1 files changed, 200 insertions, 217 deletions

diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 717ed7ddb2f6..fc8e7c9ad858 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -1,15 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * NVMe over Fabrics loopback device.
  * Copyright (c) 2015-2016 HGST, a Western Digital Company.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/scatterlist.h>
@@ -23,18 +15,10 @@
 
 #define NVME_LOOP_MAX_SEGMENTS		256
 
-/*
- * We handle AEN commands ourselves and don't even let the
- * block layer know about them.
- */
-#define NVME_LOOP_NR_AEN_COMMANDS	1
-#define NVME_LOOP_AQ_BLKMQ_DEPTH	\
-	(NVME_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS)
-
 struct nvme_loop_iod {
 	struct nvme_request	nvme_req;
 	struct nvme_command	cmd;
-	struct nvme_completion	rsp;
+	struct nvme_completion	cqe;
 	struct nvmet_req	req;
 	struct nvme_loop_queue	*queue;
 	struct work_struct	work;
@@ -49,11 +33,12 @@ struct nvme_loop_ctrl {
 
 	struct list_head	list;
 	struct blk_mq_tag_set	tag_set;
-	struct nvme_loop_iod	async_event_iod;
 	struct nvme_ctrl	ctrl;
 
-	struct nvmet_ctrl	*target_ctrl;
-	struct work_struct	delete_work;
+	struct nvmet_port	*port;
+
+	/* Must be last --ends in a flexible-array member. */
+	struct nvme_loop_iod	async_event_iod;
 };
 
 static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
@@ -61,13 +46,19 @@ static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
 	return container_of(ctrl, struct nvme_loop_ctrl, ctrl);
 }
 
+enum nvme_loop_queue_flags {
+	NVME_LOOP_Q_LIVE	= 0,
+};
+
 struct nvme_loop_queue {
 	struct nvmet_cq		nvme_cq;
 	struct nvmet_sq		nvme_sq;
 	struct nvme_loop_ctrl	*ctrl;
+	unsigned long		flags;
 };
 
-static struct nvmet_port *nvmet_loop_port;
+static LIST_HEAD(nvme_loop_ports);
+static DEFINE_MUTEX(nvme_loop_ports_mutex);
 
 static LIST_HEAD(nvme_loop_ctrl_list);
 static DEFINE_MUTEX(nvme_loop_ctrl_mutex);
@@ -75,7 +66,7 @@ static DEFINE_MUTEX(nvme_loop_ctrl_mutex);
 static void nvme_loop_queue_response(struct nvmet_req *nvme_req);
 static void nvme_loop_delete_ctrl(struct nvmet_ctrl *ctrl);
 
-static struct nvmet_fabrics_ops nvme_loop_ops;
+static const struct nvmet_fabrics_ops nvme_loop_ops;
 
 static inline int nvme_loop_queue_idx(struct nvme_loop_queue *queue)
 {
@@ -86,8 +77,7 @@ static void nvme_loop_complete_rq(struct request *req)
 {
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
 
-	nvme_cleanup_cmd(req);
-	sg_free_table_chained(&iod->sg_table, true);
+	sg_free_table_chained(&iod->sg_table, NVME_INLINE_SG_CNT);
 	nvme_complete_rq(req);
 }
 
@@ -104,7 +94,7 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 {
 	struct nvme_loop_queue *queue =
 		container_of(req->sq, struct nvme_loop_queue, nvme_sq);
-	struct nvme_completion *cqe = req->rsp;
+	struct nvme_completion *cqe = req->cqe;
 
 	/*
 	 * AEN requests are special as they don't time out and can
@@ -112,22 +102,23 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvme_loop_queue_idx(queue) == 0 &&
-			cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) {
+	if (unlikely(nvme_is_aen_req(nvme_loop_queue_idx(queue),
+				     cqe->command_id))) {
 		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
 				&cqe->result);
 	} else {
 		struct request *rq;
 
