1// SPDX-License-Identifier: GPL-2.0 2/* 3 * NVMe over Fabrics common host code. 4 * Copyright (c) 2015-2016 HGST, a Western Digital Company. 5 */ 6#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt 7#include <linux/init.h> 8#include <linux/miscdevice.h> 9#include <linux/module.h> 10#include <linux/mutex.h> 11#include <linux/parser.h> 12#include <linux/seq_file.h> 13#include "nvme.h" 14#include "fabrics.h" 15 16static LIST_HEAD(nvmf_transports); 17static DECLARE_RWSEM(nvmf_transports_rwsem); 18 19static LIST_HEAD(nvmf_hosts); 20static DEFINE_MUTEX(nvmf_hosts_mutex); 21 22static struct nvmf_host *nvmf_default_host; 23 24static struct nvmf_host *__nvmf_host_find(const char *hostnqn) 25{ 26 struct nvmf_host *host; 27 28 list_for_each_entry(host, &nvmf_hosts, list) { 29 if (!strcmp(host->nqn, hostnqn)) 30 return host; 31 } 32 33 return NULL; 34} 35 36static struct nvmf_host *nvmf_host_add(const char *hostnqn) 37{ 38 struct nvmf_host *host; 39 40 mutex_lock(&nvmf_hosts_mutex); 41 host = __nvmf_host_find(hostnqn); 42 if (host) { 43 kref_get(&host->ref); 44 goto out_unlock; 45 } 46 47 host = kmalloc(sizeof(*host), GFP_KERNEL); 48 if (!host) 49 goto out_unlock; 50 51 kref_init(&host->ref); 52 strlcpy(host->nqn, hostnqn, NVMF_NQN_SIZE); 53 54 list_add_tail(&host->list, &nvmf_hosts); 55out_unlock: 56 mutex_unlock(&nvmf_hosts_mutex); 57 return host; 58} 59 60static struct nvmf_host *nvmf_host_default(void) 61{ 62 struct nvmf_host *host; 63 64 host = kmalloc(sizeof(*host), GFP_KERNEL); 65 if (!host) 66 return NULL; 67 68 kref_init(&host->ref); 69 uuid_gen(&host->id); 70 snprintf(host->nqn, NVMF_NQN_SIZE, 71 "nqn.2014-08.org.nvmexpress:uuid:%pUb", &host->id); 72 73 mutex_lock(&nvmf_hosts_mutex); 74 list_add_tail(&host->list, &nvmf_hosts); 75 mutex_unlock(&nvmf_hosts_mutex); 76 77 return host; 78} 79 80static void nvmf_host_destroy(struct kref *ref) 81{ 82 struct nvmf_host *host = container_of(ref, struct nvmf_host, ref); 83 84 mutex_lock(&nvmf_hosts_mutex); 85 list_del(&host->list); 86 mutex_unlock(&nvmf_hosts_mutex); 87 88 kfree(host); 89} 90 91static void nvmf_host_put(struct nvmf_host *host) 92{ 93 if (host) 94 kref_put(&host->ref, nvmf_host_destroy); 95} 96 97/** 98 * nvmf_get_address() - Get address/port 99 * @ctrl: Host NVMe controller instance which we got the address 100 * @buf: OUTPUT parameter that will contain the address/port 101 * @size: buffer size 102 */ 103int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size) 104{ 105 int len = 0; 106 107 if (ctrl->opts->mask & NVMF_OPT_TRADDR) 108 len += scnprintf(buf, size, "traddr=%s", ctrl->opts->traddr); 109 if (ctrl->opts->mask & NVMF_OPT_TRSVCID) 110 len += scnprintf(buf + len, size - len, "%strsvcid=%s", 111 (len) ? "," : "", ctrl->opts->trsvcid); 112 if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR) 113 len += scnprintf(buf + len, size - len, "%shost_traddr=%s", 114 (len) ? "," : "", ctrl->opts->host_traddr); 115 len += scnprintf(buf + len, size - len, "\n"); 116 117 return len; 118} 119EXPORT_SYMBOL_GPL(nvmf_get_address); 120 121/** 122 * nvmf_reg_read32() - NVMe Fabrics "Property Get" API function. 123 * @ctrl: Host NVMe controller instance maintaining the admin 124 * queue used to submit the property read command to 125 * the allocated NVMe controller resource on the target system. 126 * @off: Starting offset value of the targeted property 127 * register (see the fabrics section of the NVMe standard). 128 * @val: OUTPUT parameter that will contain the value of 129 * the property after a successful read. 130 * 131 * Used by the host system to retrieve a 32-bit capsule property value 132 * from an NVMe controller on the target system. 133 * 134 * ("Capsule property" is an "PCIe register concept" applied to the 135 * NVMe fabrics space.) 136 * 137 * Return: 138 * 0: successful read 139 * > 0: NVMe error status code 140 * < 0: Linux errno error code 141 */ 142int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val) 143{ 144 struct nvme_command cmd; 145 union nvme_result res; 146 int ret; 147 148 memset(&cmd, 0, sizeof(cmd)); 149 cmd.prop_get.opcode = nvme_fabrics_command; 150 cmd.prop_get.fctype = nvme_fabrics_type_property_get; 151 cmd.prop_get.offset = cpu_to_le32(off); 152 153 ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0, 154 NVME_QID_ANY, 0, 0, false); 155 156 if (ret >= 0) 157 *val = le64_to_cpu(res.u64); 158 if (unlikely(ret != 0)) 159 dev_err(ctrl->device, 160 "Property Get error: %d, offset %#x\n", 161 ret > 0 ? ret & ~NVME_SC_DNR : ret, off); 162 163 return ret; 164} 165EXPORT_SYMBOL_GPL(nvmf_reg_read32); 166 167/** 168 * nvmf_reg_read64() - NVMe Fabrics "Property Get" API function. 