aboutsummaryrefslogtreecommitdiff
path: root/drivers/nvme/target/admin-cmd.c
blob: fe6b8aa90b534cf9dd4bf0cc6be41e128563df6d (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
// SPDX-License-Identifier: GPL-2.0
/*
 * NVMe admin command implementation.
 * Copyright (c) 2015-2016 HGST, a Western Digital Company.
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/rculist.h>
#include <linux/part_stat.h>

#include <generated/utsrelease.h>
#include <asm/unaligned.h>
#include "nvmet.h"

u32 nvmet_get_log_page_len(struct nvme_command *cmd)
{
	u32 len = le16_to_cpu(cmd->get_log_page.numdu);

	len <<= 16;
	len += le16_to_cpu(cmd->get_log_page.numdl);
	/* NUMD is a 0's based value */
	len += 1;
	len *= sizeof(u32);

	return len;
}

static u32 nvmet_feat_data_len(struct nvmet_req *req, u32 cdw10)
{
	switch (cdw10 & 0xff) {
	case NVME_FEAT_HOST_ID:
		return sizeof(req->sq->ctrl->hostid);
	default:
		return 0;
	}
}

u64 nvmet_get_log_page_offset(struct nvme_command *cmd)
{
	return le64_to_cpu(cmd->get_log_page.lpo);
}

static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
{
	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->transfer_len));
}

static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
{
	struct nvmet_ctrl *ctrl = req->sq->ctrl;
	unsigned long flags;
	off_t offset = 0;
	u64 slot;
	u64 i;

	spin_lock_irqsave(&ctrl->error_lock, flags);
	slot = ctrl->err_counter % NVMET_ERROR_LOG_SLOTS;

	for (i = 0; i < NVMET_ERROR_LOG_SLOTS; i++) {
		if (nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot],
				sizeof(struct nvme_error_slot)))
			break;

		if (slot == 0)
			slot = NVMET_ERROR_LOG_SLOTS - 1;
		else
			slot--;
		offset += sizeof(struct nvme_error_slot);
	}
	spin_unlock_irqrestore(&ctrl->error_lock, flags);
	nvmet_req_complete(req, 0);
}

static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
		struct nvme_smart_log *slog)
{
	u64 host_reads, host_writes, data_units_read, data_units_written;
	u16 status;

	status = nvmet_req_find_ns(req);
	if (status)
		return status;

	/* we don't have the right data for file backed ns */
	if (!req->ns->bdev)
		return NVME_SC_SUCCESS;

	host_reads = part_stat_read(req->ns->bdev, ios[READ]);
	data_units_read =
		DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[READ]), 1000);
	host_writes = part_stat_read(req->ns->bdev, ios[WRITE]);
	data_units_written =
		DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[WRITE]), 1000);

	put_unaligned_le64(host_reads, &slog->host_reads[0]);
	put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
	put_unaligned_le64(host_writes, &slog->host_writes[0]);
	put_unaligned_le64(data_units_written, &slog->data_units_written[0]);

	return NVME_SC_SUCCESS;
}

static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
		struct nvme_smart_log *slog)
{
	u64 host_reads = 0, host_writes = 0;
	u64 data_units_read = 0, data_units_written = 0;
	struct nvmet_ns *ns;
	struct nvmet_ctrl *ctrl;
	unsigned long idx;

	ctrl = req->sq->ctrl;
	xa_for_each(&ctrl->subsys->namespaces, idx, ns) {
		/* we don't have the right data for file backed ns */
		if (!ns->bdev)
			continue;
		host_reads += part_stat_read(ns->bdev, ios[READ]);
		data_units_read += DIV_ROUND_UP(
			part_stat_read(ns->bdev, sectors[READ]), 1000);
		host_writes += part_stat_read(ns->bdev, ios[WRITE]);
		data_units_written += DIV_ROUND_UP(
			part_stat_read(ns->bdev, sectors[WRITE]), 1000);
	}

	put_unaligned_le64(host_reads, &slog->host_reads[0]);
	put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
	put_unaligned_le64(host_writes, &slog->host_writes[0]);
	put_unaligned_le64(data_units_written, &slog->data_units_written[0]);

	return NVME_SC_SUCCESS;
}

static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
{
	struct nvme_smart_log *log;
	u16 status = NVME_SC_INTERNAL;
	unsigned long flags;

	if (req->transfer_len != sizeof(*log))
		goto out;

	log = kzalloc(sizeof(*log), GFP_KERNEL);
	if (!log)
		goto out;

	if (req->cmd->get_log_page.nsid == cpu_to_le32(NVME_NSID_ALL))
		status = nvmet_get_smart_log_all(req, log);
	else
		status = nvmet_get_smart_log_nsid(req, log);
	if (status)
		goto out_free_log;

	spin_lock_irqsave(&req->sq->ctrl->error_lock, flags);
	put_unaligned_le64(req->sq->ctrl->err_counter,
			&log->num_err_log_entries);
	spin_unlock_irqrestore(&req->sq->ctrl->error_lock, flags);

	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
out_free_log:
	kfree(log);
out:
	nvmet_req_complete(req, status);
}

static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
{
	u16 status = NVME_SC_INTERNAL;
	struct nvme_effects_log *log;

	log = kzalloc(sizeof(*log), GFP_KERNEL);
	if (!log)
		goto out;

	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);

	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);

	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));

	kfree(log);
out:
	nvmet_req_complete(req, status);
}

static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
{
	struct nvmet_ctrl *ctrl = req->sq->ctrl;
	u16 status = NVME_SC_INTERNAL;
	size_t len;

	if (req->transfer_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32))
		goto out;

	mutex_lock(&ctrl->lock);
	if (ctrl->nr_changed_ns == U32_MAX)
		len = sizeof(__le32);
	else
		len = ctrl->nr_changed_ns * sizeof(__le32);
	status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len);
	if (!status)
		status = nvmet_zero_sgl(req, len, req->transfer_len - len);
	ctrl->nr_changed_ns = 0;
	nvmet_clear_aen_bit(req, NVME_AEN_BIT_NS_ATTR);
	mutex_unlock(&ctrl->lock);
out:
	nvmet_req_complete(req, status);
}

static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
		struct nvme_ana_group_desc *desc)
{
	struct nvmet_ctrl *ctrl = req->sq->ctrl;
	struct nvmet_ns *ns;
	unsigned long idx;
	u32 count = 0;

	if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
		xa_for_each(&ctrl->subsys->namespaces, idx, ns)
			if (ns->anagrpid == grpid)
				desc->nsids[count++] = cpu_to_le32(ns->nsid);
	}

	desc->grpid = cpu_to_le32(grpid);
	desc->nnsids = cpu_to_le32(count);
	desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
	desc->state = req->port->ana_state[grpid];
	memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
	return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
}

static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
{
	struct nvme_ana_rsp_hdr hdr = { 0, };
	struct nvme_ana_group_desc *desc;
	size_t offset = sizeof(struct nvme_ana_rsp_hdr); /* start beyond hdr */
	size_t len;
	u32 grpid;
	u16 ngrps = 0;
	u16 status;

	status = NVME_SC_INTERNAL;
	desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
			NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
	if (!desc)
		goto out;

	down_read(&nvmet_ana_sem);
	for (grpid = 1; grpid <= NVMET_MAX_ANAGRPS; grpid++) {
		if (!nvmet_ana_group_enabled[grpid])
			continue;
		len = nvmet_format_ana_group(req, grpid, desc);
		status = nvmet_copy_to_sgl(req, offset, desc, len);
		if (status)
			break;
		offset += len;
		ngrps++;
	}
	for ( ; grpid <= NVMET_MAX_ANAGRPS; grpid++) {
		if (nvmet_ana_group_enabled[grpid])
			ngrps++;
	}

	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
	hdr.ngrps = cpu_to_le16(ngrps);
	nvmet_clear_aen_bit(req, NVME_AEN_BIT_ANA_CHANGE);
	up_read(&nvmet_ana_sem);

	kfree(desc);

	/* copy the header last once we know the number of groups */
	status = nvmet_copy_to_sgl(req, 0, &hdr, sizeof(hdr));
out:
	nvmet_req_complete(req, status);
}

static void nvmet_execute_get_log_page(struct nvmet_req *req)
{
	if (!nvmet_check_transfer_len(req, nvmet_get_log_page_len(req->cmd)))
		return;

	switch (req->cmd->get_log_page.lid) {
	case NVME_LOG_ERROR:
		return nvmet_execute_get_log_page_error(req);
	case NVME_LOG_SMART:
		return nvmet_execute_get_log_page_smart(req);
	case NVME_LOG_FW_SLOT:
		/*
		 * We only support a single firmware slot which always is
		 * active, so we can zero out the whole firmware slot log and
		 * still claim to fully implement this mandatory log page.
		 */
		return nvmet_execute_get_log_page_noop(req);
	case NVME_LOG_CHANGED_NS:
		return nvmet_execute_get_log_changed_ns(req);
	case NVME_LOG_CMD_EFFECTS:
		return nvmet_execute_get_log_cmd_effects_ns(req);
	case NVME_LOG_ANA:
		return nvmet_execute_get_log_page_ana(req);
	}
	pr_err("unhandled lid %d on qid %d\n",
	       req->cmd->get_log_page.lid, req->sq->qid);
	req->error_loc = offsetof(struct nvme_get_log_page_command, lid);
	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
}

static u16 nvmet_set_model_number(struct nvmet_subsys *subsys)
{
	u16 status = 0;

	mutex_lock(&subsys->lock);
	if (!subsys->model_number) {
		subsys->model_number =
			kstrdup(NVMET_DEFAULT_CTRL_MODEL, GFP_KERNEL);
		if (!subsys->model_number)
			status = NVME_SC_INTERNAL;
	}
	mutex_unlock(&subsys->lock);

	return status;
}

static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
{
	struct nvmet_ctrl *ctrl = req->sq->ctrl;
	struct nvmet_subsys *subsys = ctrl->subsys;
	struct nvme_id_ctrl *id;
	u32 cmd_capsule_size;
	u16 status = 0;

	/*
	 * If there is no model number yet, set it now.  It will then remain
	 * stable for the life time of the subsystem.
	 */
	if (!subsys->model_number) {
		status = nvmet_set_model_number(subsys);
		if (status)
			goto out;
	}

	id = kzalloc(sizeof(*id), GFP_KERNEL);
	if (!id) {
		status = NVME_SC_INTERNAL;
		goto out;
	}

	/* XXX: figure out how to assign real vendors IDs. */
	id->vid = 0;
	id->ssvid = 0;

	memset(id->sn, ' ', sizeof(id->sn));
	bin2hex(id->sn, &ctrl->subsys->serial,
		min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
	memcpy_and_pad(id->mn, sizeof(id->mn), subsys->model_number,
		       strlen(subsys->model_number), ' ');
	memcpy_and_pad(id->fr, sizeof(id->fr),
		       UTS_RELEASE, strlen(UTS_RELEASE), ' ');

	id->rab = 6;

	/*
	 * XXX: figure out how we can assign a IEEE OUI, but until then
	 * the safest is to leave it as zeroes.
	 */

	/* we support multiple ports, multiples hosts and ANA: */
	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);

	/* Limit MDTS according to transport capability */
	if (ctrl->ops->get_mdts)
		id->mdts = ctrl->ops->get_mdts(ctrl);
	else
		id->mdts = 0;

	id->cntlid = cpu_to_le16(ctrl->cntlid);
	id->ver = cpu_to_le32(ctrl->subsys->ver);

	/* XXX: figure out what to do about RTD3R/RTD3 */
	id->oaes = cpu_to_le32(NVMET_AEN_CFG_OPTIONAL);
	id->ctratt = cpu_to_le32(NVME_CTRL_ATTR_HID_128_BIT |
		NVME_CTRL_ATTR_TBKAS);

	id->oacs = 0;

	/*
	 * We don't really have a practical limit on the number of abort
	 * comands.  But we don't do anything useful for abort either, so
	 * no point in allowing more abort commands than the spec requires.
	 */
	id->acl = 3;

	id->aerl = NVMET_ASYNC_EVENTS - 1;

	/* first slot is read-only, only one slot supported */
	id->frmw = (1 << 0) | (1 << 1);
	id->lpa = (1 << 0) | (1 << 1) | (1 << 2);
	id->elpe = NVMET_ERROR_LOG_SLOTS - 1;
	id->npss = 0;

	/* We support keep-alive timeout in granularity of seconds */
	id->kas = cpu_to_le16(NVMET_KAS);

	id->sqes = (0x6 << 4) | 0x6;
	id->cqes = (0x4 << 4) | 0x4;

	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);

	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
			NVME_CTRL_ONCS_WRITE_ZEROES);

	/* XXX: don't report vwc if the underlying device is write through */
	id->vwc = NVME_CTRL_VWC_PRESENT;

	/*
	 * We can't support atomic writes bigger than a LBA without support
	 * from the backend device.
	 */
	id->awun = 0;
	id->awupf = 0;

	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
	if (ctrl->ops->flags & NVMF_KEYED_SGLS)
		id->sgls |= cpu_to_le32(1 << 2);
	if (req->port->inline_data_size)
		id->sgls |= cpu_to_le32(1 << 20);

	strlcpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn));

	/*
	 * Max command capsule size is sqe + in-capsule data size.
	 * Disable in-capsule data for Metadata capable controllers.
	 */
	cmd_capsule_size = sizeof(struct nvme_command);
	if (!ctrl->pi_support)
		cmd_capsule_size += req->port->inline_data_size;
	id->ioccsz = cpu_to_le32(cmd_capsule_size / 16);

	/* Max response capsule size is cqe */
	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);

	id->msdbd = ctrl->ops->msdbd;

	id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4);
	id->anatt = 10; /* random value */
	id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS);
	id->nanagrpid = cpu_to_le32(NVMET_MAX_ANAGRPS);

	/*
	 * Meh, we don't really support any power state.  Fake up the same
	 * values that qemu does.
	 */
	id->psd[0].max_power = cpu_to_le16(0x9c4);
	id->psd[0].entry_lat = cpu_to_le32(0x10);
	id->psd[0].exit_lat = cpu_to_le32(0x4);

	id->nwpc = 1 << 0; /* write protect and no write protect */

	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));

	kfree(id);
out:
	nvmet_req_complete(req, status);
}

static void nvmet_execute_identify_ns(struct nvmet_req *req)
{
	struct nvme_id_ns *id;
	u16 status;

	if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
		req->error_loc = offsetof(struct nvme_identify, nsid);
		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
		goto out;
	}

	id = kzalloc(sizeof(*id), GFP_KERNEL);
	if (!id) {
		status = NVME_SC_INTERNAL;
		goto out;
	}

	/* return an all zeroed buffer if we can't find an active namespace */
	status = nvmet_req_find_ns(req);
	if (status) {
		status = 0;
		goto done;
	}

	nvmet_ns_revalidate(req->ns);

	/*
	 * nuse = ncap = nsze isn't always true, but we have no way to find
	 * that out from the underlying device.
	 */
	id->ncap = id->nsze =
		cpu_to_le64(req->ns->size >> req->ns->blksize_shift);
	switch (req->port->ana_state[req->ns->anagrpid]) {
	case NVME_ANA_INACCESSIBLE:
	case NVME_ANA_PERSISTENT_LOSS:
		break;
	default:
		id->nuse = id->nsze;
		break;
        }

	if (req->ns->bdev)
		nvmet_bdev_set_limits(req->ns->bdev, id);

	/*
	 * We just provide a single LBA format that matches what the
	 * underlying device reports.
	 */
	id->nlbaf = 0;
	id->flbas = 0;

	/*
	 * Our namespace might always be shared.  Not just with other
	 * controllers, but also with any other user of the block device.
	 */
	id->nmic = (1 << 0);
	id->anagrpid = cpu_to_le32(req->ns->anagrpid);

	memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid));

	id->lbaf[0].ds = req->ns->blksize_shift;

	if (req->sq->ctrl->pi_support && nvmet_ns_has_pi(req->ns)) {
		id->dpc = NVME_NS_DPC_PI_FIRST | NVME_NS_DPC_PI_LAST |
			  NVME_NS_DPC_PI_TYPE1 | NVME_NS_DPC_PI_TYPE2 |
			  NVME_NS_DPC_PI_TYPE3;
		id->mc = NVME_MC_EXTENDED_LBA;
		id->dps = req->ns->pi_type;
		id->flbas = NVME_NS_FLBAS_META_EXT;
		id->lbaf[0].ms = cpu_to_le16(req->ns->metadata_size);
	}

	if (req->ns->readonly)
		id->nsattr |= (1 << 0);
done:
	if (!status)
		status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));

	kfree(id);
out:
	nvmet_req_complete(req, status);
}

static void nvmet_execute_identify_nslist(struct nvmet_req *req)
{
	static const int buf_size = NVME_IDENTIFY_DATA_SIZE;
	struct nvmet_ctrl *ctrl = req->sq->ctrl;
	struct nvmet_ns *ns;
	unsigned long idx;
	u32 min_nsid = le32_to_cpu(req->cmd->identify.nsid);
	__le32 *list;
	u16 status = 0;
	int i = 0;

	list = kzalloc(buf_size, GFP_KERNEL);
	if (!list) {
		status = NVME_SC_INTERNAL;
		goto out;
	}

	xa_for_each(&ctrl->subsys->namespaces, idx, ns) {
		if (ns->nsid <= min_nsid)
			continue;
		list[i++] = cpu_to_le32(ns->nsid);
		if (i == buf_size / sizeof(__le32))
			break;
	}

	status = nvmet_copy_to_sgl(req, 0, list, buf_size);

	kfree(list);
out:
	nvmet_req_complete(req, status);
}

static u16 nvmet_copy_ns_identifier(struct nvmet_req *req, u8 type, u8 len,
				    void *id, off_t *off)
{
	struct nvme_ns_id_desc desc = {
		.nidt = type,
		.nidl = len,
	};
	u16 status;

	status = nvmet_copy_to_sgl(req, *off, &desc, sizeof(desc));
	if (status)
		return status;
	*off += sizeof(desc);

	status = nvmet_copy_to_sgl(req, *off, id, len);
	if (status)
		return status;
	*off += len;

	return 0;
}

static void nvmet_execute_identify_desclist(struct nvmet_req *req)
{
	off_t off = 0;
	u16 status;

	status = nvmet_req_find_ns(req);
	if (status)
		goto out;

	if (memchr_inv(&req->ns->uuid, 0, sizeof(req->ns->uuid))) {
		status = nvmet_copy_ns_identifier(req, NVME_NIDT_UUID,
						  NVME_NIDT_UUID_LEN,
						  &req->ns->uuid, &off);
		if (status)
			goto out;
	}
	if (memchr_inv(req->ns->nguid, 0, sizeof(req->ns->nguid))) {
		status = nvmet_copy_ns_identifier(req, NVME_NIDT_NGUID,
						  NVME_NIDT_NGUID_LEN,
						  &req->ns->nguid, &off);
		if (status)
			goto out;
	}

	if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off,
			off) != NVME_IDENTIFY_DATA_SIZE - off)
		status = NVME_SC_INTERNAL | NVME_SC_DNR;

out:
	nvmet_req_complete(req, status);
}

static void nvmet_execute_identify(struct nvmet_req *req)
{
	if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE))
		return;

	switch (req->cmd->identify.cns) {
	case NVME_ID_CNS_NS:
		return nvmet_execute_identify_ns(req);
	case NVME_ID_CNS_CTRL:
		return nvmet_execute_identify_ctrl(req);
	case NVME_ID_CNS_NS_ACTIVE_LIST:
		return nvmet_execute_identify_nslist(req);
	case NVME_ID_CNS_NS_DESC_LIST:
		return nvmet_execute_identify_desclist(req);
	}

	pr_err("unhandled identify cns %d on qid %d\n",
	       req->cmd->identify.cns, req->sq->qid);
	req->error_loc = offsetof(struct nvme_identify, cns);
	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
}

/*
 * A "minimum viable" abort implementation: the command is mandatory in the
 * spec, but we are not required to do any useful work.  We couldn't really
 * do a useful abort, so don't bother even with waiting for the command
 * to be exectuted and return immediately telling the command to abort
 * wasn't found.
 */
static void nvmet_execute_abort(struct nvmet_req *req)
{
	if (!nvmet_check_transfer_len(req, 0))
		return;
	nvmet_set_result(req, 1);
	nvmet_req_complete(req, 0);
}

static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req)
{
	u16 status;

	if (req->ns->file)
		status = nvmet_file_flush(req);
	else
		status = nvmet_bdev_flush(req);

	if (status)
		pr_err("write protect flush failed nsid: %u\n", req->ns->nsid);
	return status;
}

static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
{
	u32 write_protect = le32_to_cpu(req->cmd->common.cdw11);
	struct nvmet_subsys *subsys = nvmet_req_subsys(req);
	u16 status;

	status = nvmet_req_find_ns(req);
	if (status)
		return status;

	mutex_lock(&subsys->lock);
	switch (write_protect) {
	case NVME_NS_WRITE_PROTECT:
		req->ns->readonly = true;
		status = nvmet_write_protect_flush_sync(req);
		if (status)
			req->ns->readonly = false;
		break;
	case NVME_NS_NO_WRITE_PROTECT:
		req->ns->readonly = false;
		status = 0;
		break;
	default:
		break;
	}

	if (!status)
		nvmet_ns_changed(subsys, req->ns->nsid);
	mutex_unlock(&subsys->lock);
	return status;
}

u16 nvmet_set_feat_kato(struct nvmet_req *req)
{
	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);

	nvmet_stop_keep_alive_timer(req->sq->ctrl);
	req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
	nvmet_start_keep_alive_timer(req->sq->ctrl);

	nvmet_set_result(req, req->sq->ctrl->kato);

	return 0;
}

u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
{
	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);

	if (val32 & ~mask) {
		req->error_loc = offsetof(struct nvme_common_command, cdw11);
		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
	}

	WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
	nvmet_set_result(req, val32);

	return 0;
}

void nvmet_execute_set_features(struct nvmet_req *req)
{
	struct nvmet_subsys *subsys = nvmet_req_subsys(req);
	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
	u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
	u16 status = 0;
	u16 nsqr;
	u16 ncqr;

	if (!nvmet_check_transfer_len(req, 0))
		return;

	switch (cdw10 & 0xff) {
	case NVME_FEAT_NUM_QUEUES:
		ncqr = (cdw11 >> 16) & 0xffff;
		nsqr = cdw11 & 0xffff;
		if (ncqr == 0xffff || nsqr == 0xffff) {
			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
			break;
		}
		nvmet_set_result(req,
			(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
		break;
	case NVME_FEAT_KATO:
		status = nvmet_set_feat_kato(req);
		break;
	case NVME_FEAT_ASYNC_EVENT:
		status = nvmet_set_feat_async_event(req, NVMET_AEN_CFG_ALL);
		break;
	case NVME_FEAT_HOST_ID:
		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
		break;
	case NVME_FEAT_WRITE_PROTECT:
		status = nvmet_set_feat_write_protect(req);
		break;
	default:
		req->error_loc = offsetof(struct nvme_common_command, cdw10);
		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
		break;
	}

	nvmet_req_complete(req, status);
}

static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
{
	struct nvmet_subsys *subsys = nvmet_req_subsys(req);
	u32 result;

	result = nvmet_req_find_ns(req);
	if (result)
		return result;

	mutex_lock(&subsys->lock);
	if (req->ns->readonly == true)
		result = NVME_NS_WRITE_PROTECT;
	else
		result = NVME_NS_NO_WRITE_PROTECT;
	nvmet_set_result(req, result);
	mutex_unlock(&subsys->lock);

	return 0;
}

void nvmet_get_feat_kato(struct nvmet_req *req)
{
	nvmet_set_result(req, req->sq->ctrl->kato * 1000);
}

void nvmet_get_feat_async_event(struct nvmet_req *req)
{
	nvmet_set_result(req, READ_ONCE(req->sq->ctrl->aen_enabled));
}

void nvmet_execute_get_features(struct nvmet_req *req)
{
	struct nvmet_subsys *subsys = nvmet_req_subsys(req);
	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
	u16 status = 0;

	if (!nvmet_check_transfer_len(req, nvmet_feat_data_len(req, cdw10)))
		return;

	switch (cdw10 & 0xff) {
	/*
	 * These features are mandatory in the spec, but we don't
	 * have a useful way to implement them.  We'll eventually
	 * need to come up with some fake values for these.
	 */
#if 0
	case NVME_FEAT_ARBITRATION:
		break;
	case NVME_FEAT_POWER_MGMT:
		break;
	case NVME_FEAT_TEMP_THRESH:
		break;
	case NVME_FEAT_ERR_RECOVERY:
		break;
	case NVME_FEAT_IRQ_COALESCE:
		break;
	case NVME_FEAT_IRQ_CONFIG:
		break;
	case NVME_FEAT_WRITE_ATOMIC:
		break;
#endif
	case NVME_FEAT_ASYNC_EVENT:
		nvmet_get_feat_async_event(req);
		break;
	case NVME_FEAT_VOLATILE_WC:
		nvmet_set_result(req, 1);
		break;
	case NVME_FEAT_NUM_QUEUES:
		nvmet_set_result(req,
			(subsys->max_qid-1) | ((subsys->max_qid-1) << 16));
		break;
	case NVME_FEAT_KATO:
		nvmet_get_feat_kato(req);
		break;
	case NVME_FEAT_HOST_ID:
		/* need 128-bit host identifier flag */
		if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) {
			req->error_loc =
				offsetof(struct nvme_common_command, cdw11);
			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
			break;
		}

		status = nvmet_copy_to_sgl(req, 0, &req->sq->ctrl->hostid,
				sizeof(req->sq->ctrl->hostid));
		break;
	case NVME_FEAT_WRITE_PROTECT:
		status = nvmet_get_feat_write_protect(req);
		break;
	default:
		req->error_loc =
			offsetof(struct nvme_common_command, cdw10);
		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
		break;
	}

	nvmet_req_complete(req, status);
}

void nvmet_execute_async_event(struct nvmet_req *req)
{
	struct nvmet_ctrl *ctrl = req->sq->ctrl;

	if (!nvmet_check_transfer_len(req, 0))
		return;

	mutex_lock(&ctrl->lock);
	if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) {
		mutex_unlock(&ctrl->lock);
		nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_SC_DNR);
		return;
	}
	ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
	mutex_unlock(&ctrl->lock);

	schedule_work(&ctrl->async_event_work);
}

void nvmet_execute_keep_alive(struct nvmet_req *req)
{
	struct nvmet_ctrl *ctrl = req->sq->ctrl;

	if (!nvmet_check_transfer_len(req, 0))
		return;

	pr_debug("ctrl %d update keep-alive timer for %d secs\n",
		ctrl->cntlid, ctrl->kato);

	mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
	nvmet_req_complete(req, 0);
}

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

	if (nvme_is_fabrics(cmd))
		return nvmet_parse_fabrics_cmd(req);
	if (nvmet_req_subsys(req)->type == NVME_NQN_DISC)
		return nvmet_parse_discovery_cmd(req);

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

	if (nvmet_req_passthru_ctrl(req))
		return nvmet_parse_passthru_admin_cmd(req);

	switch (cmd->common.opcode) {
	case nvme_admin_get_log_page:
		req->execute = nvmet_execute_get_log_page;
		return 0;
	case nvme_admin_identify:
		req->execute = nvmet_execute_identify;
		return 0;
	case nvme_admin_abort_cmd:
		req->execute = nvmet_execute_abort;
		return 0;
	case nvme_admin_set_features:
		req->execute = nvmet_execute_set_features;
		return 0;
	case nvme_admin_get_features:
		req->execute = nvmet_execute_get_features;
		return 0;
	case nvme_admin_async_event:
		req->execute = nvmet_execute_async_event;
		return 0;
	case nvme_admin_keep_alive:
		req->execute = nvmet_execute_keep_alive;
		return 0;
	}

	pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
	       req->sq->qid);
	req->error_loc = offsetof(struct nvme_common_command, opcode);
	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}