-		rq = blk_mq_tag_to_rq(nvme_loop_tagset(queue), cqe->command_id);
+		rq = nvme_find_rq(nvme_loop_tagset(queue), cqe->command_id);
 		if (!rq) {
 			dev_err(queue->ctrl->ctrl.device,
-				"tag 0x%x on queue %d not found\n",
+				"got bad command_id %#x on queue %d\n",
 				cqe->command_id, nvme_loop_queue_idx(queue));
 			return;
 		}
 
-		nvme_end_request(rq, cqe->status, cqe->result);
+		if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
+			nvme_loop_complete_rq(rq);
 	}
 }
 
@@ -139,20 +130,6 @@ static void nvme_loop_execute_work(struct work_struct *work)
 	iod->req.execute(&iod->req);
 }
 
-static enum blk_eh_timer_return
-nvme_loop_timeout(struct request *rq, bool reserved)
-{
-	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(rq);
-
-	/* queue error recovery */
-	nvme_reset_ctrl(&iod->queue->ctrl->ctrl);
-
-	/* fail with DNR on admin cmd timeout */
-	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
-
-	return BLK_EH_HANDLED;
-}
-
 static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
@@ -160,40 +137,41 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_loop_queue *queue = hctx->driver_data;
 	struct request *req = bd->rq;
 	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
+	bool queue_ready = test_bit(NVME_LOOP_Q_LIVE, &queue->flags);
 	blk_status_t ret;
 
-	ret = nvme_setup_cmd(ns, req, &iod->cmd);
+	if (!nvme_check_ready(&queue->ctrl->ctrl, req, queue_ready))
+		return nvme_fail_nonready_command(&queue->ctrl->ctrl, req);
+
+	ret = nvme_setup_cmd(ns, req);
 	if (ret)
 		return ret;
 
+	nvme_start_request(req);
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
-	iod->req.port = nvmet_loop_port;
-	if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
-			&queue->nvme_sq, &nvme_loop_ops)) {
-		nvme_cleanup_cmd(req);
-		blk_mq_start_request(req);
-		nvme_loop_queue_response(&iod->req);
+	iod->req.port = queue->ctrl->port;
+	if (!nvmet_req_init(&iod->req, &queue->nvme_sq, &nvme_loop_ops))
 		return BLK_STS_OK;
-	}
 
-	if (blk_rq_bytes(req)) {
+	if (blk_rq_nr_phys_segments(req)) {
 		iod->sg_table.sgl = iod->first_sgl;
 		if (sg_alloc_table_chained(&iod->sg_table,
 				blk_rq_nr_phys_segments(req),
-				iod->sg_table.sgl))
+				iod->sg_table.sgl, NVME_INLINE_SG_CNT)) {
+			nvme_cleanup_cmd(req);
 			return BLK_STS_RESOURCE;
+		}
 
 		iod->req.sg = iod->sg_table.sgl;
-		iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
+		iod->req.sg_cnt = blk_rq_map_sg(req, iod->sg_table.sgl);
+		iod->req.transfer_len = blk_rq_payload_bytes(req);
 	}
 
-	blk_mq_start_request(req);
-
-	schedule_work(&iod->work);
+	queue_work(nvmet_wq, &iod->work);
 	return BLK_STS_OK;
 }
 
-static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
+static void nvme_loop_submit_async_event(struct nvme_ctrl *arg)
 {
 	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(arg);
 	struct nvme_loop_queue *queue = &ctrl->queues[0];
@@ -201,23 +179,22 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
 
 	memset(&iod->cmd, 0, sizeof(iod->cmd));
 	iod->cmd.common.opcode = nvme_admin_async_event;
-	iod->cmd.common.command_id = NVME_LOOP_AQ_BLKMQ_DEPTH;
+	iod->cmd.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
 
-	if (!nvmet_req_init(&iod->req, &queue->nvme_cq, &queue->nvme_sq,
-			&nvme_loop_ops)) {
+	if (!nvmet_req_init(&iod->req, &queue->nvme_sq, &nvme_loop_ops)) {
 		dev_err(ctrl->ctrl.device, "failed async event work\n");
 		return;
 	}
 
