1// SPDX-License-Identifier: GPL-2.0 2/* 3 * NVMe over Fabrics loopback device. 4 * Copyright (c) 2015-2016 HGST, a Western Digital Company. 5 */ 6#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt 7#include <linux/scatterlist.h> 8#include <linux/blk-mq.h> 9#include <linux/nvme.h> 10#include <linux/module.h> 11#include <linux/parser.h> 12#include "nvmet.h" 13#include "../host/nvme.h" 14#include "../host/fabrics.h" 15 16#define NVME_LOOP_MAX_SEGMENTS 256 17 18struct nvme_loop_iod { 19 struct nvme_request nvme_req; 20 struct nvme_command cmd; 21 struct nvme_completion cqe; 22 struct nvmet_req req; 23 struct nvme_loop_queue *queue; 24 struct work_struct work; 25 struct sg_table sg_table; 26 struct scatterlist first_sgl[]; 27}; 28 29struct nvme_loop_ctrl { 30 struct nvme_loop_queue *queues; 31 32 struct blk_mq_tag_set admin_tag_set; 33 34 struct list_head list; 35 struct blk_mq_tag_set tag_set; 36 struct nvme_loop_iod async_event_iod; 37 struct nvme_ctrl ctrl; 38 39 struct nvmet_port *port; 40}; 41 42static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl) 43{ 44 return container_of(ctrl, struct nvme_loop_ctrl, ctrl); 45} 46 47enum nvme_loop_queue_flags { 48 NVME_LOOP_Q_LIVE = 0, 49}; 50 51struct nvme_loop_queue { 52 struct nvmet_cq nvme_cq; 53 struct nvmet_sq nvme_sq; 54 struct nvme_loop_ctrl *ctrl; 55 unsigned long flags; 56}; 57 58static LIST_HEAD(nvme_loop_ports); 59static DEFINE_MUTEX(nvme_loop_ports_mutex); 60 61static LIST_HEAD(nvme_loop_ctrl_list); 62static DEFINE_MUTEX(nvme_loop_ctrl_mutex); 63 64static void nvme_loop_queue_response(struct nvmet_req *nvme_req); 65static void nvme_loop_delete_ctrl(struct nvmet_ctrl *ctrl); 66 67static const struct nvmet_fabrics_ops nvme_loop_ops; 68 69static inline int nvme_loop_queue_idx(struct nvme_loop_queue *queue) 70{ 71 return queue - queue->ctrl->queues; 72} 73 74static void nvme_loop_complete_rq(struct request *req) 75{ 76 struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); 77 78 sg_free_table_chained(&iod->sg_table, NVME_INLINE_SG_CNT); 79 nvme_complete_rq(req); 80} 81 82static struct blk_mq_tags *nvme_loop_tagset(struct nvme_loop_queue *queue) 83{ 84 u32 queue_idx = nvme_loop_queue_idx(queue); 85 86 if (queue_idx == 0) 87 return queue->ctrl->admin_tag_set.tags[queue_idx]; 88 return queue->ctrl->tag_set.tags[queue_idx - 1]; 89} 90 91static void nvme_loop_queue_response(struct nvmet_req *req) 92{ 93 struct nvme_loop_queue *queue = 94 container_of(req->sq, struct nvme_loop_queue, nvme_sq); 95 struct nvme_completion *cqe = req->cqe; 96 97 /* 98 * AEN requests are special as they don't time out and can 99 * survive any kind of queue freeze and often don't respond to 100 * aborts. We don't even bother to allocate a struct request 101 * for them but rather special case them here. 102 */ 103 if (unlikely(nvme_is_aen_req(nvme_loop_queue_idx(queue), 104 cqe->command_id))) { 105 nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, 106 &cqe->result); 107 } else { 108 struct request *rq; 109 110 rq = nvme_find_rq(nvme_loop_tagset(queue), cqe->command_id); 111 if (!rq) { 112 dev_err(queue->ctrl->ctrl.device, 113 "got bad command_id %#x on queue %d\n", 114 cqe->command_id, nvme_loop_queue_idx(queue)); 115 return; 116 } 117 118 if (!nvme_try_complete_req(rq, cqe->status, cqe->result)) 119 nvme_loop_complete_rq(rq); 120 } 121} 122 123static void nvme_loop_execute_work(struct work_struct *work) 124{ 125 struct nvme_loop_iod *iod = 126 container_of(work, struct nvme_loop_iod, work); 127 128 iod->req.execute(&iod->req); 129} 130 