loop.c 18.5 KB
Newer Older
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
/*
 * 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>
#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

/*
 * 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	\
32
	(NVME_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS)
33 34

struct nvme_loop_iod {
35
	struct nvme_request	nvme_req;
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
	struct nvme_command	cmd;
	struct nvme_completion	rsp;
	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_ctrl	*target_ctrl;
	struct work_struct	delete_work;
};

static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
{
	return container_of(ctrl, struct nvme_loop_ctrl, ctrl);
}

struct nvme_loop_queue {
	struct nvmet_cq		nvme_cq;
	struct nvmet_sq		nvme_sq;
	struct nvme_loop_ctrl	*ctrl;
};

static struct nvmet_port *nvmet_loop_port;

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 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);

	nvme_cleanup_cmd(req);
	sg_free_table_chained(&iod->sg_table, true);
91
	nvme_complete_rq(req);
92 93
}

94 95 96
static struct blk_mq_tags *nvme_loop_tagset(struct nvme_loop_queue *queue)
{
	u32 queue_idx = nvme_loop_queue_idx(queue);
97

98 99 100
	if (queue_idx == 0)
		return queue->ctrl->admin_tag_set.tags[queue_idx];
	return queue->ctrl->tag_set.tags[queue_idx - 1];
101 102
}

103
static void nvme_loop_queue_response(struct nvmet_req *req)
104
{
105 106 107
	struct nvme_loop_queue *queue =
		container_of(req->sq, struct nvme_loop_queue, nvme_sq);
	struct nvme_completion *cqe = req->rsp;
108 109 110 111 112 113 114

	/*
	 * 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.
	 */
115
	if (unlikely(nvme_loop_queue_idx(queue) == 0 &&
116
			cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) {
117
		nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
118
				&cqe->result);
119
	} else {
120 121 122 123 124 125 126 127 128
		struct request *rq;

		rq = blk_mq_tag_to_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",
				cqe->command_id, nvme_loop_queue_idx(queue));
			return;
		}
129

130
		nvme_end_request(rq, cqe->status, cqe->result);
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147
	}
}

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 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 */
148
	nvme_reset_ctrl(&iod->queue->ctrl->ctrl);
149 150

	/* fail with DNR on admin cmd timeout */
151
	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
152 153 154 155

	return BLK_EH_HANDLED;
}

156
static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
157 158 159 160 161 162
		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);
163
	blk_status_t ret;
164 165

	ret = nvme_setup_cmd(ns, req, &iod->cmd);
166
	if (ret)
167 168 169 170 171 172 173 174 175
		return ret;

	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);
176
		return BLK_STS_OK;
177 178 179 180
	}

	if (blk_rq_bytes(req)) {
		iod->sg_table.sgl = iod->first_sgl;
181
		if (sg_alloc_table_chained(&iod->sg_table,
182
				blk_rq_nr_phys_segments(req),
183 184
				iod->sg_table.sgl))
			return BLK_STS_RESOURCE;
185 186 187 188 189 190 191 192

		iod->req.sg = iod->sg_table.sgl;
		iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
	}

	blk_mq_start_request(req);

	schedule_work(&iod->work);
193
	return BLK_STS_OK;
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
}

static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
{
	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_LOOP_AQ_BLKMQ_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;
	}

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

226 227 228
static int nvme_loop_init_request(struct blk_mq_tag_set *set,
		struct request *req, unsigned int hctx_idx,
		unsigned int numa_node)
229
{
230
	struct nvme_loop_ctrl *ctrl = set->driver_data;
231

232 233
	return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req),
			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
234 235 236 237 238 239 240 241
}

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_queue *queue = &ctrl->queues[hctx_idx + 1];

242
	BUG_ON(hctx_idx >= ctrl->ctrl.queue_count);
243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259

	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 = data;
	struct nvme_loop_queue *queue = &ctrl->queues[0];