-	schedule_work(&iod->work);
+	queue_work(nvmet_wq, &iod->work);
 }
 
 static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl,
 		struct nvme_loop_iod *iod, unsigned int queue_idx)
 {
 	iod->req.cmd = &iod->cmd;
-	iod->req.rsp = &iod->rsp;
+	iod->req.cqe = &iod->cqe;
 	iod->queue = &ctrl->queues[queue_idx];
 	INIT_WORK(&iod->work, nvme_loop_execute_work);
 	return 0;
@@ -227,20 +204,33 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set,
 		struct request *req, unsigned int hctx_idx,
 		unsigned int numa_node)
 {
-	struct nvme_loop_ctrl *ctrl = set->driver_data;
+	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(set->driver_data);
+	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
 
+	nvme_req(req)->ctrl = &ctrl->ctrl;
+	nvme_req(req)->cmd = &iod->cmd;
 	return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req),
 			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
 }
 
+static struct lock_class_key loop_hctx_fq_lock_key;
+
 static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 		unsigned int hctx_idx)
 {
-	struct nvme_loop_ctrl *ctrl = data;
+	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(data);
 	struct nvme_loop_queue *queue = &ctrl->queues[hctx_idx + 1];
 
 	BUG_ON(hctx_idx >= ctrl->ctrl.queue_count);
 
+	/*
+	 * flush_end_io() can be called recursively for us, so use our own
+	 * lock class key for avoiding lockdep possible recursive locking,
+	 * then we can remove the dynamically allocated lock class for each
+	 * flush queue, that way may cause horrible boot delay.
+	 */
+	blk_mq_hctx_set_fq_lock_class(hctx, &loop_hctx_fq_lock_key);
+
 	hctx->driver_data = queue;
 	return 0;
 }
@@ -248,7 +238,7 @@ static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 		unsigned int hctx_idx)
 {
-	struct nvme_loop_ctrl *ctrl = data;
+	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(data);
 	struct nvme_loop_queue *queue = &ctrl->queues[0];
 
 	BUG_ON(hctx_idx != 0);
@@ -262,7 +252,6 @@ static const struct blk_mq_ops nvme_loop_mq_ops = {
 	.complete	= nvme_loop_complete_rq,
 	.init_request	= nvme_loop_init_request,
 	.init_hctx	= nvme_loop_init_hctx,
-	.timeout	= nvme_loop_timeout,
 };
 
 static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
@@ -270,14 +259,22 @@ static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
 	.complete	= nvme_loop_complete_rq,
 	.init_request	= nvme_loop_init_request,
 	.init_hctx	= nvme_loop_init_admin_hctx,
-	.timeout	= nvme_loop_timeout,
 };
 
 static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
 {
+	if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags))
+		return;
+	/*
+	 * It's possible that some requests might have been added
+	 * after admin queue is stopped/quiesced. So now start the
+	 * queue to flush these requests to the completion.
+	 */
+	nvme_unquiesce_admin_queue(&ctrl->ctrl);
+
 	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
-	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+	nvmet_cq_put(&ctrl->queues[0].nvme_cq);
+	nvme_remove_admin_tag_set(&ctrl->ctrl);
 }
 
 static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl)
@@ -291,10 +288,8 @@ static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl)
 	list_del(&ctrl->list);
 	mutex_unlock(&nvme_loop_ctrl_mutex);
 
-	if (nctrl->tagset) {
-		blk_cleanup_queue(ctrl->ctrl.connect_q);
-		blk_mq_free_tag_set(&ctrl->tag_set);
-	}
+	if (nctrl->tagset)
+		nvme_remove_io_tag_set(nctrl);
 	kfree(ctrl->queues);
 	nvmf_free_options(nctrl->opts);
 free_ctrl:
@@ -305,8 +300,18 @@ static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
 {
 	int i;
 