131static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, 132 const struct blk_mq_queue_data *bd) 133{ 134 struct nvme_ns *ns = hctx->queue->queuedata; 135 struct nvme_loop_queue *queue = hctx->driver_data; 136 struct request *req = bd->rq; 137 struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); 138 bool queue_ready = test_bit(NVME_LOOP_Q_LIVE, &queue->flags); 139 blk_status_t ret; 140 141 if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready)) 142 return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req); 143 144 ret = nvme_setup_cmd(ns, req, &iod->cmd); 145 if (ret) 146 return ret; 147 148 blk_mq_start_request(req); 149 iod->cmd.common.flags |= NVME_CMD_SGL_METABUF; 150 iod->req.port = queue->ctrl->port; 151 if (!nvmet_req_init(&iod->req, &queue->nvme_cq, 152 &queue->nvme_sq, &nvme_loop_ops)) 153 return BLK_STS_OK; 154 155 if (blk_rq_nr_phys_segments(req)) { 156 iod->sg_table.sgl = iod->first_sgl; 157 if (sg_alloc_table_chained(&iod->sg_table, 158 blk_rq_nr_phys_segments(req), 159 iod->sg_table.sgl, NVME_INLINE_SG_CNT)) { 160 nvme_cleanup_cmd(req); 161 return BLK_STS_RESOURCE; 162 } 163 164 iod->req.sg = iod->sg_table.sgl; 165 iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl); 166 iod->req.transfer_len = blk_rq_payload_bytes(req); 167 } 168 169 schedule_work(&iod->work); 170 return BLK_STS_OK; 171} 172 173static void nvme_loop_submit_async_event(struct nvme_ctrl *arg) 174{ 175 struct nvme_loop_ctrl *ctrl = to_loop_ctrl(arg); 176 struct nvme_loop_queue *queue = &ctrl->queues[0]; 177 struct nvme_loop_iod *iod = &ctrl->async_event_iod; 178 179 memset(&iod->cmd, 0, sizeof(iod->cmd)); 180 iod->cmd.common.opcode = nvme_admin_async_event; 181 iod->cmd.common.command_id = NVME_AQ_BLK_MQ_DEPTH; 182 iod->cmd.common.flags |= NVME_CMD_SGL_METABUF; 183 184 if (!nvmet_req_init(&iod->req, &queue->nvme_cq, &queue->nvme_sq, 185 &nvme_loop_ops)) { 186 dev_err(ctrl->ctrl.device, "failed async event work\n"); 187 return; 188 } 189 190 schedule_work(&iod->work); 191} 192 193static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl, 194 struct nvme_loop_iod *iod, unsigned int queue_idx) 195{ 196 iod->req.cmd = &iod->cmd; 197 iod->req.cqe = &iod->cqe; 198 iod->queue = &ctrl->queues[queue_idx]; 199 INIT_WORK(&iod->work, nvme_loop_execute_work); 200 return 0; 201} 202 203static int nvme_loop_init_request(struct blk_mq_tag_set *set, 204 struct request *req, unsigned int hctx_idx, 205 unsigned int numa_node) 206{ 207 struct nvme_loop_ctrl *ctrl = set->driver_data; 208 209 nvme_req(req)->ctrl = &ctrl->ctrl; 210 return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req), 211 (set == &ctrl->tag_set) ? hctx_idx + 1 : 0); 212} 213 214static struct lock_class_key loop_hctx_fq_lock_key; 215 216static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, 217 unsigned int hctx_idx) 218{ 219 struct nvme_loop_ctrl *ctrl = data; 220 struct nvme_loop_queue *queue = &ctrl->queues[hctx_idx + 1]; 221 222 BUG_ON(hctx_idx >= ctrl->ctrl.queue_count); 223 224 /* 225 * flush_end_io() can be called recursively for us, so use our own 226 * lock class key for avoiding lockdep possible recursive locking, 227 * then we can remove the dynamically allocated lock class for each 228 * flush queue, that way may cause horrible boot delay. 