169 * @ctrl: Host NVMe controller instance maintaining the admin 170 * queue used to submit the property read command to 171 * the allocated controller resource on the target system. 172 * @off: Starting offset value of the targeted property 173 * register (see the fabrics section of the NVMe standard). 174 * @val: OUTPUT parameter that will contain the value of 175 * the property after a successful read. 176 * 177 * Used by the host system to retrieve a 64-bit capsule property value 178 * from an NVMe controller on the target system. 179 * 180 * ("Capsule property" is an "PCIe register concept" applied to the 181 * NVMe fabrics space.) 182 * 183 * Return: 184 * 0: successful read 185 * > 0: NVMe error status code 186 * < 0: Linux errno error code 187 */ 188int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val) 189{ 190 struct nvme_command cmd; 191 union nvme_result res; 192 int ret; 193 194 memset(&cmd, 0, sizeof(cmd)); 195 cmd.prop_get.opcode = nvme_fabrics_command; 196 cmd.prop_get.fctype = nvme_fabrics_type_property_get; 197 cmd.prop_get.attrib = 1; 198 cmd.prop_get.offset = cpu_to_le32(off); 199 200 ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0, 201 NVME_QID_ANY, 0, 0, false); 202 203 if (ret >= 0) 204 *val = le64_to_cpu(res.u64); 205 if (unlikely(ret != 0)) 206 dev_err(ctrl->device, 207 "Property Get error: %d, offset %#x\n", 208 ret > 0 ? ret & ~NVME_SC_DNR : ret, off); 209 return ret; 210} 211EXPORT_SYMBOL_GPL(nvmf_reg_read64); 212 213/** 214 * nvmf_reg_write32() - NVMe Fabrics "Property Write" API function. 215 * @ctrl: Host NVMe controller instance maintaining the admin 216 * queue used to submit the property read command to 217 * the allocated NVMe controller resource on the target system. 218 * @off: Starting offset value of the targeted property 219 * register (see the fabrics section of the NVMe standard). 220 * @val: Input parameter that contains the value to be 221 * written to the property. 222 * 223 * Used by the NVMe host system to write a 32-bit capsule property value 224 * to an NVMe controller on the target system. 225 * 226 * ("Capsule property" is an "PCIe register concept" applied to the 227 * NVMe fabrics space.) 228 * 229 * Return: 230 * 0: successful write 231 * > 0: NVMe error status code 232 * < 0: Linux errno error code 233 */ 234int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val) 235{ 236 struct nvme_command cmd; 237 int ret; 238 239 memset(&cmd, 0, sizeof(cmd)); 240 cmd.prop_set.opcode = nvme_fabrics_command; 241 cmd.prop_set.fctype = nvme_fabrics_type_property_set; 242 cmd.prop_set.attrib = 0; 243 cmd.prop_set.offset = cpu_to_le32(off); 244 cmd.prop_set.value = cpu_to_le64(val); 245 246 ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0, 0, 247 NVME_QID_ANY, 0, 0, false); 248 if (unlikely(ret)) 249 dev_err(ctrl->device, 250 "Property Set error: %d, offset %#x\n", 251 ret > 0 ? ret & ~NVME_SC_DNR : ret, off); 252 return ret; 253} 254EXPORT_SYMBOL_GPL(nvmf_reg_write32); 255 256/** 257 * nvmf_log_connect_error() - Error-parsing-diagnostic print 258 * out function for connect() errors. 259 * 260 * @ctrl: the specific /dev/nvmeX device that had the error. 261 * 262 * @errval: Error code to be decoded in a more human-friendly 263 * printout. 264 * 265 * @offset: For use with the NVMe error code NVME_SC_CONNECT_INVALID_PARAM. 266 * 267 * @cmd: This is the SQE portion of a submission capsule. 268 * 269 * @data: This is the "Data" portion of a submission capsule. 