summaryrefslogtreecommitdiffstats
path: root/drivers/nvme/host/fabrics.c
blob: b2ab213f43dead83370a883ad64e8875de964c41 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
/*
 * NVMe over Fabrics common host code.
 * 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/init.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
#include "nvme.h"
#include "fabrics.h"

static LIST_HEAD(nvmf_transports);
static DECLARE_RWSEM(nvmf_transports_rwsem);

static LIST_HEAD(nvmf_hosts);
static DEFINE_MUTEX(nvmf_hosts_mutex);

static struct nvmf_host *nvmf_default_host;

static struct nvmf_host *__nvmf_host_find(const char *hostnqn)
{
	struct nvmf_host *host;

	list_for_each_entry(host, &nvmf_hosts, list) {
		if (!strcmp(host->nqn, hostnqn))
			return host;
	}

	return NULL;
}

static struct nvmf_host *nvmf_host_add(const char *hostnqn)
{
	struct nvmf_host *host;

	mutex_lock(&nvmf_hosts_mutex);
	host = __nvmf_host_find(hostnqn);
	if (host) {
		kref_get(&host->ref);
		goto out_unlock;
	}

	host = kmalloc(sizeof(*host), GFP_KERNEL);
	if (!host)
		goto out_unlock;

	kref_init(&host->ref);
	strlcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);

	list_add_tail(&host->list, &nvmf_hosts);
out_unlock:
	mutex_unlock(&nvmf_hosts_mutex);
	return host;
}

static struct nvmf_host *nvmf_host_default(void)
{
	struct nvmf_host *host;

	host = kmalloc(sizeof(*host), GFP_KERNEL);
	if (!host)
		return NULL;

	kref_init(&host->ref);
	uuid_gen(&host->id);
	snprintf(host->nqn, NVMF_NQN_SIZE,
		"nqn.2014-08.org.nvmexpress:uuid:%pUb", &host->id);

	mutex_lock(&nvmf_hosts_mutex);
	list_add_tail(&host->list, &nvmf_hosts);
	mutex_unlock(&nvmf_hosts_mutex);

	return host;
}

static void nvmf_host_destroy(struct kref *ref)
{
	struct nvmf_host *host = container_of(ref, struct nvmf_host, ref);

	mutex_lock(&nvmf_hosts_mutex);
	list_del(&host->list);
	mutex_unlock(&nvmf_hosts_mutex);

	kfree(host);
}

static void nvmf_host_put(struct nvmf_host *host)
{
	if (host)
		kref_put(&host->ref, nvmf_host_destroy);
}

/**
 * nvmf_get_address() -  Get address/port
 * @ctrl:	Host NVMe controller instance which we got the address
 * @buf:	OUTPUT parameter that will contain the address/port
 * @size:	buffer size
 */
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
{
	int len = 0;

	if (ctrl->opts->mask & NVMF_OPT_TRADDR)
		len += snprintf(buf, size, "traddr=%s", ctrl->opts->traddr);
	if (ctrl->opts->mask & NVMF_OPT_TRSVCID)
		len += snprintf(buf + len, size - len, "%strsvcid=%s",
				(len) ? "," : "", ctrl->opts->trsvcid);
	if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)
		len += snprintf(buf + len, size - len, "%shost_traddr=%s",
				(len) ? "," : "", ctrl->opts->host_traddr);
	len += snprintf(buf + len, size - len, "\n");

	return len;
}
EXPORT_SYMBOL_GPL(nvmf_get_address);

/**
 * nvmf_reg_read32() -  NVMe Fabrics "Property Get" API function.
 * @ctrl:	Host NVMe controller instance maintaining the admin
 *		queue used to submit the property read command to
 *		the allocated NVMe controller resource on the target system.
 * @off:	Starting offset value of the targeted property
 *		register (see the fabrics section of the NVMe standard).
 * @val:	OUTPUT parameter that will contain the value of
 *		the property after a successful read.
 *
 * Used by the host system to retrieve a 32-bit capsule property value
 * from an NVMe controller on the target system.
 *
 * ("Capsule property" is an "PCIe register concept" applied to the
 * NVMe fabrics space.)
 *
 * Return:
 *	0: successful read
 *	> 0: NVMe error status code
 *	< 0: Linux errno error code
 */
int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
{
	struct nvme_command cmd;
	union nvme_result res;
	int ret;

	memset(&cmd, 0, sizeof(cmd));
	cmd.prop_get.opcode = nvme_fabrics_command;
	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
	cmd.prop_get.offset = cpu_to_le32(off);

