aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/nvme/target/core.c
blob: 74d4b785d2daac7d203108f06286221b5337f993 (plain) (blame)
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
/*
 * Common code for the NVMe target.
 * 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/module.h>
#include <linux/random.h>
#include <linux/rculist.h>

#include "nvmet.h"

static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
static DEFINE_IDA(cntlid_ida);

/*
 * This read/write semaphore is used to synchronize access to configuration
 * information on a target system that will result in discovery log page
 * information change for at least one host.
 * The full list of resources to protected by this semaphore is:
 *
 *  - subsystems list
 *  - per-subsystem allowed hosts list
 *  - allow_any_host subsystem attribute
 *  - nvmet_genctr
 *  - the nvmet_transports array
 *
 * When updating any of those lists/structures write lock should be obtained,
 * while when reading (popolating discovery log page or checking host-subsystem
 * link) read lock is obtained to allow concurrent reads.
 */
DECLARE_RWSEM(nvmet_config_sem);

static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
		const char *subsysnqn);

u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
		size_t len)
{
	if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
	return 0;
}

u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
{
	if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
	return 0;
}

u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
{
	if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len)
		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
	return 0;
}

static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys)
{
	struct nvmet_ns *ns;

	if (list_empty(&subsys->namespaces))
		return 0;

	ns = list_last_entry(&subsys->namespaces, struct nvmet_ns, dev_link);
	return ns->nsid;
}

static u32 nvmet_async_event_result(struct nvmet_async_event *aen)
{
	return aen->event_type | (aen->event_info << 8) | (aen->log_page << 16);
}

static void nvmet_async_events_free(struct nvmet_ctrl *ctrl)
{
	struct nvmet_req *req;

	while (1) {
		mutex_lock(&ctrl->lock);
		if (!ctrl->nr_async_event_cmds) {
			mutex_unlock(&ctrl->lock);
			return;
		}

		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
		mutex_unlock(&ctrl->lock);
		nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
	}
}

static void nvmet_async_event_work(struct work_struct *work)
{
	struct nvmet_ctrl *ctrl =
		container_of(work, struct nvmet_ctrl, async_event_work);
	struct nvmet_async_event *aen;
	struct nvmet_req *req;

	while (1) {
		mutex_lock(&ctrl->lock);
		aen = list_first_entry_or_null(&ctrl->async_events,
				struct nvmet_async_event, entry);
		if (!aen || !ctrl->nr_async_event_cmds) {
			mutex_unlock(&ctrl->lock);
			return;
		}

		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
		nvmet_set_result(req, nvmet_async_event_result(aen));

		list_del(&aen->entry);
		kfree(aen);

		mutex_unlock(&ctrl->lock);
		nvmet_req_complete(req, 0);
	}
}

static void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
		u8 event_info, u8 log_page)
{
	struct nvmet_async_event *aen;

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

	aen->event_type = event_type;
	aen->event_info = event_info;
	aen->log_page = log_page;

	mutex_lock(&ctrl->lock);
	list_add_tail(&aen->entry, &ctrl->async_events);
	mutex_unlock(&ctrl->lock);

	schedule_work(&ctrl->async_event_work);
}

static bool nvmet_aen_disabled(struct nvmet_ctrl *ctrl, u32 aen)
{
	if (!(READ_ONCE(ctrl->aen_enabled) & aen))
		return true;
	return test_and_set_bit(aen, &ctrl->aen_masked);
}

static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
{
	u32 i;

	mutex_lock(&ctrl->lock);
	if (ctrl->nr_changed_ns > NVME_MAX_CHANGED_NAMESPACES)
		goto out_unlock;

	for (i = 0; i < ctrl->nr_changed_ns; i++) {
		if (ctrl->changed_ns_list[i] == nsid)
			goto out_unlock;
	}

	if (ctrl->nr_changed_ns == NVME_MAX_CHANGED_NAMESPACES) {
		ctrl->changed_ns_list[0] = cpu_to_le32(0xffffffff);
		ctrl->nr_changed_ns = U32_MAX;
		goto out_unlock;
	}

	ctrl->changed_ns_list[ctrl->nr_changed_ns++] = nsid;
out_unlock:
	mutex_unlock(&ctrl->lock);
}

static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
{
	struct nvmet_ctrl *ctrl;