270 */ 271static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, 272 int errval, int offset, struct nvme_command *cmd, 273 struct nvmf_connect_data *data) 274{ 275 int err_sctype = errval & (~NVME_SC_DNR); 276 277 switch (err_sctype) { 278 279 case (NVME_SC_CONNECT_INVALID_PARAM): 280 if (offset >> 16) { 281 char *inv_data = "Connect Invalid Data Parameter"; 282 283 switch (offset & 0xffff) { 284 case (offsetof(struct nvmf_connect_data, cntlid)): 285 dev_err(ctrl->device, 286 "%s, cntlid: %d\n", 287 inv_data, data->cntlid); 288 break; 289 case (offsetof(struct nvmf_connect_data, hostnqn)): 290 dev_err(ctrl->device, 291 "%s, hostnqn \"%s\"\n", 292 inv_data, data->hostnqn); 293 break; 294 case (offsetof(struct nvmf_connect_data, subsysnqn)): 295 dev_err(ctrl->device, 296 "%s, subsysnqn \"%s\"\n", 297 inv_data, data->subsysnqn); 298 break; 299 default: 300 dev_err(ctrl->device, 301 "%s, starting byte offset: %d\n", 302 inv_data, offset & 0xffff); 303 break; 304 } 305 } else { 306 char *inv_sqe = "Connect Invalid SQE Parameter"; 307 308 switch (offset) { 309 case (offsetof(struct nvmf_connect_command, qid)): 310 dev_err(ctrl->device, 311 "%s, qid %d\n", 312 inv_sqe, cmd->connect.qid); 313 break; 314 default: 315 dev_err(ctrl->device, 316 "%s, starting byte offset: %d\n", 317 inv_sqe, offset); 318 } 319 } 320 break; 321 322 case NVME_SC_CONNECT_INVALID_HOST: 323 dev_err(ctrl->device, 324 "Connect for subsystem %s is not allowed, hostnqn: %s\n", 325 data->subsysnqn, data->hostnqn); 326 break; 327 328 case NVME_SC_CONNECT_CTRL_BUSY: 329 dev_err(ctrl->device, 330 "Connect command failed: controller is busy or not available\n"); 331 break; 332 333 case NVME_SC_CONNECT_FORMAT: 334 dev_err(ctrl->device, 335 "Connect incompatible format: %d", 336 cmd->connect.recfmt); 337 break; 338 339 case NVME_SC_HOST_PATH_ERROR: 340 dev_err(ctrl->device, 341 "Connect command failed: host path error\n"); 342 break; 343 344 default: 345 dev_err(ctrl->device, 346 "Connect command failed, error wo/DNR bit: %d\n", 347 err_sctype); 348 break; 349 } /* switch (err_sctype) */ 350} 351 352/** 353 * nvmf_connect_admin_queue() - NVMe Fabrics Admin Queue "Connect" 354 * API function. 355 * @ctrl: Host nvme controller instance used to request 356 * a new NVMe controller allocation on the target 357 * system and establish an NVMe Admin connection to 358 * that controller. 359 * 360 * This function enables an NVMe host device to request a new allocation of 361 * an NVMe controller resource on a target system as well establish a 362 * fabrics-protocol connection of the NVMe Admin queue between the 363 * host system device and the allocated NVMe controller on the 364 * target system via a NVMe Fabrics "Connect" command. 365 * 366 * Return: 367 * 0: success 368 * > 0: NVMe error status code 369 * < 0: Linux errno error code 370 * 371 */ 372int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) 373{ 374 struct nvme_command cmd; 375 union nvme_result res; 376 struct nvmf_connect_data *data; 377 int ret; 378 379 memset(&cmd, 0, sizeof(cmd)); 380 cmd.connect.opcode = nvme_fabrics_command; 381 cmd.connect.fctype = nvme_fabrics_type_connect; 382 cmd.connect.qid = 0; 383 cmd.connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1); 384 385 /* 386 * Set keep-alive timeout in seconds granularity (ms * 1000) 387 * and add a grace period for controller kato enforcement 388 */ 389 cmd.connect.kato = ctrl->kato ? 390 cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000) : 0; 391 392 if (ctrl->opts->disable_sqflow) 393 cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; 394 395 data = kzalloc(sizeof(*data), GFP_KERNEL); 396 if (!data) 397 return -ENOMEM; 398 399 uuid_copy(&data->hostid, &ctrl->opts->host->id); 400 data->cntlid = cpu_to_le16(0xffff); 401 strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); 402 strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); 403 404 ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, 405 data, sizeof(*data), 0, NVME_QID_ANY, 1, 406 BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, false); 407 if (ret) { 408 nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32), 409 &cmd, data); 410 goto out_free_data; 411 } 412 413 ctrl->cntlid = le16_to_cpu(res.u16); 414 415out_free_data: 416 kfree(data); 417 return ret; 418} 419EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue); 420 421/** 422 * nvmf_connect_io_queue() - NVMe Fabrics I/O Queue "Connect" 423 * API function. 424 * @ctrl: Host nvme controller instance used to establish an 425 * NVMe I/O queue connection to the already allocated NVMe 426 * controller on the target system. 