summaryrefslogtreecommitdiff
path: root/drivers/nvme/target/loop.c
blob: a9d112d34d4f434ff0ba3310435581cb49285cbb (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
// SPDX-License-Identifier: GPL-2.0
/*
 * NVMe over Fabrics loopback device.
 * Copyright (c) 2015-2016 HGST, a Western Digital Company.
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/scatterlist.h>
#include <linux/blk-mq.h>
#include <linux/nvme.h>
#include <linux/module.h>
#include <linux/parser.h>
#include "nvmet.h"
#include "../host/nvme.h"
#include "../host/fabrics.h"

#define NVME_LOOP_MAX_SEGMENTS		256

struct nvme_loop_iod {
	struct nvme_request	nvme_req;
	struct nvme_command	cmd;
	struct nvme_completion	cqe;
	struct nvmet_req	req;
	struct nvme_loop_queue	*queue;
	struct work_struct	work;
	struct sg_table		sg_table;
	struct scatterlist	first_sgl[];
};

struct nvme_loop_ctrl {
	struct nvme_loop_queue	*queues;

	struct blk_mq_tag_set	admin_tag_set;

	struct list_head	list;
	struct blk_mq_tag_set	tag_set;
	struct nvme_loop_iod	async_event_iod;
	struct nvme_ctrl	ctrl;

	struct nvmet_port	*port;
};

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 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);

static void nvme_loop_queue_response(struct nvmet_req *nvme_req);
static void nvme_loop_delete_ctrl(struct nvmet_ctrl *ctrl);

static const struct nvmet_fabrics_ops nvme_loop_ops;

static inline int nvme_loop_queue_idx(struct nvme_loop_queue *queue)
{
	return queue - queue->ctrl->queues;
}

static void nvme_loop_complete_rq(struct request *req)
{
	struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);

	sg_free_table_chained(&iod->sg_table, NVME_INLINE_SG_CNT);
	nvme_complete_rq(req);
}

static struct blk_mq_tags *nvme_loop_tagset(struct nvme_loop_queue *queue)
{
	u32 queue_idx = nvme_loop_queue_idx(queue);

	if (queue_idx == 0)
		return queue->ctrl->admin_tag_set.tags[queue_idx];
	return queue->ctrl->tag_set.tags[queue_idx - 1];
}

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->cqe;

	/*
	 * AEN requests are special as they don't time out and can
	 * survive any kind of queue freeze and often don't respond to
	 * aborts.  We don't even bother to allocate a struct request
	 * for them but rather special case them here.
	 */
	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 = nvme_find_rq(nvme_loop_tagset(queue), cqe->command_id);
		if (!rq) {
			dev_err(queue->ctrl->ctrl.device,
				"got bad command_id %#x on queue %d\n",
				cqe->command_id, nvme_loop_queue_idx(queue));
			return;
		}

		if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
			nvme_loop_complete_rq(rq);
	}
}

static void nvme_loop_execute_work(struct work_struct *work)
{
	struct nvme_loop_iod *iod =
		container_of(work, struct nvme_loop_iod, work);

	iod->req.execute(&iod->req);
}

static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
		const struct blk_mq_queue_data *bd)
{
	struct nvme_ns *ns = hctx->queue->queuedata;
	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;

	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 = queue->ctrl->port;
	if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
			&queue->nvme_sq, &nvme_loop_ops))
		return BLK_STS_OK;

	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, 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.transfer_len = blk_rq_payload_bytes(req);
	}

	queue_work(nvmet_wq, &iod->work);
	return BLK_STS_OK;
}

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];
	struct nvme_loop_iod *iod = &ctrl->async_event_iod;

	memset(&iod->cmd, 0, sizeof(iod->cmd));
	iod->cmd.common.opcode = nvme_admin_async_event;
	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)) {
		dev_err(ctrl->ctrl.device, "failed async event work\n");
		return;
	}

	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.cqe = &iod->cqe;
	iod->queue = &ctrl->queues[queue_idx];
	INIT_WORK(&iod->work, nvme_loop_execute_work);
	return 0;
}