	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_NS_ATTR))
			continue;
		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
				NVME_AER_NOTICE_NS_CHANGED,
				NVME_LOG_CHANGED_NS);
	}
}

int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
{
	int ret = 0;

	down_write(&nvmet_config_sem);
	if (nvmet_transports[ops->type])
		ret = -EINVAL;
	else
		nvmet_transports[ops->type] = ops;
	up_write(&nvmet_config_sem);

	return ret;
}
EXPORT_SYMBOL_GPL(nvmet_register_transport);

void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops)
{
	down_write(&nvmet_config_sem);
	nvmet_transports[ops->type] = NULL;
	up_write(&nvmet_config_sem);
}
EXPORT_SYMBOL_GPL(nvmet_unregister_transport);

int nvmet_enable_port(struct nvmet_port *port)
{
	const struct nvmet_fabrics_ops *ops;
	int ret;

	lockdep_assert_held(&nvmet_config_sem);

	ops = nvmet_transports[port->disc_addr.trtype];
	if (!ops) {
		up_write(&nvmet_config_sem);
		request_module("nvmet-transport-%d", port->disc_addr.trtype);
		down_write(&nvmet_config_sem);
		ops = nvmet_transports[port->disc_addr.trtype];
		if (!ops) {
			pr_err("transport type %d not supported\n",
				port->disc_addr.trtype);
			return -EINVAL;
		}
	}

	if (!try_module_get(ops->owner))
		return -EINVAL;

	ret = ops->add_port(port);
	if (ret) {
		module_put(ops->owner);
		return ret;
	}

	port->enabled = true;
	return 0;
}

void nvmet_disable_port(struct nvmet_port *port)
{
	const struct nvmet_fabrics_ops *ops;

	lockdep_assert_held(&nvmet_config_sem);

	port->enabled = false;

	ops = nvmet_transports[port->disc_addr.trtype];
	ops->remove_port(port);
	module_put(ops->owner);
}

static void nvmet_keep_alive_timer(struct work_struct *work)
{
	struct nvmet_ctrl *ctrl = container_of(to_delayed_work(work),
			struct nvmet_ctrl, ka_work);

	pr_err("ctrl %d keep-alive timer (%d seconds) expired!\n",
		ctrl->cntlid, ctrl->kato);

	nvmet_ctrl_fatal_error(ctrl);
}

static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
{
	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
		ctrl->cntlid, ctrl->kato);

	INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer);
	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
}

static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
{
	pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid);

	cancel_delayed_work_sync(&ctrl->ka_work);
}

static struct nvmet_ns *__nvmet_find_namespace(struct nvmet_ctrl *ctrl,
		__le32 nsid)
{
	struct nvmet_ns *ns;

	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
		if (ns->nsid == le32_to_cpu(nsid))
			return ns;
	}

	return NULL;
}

struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid)
{
	struct nvmet_ns *ns;

	rcu_read_lock();
	ns = __nvmet_find_namespace(ctrl, nsid);
	if (ns)
		percpu_ref_get(&ns->ref);
	rcu_read_unlock();

	return ns;
}

static void nvmet_destroy_namespace(struct percpu_ref *ref)
{
	struct nvmet_ns *ns = container_of(ref, struct nvmet_ns, ref);

	complete(&ns->disable_done);
}

void nvmet_put_namespace(struct nvmet_ns *ns)
{
	percpu_ref_put(&ns->ref);
}

static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
{
	nvmet_bdev_ns_disable(ns);
	nvmet_file_ns_disable(ns);
}

int nvmet_ns_enable(struct nvmet_ns *ns)
{
	struct nvmet_subsys *subsys = ns->subsys;
	int ret = 0;

	mutex_lock(&subsys->lock);
	if (ns->enabled)
		goto out_unlock;

	ret = nvmet_bdev_ns_enable(ns);
	if (ret)
		ret = nvmet_file_ns_enable(ns);
	if (ret)
		goto out_unlock;

	ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace,
				0, GFP_KERNEL);
	if (ret)
		goto out_dev_put;

	if (ns->nsid > subsys->max_nsid)
		subsys->max_nsid = ns->nsid;

	/*
	 * The namespaces list needs to be sorted to simplify the implementation
	 * of the Identify Namepace List subcommand.
	 */
	if (list_empty(&subsys->namespaces)) {
		list_add_tail_rcu(&ns->dev_link, &subsys->namespaces);
	} else {
		struct nvmet_ns *old;

		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link) {
			BUG_ON(ns->nsid == old->nsid);
			if (ns->nsid < old->nsid)
				break;
		}