-	for (i = 1; i < ctrl->ctrl.queue_count; i++)
+	for (i = 1; i < ctrl->ctrl.queue_count; i++) {
+		clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
 		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+		nvmet_cq_put(&ctrl->queues[i].nvme_cq);
+	}
+	ctrl->ctrl.queue_count = 1;
+	/*
+	 * It's possible that some requests might have been added
+	 * after io queue is stopped/quiesced. So now start the
+	 * queue to flush these requests to the completion.
+	 */
+	nvme_unquiesce_io_queues(&ctrl->ctrl);
 }
 
 static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -324,9 +329,13 @@ static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
 
 	for (i = 1; i <= nr_io_queues; i++) {
 		ctrl->queues[i].ctrl = ctrl;
-		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
-		if (ret)
+		nvmet_cq_init(&ctrl->queues[i].nvme_cq);
+		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq,
+				&ctrl->queues[i].nvme_cq);
+		if (ret) {
+			nvmet_cq_put(&ctrl->queues[i].nvme_cq);
 			goto out_destroy_queues;
+		}
 
 		ctrl->ctrl.queue_count++;
 	}
@@ -346,6 +355,7 @@ static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
 		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
 		if (ret)
 			return ret;
+		set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
 	}
 
 	return 0;
@@ -355,123 +365,75 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 {
 	int error;
 
-	memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
-	ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops;
-	ctrl->admin_tag_set.queue_depth = NVME_LOOP_AQ_BLKMQ_DEPTH;
-	ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
-	ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
-	ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
-		SG_CHUNK_SIZE * sizeof(struct scatterlist);
-	ctrl->admin_tag_set.driver_data = ctrl;
-	ctrl->admin_tag_set.nr_hw_queues = 1;
-	ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
-
 	ctrl->queues[0].ctrl = ctrl;
-	error = nvmet_sq_init(&ctrl->queues[0].nvme_sq);
-	if (error)
+	nvmet_cq_init(&ctrl->queues[0].nvme_cq);
+	error = nvmet_sq_init(&ctrl->queues[0].nvme_sq,
+			&ctrl->queues[0].nvme_cq);
+	if (error) {
+		nvmet_cq_put(&ctrl->queues[0].nvme_cq);
 		return error;
+	}
 	ctrl->ctrl.queue_count = 1;
 
-	error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
+	error = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set,
+			&nvme_loop_admin_mq_ops,
+			sizeof(struct nvme_loop_iod) +
+			NVME_INLINE_SG_CNT * sizeof(struct scatterlist));
 	if (error)
 		goto out_free_sq;
 
-	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
-	if (IS_ERR(ctrl->ctrl.admin_q)) {
-		error = PTR_ERR(ctrl->ctrl.admin_q);
-		goto out_free_tagset;
-	}
+	/* reset stopped state for the fresh admin queue */
+	clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->ctrl.flags);
 
 	error = nvmf_connect_admin_queue(&ctrl->ctrl);
 	if (error)
-		goto out_cleanup_queue;
+		goto out_cleanup_tagset;
 
-	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
-	if (error) {
-		dev_err(ctrl->ctrl.device,
-			"prop_get NVME_REG_CAP failed\n");
-		goto out_cleanup_queue;
-	}
-
-	ctrl->ctrl.sqsize =
-		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
+	set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
 
-	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
+	error = nvme_enable_ctrl(&ctrl->ctrl);
 	if (error)
-		goto out_cleanup_queue;
+		goto out_cleanup_tagset;
 
 	ctrl->ctrl.max_hw_sectors =
-		(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
+		(NVME_LOOP_MAX_SEGMENTS - 1) << PAGE_SECTORS_SHIFT;
 
-	error = nvme_init_identify(&ctrl->ctrl);
+	nvme_unquiesce_admin_queue(&ctrl->ctrl);
+
+	error = nvme_init_ctrl_finish(&ctrl->ctrl, false);
 	if (error)
-		goto out_cleanup_queue;
+		goto out_cleanup_tagset;
 
 	return 0;
 