229 */ 230 blk_mq_hctx_set_fq_lock_class(hctx, &loop_hctx_fq_lock_key); 231 232 hctx->driver_data = queue; 233 return 0; 234} 235 236static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, 237 unsigned int hctx_idx) 238{ 239 struct nvme_loop_ctrl *ctrl = data; 240 struct nvme_loop_queue *queue = &ctrl->queues[0]; 241 242 BUG_ON(hctx_idx != 0); 243 244 hctx->driver_data = queue; 245 return 0; 246} 247 248static const struct blk_mq_ops nvme_loop_mq_ops = { 249 .queue_rq = nvme_loop_queue_rq, 250 .complete = nvme_loop_complete_rq, 251 .init_request = nvme_loop_init_request, 252 .init_hctx = nvme_loop_init_hctx, 253}; 254 255static const struct blk_mq_ops nvme_loop_admin_mq_ops = { 256 .queue_rq = nvme_loop_queue_rq, 257 .complete = nvme_loop_complete_rq, 258 .init_request = nvme_loop_init_request, 259 .init_hctx = nvme_loop_init_admin_hctx, 260}; 261 262static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl) 263{ 264 if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags)) 265 return; 266 nvmet_sq_destroy(&ctrl->queues[0].nvme_sq); 267 blk_cleanup_queue(ctrl->ctrl.admin_q); 268 blk_cleanup_queue(ctrl->ctrl.fabrics_q); 269 blk_mq_free_tag_set(&ctrl->admin_tag_set); 270} 271 272static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl) 273{ 274 struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl); 275 276 if (list_empty(&ctrl->list)) 277 goto free_ctrl; 278 279 mutex_lock(&nvme_loop_ctrl_mutex); 280 list_del(&ctrl->list); 281 mutex_unlock(&nvme_loop_ctrl_mutex); 282 283 if (nctrl->tagset) { 284 blk_cleanup_queue(ctrl->ctrl.connect_q); 285 blk_mq_free_tag_set(&ctrl->tag_set); 286 } 287 kfree(ctrl->queues); 288 nvmf_free_options(nctrl->opts); 289free_ctrl: 290 kfree(ctrl); 291} 292 293static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl) 294{ 295 int i; 296 297 for (i = 1; i < ctrl->ctrl.queue_count; i++) { 298 clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags); 299 nvmet_sq_destroy(&ctrl->queues[i].nvme_sq); 300 } 301 ctrl->ctrl.queue_count = 1; 302} 303 304static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl) 305{ 306 struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; 307 unsigned int nr_io_queues; 308 int ret, i; 309 310 nr_io_queues = min(opts->nr_io_queues, num_online_cpus()); 311 ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); 312 if (ret || !nr_io_queues) 313 return ret; 314 315 dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues); 316 317 for (i = 1; i <= nr_io_queues; i++) { 318 ctrl->queues[i].ctrl = ctrl; 319 ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq); 320 if (ret) 321 goto out_destroy_queues; 322 323 ctrl->ctrl.queue_count++; 324 } 325 326 return 0; 327 328out_destroy_queues: 329 nvme_loop_destroy_io_queues(ctrl); 330 return ret; 331} 332 333static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl) 334{ 335 int i, ret; 336 337 for (i = 1; i < ctrl->ctrl.queue_count; i++) { 338 ret = nvmf_connect_io_queue(&ctrl->ctrl, i, false); 339 if (ret) 340 return ret; 341 set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags); 342 } 343 344 return 0; 345} 346 347static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) 348{ 349 int error; 350 351 memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); 352 ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops; 353 ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; 354 ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */ 355 ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node; 356 ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) + 357 NVME_INLINE_SG_CNT * sizeof(struct scatterlist); 358 ctrl->admin_tag_set.driver_data = ctrl; 359 ctrl->admin_tag_set.nr_hw_queues = 1; 360 ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT; 361 ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED; 362 363 