		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
	}

	nvmet_ns_changed(subsys, ns->nsid);
	ns->enabled = true;
	ret = 0;
out_unlock:
	mutex_unlock(&subsys->lock);
	return ret;
out_dev_put:
	nvmet_ns_dev_disable(ns);
	goto out_unlock;
}

void nvmet_ns_disable(struct nvmet_ns *ns)
{
	struct nvmet_subsys *subsys = ns->subsys;

	mutex_lock(&subsys->lock);
	if (!ns->enabled)
		goto out_unlock;

	ns->enabled = false;
	list_del_rcu(&ns->dev_link);
	if (ns->nsid == subsys->max_nsid)
		subsys->max_nsid = nvmet_max_nsid(subsys);
	mutex_unlock(&subsys->lock);

	/*
	 * Now that we removed the namespaces from the lookup list, we
	 * can kill the per_cpu ref and wait for any remaining references
	 * to be dropped, as well as a RCU grace period for anyone only
	 * using the namepace under rcu_read_lock().  Note that we can't
	 * use call_rcu here as we need to ensure the namespaces have
	 * been fully destroyed before unloading the module.
	 */
	percpu_ref_kill(&ns->ref);
	synchronize_rcu();
	wait_for_completion(&ns->disable_done);
	percpu_ref_exit(&ns->ref);

	mutex_lock(&subsys->lock);
	nvmet_ns_changed(subsys, ns->nsid);
	nvmet_ns_dev_disable(ns);
out_unlock:
	mutex_unlock(&subsys->lock);
}

void nvmet_ns_free(struct nvmet_ns *ns)
{
	nvmet_ns_disable(ns);

	kfree(ns->device_path);
	kfree(ns);
}

struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
{
	struct nvmet_ns *ns;

	ns = kzalloc(sizeof(*ns), GFP_KERNEL);
	if (!ns)
		return NULL;

	INIT_LIST_HEAD(&ns->dev_link);
	init_completion(&ns->disable_done);

	ns->nsid = nsid;
	ns->subsys = subsys;
	uuid_gen(&ns->uuid);

	return ns;
}

static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
{
	u32 old_sqhd, new_sqhd;
	u16 sqhd;

	if (status)
		nvmet_set_status(req, status);

	if (req->sq->size) {
		do {
			old_sqhd = req->sq->sqhd;
			new_sqhd = (old_sqhd + 1) % req->sq->size;
		} while (cmpxchg(&req->sq->sqhd, old_sqhd, new_sqhd) !=
					old_sqhd);
	}
	sqhd = req->sq->sqhd & 0x0000FFFF;
	req->rsp->sq_head = cpu_to_le16(sqhd);
	req->rsp->sq_id = cpu_to_le16(req->sq->qid);
	req->rsp->command_id = req->cmd->common.command_id;

	if (req->ns)
		nvmet_put_namespace(req->ns);
	req->ops->queue_response(req);
}

void nvmet_req_complete(struct nvmet_req *req, u16 status)
{
	__nvmet_req_complete(req, status);
	percpu_ref_put(&req->sq->ref);
}
EXPORT_SYMBOL_GPL(nvmet_req_complete);

void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq,
		u16 qid, u16 size)
{
	cq->qid = qid;
	cq->size = size;

	ctrl->cqs[qid] = cq;
}

void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
		u16 qid, u16 size)
{
	sq->sqhd = 0;
	sq->qid = qid;
	sq->size = size;

	ctrl->sqs[qid] = sq;
}

static void nvmet_confirm_sq(struct percpu_ref *ref)
{
	struct nvmet_sq *sq = container_of(ref, struct nvmet_sq, ref);

	complete(&sq->confirm_done);
}

void nvmet_sq_destroy(struct nvmet_sq *sq)
{
	/*
	 * If this is the admin queue, complete all AERs so that our
	 * queue doesn't have outstanding requests on it.
	 */
	if (sq->ctrl && sq->ctrl->sqs && sq->ctrl->sqs[0] == sq)
		nvmet_async_events_free(sq->ctrl);
	percpu_ref_kill_and_confirm(&sq->ref, nvmet_confirm_sq);
	wait_for_completion(&sq->confirm_done);
	wait_for_completion(&sq->free_done);
	percpu_ref_exit(&sq->ref);