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 = 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 = 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;
}

static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
		unsigned int hctx_idx)
{
	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(data);
	struct nvme_loop_queue *queue = &ctrl->queues[0];

	BUG_ON(hctx_idx != 0);

	hctx->driver_data = queue;
	return 0;
}

static const struct blk_mq_ops nvme_loop_mq_ops = {
	.queue_rq	= nvme_loop_queue_rq,
	.complete	= nvme_loop_complete_rq,
	.init_request	= nvme_loop_init_request,
	.init_hctx	= nvme_loop_init_hctx,
};

static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
	.queue_rq	= nvme_loop_queue_rq,
	.complete	= nvme_loop_complete_rq,
	.init_request	= nvme_loop_init_request,
	.init_hctx	= nvme_loop_init_admin_hctx,
};

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);
	nvme_remove_admin_tag_set(&ctrl->ctrl);
}

static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl)
{
	struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl);

	if (list_empty(&ctrl->list))
		goto free_ctrl;

	mutex_lock(&nvme_loop_ctrl_mutex);
	list_del(&ctrl->list);
	mutex_unlock(&nvme_loop_ctrl_mutex);

	if (nctrl->tagset)
		nvme_remove_io_tag_set(nctrl);
	kfree(ctrl->queues);
	nvmf_free_options(nctrl->opts);
free_ctrl:
	kfree(ctrl);
}

static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
{
	int 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);
	}
	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)
{
	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
	unsigned int nr_io_queues;
	int ret, i;

	nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
	if (ret || !nr_io_queues)
		return ret;

	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues);

	for (i = 1; i <= nr_io_queues; i++) {
		ctrl->queues[i].ctrl = ctrl;
		ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
		if (ret)
			goto out_destroy_queues;

		ctrl->ctrl.queue_count++;
	}

	return 0;

out_destroy_queues:
	nvme_loop_destroy_io_queues(ctrl);
	return ret;
}

static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
{
	int i, ret;

	for (i = 1; i < ctrl->ctrl.queue_count; i++) {
		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
		if (ret)
			return ret;
		set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);
	}

	return 0;
}

static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
{
	int error;

	ctrl->queues[0].ctrl = ctrl;
	error = nvmet_sq_init(&ctrl->queues[0].nvme_sq);
	if (error)
		return error;
	ctrl->ctrl.queue_count = 1;

	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;

	/* 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_tagset;

	set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);

	error = nvme_enable_ctrl(&ctrl->ctrl);
	if (error)
		goto out_cleanup_tagset;

	ctrl->ctrl.max_hw_sectors =
		(NVME_LOOP_MAX_SEGMENTS - 1) << PAGE_SECTORS_SHIFT;

	nvme_unquiesce_admin_queue(&ctrl->ctrl);

	error = nvme_init_ctrl_finish(&ctrl->ctrl, false);
	if (error)
		goto out_cleanup_tagset;

	return 0;

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);
	return error;
}

static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
{
	if (ctrl->ctrl.queue_count > 1) {
		nvme_quiesce_io_queues(&ctrl->ctrl);
		nvme_cancel_tagset(&ctrl->ctrl);
		nvme_loop_destroy_io_queues(ctrl);
	}

	nvme_quiesce_admin_queue(&ctrl->ctrl);
	if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE)
		nvme_disable_ctrl(&ctrl->ctrl, true);

	nvme_cancel_admin_tagset(&ctrl->ctrl);
	nvme_loop_destroy_admin_queue(ctrl);
}

static void nvme_loop_delete_ctrl_host(struct nvme_ctrl *ctrl)
{
	nvme_loop_shutdown_ctrl(to_loop_ctrl(ctrl));
}

static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl)
{
	struct nvme_loop_ctrl *ctrl;

	mutex_lock(&nvme_loop_ctrl_mutex);
	list_for_each_entry(ctrl, &nvme_loop_ctrl_list, list) {
		if (ctrl->ctrl.cntlid == nctrl->cntlid)
			nvme_delete_ctrl(&ctrl->ctrl);
	}
	mutex_unlock(&nvme_loop_ctrl_mutex);
}