	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res, NULL, 0, 0,
			NVME_QID_ANY, 0, 0, false);

	if (ret >= 0)
		*val = le64_to_cpu(res.u64);
	if (unlikely(ret != 0))
		dev_err(ctrl->device,
			"Property Get error: %d, offset %#x\n",
			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);

	return ret;
}
EXPORT_SYMBOL_GPL(nvmf_reg_read32);

/**
 * nvmf_reg_read64() -  NVMe Fabrics "Property Get" API function.
 * @ctrl:	Host NVMe controller instance maintaining the admin
 *		queue used to submit the property read command to
 *		the allocated controller resource on the target system.
 * @off:	Starting offset value of the targeted property
 *		register (see the fabrics section of the NVMe standard).
 * @val:	OUTPUT parameter that will contain the value of
 *		the property after a successful read.
 *
 * Used by the host system to retrieve a 64-bit capsule property value
 * from an NVMe controller on the target system.
 *
 * ("Capsule property" is an "PCIe register concept" applied to the
 * NVMe fabrics space.)
 *
 * Return:
 *	0: successful read
 *	> 0: NVMe error status code
 *	< 0: Linux errno error code
 */
int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
{
	struct nvme_command cmd;
	union nvme_result res;
	int ret;

	memset(&cmd, 0, sizeof(cmd));
	cmd.prop_get.opcode = nvme_fabrics_command;
	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
	cmd.prop_get.attrib = 1;
	cmd.prop_get.offset = cpu_to_le32(off);

	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res, NULL, 0, 0,
			NVME_QID_ANY, 0, 0, false);

	if (ret >= 0)
		*val = le64_to_cpu(res.u64);
	if (unlikely(ret != 0))
		dev_err(ctrl->device,
			"Property Get error: %d, offset %#x\n",
			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
	return ret;
}
EXPORT_SYMBOL_GPL(nvmf_reg_read64);

/**
 * nvmf_reg_write32() -  NVMe Fabrics "Property Write" API function.
 * @ctrl:	Host NVMe controller instance maintaining the admin
 *		queue used to submit the property read command to
 *		the allocated NVMe controller resource on the target system.
 * @off:	Starting offset value of the targeted property
 *		register (see the fabrics section of the NVMe standard).
 * @val:	Input parameter that contains the value to be
 *		written to the property.
 *
 * Used by the NVMe host system to write a 32-bit capsule property value
 * to an NVMe controller on the target system.
 *
 * ("Capsule property" is an "PCIe register concept" applied to the
 * NVMe fabrics space.)
 *
 * Return:
 *	0: successful write
 *	> 0: NVMe error status code
 *	< 0: Linux errno error code
 */
int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
{
	struct nvme_command cmd;
	int ret;

	memset(&cmd, 0, sizeof(cmd));
	cmd.prop_set.opcode = nvme_fabrics_command;
	cmd.prop_set.fctype = nvme_fabrics_type_property_set;
	cmd.prop_set.attrib = 0;
	cmd.prop_set.offset = cpu_to_le32(off);
	cmd.prop_set.value = cpu_to_le64(val);

	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, NULL, 0, 0,
			NVME_QID_ANY, 0, 0, false);
	if (unlikely(ret))
		dev_err(ctrl->device,
			"Property Set error: %d, offset %#x\n",
			ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
	return ret;
}
EXPORT_SYMBOL_GPL(nvmf_reg_write32);

/**
 * nvmf_log_connect_error() - Error-parsing-diagnostic print
 * out function for connect() errors.
 *
 * @ctrl: the specific /dev/nvmeX device that had the error.
 *
 * @errval: Error code to be decoded in a more human-friendly
 *	    printout.
 *
 * @offset: For use with the NVMe error code NVME_SC_CONNECT_INVALID_PARAM.
 *
 * @cmd: This is the SQE portion of a submission capsule.
 *
 * @data: This is the "Data" portion of a submission capsule.
 */
static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
		int errval, int offset, struct nvme_command *cmd,
		struct nvmf_connect_data *data)
{
	int err_sctype = errval & (~NVME_SC_DNR);

	switch (err_sctype) {

	case (NVME_SC_CONNECT_INVALID_PARAM):
		if (offset >> 16) {
			char *inv_data = "Connect Invalid Data Parameter";