	BUG_ON(hctx_idx != 0);

	hctx->driver_data = queue;
	return 0;
}

260
static const struct blk_mq_ops nvme_loop_mq_ops = {
261 262 263 264 265 266 267
	.queue_rq	= nvme_loop_queue_rq,
	.complete	= nvme_loop_complete_rq,
	.init_request	= nvme_loop_init_request,
	.init_hctx	= nvme_loop_init_hctx,
	.timeout	= nvme_loop_timeout,
};

268
static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
269 270
	.queue_rq	= nvme_loop_queue_rq,
	.complete	= nvme_loop_complete_rq,
271
	.init_request	= nvme_loop_init_request,
272 273 274 275 276 277
	.init_hctx	= nvme_loop_init_admin_hctx,
	.timeout	= nvme_loop_timeout,
};

static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
{
278
	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
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
	blk_cleanup_queue(ctrl->ctrl.admin_q);
	blk_mq_free_tag_set(&ctrl->admin_tag_set);
}

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) {
		blk_cleanup_queue(ctrl->ctrl.connect_q);
		blk_mq_free_tag_set(&ctrl->tag_set);
	}
	kfree(ctrl->queues);
	nvmf_free_options(nctrl->opts);
free_ctrl:
	kfree(ctrl);
}

304 305 306 307
static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
{
	int i;

308
	for (i = 1; i < ctrl->ctrl.queue_count; i++)
309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330
		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
}

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;

331
		ctrl->ctrl.queue_count++;
332 333 334 335 336 337 338 339 340
	}

	return 0;

out_destroy_queues:
	nvme_loop_destroy_io_queues(ctrl);
	return ret;
}

341 342 343 344
static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
{
	int i, ret;

345
	for (i = 1; i < ctrl->ctrl.queue_count; i++) {
346 347 348 349 350 351 352 353
		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
		if (ret)
			return ret;
	}

	return 0;
}

354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
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)
		return error;
373
	ctrl->ctrl.queue_count = 1;
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388

	error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
	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;
	}

	error = nvmf_connect_admin_queue(&ctrl->ctrl);
	if (error)
		goto out_cleanup_queue;

389
	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->ctrl.cap);
390 391 392 393 394 395 396
	if (error) {
		dev_err(ctrl->ctrl.device,
			"prop_get NVME_REG_CAP failed\n");
		goto out_cleanup_queue;
	}

	ctrl->ctrl.sqsize =
397
		min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize);
398

399
	error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
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
	if (error)
		goto out_cleanup_queue;

	ctrl->ctrl.max_hw_sectors =
		(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);

	error = nvme_init_identify(&ctrl->ctrl);
	if (error)
		goto out_cleanup_queue;

	nvme_start_keep_alive(&ctrl->ctrl);

	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_free_sq:
	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
	return error;
}

static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
{
	nvme_stop_keep_alive(&ctrl->ctrl);

427
	if (ctrl->ctrl.queue_count > 1) {
428 429 430
		nvme_stop_queues(&ctrl->ctrl);
		blk_mq_tagset_busy_iter(&ctrl->tag_set,
					nvme_cancel_request, &ctrl->ctrl);
431
		nvme_loop_destroy_io_queues(ctrl);
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
	}

	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
		nvme_shutdown_ctrl(&ctrl->ctrl);

	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
				nvme_cancel_request, &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_uninit_ctrl(&ctrl->ctrl);
449
	nvme_loop_shutdown_ctrl(ctrl);
450 451 452 453 454 455 456 457
	nvme_put_ctrl(&ctrl->ctrl);
}

static int __nvme_loop_del_ctrl(struct nvme_loop_ctrl *ctrl)
{
	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
		return -EBUSY;

458
	if (!queue_work(nvme_wq, &ctrl->delete_work))
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
		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;
}

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_loop_del_ctrl(ctrl);
	}
	mutex_unlock(&nvme_loop_ctrl_mutex);
}

static void nvme_loop_reset_ctrl_work(struct work_struct *work)
{
492 493
	struct nvme_loop_ctrl *ctrl =
		container_of(work, struct nvme_loop_ctrl, ctrl.reset_work);
494
	bool changed;
495
	int ret;
496 497 498 499 500 501 502

	nvme_loop_shutdown_ctrl(ctrl);