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);
	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;

	ret = nvme_loop_init_io_queues(ctrl);
	if (ret)
		goto out_destroy_admin;

	ret = nvme_loop_connect_io_queues(ctrl);
	if (ret)
		goto out_destroy_io;

	blk_mq_update_nr_hw_queues(&ctrl->tag_set,
			ctrl->ctrl.queue_count - 1);

	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE))
		WARN_ON_ONCE(1);

	nvme_start_ctrl(&ctrl->ctrl);

	return;

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);
}

static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
	.name			= "loop",
	.module			= THIS_MODULE,
	.flags			= NVME_F_FABRICS,
	.reg_read32		= nvmf_reg_read32,
	.reg_read64		= nvmf_reg_read64,
	.reg_write32		= nvmf_reg_write32,
	.free_ctrl		= nvme_loop_free_ctrl,
	.submit_async_event	= nvme_loop_submit_async_event,
	.delete_ctrl		= nvme_loop_delete_ctrl_host,
	.get_address		= nvmf_get_address,
};

static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
{
	int ret;

	ret = nvme_loop_init_io_queues(ctrl);
	if (ret)
		return ret;

	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;

	ret = nvme_loop_connect_io_queues(ctrl);
	if (ret)
		goto out_cleanup_tagset;

	return 0;

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;
	int ret;

	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
	if (!ctrl)
		return ERR_PTR(-ENOMEM);
	ctrl->ctrl.opts = opts;
	INIT_LIST_HEAD(&ctrl->list);

	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.kato = opts->kato;
	ctrl->port = nvme_loop_find_port(&ctrl->ctrl);

	ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
			GFP_KERNEL);
	if (!ctrl->queues)
		goto out_uninit_ctrl;

	ret = nvme_loop_configure_admin_queue(ctrl);
	if (ret)
		goto out_free_queues;

	if (opts->queue_size > ctrl->ctrl.maxcmd) {
		/* warn if maxcmd is lower than queue_size */
		dev_warn(ctrl->ctrl.device,
			"queue_size %zu > ctrl maxcmd %u, clamping down\n",
			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);
		if (ret)
			goto out_remove_admin_queue;
	}

	nvme_loop_init_iod(ctrl, &ctrl->async_event_iod, 0);

	dev_info(ctrl->ctrl.device,
		 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);

	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);
	mutex_unlock(&nvme_loop_ctrl_mutex);

	nvme_start_ctrl(&ctrl->ctrl);

	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);
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);
}

static int nvme_loop_add_port(struct nvmet_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)
{
	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 const struct nvmet_fabrics_ops nvme_loop_ops = {
	.owner		= THIS_MODULE,
	.type		= NVMF_TRTYPE_LOOP,
	.add_port	= nvme_loop_add_port,
	.remove_port	= nvme_loop_remove_port,
	.queue_response = nvme_loop_queue_response,
	.delete_ctrl	= nvme_loop_delete_ctrl,
};

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)
{
	int ret;

	ret = nvmet_register_transport(&nvme_loop_ops);
	if (ret)
		return ret;

	ret = nvmf_register_transport(&nvme_loop_transport);
	if (ret)
		nvmet_unregister_transport(&nvme_loop_ops);

	return ret;
}

static void __exit nvme_loop_cleanup_module(void)
{
	struct nvme_loop_ctrl *ctrl, *next;

	nvmf_unregister_transport(&nvme_loop_transport);
	nvmet_unregister_transport(&nvme_loop_ops);

	mutex_lock(&nvme_loop_ctrl_mutex);
	list_for_each_entry_safe(ctrl, next, &nvme_loop_ctrl_list, list)
		nvme_delete_ctrl(&ctrl->ctrl);
	mutex_unlock(&nvme_loop_ctrl_mutex);

	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 */