			switch (offset & 0xffff) {
			case (offsetof(struct nvmf_connect_data, cntlid)):
				dev_err(ctrl->device,
					"%s, cntlid: %d\n",
					inv_data, data->cntlid);
				break;
			case (offsetof(struct nvmf_connect_data, hostnqn)):
				dev_err(ctrl->device,
					"%s, hostnqn \"%s\"\n",
					inv_data, data->hostnqn);
				break;
			case (offsetof(struct nvmf_connect_data, subsysnqn)):
				dev_err(ctrl->device,
					"%s, subsysnqn \"%s\"\n",
					inv_data, data->subsysnqn);
				break;
			default:
				dev_err(ctrl->device,
					"%s, starting byte offset: %d\n",
				       inv_data, offset & 0xffff);
				break;
			}
		} else {
			char *inv_sqe = "Connect Invalid SQE Parameter";

			switch (offset) {
			case (offsetof(struct nvmf_connect_command, qid)):
				dev_err(ctrl->device,
				       "%s, qid %d\n",
					inv_sqe, cmd->connect.qid);
				break;
			default:
				dev_err(ctrl->device,
					"%s, starting byte offset: %d\n",
					inv_sqe, offset);
			}
		}
		break;

	case NVME_SC_CONNECT_INVALID_HOST:
		dev_err(ctrl->device,
			"Connect for subsystem %s is not allowed, hostnqn: %s\n",
			data->subsysnqn, data->hostnqn);
		break;

	case NVME_SC_CONNECT_CTRL_BUSY:
		dev_err(ctrl->device,
			"Connect command failed: controller is busy or not available\n");
		break;

	case NVME_SC_CONNECT_FORMAT:
		dev_err(ctrl->device,
			"Connect incompatible format: %d",
			cmd->connect.recfmt);
		break;

	default:
		dev_err(ctrl->device,
			"Connect command failed, error wo/DNR bit: %d\n",
			err_sctype);
		break;
	} /* switch (err_sctype) */
}

/**
 * nvmf_connect_admin_queue() - NVMe Fabrics Admin Queue "Connect"
 *				API function.
 * @ctrl:	Host nvme controller instance used to request
 *              a new NVMe controller allocation on the target
 *              system and  establish an NVMe Admin connection to
 *              that controller.
 *
 * This function enables an NVMe host device to request a new allocation of
 * an NVMe controller resource on a target system as well establish a
 * fabrics-protocol connection of the NVMe Admin queue between the
 * host system device and the allocated NVMe controller on the
 * target system via a NVMe Fabrics "Connect" command.
 *
 * Return:
 *	0: success
 *	> 0: NVMe error status code
 *	< 0: Linux errno error code
 *
 */
int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
{
	struct nvme_command cmd;
	union nvme_result res;
	struct nvmf_connect_data *data;
	int ret;

	memset(&cmd, 0, sizeof(cmd));
	cmd.connect.opcode = nvme_fabrics_command;
	cmd.connect.fctype = nvme_fabrics_type_connect;
	cmd.connect.qid = 0;
	cmd.connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1);

	/*
	 * Set keep-alive timeout in seconds granularity (ms * 1000)
	 * and add a grace period for controller kato enforcement
	 */
	cmd.connect.kato = ctrl->opts->discovery_nqn ? 0 :
		cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000);

	if (ctrl->opts->disable_sqflow)
		cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;

	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		return -ENOMEM;

	uuid_copy(&data->hostid, &ctrl->opts->host->id);
	data->cntlid = cpu_to_le16(0xffff);
	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);

	ret = __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, &res,
			data, sizeof(*data), 0, NVME_QID_ANY, 1,
			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, false);
	if (ret) {
		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
				       &cmd, data);
		goto out_free_data;
	}

	ctrl->cntlid = le16_to_cpu(res.u16);

out_free_data:
	kfree(data);
	return ret;
}
EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue);

/**
 * nvmf_connect_io_queue() - NVMe Fabrics I/O Queue "Connect"
 *			     API function.
 * @ctrl:	Host nvme controller instance used to establish an
 *		NVMe I/O queue connection to the already allocated NVMe
 *		controller on the target system.
 * @qid:	NVMe I/O queue number for the new I/O connection between
 *		host and target (note qid == 0 is illegal as this is
 *		the Admin queue, per NVMe standard).
 *
 * This function issues a fabrics-protocol connection
 * of a NVMe I/O queue (via NVMe Fabrics "Connect" command)
 * between the host system device and the allocated NVMe controller
 * on the target system.
 *
 * Return:
 *	0: success
 *	> 0: NVMe error status code
 *	< 0: Linux errno error code
 */
int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll)
{
	struct nvme_command cmd;
	struct nvmf_connect_data *data;
	union nvme_result res;
	int ret;

	memset(&cmd, 0, sizeof(cmd));
	cmd.connect.opcode = nvme_fabrics_command;
	cmd.connect.fctype = nvme_fabrics_type_connect;
	cmd.connect.qid = cpu_to_le16(qid);
	cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize);

	if (ctrl->opts->disable_sqflow)
		cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;

