNECTING\n");
+			"failed to mark controller CONNECTING\n");
 		goto out;
 	}
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 2bc059f7d73c..4d84a73ee12d 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -887,7 +887,7 @@ free_ctrl:
 static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 {
 	/* If we are resetting/deleting then do nothing */
-	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) {
 		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
 			ctrl->ctrl.state == NVME_CTRL_LIVE);
 		return;
@@ -973,7 +973,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_start_queues(&ctrl->ctrl);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure should never happen */
 		WARN_ON_ONCE(1);
 		return;
@@ -1051,7 +1051,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 	struct nvme_rdma_device *dev = queue->device;
 	struct ib_device *ibdev = dev->dev;
 
-	if (!blk_rq_bytes(rq))
+	if (!blk_rq_payload_bytes(rq))
 		return;
 
 	if (req->mr) {
@@ -1166,7 +1166,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 
 	c->common.flags |= NVME_CMD_SGL_METABUF;
 
-	if (!blk_rq_bytes(rq))
+	if (!blk_rq_payload_bytes(rq))
 		return nvme_rdma_set_sg_null(c);
 
 	req->sg_table.sgl = req->first_sgl;
@@ -1756,7 +1756,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure should never happen */
 		WARN_ON_ONCE(1);
 		return;
@@ -1784,11 +1784,8 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 	return;
 
 out_fail:
-	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
-	nvme_remove_namespaces(&ctrl->ctrl);
-	nvme_rdma_shutdown_ctrl(ctrl, true);
-	nvme_uninit_ctrl(&ctrl->ctrl);
-	nvme_put_ctrl(&ctrl->ctrl);
+	++ctrl->ctrl.nr_reconnects;
+	nvme_rdma_reconnect_or_remove(ctrl);
 }
 
 static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
@@ -1942,6 +1939,9 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	if (!ctrl->queues)
 		goto out_uninit_ctrl;
 
+	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
+	WARN_ON_ONCE(!changed);
+
 	ret = nvme_rdma_configure_admin_queue(ctrl, true);
 	if (ret)
 		goto out_kfree_queues;