	if (sq->ctrl) {
		nvmet_ctrl_put(sq->ctrl);
		sq->ctrl = NULL; /* allows reusing the queue later */
	}
}
EXPORT_SYMBOL_GPL(nvmet_sq_destroy);

static void nvmet_sq_free(struct percpu_ref *ref)
{
	struct nvmet_sq *sq = container_of(ref, struct nvmet_sq, ref);

	complete(&sq->free_done);
}

int nvmet_sq_init(struct nvmet_sq *sq)
{
	int ret;

	ret = percpu_ref_init(&sq->ref, nvmet_sq_free, 0, GFP_KERNEL);
	if (ret) {
		pr_err("percpu_ref init failed!\n");
		return ret;
	}
	init_completion(&sq->free_done);
	init_completion(&sq->confirm_done);

	return 0;
}
EXPORT_SYMBOL_GPL(nvmet_sq_init);

static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
{
	struct nvme_command *cmd = req->cmd;
	u16 ret;

	ret = nvmet_check_ctrl_status(req, cmd);
	if (unlikely(ret))
		return ret;

	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
	if (unlikely(!req->ns))
		return NVME_SC_INVALID_NS | NVME_SC_DNR;

	if (req->ns->file)
		return nvmet_file_parse_io_cmd(req);
	else
		return nvmet_bdev_parse_io_cmd(req);
}

bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
		struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops)
{
	u8 flags = req->cmd->common.flags;
	u16 status;

	req->cq = cq;
	req->sq = sq;
	req->ops = ops;
	req->sg = NULL;
	req->sg_cnt = 0;
	req->transfer_len = 0;
	req->rsp->status = 0;
	req->ns = NULL;

	/* no support for fused commands yet */
	if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
		goto fail;
	}

	/*
	 * For fabrics, PSDT field shall describe metadata pointer (MPTR) that
	 * contains an address of a single contiguous physical buffer that is
	 * byte aligned.
	 */
	if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) {
		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
		goto fail;
	}

	if (unlikely(!req->sq->ctrl))
		/* will return an error for any Non-connect command: */
		status = nvmet_parse_connect_cmd(req);
	else if (likely(req->sq->qid != 0))
		status = nvmet_parse_io_cmd(req);
	else if (req->cmd->common.opcode == nvme_fabrics_command)
		status = nvmet_parse_fabrics_cmd(req);
	else if (req->sq->ctrl->subsys->type == NVME_NQN_DISC)
		status = nvmet_parse_discovery_cmd(req);
	else
		status = nvmet_parse_admin_cmd(req);

	if (status)
		goto fail;

	if (unlikely(!percpu_ref_tryget_live(&sq->ref))) {
		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
		goto fail;
	}

	return true;

fail:
	__nvmet_req_complete(req, status);
	return false;
}
EXPORT_SYMBOL_GPL(nvmet_req_init);

void nvmet_req_uninit(struct nvmet_req *req)
{
	percpu_ref_put(&req->sq->ref);
	if (req->ns)
		nvmet_put_namespace(req->ns);
}
EXPORT_SYMBOL_GPL(nvmet_req_uninit);

void nvmet_req_execute(struct nvmet_req *req)
{
	if (unlikely(req->data_len != req->transfer_len))
		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
	else
		req->execute(req);
}
EXPORT_SYMBOL_GPL(nvmet_req_execute);

static inline bool nvmet_cc_en(u32 cc)
{
	return (cc >> NVME_CC_EN_SHIFT) & 0x1;
}

static inline u8 nvmet_cc_css(u32 cc)
{
	return (cc >> NVME_CC_CSS_SHIFT) & 0x7;
}

static inline u8 nvmet_cc_mps(u32 cc)
{
	return (cc >> NVME_CC_MPS_SHIFT) & 0xf;
}

static inline u8 nvmet_cc_ams(u32 cc)
{
	return (cc >> NVME_CC_AMS_SHIFT) & 0x7;
}

static inline u8 nvmet_cc_shn(u32 cc)
{
	return (cc >> NVME_CC_SHN_SHIFT) & 0x3;
}

static inline u8 nvmet_cc_iosqes(u32 cc)
{
	return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf;
}

static inline u8 nvmet_cc_iocqes(u32 cc)
{
	return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf;
}

static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
{
	lockdep_assert_held(&ctrl->lock);

	if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
	    nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES ||
	    nvmet_cc_mps(ctrl->cc) != 0 ||
	    nvmet_cc_ams(ctrl->cc) != 0 ||
	    nvmet_cc_css(ctrl->cc) != 0) {
		ctrl->csts = NVME_CSTS_CFS;
		return;
	}

	ctrl->csts = NVME_CSTS_RDY;