	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		return -ENOMEM;

	uuid_copy(&data->hostid, &ctrl->opts->host->id);
	data->cntlid = cpu_to_le16(ctrl->cntlid);
	strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
	strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);

	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res,
			data, sizeof(*data), 0, qid, 1,
			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, poll);
	if (ret) {
		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
				       &cmd, data);
	}
	kfree(data);
	return ret;
}
EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);

bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
{
	if (ctrl->opts->max_reconnects == -1 ||
	    ctrl->nr_reconnects < ctrl->opts->max_reconnects)
		return true;

	return false;
}
EXPORT_SYMBOL_GPL(nvmf_should_reconnect);

/**
 * nvmf_register_transport() - NVMe Fabrics Library registration function.
 * @ops:	Transport ops instance to be registered to the
 *		common fabrics library.
 *
 * API function that registers the type of specific transport fabric
 * being implemented to the common NVMe fabrics library. Part of
 * the overall init sequence of starting up a fabrics driver.
 */
int nvmf_register_transport(struct nvmf_transport_ops *ops)
{
	if (!ops->create_ctrl)
		return -EINVAL;

	down_write(&nvmf_transports_rwsem);
	list_add_tail(&ops->entry, &nvmf_transports);
	up_write(&nvmf_transports_rwsem);

	return 0;
}
EXPORT_SYMBOL_GPL(nvmf_register_transport);

/**
 * nvmf_unregister_transport() - NVMe Fabrics Library unregistration function.
 * @ops:	Transport ops instance to be unregistered from the
 *		common fabrics library.
 *
 * Fabrics API function that unregisters the type of specific transport
 * fabric being implemented from the common NVMe fabrics library.
 * Part of the overall exit sequence of unloading the implemented driver.
 */
void nvmf_unregister_transport(struct nvmf_transport_ops *ops)
{
	down_write(&nvmf_transports_rwsem);
	list_del(&ops->entry);
	up_write(&nvmf_transports_rwsem);
}
EXPORT_SYMBOL_GPL(nvmf_unregister_transport);

static struct nvmf_transport_ops *nvmf_lookup_transport(
		struct nvmf_ctrl_options *opts)
{
	struct nvmf_transport_ops *ops;

	lockdep_assert_held(&nvmf_transports_rwsem);

	list_for_each_entry(ops, &nvmf_transports, entry) {
		if (strcmp(ops->name, opts->transport) == 0)
			return ops;
	}

	return NULL;
}

/*
 * For something we're not in a state to send to the device the default action
 * is to busy it and retry it after the controller state is recovered.  However,
 * if the controller is deleting or if anything is marked for failfast or
 * nvme multipath it is immediately failed.
 *
 * Note: commands used to initialize the controller will be marked for failfast.
 * Note: nvme cli/ioctl commands are marked for failfast.
 */
blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
		struct request *rq)
{
	if (ctrl->state != NVME_CTRL_DELETING &&
	    ctrl->state != NVME_CTRL_DEAD &&
	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
		return BLK_STS_RESOURCE;

	nvme_req(rq)->status = NVME_SC_HOST_PATH_ERROR;
	blk_mq_start_request(rq);
	nvme_complete_rq(rq);
	return BLK_STS_OK;
}
EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command);

bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
		bool queue_live)
{
	struct nvme_request *req = nvme_req(rq);

	/*
	 * If we are in some state of setup or teardown only allow
	 * internally generated commands.
	 */
	if (!blk_rq_is_passthrough(rq) || (req->flags & NVME_REQ_USERCMD))
		return false;

