summaryrefslogtreecommitdiff
path: root/drivers/nvme/target/passthru.c
blob: 89d91dc999a6db57ca56fdc561d84aa51a42ae02 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * NVMe Over Fabrics Target Passthrough command implementation.
 *
 * Copyright (c) 2017-2018 Western Digital Corporation or its
 * affiliates.
 * Copyright (c) 2019-2020, Eideticom Inc.
 *
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>

#include "../host/nvme.h"
#include "nvmet.h"

MODULE_IMPORT_NS(NVME_TARGET_PASSTHRU);

/*
 * xarray to maintain one passthru subsystem per nvme controller.
 */
static DEFINE_XARRAY(passthru_subsystems);

static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
{
	struct nvmet_ctrl *ctrl = req->sq->ctrl;
	struct nvme_ctrl *pctrl = ctrl->subsys->passthru_ctrl;
	u16 status = NVME_SC_SUCCESS;
	struct nvme_id_ctrl *id;
	u32 max_hw_sectors;
	int page_shift;

	id = kzalloc(sizeof(*id), GFP_KERNEL);
	if (!id)
		return NVME_SC_INTERNAL;

	status = nvmet_copy_from_sgl(req, 0, id, sizeof(*id));
	if (status)
		goto out_free;

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

	/*
	 * The passthru NVMe driver may have a limit on the number of segments
	 * which depends on the host's memory fragementation. To solve this,
	 * ensure mdts is limited to the pages equal to the number of segments.
	 */
	max_hw_sectors = min_not_zero(pctrl->max_segments << (PAGE_SHIFT - 9),
				      pctrl->max_hw_sectors);

	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;

	id->mdts = ilog2(max_hw_sectors) + 9 - page_shift;

	id->acl = 3;
	/*
	 * We export aerl limit for the fabrics controller, update this when
	 * passthru based aerl support is added.
	 */
	id->aerl = NVMET_ASYNC_EVENTS - 1;

	/* emulate kas as most of the PCIe ctrl don't have a support for kas */
	id->kas = cpu_to_le16(NVMET_KAS);

	/* don't support host memory buffer */
	id->hmpre = 0;
	id->hmmin = 0;

	id->sqes = min_t(__u8, ((0x6 << 4) | 0x6), id->sqes);
	id->cqes = min_t(__u8, ((0x4 << 4) | 0x4), id->cqes);
	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);

	/* don't support fuse commands */
	id->fuses = 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);

	/*
	 * When passsthru controller is setup using nvme-loop transport it will
	 * export the passthru ctrl subsysnqn (PCIe NVMe ctrl) and will fail in
	 * the nvme/host/core.c in the nvme_init_subsystem()->nvme_active_ctrl()
	 * code path with duplicate ctr subsynqn. In order to prevent that we
	 * mask the passthru-ctrl subsysnqn with the target ctrl subsysnqn.
	 */
	memcpy(id->subnqn, ctrl->subsysnqn, sizeof(id->subnqn));

	/* use fabric id-ctrl values */
	id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) +
				req->port->inline_data_size) / 16);
	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);

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

	/* Support multipath connections with fabrics */
	id->cmic |= 1 << 1;

	/* Disable reservations, see nvmet_parse_passthru_io_cmd() */
	id->oncs &= cpu_to_le16(~NVME_CTRL_ONCS_RESERVATIONS);

	status = nvmet_copy_to_sgl(req, 0, id, sizeof(struct nvme_id_ctrl));

out_free:
	kfree(id);
	return status;
}

static u16 nvmet_passthru_override_id_ns(struct nvmet_req *req)
{
	u16 status = NVME_SC_SUCCESS;
	struct nvme_id_ns *id;
	int i;

	id = kzalloc(sizeof(*id), GFP_KERNEL);
	if (!id)
		return NVME_SC_INTERNAL;

	status = nvmet_copy_from_sgl(req, 0, id, sizeof(struct nvme_id_ns));
	if (status)
		goto out_free;

	for (i = 0; i < (id->nlbaf + 1); i++)
		if (id->lbaf[i].ms)
			memset(&id->lbaf[i], 0, sizeof(id->lbaf[i]));

	id->flbas = id->flbas & ~(1 << 4);

	/*
	 * Presently the NVMEof target code does not support sending
	 * metadata, so we must disable it here. This should be updated
	 * once target starts supporting metadata.
	 */
	id->mc = 0;