	/*
	 * Controllers that are not yet enabled should not really enforce the
	 * keep alive timeout, but we still want to track a timeout and cleanup
	 * in case a host died before it enabled the controller.  Hence, simply
	 * reset the keep alive timer when the controller is enabled.
	 */
	mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
}

static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)
{
	lockdep_assert_held(&ctrl->lock);

	/* XXX: tear down queues? */
	ctrl->csts &= ~NVME_CSTS_RDY;
	ctrl->cc = 0;
}

void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new)
{
	u32 old;

	mutex_lock(&ctrl->lock);
	old = ctrl->cc;
	ctrl->cc = new;

	if (nvmet_cc_en(new) && !nvmet_cc_en(old))
		nvmet_start_ctrl(ctrl);
	if (!nvmet_cc_en(new) && nvmet_cc_en(old))
		nvmet_clear_ctrl(ctrl);
	if (nvmet_cc_shn(new) && !nvmet_cc_shn(old)) {
		nvmet_clear_ctrl(ctrl);
		ctrl->csts |= NVME_CSTS_SHST_CMPLT;
	}
	if (!nvmet_cc_shn(new) && nvmet_cc_shn(old))
		ctrl->csts &= ~NVME_CSTS_SHST_CMPLT;
	mutex_unlock(&ctrl->lock);
}

static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
{
	/* command sets supported: NVMe command set: */
	ctrl->cap = (1ULL << 37);
	/* CC.EN timeout in 500msec units: */
	ctrl->cap |= (15ULL << 24);
	/* maximum queue entries supported: */
	ctrl->cap |= NVMET_QUEUE_SIZE - 1;
}

u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid,
		struct nvmet_req *req, struct nvmet_ctrl **ret)
{
	struct nvmet_subsys *subsys;
	struct nvmet_ctrl *ctrl;
	u16 status = 0;

	subsys = nvmet_find_get_subsys(req->port, subsysnqn);
	if (!subsys) {
		pr_warn("connect request for invalid subsystem %s!\n",
			subsysnqn);
		req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn);
		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
	}

	mutex_lock(&subsys->lock);
	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
		if (ctrl->cntlid == cntlid) {
			if (strncmp(hostnqn, ctrl->hostnqn, NVMF_NQN_SIZE)) {
				pr_warn("hostnqn mismatch.\n");
				continue;
			}
			if (!kref_get_unless_zero(&ctrl->ref))
				continue;

			*ret = ctrl;
			goto out;
		}
	}

	pr_warn("could not find controller %d for subsys %s / host %s\n",
		cntlid, subsysnqn, hostnqn);
	req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid);
	status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;

out:
	mutex_unlock(&subsys->lock);
	nvmet_subsys_put(subsys);
	return status;
}

u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd)
{
	if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
		pr_err("got cmd %d while CC.EN == 0 on qid = %d\n",
		       cmd->common.opcode, req->sq->qid);
		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
	}

	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
		pr_err("got cmd %d while CSTS.RDY == 0 on qid = %d\n",
		       cmd->common.opcode, req->sq->qid);
		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
	}
	return 0;
}

static bool __nvmet_host_allowed(struct nvmet_subsys *subsys,
		const char *hostnqn)
{
	struct nvmet_host_link *p;

	if (subsys->allow_any_host)
		return true;

	list_for_each_entry(p, &subsys->hosts, entry) {
		if (!strcmp(nvmet_host_name(p->host), hostnqn))
			return true;
	}

	return false;
}

static bool nvmet_host_discovery_allowed(struct nvmet_req *req,
		const char *hostnqn)
{
	struct nvmet_subsys_link *s;

	list_for_each_entry(s, &req->port->subsystems, entry) {
		if (__nvmet_host_allowed(s->subsys, hostnqn))
			return true;
	}

	return false;
}

bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
		const char *hostnqn)
{
	lockdep_assert_held(&nvmet_config_sem);

	if (subsys->type == NVME_NQN_DISC)
		return nvmet_host_discovery_allowed(req, hostnqn);
	else
		return __nvmet_host_allowed(subsys, hostnqn);
}

u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
		struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp)
{
	struct nvmet_subsys *subsys;
	struct nvmet_ctrl *ctrl;
	int ret;
	u16 status;

	status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
	subsys = nvmet_find_get_subsys(req->port, subsysnqn);
	if (!subsys) {
		pr_warn("connect request for invalid subsystem %s!\n",
			subsysnqn);
		req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn);
		goto out;
	}

	status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
	down_read(&nvmet_config_sem);
	if (!nvmet_host_allowed(req, subsys, hostnqn)) {
		pr_info("connect by host %s for subsystem %s not allowed\n",
			hostnqn, subsysnqn);
		req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn);
		up_read(&nvmet_config_sem);
		status = NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR;
		goto out_put_subsystem;
	}
	up_read(&nvmet_config_sem);

	status = NVME_SC_INTERNAL;
	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
	if (!ctrl)
		goto out_put_subsystem;
	mutex_init(&ctrl->lock);

	nvmet_init_cap(ctrl);

	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
	INIT_LIST_HEAD(&ctrl->async_events);

	memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
	memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);

	kref_init(&ctrl->ref);
	ctrl->subsys = subsys;
	WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);

	ctrl->changed_ns_list = kmalloc_array(NVME_MAX_CHANGED_NAMESPACES,
			sizeof(__le32), GFP_KERNEL);
	if (!ctrl->changed_ns_list)
		goto out_free_ctrl;

	ctrl->cqs = kcalloc(subsys->max_qid + 1,
			sizeof(struct nvmet_cq *),
			GFP_KERNEL);
	if (!ctrl->cqs)
		goto out_free_changed_ns_list;

	ctrl->sqs = kcalloc(subsys->max_qid + 1,
			sizeof(struct nvmet_sq *),
			GFP_KERNEL);
	if (!ctrl->sqs)
		goto out_free_cqs;

	ret = ida_simple_get(&cntlid_ida,
			     NVME_CNTLID_MIN, NVME_CNTLID_MAX,
			     GFP_KERNEL);
	if (ret < 0) {
		status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
		goto out_free_sqs;
	}
	ctrl->cntlid = ret;

	ctrl->ops = req->ops;
	if (ctrl->subsys->type == NVME_NQN_DISC) {
		/* Don't accept keep-alive timeout for discovery controllers */
		if (kato) {
			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
			goto out_remove_ida;
		}

		/*
		 * Discovery controllers use some arbitrary high value in order
		 * to cleanup stale discovery sessions
		 *
		 * From the latest base diff RC:
		 * "The Keep Alive command is not supported by
		 * Discovery controllers. A transport may specify a
		 * fixed Discovery controller activity timeout value
		 * (e.g., 2 minutes).  If no commands are received
		 * by a Discovery controller within that time
		 * period, the controller may perform the
		 * actions for Keep Alive Timer expiration".
		 */
		ctrl->kato = NVMET_DISC_KATO;
	} else {
		/* keep-alive timeout in seconds */
		ctrl->kato = DIV_ROUND_UP(kato, 1000);
	}
	nvmet_start_keep_alive_timer(ctrl);

	mutex_lock(&subsys->lock);
	list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
	mutex_unlock(&subsys->lock);

	*ctrlp = ctrl;
	return 0;

out_remove_ida:
	ida_simple_remove(&cntlid_ida, ctrl->cntlid);
out_free_sqs:
	kfree(ctrl->sqs);
out_free_cqs:
	kfree(ctrl->cqs);
out_free_changed_ns_list:
	kfree(ctrl->changed_ns_list);
out_free_ctrl:
	kfree(ctrl);
out_put_subsystem:
	nvmet_subsys_put(subsys);
out:
	return status;
}

static void nvmet_ctrl_free(struct kref *ref)
{
	struct nvmet_ctrl *ctrl = container_of(ref, struct nvmet_ctrl, ref);
	struct nvmet_subsys *subsys = ctrl->subsys;

	mutex_lock(&subsys->lock);
	list_del(&ctrl->subsys_entry);
	mutex_unlock(&subsys->lock);

	nvmet_stop_keep_alive_timer(ctrl);

	flush_work(&ctrl->async_event_work);
	cancel_work_sync(&ctrl->fatal_err_work);

	ida_simple_remove(&cntlid_ida, ctrl->cntlid);

	kfree(ctrl->sqs);
	kfree(ctrl->cqs);
	kfree(ctrl->changed_ns_list);
	kfree(ctrl);

	nvmet_subsys_put(subsys);
}

void nvmet_ctrl_put(struct nvmet_ctrl *ctrl)
{
	kref_put(&ctrl->ref, nvmet_ctrl_free);
}

static void nvmet_fatal_error_handler(struct work_struct *work)
{
	struct nvmet_ctrl *ctrl =
			container_of(work, struct nvmet_ctrl, fatal_err_work);

	pr_err("ctrl %d fatal error occurred!\n", ctrl->cntlid);
	ctrl->ops->delete_ctrl(ctrl);
}

void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl)
{
	mutex_lock(&ctrl->lock);
	if (!(ctrl->csts & NVME_CSTS_CFS)) {
		ctrl->csts |= NVME_CSTS_CFS;
		INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler);
		schedule_work(&ctrl->fatal_err_work);
	}
	mutex_unlock(&ctrl->lock);
}
EXPORT_SYMBOL_GPL(nvmet_ctrl_fatal_error);

static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
		const char *subsysnqn)
{
	struct nvmet_subsys_link *p;

	if (!port)
		return NULL;

	if (!strncmp(NVME_DISC_SUBSYS_NAME, subsysnqn,
			NVMF_NQN_SIZE)) {
		if (!kref_get_unless_zero(&nvmet_disc_subsys->ref))
			return NULL;
		return nvmet_disc_subsys;
	}

	down_read(&nvmet_config_sem);
	list_for_each_entry(p, &port->subsystems, entry) {
		if (!strncmp(p->subsys->subsysnqn, subsysnqn,
				NVMF_NQN_SIZE)) {
			if (!kref_get_unless_zero(&p->subsys->ref))
				break;
			up_read(&nvmet_config_sem);
			return p->subsys;
		}
	}
	up_read(&nvmet_config_sem);
	return NULL;
}

struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
		enum nvme_subsys_type type)
{
	struct nvmet_subsys *subsys;

	subsys = kzalloc(sizeof(*subsys), GFP_KERNEL);
	if (!subsys)
		return NULL;

	subsys->ver = NVME_VS(1, 3, 0); /* NVMe 1.3.0 */
	/* generate a random serial number as our controllers are ephemeral: */
	get_random_bytes(&subsys->serial, sizeof(subsys->serial));

	switch (type) {
	case NVME_NQN_NVME:
		subsys->max_qid = NVMET_NR_QUEUES;
		break;
	case NVME_NQN_DISC:
		subsys->max_qid = 0;
		break;
	default:
		pr_err("%s: Unknown Subsystem type - %d\n", __func__, type);
		kfree(subsys);
		return NULL;
	}
	subsys->type = type;
	subsys->subsysnqn = kstrndup(subsysnqn, NVMF_NQN_SIZE,
			GFP_KERNEL);
	if (!subsys->subsysnqn) {
		kfree(subsys);
		return NULL;
	}

	kref_init(&subsys->ref);

	mutex_init(&subsys->lock);
	INIT_LIST_HEAD(&subsys->namespaces);
	INIT_LIST_HEAD(&subsys->ctrls);
	INIT_LIST_HEAD(&subsys->hosts);

	return subsys;
}

static void nvmet_subsys_free(struct kref *ref)
{
	struct nvmet_subsys *subsys =
		container_of(ref, struct nvmet_subsys, ref);

	WARN_ON_ONCE(!list_empty(&subsys->namespaces));

	kfree(subsys->subsysnqn);
	kfree(subsys);
}

void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys)
{
	struct nvmet_ctrl *ctrl;

	mutex_lock(&subsys->lock);
	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
		ctrl->ops->delete_ctrl(ctrl);
	mutex_unlock(&subsys->lock);
}

void nvmet_subsys_put(struct nvmet_subsys *subsys)
{
	kref_put(&subsys->ref, nvmet_subsys_free);
}

static int __init nvmet_init(void)
{
	int error;

	error = nvmet_init_discovery();
	if (error)
		goto out;

	error = nvmet_init_configfs();
	if (error)
		goto out_exit_discovery;
	return 0;

out_exit_discovery:
	nvmet_exit_discovery();
out:
	return error;
}

static void __exit nvmet_exit(void)
{
	nvmet_exit_configfs();
	nvmet_exit_discovery();
	ida_destroy(&cntlid_ida);

	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);
}

module_init(nvmet_init);
module_exit(nvmet_exit);

MODULE_LICENSE("GPL v2");