	/*
	 * Only allow commands on a live queue, except for the connect command,
	 * which is require to set the queue live in the appropinquate states.
	 */
	switch (ctrl->state) {
	case NVME_CTRL_NEW:
	case NVME_CTRL_CONNECTING:
		if (req->cmd->common.opcode == nvme_fabrics_command &&
		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
			return true;
		break;
	default:
		break;
	case NVME_CTRL_DEAD:
		return false;
	}

	return queue_live;
}
EXPORT_SYMBOL_GPL(__nvmf_check_ready);

static const match_table_t opt_tokens = {
	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},
	{ NVMF_OPT_TRADDR,		"traddr=%s"		},
	{ NVMF_OPT_TRSVCID,		"trsvcid=%s"		},
	{ NVMF_OPT_NQN,			"nqn=%s"		},
	{ NVMF_OPT_QUEUE_SIZE,		"queue_size=%d"		},
	{ NVMF_OPT_NR_IO_QUEUES,	"nr_io_queues=%d"	},
	{ NVMF_OPT_RECONNECT_DELAY,	"reconnect_delay=%d"	},
	{ NVMF_OPT_CTRL_LOSS_TMO,	"ctrl_loss_tmo=%d"	},
	{ NVMF_OPT_KATO,		"keep_alive_tmo=%d"	},
	{ NVMF_OPT_HOSTNQN,		"hostnqn=%s"		},
	{ NVMF_OPT_HOST_TRADDR,		"host_traddr=%s"	},
	{ NVMF_OPT_HOST_ID,		"hostid=%s"		},
	{ NVMF_OPT_DUP_CONNECT,		"duplicate_connect"	},
	{ NVMF_OPT_DISABLE_SQFLOW,	"disable_sqflow"	},
	{ NVMF_OPT_HDR_DIGEST,		"hdr_digest"		},
	{ NVMF_OPT_DATA_DIGEST,		"data_digest"		},
	{ NVMF_OPT_NR_WRITE_QUEUES,	"nr_write_queues=%d"	},
	{ NVMF_OPT_NR_POLL_QUEUES,	"nr_poll_queues=%d"	},
	{ NVMF_OPT_ERR,			NULL			}
};

static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
		const char *buf)
{
	substring_t args[MAX_OPT_ARGS];
	char *options, *o, *p;
	int token, ret = 0;
	size_t nqnlen  = 0;
	int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO;
	uuid_t hostid;

	/* Set defaults */
	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
	opts->nr_io_queues = num_online_cpus();
	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
	opts->kato = NVME_DEFAULT_KATO;
	opts->duplicate_connect = false;
	opts->hdr_digest = false;
	opts->data_digest = false;

	options = o = kstrdup(buf, GFP_KERNEL);
	if (!options)
		return -ENOMEM;

	uuid_gen(&hostid);

	while ((p = strsep(&o, ",\n")) != NULL) {
		if (!*p)
			continue;

		token = match_token(p, opt_tokens, args);
		opts->mask |= token;
		switch (token) {
		case NVMF_OPT_TRANSPORT:
			p = match_strdup(args);
			if (!p) {
				ret = -ENOMEM;
				goto out;
			}
			kfree(opts->transport);
			opts->transport = p;
			break;
		case NVMF_OPT_NQN:
			p = match_strdup(args);
			if (!p) {
				ret = -ENOMEM;
				goto out;
			}
			kfree(opts->subsysnqn);
			opts->subsysnqn = p;
			nqnlen = strlen(opts->subsysnqn);
			if (nqnlen >= NVMF_NQN_SIZE) {
				pr_err("%s needs to be < %d bytes\n",
					opts->subsysnqn, NVMF_NQN_SIZE);
				ret = -EINVAL;
				goto out;
			}
			opts->discovery_nqn =
				!(strcmp(opts->subsysnqn,
					 NVME_DISC_SUBSYS_NAME));
			break;
		case NVMF_OPT_TRADDR:
			p = match_strdup(args);
			if (!p) {
				ret = -ENOMEM;
				goto out;
			}
			kfree(opts->traddr);
			opts->traddr = p;
			break;
		case NVMF_OPT_TRSVCID:
			p = match_strdup(args);
			if (!p) {
				ret = -ENOMEM;
				goto out;
			}
			kfree(opts->trsvcid);
			opts->trsvcid = p;
			break;
		case NVMF_OPT_QUEUE_SIZE:
			if (match_int(args, &token)) {
				ret = -EINVAL;
				goto out;
			}
			if (token < NVMF_MIN_QUEUE_SIZE ||
			    token > NVMF_MAX_QUEUE_SIZE) {
				pr_err("Invalid queue_size %d\n", token);
				ret = -EINVAL;
				goto out;
			}
			opts->queue_size = token;
			break;
		case NVMF_OPT_NR_IO_QUEUES:
			if (match_int(args, &token)) {
				ret = -EINVAL;
				goto out;
			}
			if (token <= 0) {
				pr_err("Invalid number of IOQs %d\n", token);
				ret = -EINVAL;
				goto out;
			}
			if (opts->discovery_nqn) {
				pr_debug("Ignoring nr_io_queues value for discovery controller\n");
				break;
			}