-out_cleanup_queue:
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
-out_free_tagset:
-	blk_mq_free_tag_set(&ctrl->admin_tag_set);
+out_cleanup_tagset:
+	clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
+	nvme_remove_admin_tag_set(&ctrl->ctrl);
 out_free_sq:
 	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
+	nvmet_cq_put(&ctrl->queues[0].nvme_cq);
 	return error;
 }
 
 static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 {
 	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
+		nvme_quiesce_io_queues(&ctrl->ctrl);
+		nvme_cancel_tagset(&ctrl->ctrl);
 		nvme_loop_destroy_io_queues(ctrl);
 	}
 
-	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
-		nvme_shutdown_ctrl(&ctrl->ctrl);
+	nvme_quiesce_admin_queue(&ctrl->ctrl);
+	if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE)
+		nvme_disable_ctrl(&ctrl->ctrl, true);
 
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 	nvme_loop_destroy_admin_queue(ctrl);
 }
 
-static void nvme_loop_del_ctrl_work(struct work_struct *work)
-{
-	struct nvme_loop_ctrl *ctrl = container_of(work,
-				struct nvme_loop_ctrl, delete_work);
-
-	nvme_stop_ctrl(&ctrl->ctrl);
-	nvme_remove_namespaces(&ctrl->ctrl);
-	nvme_loop_shutdown_ctrl(ctrl);
-	nvme_uninit_ctrl(&ctrl->ctrl);
-	nvme_put_ctrl(&ctrl->ctrl);
-}
-
-static int __nvme_loop_del_ctrl(struct nvme_loop_ctrl *ctrl)
+static void nvme_loop_delete_ctrl_host(struct nvme_ctrl *ctrl)
 {
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
-		return -EBUSY;
-
-	if (!queue_work(nvme_wq, &ctrl->delete_work))
-		return -EBUSY;
-
-	return 0;
-}
-
-static int nvme_loop_del_ctrl(struct nvme_ctrl *nctrl)
-{
-	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl);
-	int ret;
-
-	ret = __nvme_loop_del_ctrl(ctrl);
-	if (ret)
-		return ret;
-
-	flush_work(&ctrl->delete_work);
-
-	return 0;
+	nvme_loop_shutdown_ctrl(to_loop_ctrl(ctrl));
 }
 
 static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl)
@@ -481,7 +443,7 @@ static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl)
 	mutex_lock(&nvme_loop_ctrl_mutex);
 	list_for_each_entry(ctrl, &nvme_loop_ctrl_list, list) {
 		if (ctrl->ctrl.cntlid == nctrl->cntlid)
-			__nvme_loop_del_ctrl(ctrl);
+			nvme_delete_ctrl(&ctrl->ctrl);
 	}
 	mutex_unlock(&nvme_loop_ctrl_mutex);
 }
@@ -490,12 +452,21 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_loop_ctrl *ctrl =
 		container_of(work, struct nvme_loop_ctrl, ctrl.reset_work);
-	bool changed;
 	int ret;
 
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_loop_shutdown_ctrl(ctrl);
 
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		if (state != NVME_CTRL_DELETING &&
+		    state != NVME_CTRL_DELETING_NOIO)
+			/* state change failure for non-deleted ctrl? */
+			WARN_ON_ONCE(1);
+		return;
+	}
+
 	ret = nvme_loop_configure_admin_queue(ctrl);
 	if (ret)
 		goto out_disable;
@@ -511,8 +482,8 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 	blk_mq_update_nr_hw_queues(&ctrl->tag_set,
 			ctrl->ctrl.queue_count - 1);
 
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE))
+		WARN_ON_ONCE(1);
 
 	nvme_start_ctrl(&ctrl->ctrl);
 