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

out_free:
	kfree(id);
	return status;
}

static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
{
	struct nvmet_req *req = container_of(w, struct nvmet_req, p.work);
	struct request *rq = req->p.rq;
	u16 status;

	nvme_execute_passthru_rq(rq);

	status = nvme_req(rq)->status;
	if (status == NVME_SC_SUCCESS &&
	    req->cmd->common.opcode == nvme_admin_identify) {
		switch (req->cmd->identify.cns) {
		case NVME_ID_CNS_CTRL:
			nvmet_passthru_override_id_ctrl(req);
			break;
		case NVME_ID_CNS_NS:
			nvmet_passthru_override_id_ns(req);
			break;
		}
	}

	req->cqe->result = nvme_req(rq)->result;
	nvmet_req_complete(req, status);
	blk_put_request(rq);
}

static void nvmet_passthru_req_done(struct request *rq,
				    blk_status_t blk_status)
{
	struct nvmet_req *req = rq->end_io_data;

	req->cqe->result = nvme_req(rq)->result;
	nvmet_req_complete(req, nvme_req(rq)->status);
	blk_put_request(rq);
}

static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
{
	int sg_cnt = req->sg_cnt;
	struct scatterlist *sg;
	int op_flags = 0;
	struct bio *bio;
	int i, ret;

	if (req->cmd->common.opcode == nvme_cmd_flush)
		op_flags = REQ_FUA;
	else if (nvme_is_write(req->cmd))
		op_flags = REQ_SYNC | REQ_IDLE;

	bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
	bio->bi_end_io = bio_put;
	bio->bi_opf = req_op(rq) | op_flags;

	for_each_sg(req->sg, sg, req->sg_cnt, i) {
		if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length,
				    sg->offset) < sg->length) {
			bio_put(bio);
			return -EINVAL;
		}
		sg_cnt--;
	}

	ret = blk_rq_append_bio(rq, &bio);
	if (unlikely(ret)) {
		bio_put(bio);
		return ret;
	}

	return 0;
}

static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
{
	struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
	struct request_queue *q = ctrl->admin_q;
	struct nvme_ns *ns = NULL;
	struct request *rq = NULL;
	u32 effects;
	u16 status;
	int ret;

	if (likely(req->sq->qid != 0)) {
		u32 nsid = le32_to_cpu(req->cmd->common.nsid);

		ns = nvme_find_get_ns(ctrl, nsid);
		if (unlikely(!ns)) {
			pr_err("failed to get passthru ns nsid:%u\n", nsid);
			status = NVME_SC_INVALID_NS | NVME_SC_DNR;
			goto fail_out;
		}

		q = ns->queue;
	}

	rq = nvme_alloc_request(q, req->cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
	if (IS_ERR(rq)) {
		rq = NULL;
		status = NVME_SC_INTERNAL;
		goto fail_out;
	}

	if (req->sg_cnt) {
		ret = nvmet_passthru_map_sg(req, rq);
		if (unlikely(ret)) {
			status = NVME_SC_INTERNAL;
			goto fail_out;
		}
	}

	/*
	 * If there are effects for the command we are about to execute, or
	 * an end_req function we need to use nvme_execute_passthru_rq()
	 * synchronously in a work item seeing the end_req function and
	 * nvme_passthru_end() can't be called in the request done callback
	 * which is typically in interrupt context.
	 */
	effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode);
	if (req->p.use_workqueue || effects) {
		INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work);
		req->p.rq = rq;
		schedule_work(&req->p.work);
	} else {
		rq->end_io_data = req;
		blk_execute_rq_nowait(rq->q, ns ? ns->disk : NULL, rq, 0,
				      nvmet_passthru_req_done);
	}

	if (ns)
		nvme_put_ns(ns);

	return;

fail_out:
	if (ns)
		nvme_put_ns(ns);
	nvmet_req_complete(req, status);
	blk_put_request(rq);
}