427 * @qid: NVMe I/O queue number for the new I/O connection between 428 * host and target (note qid == 0 is illegal as this is 429 * the Admin queue, per NVMe standard). 430 * @poll: Whether or not to poll for the completion of the connect cmd. 431 * 432 * This function issues a fabrics-protocol connection 433 * of a NVMe I/O queue (via NVMe Fabrics "Connect" command) 434 * between the host system device and the allocated NVMe controller 435 * on the target system. 436 * 437 * Return: 438 * 0: success 439 * > 0: NVMe error status code 440 * < 0: Linux errno error code 441 */ 442int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll) 443{ 444 struct nvme_command cmd; 445 struct nvmf_connect_data *data; 446 union nvme_result res; 447 int ret; 448 449 memset(&cmd, 0, sizeof(cmd)); 450 cmd.connect.opcode = nvme_fabrics_command; 451 cmd.connect.fctype = nvme_fabrics_type_connect; 452 cmd.connect.qid = cpu_to_le16(qid); 453 cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize); 454 455 if (ctrl->opts->disable_sqflow) 456 cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; 457 458 data = kzalloc(sizeof(*data), GFP_KERNEL); 459 if (!data) 460 return -ENOMEM; 461 462 uuid_copy(&data->hostid, &ctrl->opts->host->id); 463 data->cntlid = cpu_to_le16(ctrl->cntlid); 464 strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); 465 strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); 466 467 ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res, 468 data, sizeof(*data), 0, qid, 1, 469 BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, poll); 470 if (ret) { 471 nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32), 472 &cmd, data); 473 } 474 kfree(data); 475 return ret; 476} 477EXPORT_SYMBOL_GPL(nvmf_connect_io_queue); 478 479bool nvmf_should_reconnect(struct nvme_ctrl *ctrl) 480{ 481 if (ctrl->opts->max_reconnects == -1 || 482 ctrl->nr_reconnects < ctrl->opts->max_reconnects) 483 return true; 484 485 return false; 486} 487EXPORT_SYMBOL_GPL(nvmf_should_reconnect); 488 489/** 490 * nvmf_register_transport() - NVMe Fabrics Library registration function. 491 * @ops: Transport ops instance to be registered to the 492 * common fabrics library. 493 * 494 * API function that registers the type of specific transport fabric 495 * being implemented to the common NVMe fabrics library. Part of 496 * the overall init sequence of starting up a fabrics driver. 497 */ 498int nvmf_register_transport(struct nvmf_transport_ops *ops) 499{ 500 if (!ops->create_ctrl) 501 return -EINVAL; 502 503 down_write(&nvmf_transports_rwsem); 504 list_add_tail(&ops->entry, &nvmf_transports); 505 up_write(&nvmf_transports_rwsem); 506 507 return 0; 508} 509EXPORT_SYMBOL_GPL(nvmf_register_transport); 510 511/** 512 * nvmf_unregister_transport() - NVMe Fabrics Library unregistration function. 513 * @ops: Transport ops instance to be unregistered from the 514 * common fabrics library. 515 * 516 * Fabrics API function that unregisters the type of specific transport 517 * fabric being implemented from the common NVMe fabrics library. 518 * Part of the overall exit sequence of unloading the implemented driver. 519 */ 520void nvmf_unregister_transport(struct nvmf_transport_ops *ops) 521{ 522 down_write(&nvmf_transports_rwsem); 523 list_del(&ops->entry); 524 up_write(&nvmf_transports_rwsem); 525} 526EXPORT_SYMBOL_GPL(nvmf_unregister_transport); 527 528static struct nvmf_transport_ops *nvmf_lookup_transport( 529 struct nvmf_ctrl_options *opts) 530{ 531 struct nvmf_transport_ops *ops; 532 533 lockdep_assert_held(&nvmf_transports_rwsem); 534 535 list_for_each_entry(ops, &nvmf_transports, entry) { 536 if (strcmp(ops->name, opts->transport) == 0) 537 return ops; 538 } 539 540 return NULL; 541} 542 543/* 544 * For something we're not in a state to send to the device the default action 545 * is to busy it and retry it after the controller state is recovered. However, 546 * if the controller is deleting or if anything is marked for failfast or 547 * nvme multipath it is immediately failed. 548 * 549 * Note: commands used to initialize the controller will be marked for failfast. 550 * Note: nvme cli/ioctl commands are marked for failfast. 551 */ 552blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, 553 struct request *rq) 554{ 555 if (ctrl->state != NVME_CTRL_DELETING_NOIO && 556 ctrl->state != NVME_CTRL_DEAD && 557 !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) 558 return BLK_STS_RESOURCE; 559 560 nvme_req(rq)->status = NVME_SC_HOST_PATH_ERROR; 561 blk_mq_start_request(rq); 562 nvme_complete_rq(rq); 563 return BLK_STS_OK; 564} 565EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command); 566 567bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, 568 bool queue_live) 569{ 570 struct nvme_request *req = nvme_req(rq); 571 572 /* 573 * currently we have a problem sending passthru commands 574 * on the admin_q if the controller is not LIVE because we can't 575 * make sure that they are going out after the admin connect, 576 * controller enable and/or other commands in the initialization 577 * sequence. until the controller will be LIVE, fail with 578 * BLK_STS_RESOURCE so that they will be rescheduled. 579 */ 580 if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD)) 581 return false; 582 583 /* 584 * Only allow commands on a live queue, except for the connect command, 585 * which is require to set the queue live in the appropinquate states. 586 */ 587 switch (ctrl->state) { 588 case NVME_CTRL_CONNECTING: 589 if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) && 590 req->cmd->fabrics.fctype == nvme_fabrics_type_connect) 591 return true; 592 break; 593 default: 594 break; 595 case NVME_CTRL_DEAD: 596 return false; 597 } 598 599 return queue_live; 600} 601EXPORT_SYMBOL_GPL(__nvmf_check_ready); 602 603static const match_table_t opt_tokens = { 604 { NVMF_OPT_TRANSPORT, "transport=%s" }, 605 { NVMF_OPT_TRADDR, "traddr=%s" }, 606 { NVMF_OPT_TRSVCID, "trsvcid=%s" }, 607 { NVMF_OPT_NQN, "nqn=%s" }, 608 { NVMF_OPT_QUEUE_SIZE, "queue_size=%d" }, 609 { NVMF_OPT_NR_IO_QUEUES, "nr_io_queues=%d" }, 610 { NVMF_OPT_RECONNECT_DELAY, "reconnect_delay=%d" }, 611 { NVMF_OPT_CTRL_LOSS_TMO, "ctrl_loss_tmo=%d" }, 612 { NVMF_OPT_KATO, "keep_alive_tmo=%d" }, 613 { NVMF_OPT_HOSTNQN, "hostnqn=%s" }, 614 { NVMF_OPT_HOST_TRADDR, "host_traddr=%s" }, 615 { NVMF_OPT_HOST_ID, "hostid=%s" }, 616 { NVMF_OPT_DUP_CONNECT, "duplicate_connect" }, 617 { NVMF_OPT_DISABLE_SQFLOW, "disable_sqflow" }, 618 { NVMF_OPT_HDR_DIGEST, "hdr_digest" }, 619 { NVMF_OPT_DATA_DIGEST, "data_digest" }, 620 { NVMF_OPT_NR_WRITE_QUEUES, "nr_write_queues=%d" }, 621 { NVMF_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" }, 622 { NVMF_OPT_TOS, "tos=%d" }, 623 { NVMF_OPT_ERR, NULL } 624}; 625 626static int nvmf_parse_options(struct nvmf_ctrl_options *opts, 627 const char *buf) 628{ 629 substring_t args[MAX_OPT_ARGS]; 630 char *options, *o, *p; 631 int token, ret = 0; 632 size_t nqnlen = 0; 633 int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO; 634 uuid_t hostid; 635 636 /* Set defaults */ 637 opts->queue_size = NVMF_DEF_QUEUE_SIZE; 638 opts->nr_io_queues = num_online_cpus(); 639 opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY; 640 opts->kato = NVME_DEFAULT_KATO; 641 opts->duplicate_connect = false; 642 opts->hdr_digest = false; 643 opts->data_digest = false; 644 opts->tos = -1; /* < 0 == use transport default */ 645 646 options = o = kstrdup(buf, GFP_KERNEL); 647 if (!options) 648 return -ENOMEM; 649 650 uuid_gen(&hostid); 651 652 while ((p = strsep(&o, ",\n")) != NULL) { 653 if (!*p) 654 continue; 655 656 token = match_token(p, opt_tokens, args); 657 opts->mask |= token; 658 switch (token) { 659 case NVMF_OPT_TRANSPORT: 660 p = match_strdup(args); 661 if (!p) { 662 ret = -ENOMEM; 663 goto out; 664 } 665 kfree(opts->transport); 666 opts->transport = p; 667 break; 668 case NVMF_OPT_NQN: 669 p = match_strdup(args); 670 if (!p) { 671 ret = -ENOMEM; 672 goto out; 673 } 674 kfree(opts->subsysnqn); 675 opts->subsysnqn = p; 676 nqnlen = strlen(opts->subsysnqn); 677 if (nqnlen >= NVMF_NQN_SIZE) { 678 pr_err("%s needs to be < %d bytes\n", 679 opts->subsysnqn, NVMF_NQN_SIZE); 680 ret = -EINVAL; 681 goto out; 682 } 683 opts->discovery_nqn = 684 !(strcmp(opts->subsysnqn, 685 NVME_DISC_SUBSYS_NAME)); 686 break; 687 case NVMF_OPT_TRADDR: 688 p = match_strdup(args); 689 if (!p) { 690 ret = -ENOMEM; 691 goto out; 692 } 693 kfree(opts->traddr); 694 opts->traddr = p; 695 break; 696 case NVMF_OPT_TRSVCID: 697 p = match_strdup(args); 698 if (!p) { 699 ret = -ENOMEM; 700 goto out; 701 } 702 kfree(opts->trsvcid); 703 opts->trsvcid = p; 704 break; 705 case NVMF_OPT_QUEUE_SIZE: 706 if (match_int(args, &token)) { 707 ret = -EINVAL; 708 goto out; 709 } 710 if (token < NVMF_MIN_QUEUE_SIZE || 711 token > NVMF_MAX_QUEUE_SIZE) { 712 pr_err("Invalid queue_size %d\n", token); 713 ret = -EINVAL; 714 goto out; 715 } 716 opts->queue_size = token; 717 break; 718 case NVMF_OPT_NR_IO_QUEUES: 719 if (match_int(args, &token)) { 720 ret = -EINVAL; 721 goto out; 722 } 723 if (token <= 0) { 724 pr_err("Invalid number of IOQs %d\n", token); 725 ret = -EINVAL; 726 goto out; 727 } 728 if (opts->discovery_nqn) { 729 pr_debug("Ignoring nr_io_queues value for discovery controller\n"); 730 break; 731 } 732 733 opts->nr_io_queues = min_t(unsigned int, 734 num_online_cpus(), token); 735 break; 736 case NVMF_OPT_KATO: 737 if (match_int(args, &token)) { 738 ret = -EINVAL; 739 goto out; 740 } 741 742 if (token < 0) { 743 pr_err("Invalid keep_alive_tmo %d\n", token); 744 ret = -EINVAL; 745 goto out; 746 } else if (token == 0 && !opts->discovery_nqn) { 747 /* Allowed for debug */ 748 pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n"); 749 } 750 opts->kato = token; 751 break; 752 case NVMF_OPT_CTRL_LOSS_TMO: 753 if (match_int(args, &token)) { 754 ret = -EINVAL; 755 goto out; 756 } 757 758 if (token < 0) 759 pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n"); 760 ctrl_loss_tmo = token; 761 break; 762 case NVMF_OPT_HOSTNQN: 763 if (opts->host) { 764 pr_err("hostnqn already user-assigned: %s\n", 765 opts->host->nqn); 766 ret = -EADDRINUSE; 767 goto out; 768 } 769 p = match_strdup(args); 770 if (!p) { 771 ret = -ENOMEM; 772 goto out; 773 } 774 nqnlen = strlen(p); 775 if (nqnlen >= NVMF_NQN_SIZE) { 776 pr_err("%s needs to be < %d bytes\n", 777 p, NVMF_NQN_SIZE); 778 kfree(p); 779 ret = -EINVAL; 780 goto out; 781 } 782 nvmf_host_put(opts->host); 783 opts->host = nvmf_host_add(p); 784 kfree(p); 785 if (!opts->host) { 786 ret = -ENOMEM; 787 goto out; 788 } 789 break; 790 case NVMF_OPT_RECONNECT_DELAY: 791 if (match_int(args, &token)) { 792 ret = -EINVAL; 793 goto out; 794 } 795 if (token <= 0) { 796 pr_err("Invalid reconnect_delay %d\n", token); 797 ret = -EINVAL; 798 goto out; 799 } 800 opts->reconnect_delay = token; 801 break; 802 case NVMF_OPT_HOST_TRADDR: 803 p = match_strdup(args); 804 if (!p) { 805 ret = -ENOMEM; 806 goto out; 807 } 808 kfree(opts->host_traddr); 809 opts->host_traddr = p; 810 break; 811 case NVMF_OPT_HOST_ID: 812 p = match_strdup(args); 813 if (!p) { 814 ret = -ENOMEM; 815 goto out; 816 } 817 ret = uuid_parse(p, &hostid); 818 if (ret) { 819 pr_err("Invalid hostid %s\n", p); 820 ret = -EINVAL; 821 kfree(p); 822 goto out; 823 } 824 kfree(p); 825 break; 826 case NVMF_OPT_DUP_CONNECT: 827 opts->duplicate_connect = true; 828 break; 829 case NVMF_OPT_DISABLE_SQFLOW: 830 opts->disable_sqflow = true; 831 break; 832 case NVMF_OPT_HDR_DIGEST: 833 opts->hdr_digest = true; 834 break; 835 case NVMF_OPT_DATA_DIGEST: 836 opts->data_digest = true; 837 break; 838 case NVMF_OPT_NR_WRITE_QUEUES: 839 if (match_int(args, &token)) { 840 ret = -EINVAL; 841 goto out; 842 } 843 if (token <= 0) { 844 pr_err("Invalid nr_write_queues %d\n", token); 845 ret = -EINVAL; 846 goto out; 847 } 848 opts->nr_write_queues = token; 849 break; 850 case NVMF_OPT_NR_POLL_QUEUES: 851 if (match_int(args, &token)) { 852 ret = -EINVAL; 853 goto out; 854 } 855 if (token <= 0) { 856 pr_err("Invalid nr_poll_queues %d\n", token); 857 ret = -EINVAL; 858 goto out; 859 } 860 opts->nr_poll_queues = token; 861 break; 862 case NVMF_OPT_TOS: 863 if (match_int(args, &token)) { 864 ret = -EINVAL; 865 goto out; 866 } 867 if (token < 0) { 868 pr_err("Invalid type of service %d\n", token); 869 ret = -EINVAL; 870 goto out; 871 } 872 if (token > 255) { 873 pr_warn("Clamping type of service to 255\n"); 874 token = 255; 875 } 876 opts->tos = token; 877 break; 878 default: 879 pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", 880 p); 881 ret = -EINVAL; 882 goto out; 883 } 884 } 885 886 if (opts->discovery_nqn) { 887 opts->nr_io_queues = 0; 888 opts->nr_write_queues = 0; 889 opts->nr_poll_queues = 0; 890 opts->duplicate_connect = true; 891 } 892 if (ctrl_loss_tmo < 0) 893 opts->max_reconnects = -1; 894 else 895 opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo, 896 opts->reconnect_delay); 897 898 if (!opts->host) { 899 kref_get(&nvmf_default_host->ref); 900 opts->host = nvmf_default_host; 901 } 902 903 uuid_copy(&opts->host->id, &hostid); 904 905out: 906 kfree(options); 907 return ret; 908} 909 910static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts, 911 unsigned int required_opts) 912{ 913 if ((opts->mask & required_opts) != required_opts) { 914 int i; 915 916 for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) { 917 if ((opt_tokens[i].token & required_opts) && 918 !(opt_tokens[i].token & opts->mask)) { 919 pr_warn("missing parameter '%s'\n", 920 opt_tokens[i].pattern); 921 } 922 } 923 924 return -EINVAL; 925 } 926 927 return 0; 928} 929 930bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, 931 struct nvmf_ctrl_options *opts) 932{ 933 if (!nvmf_ctlr_matches_baseopts(ctrl, opts) || 934 strcmp(opts->traddr, ctrl->opts->traddr) || 935 strcmp(opts->trsvcid, ctrl->opts->trsvcid)) 936 return false; 937 938 /* 939 * Checking the local address is rough. In most cases, none is specified 940 * and the host port is selected by the stack. 941 * 942 * Assume no match if: 943 * - local address is specified and address is not the same 944 * - local address is not specified but remote is, or vice versa 945 * (admin using specific host_traddr when it matters). 946 */ 947 if ((opts->mask & NVMF_OPT_HOST_TRADDR) && 948 (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)) { 949 if (strcmp(opts->host_traddr, ctrl->opts->host_traddr)) 950 return false; 951 } else if ((opts->mask & NVMF_OPT_HOST_TRADDR) || 952 (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)) { 953 return false; 954 } 955 956 return true; 957} 958EXPORT_SYMBOL_GPL(nvmf_ip_options_match); 959 960static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts, 961 unsigned int allowed_opts) 962{ 963 if (opts->mask & ~allowed_opts) { 964 int i; 965 966 for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) { 967 if ((opt_tokens[i].token & opts->mask) && 968 (opt_tokens[i].token & ~allowed_opts)) { 969 pr_warn("invalid parameter '%s'\n", 970 opt_tokens[i].pattern); 971 } 972 } 973 974 return -EINVAL; 975 } 976 977 return 0; 978} 979 980void nvmf_free_options(struct nvmf_ctrl_options *opts) 981{ 982 nvmf_host_put(opts->host); 983 kfree(opts->transport); 984 kfree(opts->traddr); 985 kfree(opts->trsvcid); 986 kfree(opts->subsysnqn); 987 kfree(opts->host_traddr); 988 kfree(opts); 989} 990EXPORT_SYMBOL_GPL(nvmf_free_options); 991 992#define NVMF_REQUIRED_OPTS (NVMF_OPT_TRANSPORT | NVMF_OPT_NQN) 993#define NVMF_ALLOWED_OPTS (NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \ 994 NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \ 995 NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\ 996 NVMF_OPT_DISABLE_SQFLOW) 997 998static struct nvme_ctrl * 999nvmf_create_ctrl(struct device *dev, const char *buf) 1000{ 1001 struct nvmf_ctrl_options *opts; 1002 struct nvmf_transport_ops *ops; 1003 struct nvme_ctrl *ctrl; 1004 int ret; 1005 1006 opts = kzalloc(sizeof(*opts), GFP_KERNEL); 1007 if (!opts) 1008 return ERR_PTR(-ENOMEM); 1009 1010 ret = nvmf_parse_options(opts, buf); 1011 if (ret) 1012 goto out_free_opts; 1013 1014 1015 request_module("nvme-%s", opts->transport); 1016 1017 /* 1018 * Check the generic options first as we need a valid transport for 1019 * the lookup below. Then clear the generic flags so that transport 1020 * drivers don't have to care about them. 1021 */ 1022 ret = nvmf_check_required_opts(opts, NVMF_REQUIRED_OPTS); 1023 if (ret) 1024 goto out_free_opts; 1025 opts->mask &= ~NVMF_REQUIRED_OPTS; 1026 1027 down_read(&nvmf_transports_rwsem); 1028 ops = nvmf_lookup_transport(opts); 1029 if (!ops) { 1030 pr_info("no handler found for transport %s.