			opts->nr_io_queues = min_t(unsigned int,
					num_online_cpus(), token);
			break;
		case NVMF_OPT_KATO:
			if (match_int(args, &token)) {
				ret = -EINVAL;
				goto out;
			}

			if (token < 0) {
				pr_err("Invalid keep_alive_tmo %d\n", token);
				ret = -EINVAL;
				goto out;
			} else if (token == 0 && !opts->discovery_nqn) {
				/* Allowed for debug */
				pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
			}
			opts->kato = token;

			if (opts->discovery_nqn && opts->kato) {
				pr_err("Discovery controllers cannot accept KATO != 0\n");
				ret = -EINVAL;
				goto out;
			}

			break;
		case NVMF_OPT_CTRL_LOSS_TMO:
			if (match_int(args, &token)) {
				ret = -EINVAL;
				goto out;
			}

			if (token < 0)
				pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n");
			ctrl_loss_tmo = token;
			break;
		case NVMF_OPT_HOSTNQN:
			if (opts->host) {
				pr_err("hostnqn already user-assigned: %s\n",
				       opts->host->nqn);
				ret = -EADDRINUSE;
				goto out;
			}
			p = match_strdup(args);
			if (!p) {
				ret = -ENOMEM;
				goto out;
			}
			nqnlen = strlen(p);
			if (nqnlen >= NVMF_NQN_SIZE) {
				pr_err("%s needs to be < %d bytes\n",
					p, NVMF_NQN_SIZE);
				kfree(p);
				ret = -EINVAL;
				goto out;
			}
			nvmf_host_put(opts->host);
			opts->host = nvmf_host_add(p);
			kfree(p);
			if (!opts->host) {
				ret = -ENOMEM;
				goto out;
			}
			break;
		case NVMF_OPT_RECONNECT_DELAY:
			if (match_int(args, &token)) {
				ret = -EINVAL;
				goto out;
			}
			if (token <= 0) {
				pr_err("Invalid reconnect_delay %d\n", token);
				ret = -EINVAL;
				goto out;
			}
			opts->reconnect_delay = token;
			break;
		case NVMF_OPT_HOST_TRADDR:
			p = match_strdup(args);
			if (!p) {
				ret = -ENOMEM;
				goto out;
			}
			kfree(opts->host_traddr);
			opts->host_traddr = p;
			break;
		case NVMF_OPT_HOST_ID:
			p = match_strdup(args);
			if (!p) {
				ret = -ENOMEM;
				goto out;
			}
			ret = uuid_parse(p, &hostid);
			if (ret) {
				pr_err("Invalid hostid %s\n", p);
				ret = -EINVAL;
				kfree(p);
				goto out;
			}
			kfree(p);
			break;
		case NVMF_OPT_DUP_CONNECT:
			opts->duplicate_connect = true;
			break;
		case NVMF_OPT_DISABLE_SQFLOW:
			opts->disable_sqflow = true;
			break;
		case NVMF_OPT_HDR_DIGEST:
			opts->hdr_digest = true;
			break;
		case NVMF_OPT_DATA_DIGEST:
			opts->data_digest = true;
			break;
		case NVMF_OPT_NR_WRITE_QUEUES:
			if (match_int(args, &token)) {
				ret = -EINVAL;
				goto out;
			}
			if (token <= 0) {
				pr_err("Invalid nr_write_queues %d\n", token);
				ret = -EINVAL;
				goto out;
			}
			opts->nr_write_queues = token;
			break;
		case NVMF_OPT_NR_POLL_QUEUES:
			if (match_int(args, &token)) {
				ret = -EINVAL;
				goto out;
			}
			if (token <= 0) {
				pr_err("Invalid nr_poll_queues %d\n", token);
				ret = -EINVAL;
				goto out;
			}
			opts->nr_poll_queues = token;
			break;
		default:
			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
				p);
			ret = -EINVAL;
			goto out;
		}
	}

	if (opts->discovery_nqn) {
		opts->kato = 0;
		opts->nr_io_queues = 0;
		opts->duplicate_connect = true;
	}
	if (ctrl_loss_tmo < 0)
		opts->max_reconnects = -1;
	else
		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
						opts->reconnect_delay);

	if (!opts->host) {
		kref_get(&nvmf_default_host->ref);
		opts->host = nvmf_default_host;
	}

	uuid_copy(&opts->host->id, &hostid);

out:
	kfree(options);
	return ret;
}

static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts,
		unsigned int required_opts)
{
	if ((opts->mask & required_opts) != required_opts) {
		int i;