/*
 * We need to emulate set host behaviour to ensure that any requested
 * behaviour of the target's host matches the requested behaviour
 * of the device's host and fail otherwise.
 */
static void nvmet_passthru_set_host_behaviour(struct nvmet_req *req)
{
	struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
	struct nvme_feat_host_behavior *host;
	u16 status = NVME_SC_INTERNAL;
	int ret;

	host = kzalloc(sizeof(*host) * 2, GFP_KERNEL);
	if (!host)
		goto out_complete_req;

	ret = nvme_get_features(ctrl, NVME_FEAT_HOST_BEHAVIOR, 0,
				host, sizeof(*host), NULL);
	if (ret)
		goto out_free_host;

	status = nvmet_copy_from_sgl(req, 0, &host[1], sizeof(*host));
	if (status)
		goto out_free_host;

	if (memcmp(&host[0], &host[1], sizeof(host[0]))) {
		pr_warn("target host has requested different behaviour from the local host\n");
		status = NVME_SC_INTERNAL;
	}

out_free_host:
	kfree(host);
out_complete_req:
	nvmet_req_complete(req, status);
}

static u16 nvmet_setup_passthru_command(struct nvmet_req *req)
{
	req->p.use_workqueue = false;
	req->execute = nvmet_passthru_execute_cmd;
	return NVME_SC_SUCCESS;
}

u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
{
	switch (req->cmd->common.opcode) {
	case nvme_cmd_resv_register:
	case nvme_cmd_resv_report:
	case nvme_cmd_resv_acquire:
	case nvme_cmd_resv_release:
		/*
		 * Reservations cannot be supported properly because the
		 * underlying device has no way of differentiating different
		 * hosts that connect via fabrics. This could potentially be
		 * emulated in the future if regular targets grow support for
		 * this feature.
		 */
		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
	}

	return nvmet_setup_passthru_command(req);
}

/*
 * Only features that are emulated or specifically allowed in the list  are
 * passed down to the controller. This function implements the allow list for
 * both get and set features.
 */
static u16 nvmet_passthru_get_set_features(struct nvmet_req *req)
{
	switch (le32_to_cpu(req->cmd->features.fid)) {
	case NVME_FEAT_ARBITRATION:
	case NVME_FEAT_POWER_MGMT:
	case NVME_FEAT_LBA_RANGE:
	case NVME_FEAT_TEMP_THRESH:
	case NVME_FEAT_ERR_RECOVERY:
	case NVME_FEAT_VOLATILE_WC:
	case NVME_FEAT_WRITE_ATOMIC:
	case NVME_FEAT_AUTO_PST:
	case NVME_FEAT_TIMESTAMP:
	case NVME_FEAT_HCTM:
	case NVME_FEAT_NOPSC:
	case NVME_FEAT_RRL:
	case NVME_FEAT_PLM_CONFIG:
	case NVME_FEAT_PLM_WINDOW:
	case NVME_FEAT_HOST_BEHAVIOR:
	case NVME_FEAT_SANITIZE:
	case NVME_FEAT_VENDOR_START ... NVME_FEAT_VENDOR_END:
		return nvmet_setup_passthru_command(req);

	case NVME_FEAT_ASYNC_EVENT:
		/* There is no support for forwarding ASYNC events */
	case NVME_FEAT_IRQ_COALESCE:
	case NVME_FEAT_IRQ_CONFIG:
		/* The IRQ settings will not apply to the target controller */
	case NVME_FEAT_HOST_MEM_BUF:
		/*
		 * Any HMB that's set will not be passed through and will
		 * not work as expected
		 */
	case NVME_FEAT_SW_PROGRESS:
		/*
		 * The Pre-Boot Software Load Count doesn't make much
		 * sense for a target to export
		 */
	case NVME_FEAT_RESV_MASK:
	case NVME_FEAT_RESV_PERSIST:
		/* No reservations, see nvmet_parse_passthru_io_cmd() */
	default:
		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
	}
}

u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
{
	/*
	 * Passthru all vendor specific commands
	 */
	if (req->cmd->common.opcode >= nvme_admin_vendor_start)
		return nvmet_setup_passthru_command(req);