@@ -521,11 +492,12 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 out_destroy_io:
 	nvme_loop_destroy_io_queues(ctrl);
 out_destroy_admin:
+	nvme_quiesce_admin_queue(&ctrl->ctrl);
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 	nvme_loop_destroy_admin_queue(ctrl);
 out_disable:
 	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
 	nvme_uninit_ctrl(&ctrl->ctrl);
-	nvme_put_ctrl(&ctrl->ctrl);
 }
 
 static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
@@ -537,7 +509,9 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.reg_write32		= nvmf_reg_write32,
 	.free_ctrl		= nvme_loop_free_ctrl,
 	.submit_async_event	= nvme_loop_submit_async_event,
-	.delete_ctrl		= nvme_loop_del_ctrl,
+	.delete_ctrl		= nvme_loop_delete_ctrl_host,
+	.get_address		= nvmf_get_address,
+	.get_virt_boundary	= nvme_get_virt_boundary,
 };
 
 static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -548,49 +522,47 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 	if (ret)
 		return ret;
 
-	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
-	ctrl->tag_set.ops = &nvme_loop_mq_ops;
-	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
-	ctrl->tag_set.reserved_tags = 1; /* fabric connect */
-	ctrl->tag_set.numa_node = NUMA_NO_NODE;
-	ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
-	ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
-		SG_CHUNK_SIZE * sizeof(struct scatterlist);
-	ctrl->tag_set.driver_data = ctrl;
-	ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1;
-	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
-	ctrl->ctrl.tagset = &ctrl->tag_set;
-
-	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
+	ret = nvme_alloc_io_tag_set(&ctrl->ctrl, &ctrl->tag_set,
+			&nvme_loop_mq_ops, 1,
+			sizeof(struct nvme_loop_iod) +
+			NVME_INLINE_SG_CNT * sizeof(struct scatterlist));
 	if (ret)
 		goto out_destroy_queues;
 
-	ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
-	if (IS_ERR(ctrl->ctrl.connect_q)) {
-		ret = PTR_ERR(ctrl->ctrl.connect_q);
-		goto out_free_tagset;
-	}
-
 	ret = nvme_loop_connect_io_queues(ctrl);
 	if (ret)
-		goto out_cleanup_connect_q;
+		goto out_cleanup_tagset;
 
 	return 0;
 
-out_cleanup_connect_q:
-	blk_cleanup_queue(ctrl->ctrl.connect_q);
-out_free_tagset:
-	blk_mq_free_tag_set(&ctrl->tag_set);
+out_cleanup_tagset:
+	nvme_remove_io_tag_set(&ctrl->ctrl);
 out_destroy_queues:
 	nvme_loop_destroy_io_queues(ctrl);
 	return ret;
 }
 
+static struct nvmet_port *nvme_loop_find_port(struct nvme_ctrl *ctrl)
+{
+	struct nvmet_port *p, *found = NULL;
+
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_for_each_entry(p, &nvme_loop_ports, entry) {
+		/* if no transport address is specified use the first port */
+		if ((ctrl->opts->mask & NVMF_OPT_TRADDR) &&
+		    strcmp(ctrl->opts->traddr, p->disc_addr.traddr))
+			continue;
+		found = p;
+		break;
+	}
+	mutex_unlock(&nvme_loop_ports_mutex);
+	return found;
+}
+
 static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 		struct nvmf_ctrl_options *opts)
 {
 	struct nvme_loop_ctrl *ctrl;
-	bool changed;
 	int ret;
 
 	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
@@ -599,18 +571,26 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
 
-	INIT_WORK(&ctrl->delete_work, nvme_loop_del_ctrl_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_loop_reset_ctrl_work);
 
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops,
 				0 /* no quirks, we're perfect! */);
+	if (ret) {
+		kfree(ctrl);
+		goto out;
+	}
+
+	ret = nvme_add_ctrl(&ctrl->ctrl);
 	if (ret)
 		goto out_put_ctrl;
 
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
+		WARN_ON_ONCE(1);
+
 	ret = -ENOMEM;
 
-	ctrl->ctrl.sqsize = opts->queue_size - 1;
 	ctrl->ctrl.kato = opts->kato;
+	ctrl->port = nvme_loop_find_port(&ctrl->ctrl);
 