ctrl->queues[0].ctrl = ctrl; 364 error = nvmet_sq_init(&ctrl->queues[0].nvme_sq); 365 if (error) 366 return error; 367 ctrl->ctrl.queue_count = 1; 368 369 error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); 370 if (error) 371 goto out_free_sq; 372 ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set; 373 374 ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set); 375 if (IS_ERR(ctrl->ctrl.fabrics_q)) { 376 error = PTR_ERR(ctrl->ctrl.fabrics_q); 377 goto out_free_tagset; 378 } 379 380 ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); 381 if (IS_ERR(ctrl->ctrl.admin_q)) { 382 error = PTR_ERR(ctrl->ctrl.admin_q); 383 goto out_cleanup_fabrics_q; 384 } 385 /* reset stopped state for the fresh admin queue */ 386 clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->ctrl.flags); 387 388 error = nvmf_connect_admin_queue(&ctrl->ctrl); 389 if (error) 390 goto out_cleanup_queue; 391 392 set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags); 393 394 error = nvme_enable_ctrl(&ctrl->ctrl); 395 if (error) 396 goto out_cleanup_queue; 397 398 ctrl->ctrl.max_hw_sectors = 399 (NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9); 400 401 nvme_start_admin_queue(&ctrl->ctrl); 402 403 error = nvme_init_identify(&ctrl->ctrl); 404 if (error) 405 goto out_cleanup_queue; 406 407 return 0; 408 409out_cleanup_queue: 410 clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags); 411 blk_cleanup_queue(ctrl->ctrl.admin_q); 412out_cleanup_fabrics_q: 413 blk_cleanup_queue(ctrl->ctrl.fabrics_q); 414out_free_tagset: 415 blk_mq_free_tag_set(&ctrl->admin_tag_set); 416out_free_sq: 417 nvmet_sq_destroy(&ctrl->queues[0].nvme_sq); 418 return error; 419} 420 421static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl) 422{ 423 if (ctrl->ctrl.queue_count > 1) { 424 nvme_stop_queues(&ctrl->ctrl); 425 blk_mq_tagset_busy_iter(&ctrl->tag_set, 426 nvme_cancel_request, &ctrl->ctrl); 427 blk_mq_tagset_wait_completed_request(&ctrl->tag_set); 428 nvme_loop_destroy_io_queues(ctrl); 429 } 430 431 nvme_stop_admin_queue(&ctrl->ctrl); 432 if (ctrl->ctrl.state == NVME_CTRL_LIVE) 433 nvme_shutdown_ctrl(&ctrl->ctrl); 434 435 blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, 436 nvme_cancel_request, &ctrl->ctrl); 437 blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set); 438 nvme_loop_destroy_admin_queue(ctrl); 439} 440 441static void nvme_loop_delete_ctrl_host(struct nvme_ctrl *ctrl) 442{ 443 nvme_loop_shutdown_ctrl(to_loop_ctrl(ctrl)); 444} 445 446static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl) 447{ 448 struct nvme_loop_ctrl *ctrl; 449 450 mutex_lock(&nvme_loop_ctrl_mutex); 451 list_for_each_entry(ctrl, &nvme_loop_ctrl_list, list) { 452 if (ctrl->ctrl.cntlid == nctrl->cntlid) 453 nvme_delete_ctrl(&ctrl->ctrl); 454 } 455 mutex_unlock(&nvme_loop_ctrl_mutex); 456} 457 458static void nvme_loop_reset_ctrl_work(struct work_struct *work) 459{ 460 struct nvme_loop_ctrl *ctrl = 461 container_of(work, struct nvme_loop_ctrl, ctrl.reset_work); 462 int ret; 463 464 nvme_stop_ctrl(&ctrl->ctrl); 465 nvme_loop_shutdown_ctrl(ctrl); 466 467 if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { 468 if (ctrl->ctrl.state != NVME_CTRL_DELETING && 469 ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO) 470 /* state change failure for non-deleted ctrl? */ 471 WARN_ON_ONCE(1); 472 return; 473 } 474 475 ret = nvme_loop_configure_admin_queue(ctrl); 476 if (ret) 477 goto out_disable; 478 479 ret = nvme_loop_init_io_queues(ctrl); 480 if (ret) 481 goto out_destroy_admin; 482 483 ret = nvme_loop_connect_io_queues(ctrl); 484 if (ret) 485 goto out_destroy_io; 486 487 blk_mq_update_nr_hw_queues(&ctrl->tag_set, 488 ctrl->ctrl.queue_count - 1); 489 490 if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) 491 WARN_ON_ONCE(1); 492 493 nvme_start_ctrl(&ctrl->ctrl); 494 495 return; 496 497out_destroy_io: 498 nvme_loop_destroy_io_queues(ctrl); 499out_destroy_admin: 500 nvme_loop_destroy_admin_queue(ctrl); 501out_disable: 502 dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); 503 nvme_uninit_ctrl(&ctrl->ctrl); 504} 505 506static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = { 507 .name = "loop", 508 .module = THIS_MODULE, 509 .flags = NVME_F_FABRICS, 510 .reg_read32 = nvmf_reg_read32, 511 .reg_read64 = nvmf_reg_read64, 512 .reg_write32 = nvmf_reg_write32, 513 .free_ctrl = nvme_loop_free_ctrl, 514 .submit_async_event = nvme_loop_submit_async_event, 515 .delete_ctrl = nvme_loop_delete_ctrl_host, 516 .get_address = nvmf_get_address, 517}; 518 519static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) 520{ 521 int ret; 522 523 ret = nvme_loop_init_io_queues(ctrl); 524 if (ret) 525 return ret; 526 527 memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); 528 ctrl->tag_set.ops = &nvme_loop_mq_ops; 529 ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; 530 ctrl->tag_set.reserved_tags = 1; /* fabric connect */ 531 ctrl->tag_set.numa_node = ctrl->ctrl.numa_node; 532 ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; 533 ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) + 534 NVME_INLINE_SG_CNT * sizeof(struct scatterlist); 535 ctrl->tag_set.driver_data = ctrl; 536 ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1; 537 ctrl->tag_set.timeout = NVME_IO_TIMEOUT; 538 ctrl->ctrl.tagset = &ctrl->tag_set; 539 540 ret = blk_mq_alloc_tag_set(&ctrl->tag_set); 541 if (ret) 542 goto out_destroy_queues; 543 544 ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set); 545 if (IS_ERR(ctrl->ctrl.connect_q)) { 546 ret = PTR_ERR(ctrl->ctrl.connect_q); 547 goto out_free_tagset; 548 } 549 550 ret = nvme_loop_connect_io_queues(ctrl); 551 if (ret) 552 goto out_cleanup_connect_q; 553 554 return 0; 555 556out_cleanup_connect_q: 557 blk_cleanup_queue(ctrl->ctrl.connect_q); 558out_free_tagset: 559 blk_mq_free_tag_set(&ctrl->tag_set); 560out_destroy_queues: 561 nvme_loop_destroy_io_queues(ctrl); 562 return ret; 563} 564 565static struct nvmet_port *nvme_loop_find_port(struct nvme_ctrl *ctrl) 566{ 567 struct nvmet_port *p, *found = NULL; 568 569 mutex_lock(&nvme_loop_ports_mutex); 570 list_for_each_entry(p, &nvme_loop_ports, entry) { 571 /* if no transport address is specified use the first port */ 572 if ((ctrl->opts->mask & NVMF_OPT_TRADDR) && 573 strcmp(ctrl->opts->traddr, p->disc_addr.traddr)) 574 continue; 575 found = p; 576 break; 577 } 578 mutex_unlock(&nvme_loop_ports_mutex); 579 return found; 580} 581 582static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, 583 struct nvmf_ctrl_options *opts) 584{ 585 struct nvme_loop_ctrl *ctrl; 586 int ret; 587 588 ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); 589 if (!ctrl) 590 return ERR_PTR(-ENOMEM); 591 ctrl->ctrl.opts = opts; 592 INIT_LIST_HEAD(&ctrl->list); 593 594 INIT_WORK(&ctrl->ctrl.reset_work, nvme_loop_reset_ctrl_work); 595 596 ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops, 597 0 /* no quirks, we're perfect! */); 598 if (ret) { 599 kfree(ctrl); 600 goto out; 601 } 602 603 if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) 604 WARN_ON_ONCE(1); 605 606 ret = -ENOMEM; 607 608 ctrl->ctrl.sqsize = opts->queue_size - 1; 609 ctrl->ctrl.kato = opts->kato; 610 ctrl->port = nvme_loop_find_port(&ctrl->ctrl); 611 612 ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues), 613 GFP_KERNEL); 614 if (!ctrl->queues) 615 goto out_uninit_ctrl; 616 617 ret = nvme_loop_configure_admin_queue(ctrl); 618 if (ret) 619 goto out_free_queues; 620 621 if (opts->queue_size > ctrl->ctrl.maxcmd) { 622 /* warn if maxcmd is lower than queue_size */ 623 dev_warn(ctrl->ctrl.device, 624 "queue_size %zu > ctrl maxcmd %u, clamping down\n", 625 opts->queue_size, ctrl->ctrl.maxcmd); 626 opts->queue_size = ctrl->ctrl.maxcmd; 627 } 628 629 if (opts->nr_io_queues) { 630 ret = nvme_loop_create_io_queues(ctrl); 631 if (ret) 632 goto out_remove_admin_queue; 633 } 634 635 nvme_loop_init_iod(ctrl, &ctrl->async_event_iod, 0); 636 637 dev_info(ctrl->ctrl.device, 638 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn); 639 640 if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) 641 WARN_ON_ONCE(1); 642 643 mutex_lock(&nvme_loop_ctrl_mutex); 644 list_add_tail(&ctrl->list, &nvme_loop_ctrl_list); 645 mutex_unlock(&nvme_loop_ctrl_mutex); 646 647 nvme_start_ctrl(&ctrl->ctrl); 648 649 return &ctrl->ctrl; 650 651out_remove_admin_queue: 652 nvme_loop_destroy_admin_queue(ctrl); 653out_free_queues: 654 kfree(ctrl->queues); 655out_uninit_ctrl: 656 nvme_uninit_ctrl(&ctrl->ctrl); 657 nvme_put_ctrl(&ctrl->ctrl); 658out: 659 if (ret > 0) 660 ret = -EIO; 661 return ERR_PTR(ret); 662} 663 664static int nvme_loop_add_port(struct nvmet_port *port) 665{ 666 mutex_lock(&nvme_loop_ports_mutex); 667 list_add_tail(&port->entry, &nvme_loop_ports); 668 mutex_unlock(&nvme_loop_ports_mutex); 669 return 0; 670} 671 672static void nvme_loop_remove_port(struct nvmet_port *port) 673{ 674 mutex_lock(&nvme_loop_ports_mutex); 675 list_del_init(&port->entry); 676 mutex_unlock(&nvme_loop_ports_mutex); 677 678 /* 679 * Ensure any ctrls that are in the process of being 680 * deleted are in fact deleted before we return 681 * and free the port. This is to prevent active 682 * ctrls from using a port after it's freed. 683 */ 684 flush_workqueue(nvme_delete_wq); 685} 686 687static const struct nvmet_fabrics_ops nvme_loop_ops = { 688 .owner = THIS_MODULE, 689 .type = NVMF_TRTYPE_LOOP, 690 .add_port = nvme_loop_add_port, 691 .remove_port = nvme_loop_remove_port, 692 .queue_response = nvme_loop_queue_response, 693 .delete_ctrl = nvme_loop_delete_ctrl, 694}; 695 696static struct nvmf_transport_ops nvme_loop_transport = { 697 .name = "loop", 698 .module = THIS_MODULE, 699 .create_ctrl = nvme_loop_create_ctrl, 700 .allowed_opts = NVMF_OPT_TRADDR, 701}; 702 703static int __init nvme_loop_init_module(void) 704{ 705 int ret; 706 707 ret = nvmet_register_transport(&nvme_loop_ops); 708 if (ret) 709 return ret; 710 711 ret = nvmf_register_transport(&nvme_loop_transport); 712 if (ret) 713 nvmet_unregister_transport(&nvme_loop_ops); 714 715 return ret; 716} 717 718static void __exit nvme_loop_cleanup_module(void) 719{ 720 struct nvme_loop_ctrl *ctrl, *next; 721 722 nvmf_unregister_transport(&nvme_loop_transport); 723 nvmet_unregister_transport(&nvme_loop_ops); 724 725 mutex_lock(&nvme_loop_ctrl_mutex); 726 list_for_each_entry_safe(ctrl, next, &nvme_loop_ctrl_list, list) 727 nvme_delete_ctrl(&ctrl->ctrl); 728 mutex_unlock(&nvme_loop_ctrl_mutex); 729 730 flush_workqueue(nvme_delete_wq); 731} 732 733module_init(nvme_loop_init_module); 734module_exit(nvme_loop_cleanup_module); 735 736MODULE_LICENSE("GPL v2"); 737MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */ 738