		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
			if ((opt_tokens[i].token & required_opts) &&
			    !(opt_tokens[i].token & opts->mask)) {
				pr_warn("missing parameter '%s'\n",
					opt_tokens[i].pattern);
			}
		}

		return -EINVAL;
	}

	return 0;
}

bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
		struct nvmf_ctrl_options *opts)
{
	if (!nvmf_ctlr_matches_baseopts(ctrl, opts) ||
	    strcmp(opts->traddr, ctrl->opts->traddr) ||
	    strcmp(opts->trsvcid, ctrl->opts->trsvcid))
		return false;

	/*
	 * Checking the local address is rough. In most cases, none is specified
	 * and the host port is selected by the stack.
	 *
	 * Assume no match if:
	 * -  local address is specified and address is not the same
	 * -  local address is not specified but remote is, or vice versa
	 *    (admin using specific host_traddr when it matters).
	 */
	if ((opts->mask & NVMF_OPT_HOST_TRADDR) &&
	    (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)) {
		if (strcmp(opts->host_traddr, ctrl->opts->host_traddr))
			return false;
	} else if ((opts->mask & NVMF_OPT_HOST_TRADDR) ||
		   (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)) {
		return false;
	}

	return true;
}
EXPORT_SYMBOL_GPL(nvmf_ip_options_match);

static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts,
		unsigned int allowed_opts)
{
	if (opts->mask & ~allowed_opts) {
		int i;

		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
			if ((opt_tokens[i].token & opts->mask) &&
			    (opt_tokens[i].token & ~allowed_opts)) {
				pr_warn("invalid parameter '%s'\n",
					opt_tokens[i].pattern);
			}
		}

		return -EINVAL;
	}

	return 0;
}

void nvmf_free_options(struct nvmf_ctrl_options *opts)
{
	nvmf_host_put(opts->host);
	kfree(opts->transport);
	kfree(opts->traddr);
	kfree(opts->trsvcid);
	kfree(opts->subsysnqn);
	kfree(opts->host_traddr);
	kfree(opts);
}
EXPORT_SYMBOL_GPL(nvmf_free_options);

#define NVMF_REQUIRED_OPTS	(NVMF_OPT_TRANSPORT | NVMF_OPT_NQN)
#define NVMF_ALLOWED_OPTS	(NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
				 NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \
				 NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\
				 NVMF_OPT_DISABLE_SQFLOW)

static struct nvme_ctrl *
nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
{
	struct nvmf_ctrl_options *opts;
	struct nvmf_transport_ops *ops;
	struct nvme_ctrl *ctrl;
	int ret;

	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
	if (!opts)
		return ERR_PTR(-ENOMEM);

	ret = nvmf_parse_options(opts, buf);
	if (ret)
		goto out_free_opts;


	request_module("nvme-%s", opts->transport);

	/*
	 * Check the generic options first as we need a valid transport for
	 * the lookup below.  Then clear the generic flags so that transport
	 * drivers don't have to care about them.
	 */
	ret = nvmf_check_required_opts(opts, NVMF_REQUIRED_OPTS);
	if (ret)
		goto out_free_opts;
	opts->mask &= ~NVMF_REQUIRED_OPTS;

	down_read(&nvmf_transports_rwsem);
	ops = nvmf_lookup_transport(opts);
	if (!ops) {
		pr_info("no handler found for transport %s.\n",
			opts->transport);
		ret = -EINVAL;
		goto out_unlock;
	}

	if (!try_module_get(ops->module)) {
		ret = -EBUSY;
		goto out_unlock;
	}
	up_read(&nvmf_transports_rwsem);

	ret = nvmf_check_required_opts(opts, ops->required_opts);
	if (ret)
		goto out_module_put;
	ret = nvmf_check_allowed_opts(opts, NVMF_ALLOWED_OPTS |
				ops->allowed_opts | ops->required_opts);
	if (ret)
		goto out_module_put;

	ctrl = ops->create_ctrl(dev, opts);
	if (IS_ERR(ctrl)) {
		ret = PTR_ERR(ctrl);
		goto out_module_put;
	}

	module_put(ops->module);
	return ctrl;