	switch (req->cmd->common.opcode) {
	case nvme_admin_async_event:
		req->execute = nvmet_execute_async_event;
		return NVME_SC_SUCCESS;
	case nvme_admin_keep_alive:
		/*
		 * Most PCIe ctrls don't support keep alive cmd, we route keep
		 * alive to the non-passthru mode. In future please change this
		 * code when PCIe ctrls with keep alive support available.
		 */
		req->execute = nvmet_execute_keep_alive;
		return NVME_SC_SUCCESS;
	case nvme_admin_set_features:
		switch (le32_to_cpu(req->cmd->features.fid)) {
		case NVME_FEAT_ASYNC_EVENT:
		case NVME_FEAT_KATO:
		case NVME_FEAT_NUM_QUEUES:
		case NVME_FEAT_HOST_ID:
			req->execute = nvmet_execute_set_features;
			return NVME_SC_SUCCESS;
		case NVME_FEAT_HOST_BEHAVIOR:
			req->execute = nvmet_passthru_set_host_behaviour;
			return NVME_SC_SUCCESS;
		default:
			return nvmet_passthru_get_set_features(req);
		}
		break;
	case nvme_admin_get_features:
		switch (le32_to_cpu(req->cmd->features.fid)) {
		case NVME_FEAT_ASYNC_EVENT:
		case NVME_FEAT_KATO:
		case NVME_FEAT_NUM_QUEUES:
		case NVME_FEAT_HOST_ID:
			req->execute = nvmet_execute_get_features;
			return NVME_SC_SUCCESS;
		default:
			return nvmet_passthru_get_set_features(req);
		}
		break;
	case nvme_admin_identify:
		switch (req->cmd->identify.cns) {
		case NVME_ID_CNS_CTRL:
			req->execute = nvmet_passthru_execute_cmd;
			req->p.use_workqueue = true;
			return NVME_SC_SUCCESS;
		case NVME_ID_CNS_NS:
			req->execute = nvmet_passthru_execute_cmd;
			req->p.use_workqueue = true;
			return NVME_SC_SUCCESS;
		default:
			return nvmet_setup_passthru_command(req);
		}
	case nvme_admin_get_log_page:
		return nvmet_setup_passthru_command(req);
	default:
		/* Reject commands not in the allowlist above */
		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
	}
}

int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
{
	struct nvme_ctrl *ctrl;
	int ret = -EINVAL;
	void *old;

	mutex_lock(&subsys->lock);
	if (!subsys->passthru_ctrl_path)
		goto out_unlock;
	if (subsys->passthru_ctrl)
		goto out_unlock;

	if (subsys->nr_namespaces) {
		pr_info("cannot enable both passthru and regular namespaces for a single subsystem");
		goto out_unlock;
	}

	ctrl = nvme_ctrl_get_by_path(subsys->passthru_ctrl_path);
	if (IS_ERR(ctrl)) {
		ret = PTR_ERR(ctrl);
		pr_err("failed to open nvme controller %s\n",
		       subsys->passthru_ctrl_path);

		goto out_unlock;
	}

	old = xa_cmpxchg(&passthru_subsystems, ctrl->cntlid, NULL,
			 subsys, GFP_KERNEL);
	if (xa_is_err(old)) {
		ret = xa_err(old);
		goto out_put_ctrl;
	}

	if (old)
		goto out_put_ctrl;

	subsys->passthru_ctrl = ctrl;
	subsys->ver = ctrl->vs;

	if (subsys->ver < NVME_VS(1, 2, 1)) {
		pr_warn("nvme controller version is too old: %llu.%llu.%llu, advertising 1.2.1\n",
			NVME_MAJOR(subsys->ver), NVME_MINOR(subsys->ver),
			NVME_TERTIARY(subsys->ver));
		subsys->ver = NVME_VS(1, 2, 1);
	}

	mutex_unlock(&subsys->lock);
	return 0;

out_put_ctrl:
	nvme_put_ctrl(ctrl);
out_unlock:
	mutex_unlock(&subsys->lock);
	return ret;
}

static void __nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys)
{
	if (subsys->passthru_ctrl) {
		xa_erase(&passthru_subsystems, subsys->passthru_ctrl->cntlid);
		nvme_put_ctrl(subsys->passthru_ctrl);
	}
	subsys->passthru_ctrl = NULL;
	subsys->ver = NVMET_DEFAULT_VS;
}

void nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys)
{
	mutex_lock(&subsys->lock);
	__nvmet_passthru_ctrl_disable(subsys);
	mutex_unlock(&subsys->lock);
}

void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys)
{
	mutex_lock(&subsys->lock);
	__nvmet_passthru_ctrl_disable(subsys);
	mutex_unlock(&subsys->lock);
	kfree(subsys->passthru_ctrl_path);
}