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

503 504 505
	ret = nvme_loop_init_io_queues(ctrl);
	if (ret)
		goto out_destroy_admin;
506

507 508 509
	ret = nvme_loop_connect_io_queues(ctrl);
	if (ret)
		goto out_destroy_io;
510

511 512 513
	blk_mq_update_nr_hw_queues(&ctrl->tag_set,
			ctrl->ctrl.queue_count - 1);

514 515 516 517 518 519 520 521 522 523
	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
	WARN_ON_ONCE(!changed);

	nvme_queue_scan(&ctrl->ctrl);
	nvme_queue_async_events(&ctrl->ctrl);

	nvme_start_queues(&ctrl->ctrl);

	return;

524 525 526
out_destroy_io:
	nvme_loop_destroy_io_queues(ctrl);
out_destroy_admin:
527 528 529 530 531 532 533 534 535 536
	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 = {
	.name			= "loop",
	.module			= THIS_MODULE,
537
	.flags			= NVME_F_FABRICS,
538 539 540 541 542 543 544 545 546 547
	.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_del_ctrl,
};

static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
{
548
	int ret;
549

550 551
	ret = nvme_loop_init_io_queues(ctrl);
	if (ret)
552 553 554 555
		return ret;

	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
	ctrl->tag_set.ops = &nvme_loop_mq_ops;
556
	ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
557 558 559 560 561 562
	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;
563
	ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1;
564 565 566 567 568 569 570 571 572 573 574 575 576
	ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
	ctrl->ctrl.tagset = &ctrl->tag_set;

	ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
	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;
	}

577 578 579
	ret = nvme_loop_connect_io_queues(ctrl);
	if (ret)
		goto out_cleanup_connect_q;
580 581 582 583 584 585 586 587

	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_destroy_queues:
588
	nvme_loop_destroy_io_queues(ctrl);
589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
	return ret;
}

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);
	if (!ctrl)
		return ERR_PTR(-ENOMEM);
	ctrl->ctrl.opts = opts;
	INIT_LIST_HEAD(&ctrl->list);

	INIT_WORK(&ctrl->delete_work, nvme_loop_del_ctrl_work);
606
	INIT_WORK(&ctrl->ctrl.reset_work, nvme_loop_reset_ctrl_work);
607 608 609 610 611 612 613 614

	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops,
				0 /* no quirks, we're perfect! */);
	if (ret)
		goto out_put_ctrl;

	ret = -ENOMEM;

615
	ctrl->ctrl.sqsize = opts->queue_size - 1;
616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720
	ctrl->ctrl.kato = opts->kato;

	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;
	}

	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);

	kref_get(&ctrl->ctrl.kref);

	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
	WARN_ON_ONCE(!changed);

	mutex_lock(&nvme_loop_ctrl_mutex);
	list_add_tail(&ctrl->list, &nvme_loop_ctrl_list);
	mutex_unlock(&nvme_loop_ctrl_mutex);

	if (opts->nr_io_queues) {
		nvme_queue_scan(&ctrl->ctrl);
		nvme_queue_async_events(&ctrl->ctrl);
	}

	return &ctrl->ctrl;

out_remove_admin_queue:
	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);
	if (ret > 0)
		ret = -EIO;
	return ERR_PTR(ret);
}

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;
	return 0;
}

static void nvme_loop_remove_port(struct nvmet_port *port)
{
	if (port == nvmet_loop_port)
		nvmet_loop_port = NULL;
}

static 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",
	.create_ctrl	= nvme_loop_create_ctrl,
};

static int __init nvme_loop_init_module(void)
{
	int ret;

	ret = nvmet_register_transport(&nvme_loop_ops);
	if (ret)
		return ret;
721 722 723 724 725 726

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

	return ret;
727 728 729 730 731 732 733 734 735 736 737 738 739 740
}

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_loop_del_ctrl(ctrl);
	mutex_unlock(&nvme_loop_ctrl_mutex);

741
	flush_workqueue(nvme_wq);
742 743 744 745 746 747 748
}

module_init(nvme_loop_init_module);
module_exit(nvme_loop_cleanup_module);

MODULE_LICENSE("GPL v2");
MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */