summaryrefslogtreecommitdiff
path: root/drivers/nvme/host/ioctl.c
blob: 4939ed35638f16a8efdd61e394100ba53c6864c4 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2011-2014, Intel Corporation.
 * Copyright (c) 2017-2021 Christoph Hellwig.
 */
#include <linux/ptrace.h>	/* for force_successful_syscall_return */
#include <linux/nvme_ioctl.h>
#include <linux/io_uring.h>
#include "nvme.h"

enum {
	NVME_IOCTL_VEC		= (1 << 0),
	NVME_IOCTL_PARTITION	= (1 << 1),
};

static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
		unsigned int flags, bool open_for_write)
{
	u32 effects;

	/*
	 * Do not allow unprivileged passthrough on partitions, as that allows an
	 * escape from the containment of the partition.
	 */
	if (flags & NVME_IOCTL_PARTITION)
		goto admin;

	/*
	 * Do not allow unprivileged processes to send vendor specific or fabrics
	 * commands as we can't be sure about their effects.
	 */
	if (c->common.opcode >= nvme_cmd_vendor_start ||
	    c->common.opcode == nvme_fabrics_command)
		goto admin;

	/*
	 * Do not allow unprivileged passthrough of admin commands except
	 * for a subset of identify commands that contain information required
	 * to form proper I/O commands in userspace and do not expose any
	 * potentially sensitive information.
	 */
	if (!ns) {
		if (c->common.opcode == nvme_admin_identify) {
			switch (c->identify.cns) {
			case NVME_ID_CNS_NS:
			case NVME_ID_CNS_CS_NS:
			case NVME_ID_CNS_NS_CS_INDEP:
			case NVME_ID_CNS_CS_CTRL:
			case NVME_ID_CNS_CTRL:
				return true;
			}
		}
		goto admin;
	}

	/*
	 * Check if the controller provides a Commands Supported and Effects log
	 * and marks this command as supported.  If not reject unprivileged
	 * passthrough.
	 */
	effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
	if (!(effects & NVME_CMD_EFFECTS_CSUPP))
		goto admin;

	/*
	 * Don't allow passthrough for command that have intrusive (or unknown)
	 * effects.
	 */
	if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
			NVME_CMD_EFFECTS_UUID_SEL |
			NVME_CMD_EFFECTS_SCOPE_MASK))
		goto admin;

	/*
	 * Only allow I/O commands that transfer data to the controller or that
	 * change the logical block contents if the file descriptor is open for
	 * writing.
	 */
	if ((nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) &&
	    !open_for_write)
		goto admin;

	return true;
admin:
	return capable(CAP_SYS_ADMIN);
}

/*
 * Convert integer values from ioctl structures to user pointers, silently
 * ignoring the upper bits in the compat case to match behaviour of 32-bit
 * kernels.
 */
static void __user *nvme_to_user_ptr(uintptr_t ptrval)
{
	if (in_compat_syscall())
		ptrval = (compat_uptr_t)ptrval;
	return (void __user *)ptrval;
}

static void *nvme_add_user_metadata(struct request *req, void __user *ubuf,
		unsigned len, u32 seed)
{
	struct bio_integrity_payload *bip;
	int ret = -ENOMEM;
	void *buf;
	struct bio *bio = req->bio;

	buf = kmalloc(len, GFP_KERNEL);
	if (!buf)
		goto out;

	if (req_op(req) == REQ_OP_DRV_OUT) {
		ret = -EFAULT;
		if (copy_from_user(buf, ubuf, len))
			goto out_free_meta;
	} else {
		memset(buf, 0, len);
	}

	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
	if (IS_ERR(bip)) {
		ret = PTR_ERR(bip);
		goto out_free_meta;
	}

	bip->bip_iter.bi_sector = seed;
	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
			offset_in_page(buf));
	if (ret != len) {
		ret = -ENOMEM;
		goto out_free_meta;
	}

	req->cmd_flags |= REQ_INTEGRITY;
	return buf;
out_free_meta:
	kfree(buf);
out:
	return ERR_PTR(ret);
}

static int nvme_finish_user_metadata(struct request *req, void __user *ubuf,
		void *meta, unsigned len, int ret)
{
	if (!ret && req_op(req) == REQ_OP_DRV_IN &&
	    copy_to_user(ubuf, meta, len))
		ret = -EFAULT;
	kfree(meta);
	return ret;
}

static struct request *nvme_alloc_user_request(struct request_queue *q,
		struct nvme_command *cmd, blk_opf_t rq_flags,
		blk_mq_req_flags_t blk_flags)
{
	struct request *req;

	req = blk_mq_alloc_request(q, nvme_req_op(cmd) | rq_flags, blk_flags);
	if (IS_ERR(req))
		return req;
	nvme_init_request(req, cmd);
	nvme_req(req)->flags |= NVME_REQ_USERCMD;
	return req;
}

static int nvme_map_user_request(struct request *req, u64 ubuffer,
		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
		u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
		unsigned int flags)
{
	struct request_queue *q = req->q;
	struct nvme_ns *ns = q->queuedata;
	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
	struct bio *bio = NULL;
	void *meta = NULL;
	int ret;

	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
		struct iov_iter iter;

		/* fixedbufs is only for non-vectored io */
		if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
			return -EINVAL;
		ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
				rq_data_dir(req), &iter, ioucmd);
		if (ret < 0)
			goto out;
		ret = blk_rq_map_user_iov(q, req, NULL, &iter, GFP_KERNEL);
	} else {
		ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer),
				bufflen, GFP_KERNEL, flags & NVME_IOCTL_VEC, 0,
				0, rq_data_dir(req));
	}

	if (ret)
		goto out;
	bio = req->bio;
	if (bdev)
		bio_set_dev(bio, bdev);

	if (bdev && meta_buffer && meta_len) {
		meta = nvme_add_user_metadata(req, meta_buffer, meta_len,
				meta_seed);
		if (IS_ERR(meta)) {
			ret = PTR_ERR(meta);
			goto out_unmap;
		}
		*metap = meta;
	}

	return ret;

out_unmap:
	if (bio)
		blk_rq_unmap_user(bio);
out:
	blk_mq_free_request(req);
	return ret;
}

static int nvme_submit_user_cmd(struct request_queue *q,
		struct nvme_command *cmd, u64 ubuffer, unsigned bufflen,
		void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
		u64 *result, unsigned timeout, unsigned int flags)
{
	struct nvme_ns *ns = q->queuedata;
	struct nvme_ctrl *ctrl;
	struct request *req;
	void *meta = NULL;
	struct bio *bio;
	u32 effects;
	int ret;

	req = nvme_alloc_user_request(q, cmd, 0, 0);
	if (IS_ERR(req))
		return PTR_ERR(req);

	req->timeout = timeout;
	if (ubuffer && bufflen) {
		ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
				meta_len, meta_seed, &meta, NULL, flags);
		if (ret)
			return ret;
	}

	bio = req->bio;
	ctrl = nvme_req(req)->ctrl;

	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
	ret = nvme_execute_rq(req, false);
	if (result)
		*result = le64_to_cpu(nvme_req(req)->result.u64);
	if (meta)
		ret = nvme_finish_user_metadata(req, meta_buffer, meta,
						meta_len, ret);
	if (bio)
		blk_rq_unmap_user(bio);
	blk_mq_free_request(req);

	if (effects)
		nvme_passthru_end(ctrl, ns, effects, cmd, ret);

	return ret;
}

static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
{
	struct nvme_user_io io;
	struct nvme_command c;
	unsigned length, meta_len;
	void __user *metadata;

	if (copy_from_user(&io, uio, sizeof(io)))
		return -EFAULT;
	if (io.flags)
		return -EINVAL;

	switch (io.opcode) {
	case nvme_cmd_write:
	case nvme_cmd_read:
	case nvme_cmd_compare:
		break;
	default:
		return -EINVAL;
	}

	length = (io.nblocks + 1) << ns->lba_shift;

	if ((io.control & NVME_RW_PRINFO_PRACT) &&
	    ns->ms == sizeof(struct t10_pi_tuple)) {
		/*
		 * Protection information is stripped/inserted by the
		 * controller.
		 */
		if (nvme_to_user_ptr(io.metadata))
			return -EINVAL;
		meta_len = 0;
		metadata = NULL;
	} else {
		meta_len = (io.nblocks + 1) * ns->ms;
		metadata = nvme_to_user_ptr(io.metadata);
	}

	if (ns->features & NVME_NS_EXT_LBAS) {
		length += meta_len;
		meta_len = 0;
	} else if (meta_len) {
		if ((io.metadata & 3) || !io.metadata)
			return -EINVAL;
	}

	memset(&c, 0, sizeof(c));
	c.rw.opcode = io.opcode;
	c.rw.flags = io.flags;
	c.rw.nsid = cpu_to_le32(ns->head->ns_id);
	c.rw.slba = cpu_to_le64(io.slba);
	c.rw.length = cpu_to_le16(io.nblocks);
	c.rw.control = cpu_to_le16(io.control);
	c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
	c.rw.reftag = cpu_to_le32(io.reftag);
	c.rw.apptag = cpu_to_le16(io.apptag);
	c.rw.appmask = cpu_to_le16(io.appmask);

	return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
			meta_len, lower_32_bits(io.slba), NULL, 0, 0);
}

static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
					struct nvme_ns *ns, __u32 nsid)
{
	if (ns && nsid != ns->head->ns_id) {
		dev_err(ctrl->device,
			"%s: nsid (%u) in cmd does not match nsid (%u)"
			"of namespace\n",
			current->comm, nsid, ns->head->ns_id);
		return false;
	}

	return true;
}

static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
		struct nvme_passthru_cmd __user *ucmd, unsigned int flags,
		bool open_for_write)
{
	struct nvme_passthru_cmd cmd;
	struct nvme_command c;
	unsigned timeout = 0;
	u64 result;
	int status;

	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
		return -EFAULT;
	if (cmd.flags)
		return -EINVAL;
	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
		return -EINVAL;

	memset(&c, 0, sizeof(c));
	c.common.opcode = cmd.opcode;
	c.common.flags = cmd.flags;
	c.common.nsid = cpu_to_le32(cmd.nsid);
	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
	c.common.cdw15 = cpu_to_le32(cmd.cdw15);

	if (!nvme_cmd_allowed(ns, &c, 0, open_for_write))
		return -EACCES;

	if (cmd.timeout_ms)
		timeout = msecs_to_jiffies(cmd.timeout_ms);

	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
			cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
			cmd.metadata_len, 0, &result, timeout, 0);

	if (status >= 0) {
		if (put_user(result, &ucmd->result))
			return -EFAULT;
	}

	return status;
}

static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
		struct nvme_passthru_cmd64 __user *ucmd, unsigned int flags,
		bool open_for_write)
{
	struct nvme_passthru_cmd64 cmd;
	struct nvme_command c;
	unsigned timeout = 0;
	int status;

	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
		return -EFAULT;
	if (cmd.flags)
		return -EINVAL;
	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
		return -EINVAL;

	memset(&c, 0, sizeof(c));
	c.common.opcode = cmd.opcode;
	c.common.flags = cmd.flags;
	c.common.nsid = cpu_to_le32(cmd.nsid);
	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
	c.common.cdw15 = cpu_to_le32(cmd.cdw15);

	if (!nvme_cmd_allowed(ns, &c, flags, open_for_write))
		return -EACCES;

	if (cmd.timeout_ms)
		timeout = msecs_to_jiffies(cmd.timeout_ms);

	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
			cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
			cmd.metadata_len, 0, &cmd.result, timeout, flags);

	if (status >= 0) {
		if (put_user(cmd.result, &ucmd->result))
			return -EFAULT;
	}

	return status;
}

struct nvme_uring_data {
	__u64	metadata;
	__u64	addr;
	__u32	data_len;
	__u32	metadata_len;
	__u32	timeout_ms;
};

/*
 * This overlays struct io_uring_cmd pdu.
 * Expect build errors if this grows larger than that.
 */
struct nvme_uring_cmd_pdu {
	union {
		struct bio *bio;
		struct request *req;
	};
	u32 meta_len;
	u32 nvme_status;
	union {
		struct {
			void *meta; /* kernel-resident buffer */
			void __user *meta_buffer;
		};
		u64 result;
	} u;
};

static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
		struct io_uring_cmd *ioucmd)
{
	return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
}

static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd,
				    unsigned issue_flags)
{
	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
	struct request *req = pdu->req;
	int status;
	u64 result;

	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
		status = -EINTR;
	else
		status = nvme_req(req)->status;

	result = le64_to_cpu(nvme_req(req)->result.u64);

	if (pdu->meta_len)
		status = nvme_finish_user_metadata(req, pdu->u.meta_buffer,
					pdu->u.meta, pdu->meta_len, status);
	if (req->bio)
		blk_rq_unmap_user(req->bio);
	blk_mq_free_request(req);

	io_uring_cmd_done(ioucmd, status, result, issue_flags);
}

static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
			       unsigned issue_flags)
{
	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);

	if (pdu->bio)
		blk_rq_unmap_user(pdu->bio);

	io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags);
}

static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
						blk_status_t err)
{
	struct io_uring_cmd *ioucmd = req->end_io_data;
	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);

	req->bio = pdu->bio;
	if (nvme_req(req)->flags & NVME_REQ_CANCELLED) {
		pdu->nvme_status = -EINTR;
	} else {
		pdu->nvme_status = nvme_req(req)->status;
		if (!pdu->nvme_status)
			pdu->nvme_status = blk_status_to_errno(err);
	}
	pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64);

	/*
	 * For iopoll, complete it directly.
	 * Otherwise, move the completion to task work.
	 */
	if (blk_rq_is_poll(req)) {
		WRITE_ONCE(ioucmd->cookie, NULL);
		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
	} else {
		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
	}

	return RQ_END_IO_FREE;
}

static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req,
						     blk_status_t err)
{
	struct io_uring_cmd *ioucmd = req->end_io_data;
	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);

	req->bio = pdu->bio;
	pdu->req = req;

	/*
	 * For iopoll, complete it directly.
	 * Otherwise, move the completion to task work.
	 */
	if (blk_rq_is_poll(req)) {
		WRITE_ONCE(ioucmd->cookie, NULL);
		nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED);
	} else {
		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb);
	}

	return RQ_END_IO_NONE;
}

static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
		struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec)
{
	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
	const struct nvme_uring_cmd *cmd = io_uring_sqe_cmd(ioucmd->sqe);
	struct request_queue *q = ns ? ns->queue : ctrl->admin_q;
	struct nvme_uring_data d;
	struct nvme_command c;
	struct request *req;
	blk_opf_t rq_flags = REQ_ALLOC_CACHE;
	blk_mq_req_flags_t blk_flags = 0;
	void *meta = NULL;
	int ret;

	c.common.opcode = READ_ONCE(cmd->opcode);
	c.common.flags = READ_ONCE(cmd->flags);
	if (c.common.flags)
		return -EINVAL;

	c.common.command_id = 0;
	c.common.nsid = cpu_to_le32(cmd->nsid);
	if (!nvme_validate_passthru_nsid(ctrl, ns, le32_to_cpu(c.common.nsid)))
		return -EINVAL;

	c.common.cdw2[0] = cpu_to_le32(READ_ONCE(cmd->cdw2));
	c.common.cdw2[1] = cpu_to_le32(READ_ONCE(cmd->cdw3));
	c.common.metadata = 0;
	c.common.dptr.prp1 = c.common.dptr.prp2 = 0;
	c.common.cdw10 = cpu_to_le32(READ_ONCE(cmd->cdw10));
	c.common.cdw11 = cpu_to_le32(READ_ONCE(cmd->cdw11));
	c.common.cdw12 = cpu_to_le32(READ_ONCE(cmd->cdw12));
	c.common.cdw13 = cpu_to_le32(READ_ONCE(cmd->cdw13));
	c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14));
	c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15));

	if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode & FMODE_WRITE))
		return -EACCES;

	d.metadata = READ_ONCE(cmd->metadata);
	d.addr = READ_ONCE(cmd->addr);
	d.data_len = READ_ONCE(cmd->data_len);
	d.metadata_len = READ_ONCE(cmd->metadata_len);
	d.timeout_ms = READ_ONCE(cmd->timeout_ms);

	if (issue_flags & IO_URING_F_NONBLOCK) {
		rq_flags |= REQ_NOWAIT;
		blk_flags = BLK_MQ_REQ_NOWAIT;
	}
	if (issue_flags & IO_URING_F_IOPOLL)
		rq_flags |= REQ_POLLED;

	req = nvme_alloc_user_request(q, &c, rq_flags, blk_flags);
	if (IS_ERR(req))
		return PTR_ERR(req);
	req->timeout = d.timeout_ms ? msecs_to_jiffies(d.timeout_ms) : 0;

	if (d.addr && d.data_len) {
		ret = nvme_map_user_request(req, d.addr,
			d.data_len, nvme_to_user_ptr(d.metadata),
			d.metadata_len, 0, &meta, ioucmd, vec);
		if (ret)
			return ret;
	}

	if (blk_rq_is_poll(req)) {
		ioucmd->flags |= IORING_URING_CMD_POLLED;
		WRITE_ONCE(ioucmd->cookie, req);
	}

	/* to free bio on completion, as req->bio will be null at that time */
	pdu->bio = req->bio;
	pdu->meta_len = d.metadata_len;
	req->end_io_data = ioucmd;
	if (pdu->meta_len) {
		pdu->u.meta = meta;
		pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata);
		req->end_io = nvme_uring_cmd_end_io_meta;
	} else {
		req->end_io = nvme_uring_cmd_end_io;
	}
	blk_execute_rq_nowait(req, false);
	return -EIOCBQUEUED;
}

static bool is_ctrl_ioctl(unsigned int cmd)
{
	if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
		return true;
	if (is_sed_ioctl(cmd))
		return true;
	return false;
}

static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd,
		void __user *argp, bool open_for_write)
{
	switch (cmd) {
	case NVME_IOCTL_ADMIN_CMD:
		return nvme_user_cmd(ctrl, NULL, argp, 0, open_for_write);
	case NVME_IOCTL_ADMIN64_CMD:
		return nvme_user_cmd64(ctrl, NULL, argp, 0, open_for_write);
	default:
		return sed_ioctl(ctrl->opal_dev, cmd, argp);
	}
}

#ifdef COMPAT_FOR_U64_ALIGNMENT
struct nvme_user_io32 {
	__u8	opcode;
	__u8	flags;
	__u16	control;
	__u16	nblocks;
	__u16	rsvd;
	__u64	metadata;
	__u64	addr;
	__u64	slba;
	__u32	dsmgmt;
	__u32	reftag;
	__u16	apptag;
	__u16	appmask;
} __attribute__((__packed__));
#define NVME_IOCTL_SUBMIT_IO32	_IOW('N', 0x42, struct nvme_user_io32)
#endif /* COMPAT_FOR_U64_ALIGNMENT */

static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
		void __user *argp, unsigned int flags, bool open_for_write)
{
	switch (cmd) {
	case NVME_IOCTL_ID:
		force_successful_syscall_return();
		return ns->head->ns_id;
	case NVME_IOCTL_IO_CMD:
		return nvme_user_cmd(ns->ctrl, ns, argp, flags, open_for_write);
	/*
	 * struct nvme_user_io can have different padding on some 32-bit ABIs.
	 * Just accept the compat version as all fields that are used are the
	 * same size and at the same offset.
	 */
#ifdef COMPAT_FOR_U64_ALIGNMENT
	case NVME_IOCTL_SUBMIT_IO32:
#endif
	case NVME_IOCTL_SUBMIT_IO:
		return nvme_submit_io(ns, argp);
	case NVME_IOCTL_IO64_CMD_VEC:
		flags |= NVME_IOCTL_VEC;
		fallthrough;
	case NVME_IOCTL_IO64_CMD:
		return nvme_user_cmd64(ns->ctrl, ns, argp, flags,
				       open_for_write);
	default:
		return -ENOTTY;
	}
}

int nvme_ioctl(struct block_device *bdev, blk_mode_t mode,
		unsigned int cmd, unsigned long arg)
{
	struct nvme_ns *ns = bdev->bd_disk->private_data;
	bool open_for_write = mode & BLK_OPEN_WRITE;
	void __user *argp = (void __user *)arg;
	unsigned int flags = 0;

	if (bdev_is_partition(bdev))
		flags |= NVME_IOCTL_PARTITION;

	if (is_ctrl_ioctl(cmd))
		return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write);
	return nvme_ns_ioctl(ns, cmd, argp, flags, open_for_write);
}

long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct nvme_ns *ns =
		container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev);
	bool open_for_write = file->f_mode & FMODE_WRITE;
	void __user *argp = (void __user *)arg;

	if (is_ctrl_ioctl(cmd))
		return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write);
	return nvme_ns_ioctl(ns, cmd, argp, 0, open_for_write);
}

static int nvme_uring_cmd_checks(unsigned int issue_flags)
{

	/* NVMe passthrough requires big SQE/CQE support */
	if ((issue_flags & (IO_URING_F_SQE128|IO_URING_F_CQE32)) !=
	    (IO_URING_F_SQE128|IO_URING_F_CQE32))
		return -EOPNOTSUPP;
	return 0;
}

static int nvme_ns_uring_cmd(struct nvme_ns *ns, struct io_uring_cmd *ioucmd,
			     unsigned int issue_flags)
{
	struct nvme_ctrl *ctrl = ns->ctrl;
	int ret;

	BUILD_BUG_ON(sizeof(struct nvme_uring_cmd_pdu) > sizeof(ioucmd->pdu));

	ret = nvme_uring_cmd_checks(issue_flags);
	if (ret)
		return ret;

	switch (ioucmd->cmd_op) {
	case NVME_URING_CMD_IO:
		ret = nvme_uring_cmd_io(ctrl, ns, ioucmd, issue_flags, false);
		break;
	case NVME_URING_CMD_IO_VEC:
		ret = nvme_uring_cmd_io(ctrl, ns, ioucmd, issue_flags, true);
		break;
	default:
		ret = -ENOTTY;
	}

	return ret;
}

int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags)
{
	struct nvme_ns *ns = container_of(file_inode(ioucmd->file)->i_cdev,
			struct nvme_ns, cdev);

	return nvme_ns_uring_cmd(ns, ioucmd, issue_flags);
}

int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd,
				 struct io_comp_batch *iob,
				 unsigned int poll_flags)
{
	struct request *req;
	int ret = 0;

	if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
		return 0;

	req = READ_ONCE(ioucmd->cookie);
	if (req && blk_rq_is_poll(req))
		ret = blk_rq_poll(req, iob, poll_flags);
	return ret;
}
#ifdef CONFIG_NVME_MULTIPATH
static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
		void __user *argp, struct nvme_ns_head *head, int srcu_idx,
		bool open_for_write)
	__releases(&head->srcu)
{
	struct nvme_ctrl *ctrl = ns->ctrl;
	int ret;

	nvme_get_ctrl(ns->ctrl);
	srcu_read_unlock(&head->srcu, srcu_idx);
	ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write);

	nvme_put_ctrl(ctrl);
	return ret;
}

int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode,
		unsigned int cmd, unsigned long arg)
{
	struct nvme_ns_head *head = bdev->bd_disk->private_data;
	bool open_for_write = mode & BLK_OPEN_WRITE;
	void __user *argp = (void __user *)arg;
	struct nvme_ns *ns;
	int srcu_idx, ret = -EWOULDBLOCK;
	unsigned int flags = 0;

	if (bdev_is_partition(bdev))
		flags |= NVME_IOCTL_PARTITION;

	srcu_idx = srcu_read_lock(&head->srcu);
	ns = nvme_find_path(head);
	if (!ns)
		goto out_unlock;

	/*
	 * Handle ioctls that apply to the controller instead of the namespace
	 * seperately and drop the ns SRCU reference early.  This avoids a
	 * deadlock when deleting namespaces using the passthrough interface.
	 */
	if (is_ctrl_ioctl(cmd))
		return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
					       open_for_write);

	ret = nvme_ns_ioctl(ns, cmd, argp, flags, open_for_write);
out_unlock:
	srcu_read_unlock(&head->srcu, srcu_idx);
	return ret;
}

long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
		unsigned long arg)
{
	bool open_for_write = file->f_mode & FMODE_WRITE;
	struct cdev *cdev = file_inode(file)->i_cdev;
	struct nvme_ns_head *head =
		container_of(cdev, struct nvme_ns_head, cdev);
	void __user *argp = (void __user *)arg;
	struct nvme_ns *ns;
	int srcu_idx, ret = -EWOULDBLOCK;

	srcu_idx = srcu_read_lock(&head->srcu);
	ns = nvme_find_path(head);
	if (!ns)
		goto out_unlock;

	if (is_ctrl_ioctl(cmd))
		return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
				open_for_write);

	ret = nvme_ns_ioctl(ns, cmd, argp, 0, open_for_write);
out_unlock:
	srcu_read_unlock(&head->srcu, srcu_idx);
	return ret;
}

int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd,
		unsigned int issue_flags)
{
	struct cdev *cdev = file_inode(ioucmd->file)->i_cdev;
	struct nvme_ns_head *head = container_of(cdev, struct nvme_ns_head, cdev);
	int srcu_idx = srcu_read_lock(&head->srcu);
	struct nvme_ns *ns = nvme_find_path(head);
	int ret = -EINVAL;

	if (ns)
		ret = nvme_ns_uring_cmd(ns, ioucmd, issue_flags);
	srcu_read_unlock(&head->srcu, srcu_idx);
	return ret;
}
#endif /* CONFIG_NVME_MULTIPATH */

int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags)
{
	struct nvme_ctrl *ctrl = ioucmd->file->private_data;
	int ret;

	/* IOPOLL not supported yet */
	if (issue_flags & IO_URING_F_IOPOLL)
		return -EOPNOTSUPP;

	ret = nvme_uring_cmd_checks(issue_flags);
	if (ret)
		return ret;

	switch (ioucmd->cmd_op) {
	case NVME_URING_CMD_ADMIN:
		ret = nvme_uring_cmd_io(ctrl, NULL, ioucmd, issue_flags, false);
		break;
	case NVME_URING_CMD_ADMIN_VEC:
		ret = nvme_uring_cmd_io(ctrl, NULL, ioucmd, issue_flags, true);
		break;
	default:
		ret = -ENOTTY;
	}

	return ret;
}

static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
		bool open_for_write)
{
	struct nvme_ns *ns;
	int ret;

	down_read(&ctrl->namespaces_rwsem);
	if (list_empty(&ctrl->namespaces)) {
		ret = -ENOTTY;
		goto out_unlock;
	}

	ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
	if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
		dev_warn(ctrl->device,
			"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
		ret = -EINVAL;
		goto out_unlock;
	}

	dev_warn(ctrl->device,
		"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
	kref_get(&ns->kref);
	up_read(&ctrl->namespaces_rwsem);

	ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write);
	nvme_put_ns(ns);
	return ret;

out_unlock:
	up_read(&ctrl->namespaces_rwsem);
	return ret;
}

long nvme_dev_ioctl(struct file *file, unsigned int cmd,
		unsigned long arg)
{
	bool open_for_write = file->f_mode & FMODE_WRITE;
	struct nvme_ctrl *ctrl = file->private_data;
	void __user *argp = (void __user *)arg;

	switch (cmd) {
	case NVME_IOCTL_ADMIN_CMD:
		return nvme_user_cmd(ctrl, NULL, argp, 0, open_for_write);
	case NVME_IOCTL_ADMIN64_CMD:
		return nvme_user_cmd64(ctrl, NULL, argp, 0, open_for_write);
	case NVME_IOCTL_IO_CMD:
		return nvme_dev_user_cmd(ctrl, argp, open_for_write);
	case NVME_IOCTL_RESET:
		if (!capable(CAP_SYS_ADMIN))
			return -EACCES;
		dev_warn(ctrl->device, "resetting controller\n");
		return nvme_reset_ctrl_sync(ctrl);
	case NVME_IOCTL_SUBSYS_RESET:
		if (!capable(CAP_SYS_ADMIN))
			return -EACCES;
		return nvme_reset_subsystem(ctrl);
	case NVME_IOCTL_RESCAN:
		if (!capable(CAP_SYS_ADMIN))
			return -EACCES;
		nvme_queue_scan(ctrl);
		return 0;
	default:
		return -ENOTTY;
	}
}