 	ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
 			GFP_KERNEL);
@@ -628,6 +608,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 			opts->queue_size, ctrl->ctrl.maxcmd);
 		opts->queue_size = ctrl->ctrl.maxcmd;
 	}
+	ctrl->ctrl.sqsize = opts->queue_size - 1;
 
 	if (opts->nr_io_queues) {
 		ret = nvme_loop_create_io_queues(ctrl);
@@ -640,10 +621,8 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	dev_info(ctrl->ctrl.device,
 		 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
 
-	kref_get(&ctrl->ctrl.kref);
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE))
+		WARN_ON_ONCE(1);
 
 	mutex_lock(&nvme_loop_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_loop_ctrl_list);
@@ -654,6 +633,8 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	return &ctrl->ctrl;
 
 out_remove_admin_queue:
+	nvme_quiesce_admin_queue(&ctrl->ctrl);
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 	nvme_loop_destroy_admin_queue(ctrl);
 out_free_queues:
 	kfree(ctrl->queues);
@@ -661,6 +642,7 @@ out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 out_put_ctrl:
 	nvme_put_ctrl(&ctrl->ctrl);
+out:
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);
@@ -668,30 +650,28 @@ out_put_ctrl:
 
 static int nvme_loop_add_port(struct nvmet_port *port)
 {
-	/*
-	 * XXX: disalow adding more than one port so
-	 * there is no connection rejections when a
-	 * a subsystem is assigned to a port for which
-	 * loop doesn't have a pointer.
-	 * This scenario would be possible if we allowed
-	 * more than one port to be added and a subsystem
-	 * was assigned to a port other than nvmet_loop_port.
-	 */
-
-	if (nvmet_loop_port)
-		return -EPERM;
-
-	nvmet_loop_port = port;
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_add_tail(&port->entry, &nvme_loop_ports);
+	mutex_unlock(&nvme_loop_ports_mutex);
 	return 0;
 }
 
 static void nvme_loop_remove_port(struct nvmet_port *port)
 {
-	if (port == nvmet_loop_port)
-		nvmet_loop_port = NULL;
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_del_init(&port->entry);
+	mutex_unlock(&nvme_loop_ports_mutex);
+
+	/*
+	 * Ensure any ctrls that are in the process of being
+	 * deleted are in fact deleted before we return
+	 * and free the port. This is to prevent active
+	 * ctrls from using a port after it's freed.
+	 */
+	flush_workqueue(nvme_delete_wq);
 }
 
-static struct nvmet_fabrics_ops nvme_loop_ops = {
+static const struct nvmet_fabrics_ops nvme_loop_ops = {
 	.owner		= THIS_MODULE,
 	.type		= NVMF_TRTYPE_LOOP,
 	.add_port	= nvme_loop_add_port,
@@ -702,7 +682,9 @@ static struct nvmet_fabrics_ops nvme_loop_ops = {
 
 static struct nvmf_transport_ops nvme_loop_transport = {
 	.name		= "loop",
+	.module		= THIS_MODULE,
 	.create_ctrl	= nvme_loop_create_ctrl,
+	.allowed_opts	= NVMF_OPT_TRADDR,
 };
 
 static int __init nvme_loop_init_module(void)
@@ -729,14 +711,15 @@ static void __exit nvme_loop_cleanup_module(void)
 
 	mutex_lock(&nvme_loop_ctrl_mutex);
 	list_for_each_entry_safe(ctrl, next, &nvme_loop_ctrl_list, list)
-		__nvme_loop_del_ctrl(ctrl);
+		nvme_delete_ctrl(&ctrl->ctrl);
 	mutex_unlock(&nvme_loop_ctrl_mutex);
 
-	flush_workqueue(nvme_wq);
+	flush_workqueue(nvme_delete_wq);
 }
 
 module_init(nvme_loop_init_module);
 module_exit(nvme_loop_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe target loop transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */