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