\n", 1031 opts->transport); 1032 ret = -EINVAL; 1033 goto out_unlock; 1034 } 1035 1036 if (!try_module_get(ops->module)) { 1037 ret = -EBUSY; 1038 goto out_unlock; 1039 } 1040 up_read(&nvmf_transports_rwsem); 1041 1042 ret = nvmf_check_required_opts(opts, ops->required_opts); 1043 if (ret) 1044 goto out_module_put; 1045 ret = nvmf_check_allowed_opts(opts, NVMF_ALLOWED_OPTS | 1046 ops->allowed_opts | ops->required_opts); 1047 if (ret) 1048 goto out_module_put; 1049 1050 ctrl = ops->create_ctrl(dev, opts); 1051 if (IS_ERR(ctrl)) { 1052 ret = PTR_ERR(ctrl); 1053 goto out_module_put; 1054 } 1055 1056 module_put(ops->module); 1057 return ctrl; 1058 1059out_module_put: 1060 module_put(ops->module); 1061 goto out_free_opts; 1062out_unlock: 1063 up_read(&nvmf_transports_rwsem); 1064out_free_opts: 1065 nvmf_free_options(opts); 1066 return ERR_PTR(ret); 1067} 1068 1069static struct class *nvmf_class; 1070static struct device *nvmf_device; 1071static DEFINE_MUTEX(nvmf_dev_mutex); 1072 1073static ssize_t nvmf_dev_write(struct file *file, const char __user *ubuf, 1074 size_t count, loff_t *pos) 1075{ 1076 struct seq_file *seq_file = file->private_data; 1077 struct nvme_ctrl *ctrl; 1078 const char *buf; 1079 int ret = 0; 1080 1081 if (count > PAGE_SIZE) 1082 return -ENOMEM; 1083 1084 buf = memdup_user_nul(ubuf, count); 1085 if (IS_ERR(buf)) 1086 return PTR_ERR(buf); 1087 1088 mutex_lock(&nvmf_dev_mutex); 1089 if (seq_file->private) { 1090 ret = -EINVAL; 1091 goto out_unlock; 1092 } 1093 1094 ctrl = nvmf_create_ctrl(nvmf_device, buf); 1095 if (IS_ERR(ctrl)) { 1096 ret = PTR_ERR(ctrl); 1097 goto out_unlock; 1098 } 1099 1100 seq_file->private = ctrl; 1101 1102out_unlock: 1103 mutex_unlock(&nvmf_dev_mutex); 1104 kfree(buf); 1105 return ret ? ret : count; 1106} 1107 1108static int nvmf_dev_show(struct seq_file *seq_file, void *private) 1109{ 1110 struct nvme_ctrl *ctrl; 1111 int ret = 0; 1112 1113 mutex_lock(&nvmf_dev_mutex); 1114 ctrl = seq_file->private; 1115 if (!ctrl) { 1116 ret = -EINVAL; 1117 goto out_unlock; 1118 } 1119 1120 seq_printf(seq_file, "instance=%d,cntlid=%d\n", 1121 ctrl->instance, ctrl->cntlid); 1122 1123out_unlock: 1124 mutex_unlock(&nvmf_dev_mutex); 1125 return ret; 1126} 1127 1128static int nvmf_dev_open(struct inode *inode, struct file *file) 1129{ 1130 /* 1131 * The miscdevice code initializes file->private_data, but doesn't 1132 * make use of it later. 1133 */ 1134 file->private_data = NULL; 1135 return single_open(file, nvmf_dev_show, NULL); 1136} 1137 1138static int nvmf_dev_release(struct inode *inode, struct file *file) 1139{ 1140 struct seq_file *seq_file = file->private_data; 1141 struct nvme_ctrl *ctrl = seq_file->private; 1142 1143 if (ctrl) 1144 nvme_put_ctrl(ctrl); 1145 return single_release(inode, file); 1146} 1147 1148static const struct file_operations nvmf_dev_fops = { 1149 .owner = THIS_MODULE, 1150 .write = nvmf_dev_write, 1151 .read = seq_read, 1152 .open = nvmf_dev_open, 1153 .release = nvmf_dev_release, 1154}; 1155 1156static struct miscdevice nvmf_misc = { 1157 .minor = MISC_DYNAMIC_MINOR, 1158 .name = "nvme-fabrics", 1159 .fops = &nvmf_dev_fops, 1160}; 1161 1162static int __init nvmf_init(void) 1163{ 1164 int ret; 1165 1166 nvmf_default_host = nvmf_host_default(); 1167 if (!nvmf_default_host) 1168 return -ENOMEM; 1169 1170 nvmf_class = class_create(THIS_MODULE, "nvme-fabrics"); 1171 if (IS_ERR(nvmf_class)) { 1172 pr_err("couldn't register class nvme-fabrics\n"); 1173 ret = PTR_ERR(nvmf_class); 1174 goto out_free_host; 1175 } 1176 1177 nvmf_device = 1178 device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl"); 1179 if (IS_ERR(nvmf_device)) { 1180 pr_err("couldn't create nvme-fabris device!\n"); 1181 ret = PTR_ERR(nvmf_device); 1182 goto out_destroy_class; 1183 } 1184 1185 ret = misc_register(&nvmf_misc); 1186 if (ret) { 1187 pr_err("couldn't register misc device: %d\n", ret); 1188 goto out_destroy_device; 1189 } 1190 1191 return 0; 1192 1193out_destroy_device: 1194 device_destroy(nvmf_class, MKDEV(0, 0)); 1195out_destroy_class: 1196 class_destroy(nvmf_class); 1197out_free_host: 1198 nvmf_host_put(nvmf_default_host); 1199 return ret; 1200} 1201 1202static void __exit nvmf_exit(void) 1203{ 1204 misc_deregister(&nvmf_misc); 1205 device_destroy(nvmf_class, MKDEV(0, 0)); 1206 class_destroy(nvmf_class); 1207 nvmf_host_put(nvmf_default_host); 1208 1209 BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64); 1210 BUILD_BUG_ON(sizeof(struct nvmf_connect_command) != 64); 1211 BUILD_BUG_ON(sizeof(struct nvmf_property_get_command) != 64); 1212 BUILD_BUG_ON(sizeof(struct nvmf_property_set_command) != 64); 1213 BUILD_BUG_ON(sizeof(struct nvmf_connect_data) != 1024); 1214} 1215 1216MODULE_LICENSE("GPL v2"); 1217 1218module_init(nvmf_init); 1219module_exit(nvmf_exit); 1220