out_module_put:
	module_put(ops->module);
	goto out_free_opts;
out_unlock:
	up_read(&nvmf_transports_rwsem);
out_free_opts:
	nvmf_free_options(opts);
	return ERR_PTR(ret);
}

static struct class *nvmf_class;
static struct device *nvmf_device;
static DEFINE_MUTEX(nvmf_dev_mutex);

static ssize_t nvmf_dev_write(struct file *file, const char __user *ubuf,
		size_t count, loff_t *pos)
{
	struct seq_file *seq_file = file->private_data;
	struct nvme_ctrl *ctrl;
	const char *buf;
	int ret = 0;

	if (count > PAGE_SIZE)
		return -ENOMEM;

	buf = memdup_user_nul(ubuf, count);
	if (IS_ERR(buf))
		return PTR_ERR(buf);

	mutex_lock(&nvmf_dev_mutex);
	if (seq_file->private) {
		ret = -EINVAL;
		goto out_unlock;
	}

	ctrl = nvmf_create_ctrl(nvmf_device, buf, count);
	if (IS_ERR(ctrl)) {
		ret = PTR_ERR(ctrl);
		goto out_unlock;
	}

	seq_file->private = ctrl;

out_unlock:
	mutex_unlock(&nvmf_dev_mutex);
	kfree(buf);
	return ret ? ret : count;
}

static int nvmf_dev_show(struct seq_file *seq_file, void *private)
{
	struct nvme_ctrl *ctrl;
	int ret = 0;

	mutex_lock(&nvmf_dev_mutex);
	ctrl = seq_file->private;
	if (!ctrl) {
		ret = -EINVAL;
		goto out_unlock;
	}

	seq_printf(seq_file, "instance=%d,cntlid=%d\n",
			ctrl->instance, ctrl->cntlid);

out_unlock:
	mutex_unlock(&nvmf_dev_mutex);
	return ret;
}

static int nvmf_dev_open(struct inode *inode, struct file *file)
{
	/*
	 * The miscdevice code initializes file->private_data, but doesn't
	 * make use of it later.
	 */
	file->private_data = NULL;
	return single_open(file, nvmf_dev_show, NULL);
}

static int nvmf_dev_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq_file = file->private_data;
	struct nvme_ctrl *ctrl = seq_file->private;

	if (ctrl)
		nvme_put_ctrl(ctrl);
	return single_release(inode, file);
}

static const struct file_operations nvmf_dev_fops = {
	.owner		= THIS_MODULE,
	.write		= nvmf_dev_write,
	.read		= seq_read,
	.open		= nvmf_dev_open,
	.release	= nvmf_dev_release,
};

static struct miscdevice nvmf_misc = {
	.minor		= MISC_DYNAMIC_MINOR,
	.name           = "nvme-fabrics",
	.fops		= &nvmf_dev_fops,
};

static int __init nvmf_init(void)
{
	int ret;

	nvmf_default_host = nvmf_host_default();
	if (!nvmf_default_host)
		return -ENOMEM;

	nvmf_class = class_create(THIS_MODULE, "nvme-fabrics");
	if (IS_ERR(nvmf_class)) {
		pr_err("couldn't register class nvme-fabrics\n");
		ret = PTR_ERR(nvmf_class);
		goto out_free_host;
	}

	nvmf_device =
		device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
	if (IS_ERR(nvmf_device)) {
		pr_err("couldn't create nvme-fabris device!\n");
		ret = PTR_ERR(nvmf_device);
		goto out_destroy_class;
	}

	ret = misc_register(&nvmf_misc);
	if (ret) {
		pr_err("couldn't register misc device: %d\n", ret);
		goto out_destroy_device;
	}

	return 0;

out_destroy_device:
	device_destroy(nvmf_class, MKDEV(0, 0));
out_destroy_class:
	class_destroy(nvmf_class);
out_free_host:
	nvmf_host_put(nvmf_default_host);
	return ret;
}

static void __exit nvmf_exit(void)
{
	misc_deregister(&nvmf_misc);
	device_destroy(nvmf_class, MKDEV(0, 0));
	class_destroy(nvmf_class);
	nvmf_host_put(nvmf_default_host);

	BUILD_BUG_ON(sizeof(struct nvmf_connect_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvmf_property_get_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvmf_property_set_command) != 64);
	BUILD_BUG_ON(sizeof(struct nvmf_connect_data) != 1024);
}

MODULE_LICENSE("GPL v2");

module_init(nvmf_init);
module_exit(nvmf_exit);