summaryrefslogtreecommitdiff
path: root/drivers/nvme/host/multipath.c
blob: 5e3cc8c59a394fce6ba25f1c621b26903185963d (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
/*
 * Copyright (c) 2017-2018 Christoph Hellwig.
 *
 * 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.
 */

#include <linux/moduleparam.h>
#include <trace/events/block.h>
#include "nvme.h"

static bool multipath = true;
module_param(multipath, bool, 0444);
MODULE_PARM_DESC(multipath,
	"turn on native support for multiple controllers per subsystem");

inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
{
	return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
}

/*
 * If multipathing is enabled we need to always use the subsystem instance
 * number for numbering our devices to avoid conflicts between subsystems that
 * have multiple controllers and thus use the multipath-aware subsystem node
 * and those that have a single controller and use the controller node
 * directly.
 */
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
			struct nvme_ctrl *ctrl, int *flags)
{
	if (!multipath) {
		sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
	} else if (ns->head->disk) {
		sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
				ctrl->cntlid, ns->head->instance);
		*flags = GENHD_FL_HIDDEN;
	} else {
		sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
				ns->head->instance);
	}
}

void nvme_failover_req(struct request *req)
{
	struct nvme_ns *ns = req->q->queuedata;
	u16 status = nvme_req(req)->status;
	unsigned long flags;

	spin_lock_irqsave(&ns->head->requeue_lock, flags);
	blk_steal_bios(&ns->head->requeue_list, req);
	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
	blk_mq_end_request(req, 0);

	switch (status & 0x7ff) {
	case NVME_SC_ANA_TRANSITION:
	case NVME_SC_ANA_INACCESSIBLE:
	case NVME_SC_ANA_PERSISTENT_LOSS:
		/*
		 * If we got back an ANA error we know the controller is alive,
		 * but not ready to serve this namespaces.  The spec suggests
		 * we should update our general state here, but due to the fact
		 * that the admin and I/O queues are not serialized that is
		 * fundamentally racy.  So instead just clear the current path,
		 * mark the the path as pending and kick of a re-read of the ANA
		 * log page ASAP.
		 */
		nvme_mpath_clear_current_path(ns);
		if (ns->ctrl->ana_log_buf) {
			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
			queue_work(nvme_wq, &ns->ctrl->ana_work);
		}
		break;
	case NVME_SC_HOST_PATH_ERROR:
		/*
		 * Temporary transport disruption in talking to the controller.
		 * Try to send on a new path.
		 */
		nvme_mpath_clear_current_path(ns);
		break;
	default:
		/*
		 * Reset the controller for any non-ANA error as we don't know
		 * what caused the error.
		 */
		nvme_reset_ctrl(ns->ctrl);
		break;
	}

	kblockd_schedule_work(&ns->head->requeue_work);
}

void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
{
	struct nvme_ns *ns;

	down_read(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list) {
		if (ns->head->disk)
			kblockd_schedule_work(&ns->head->requeue_work);
	}
	up_read(&ctrl->namespaces_rwsem);
}

static const char *nvme_ana_state_names[] = {
	[0]				= "invalid state",
	[NVME_ANA_OPTIMIZED]		= "optimized",
	[NVME_ANA_NONOPTIMIZED]		= "non-optimized",
	[NVME_ANA_INACCESSIBLE]		= "inaccessible",
	[NVME_ANA_PERSISTENT_LOSS]	= "persistent-loss",
	[NVME_ANA_CHANGE]		= "change",
};

void nvme_mpath_clear_current_path(struct nvme_ns *ns)
{
	struct nvme_ns_head *head = ns->head;
	int node;

	if (!head)
		return;

	for_each_node(node) {
		if (ns == rcu_access_pointer(head->current_path[node]))
			rcu_assign_pointer(head->current_path[node], NULL);
	}
}

static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
{
	int found_distance = INT_MAX, fallback_distance = INT_MAX, distance;
	struct nvme_ns *found = NULL, *fallback = NULL, *ns;

	list_for_each_entry_rcu(ns, &head->list, siblings) {
		if (ns->ctrl->state != NVME_CTRL_LIVE ||
		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
			continue;

		distance = node_distance(node, dev_to_node(ns->ctrl->dev));

		switch (ns->ana_state) {
		case NVME_ANA_OPTIMIZED:
			if (distance < found_distance) {
				found_distance = distance;
				found = ns;
			}
			break;
		case NVME_ANA_NONOPTIMIZED:
			if (distance < fallback_distance) {
				fallback_distance = distance;
				fallback = ns;
			}
			break;
		default:
			break;
		}
	}

	if (!found)
		found = fallback;
	if (found)
		rcu_assign_pointer(head->current_path[node], found);
	return found;
}

static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
{
	return ns->ctrl->state == NVME_CTRL_LIVE &&
		ns->ana_state == NVME_ANA_OPTIMIZED;
}

inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
{
	int node = numa_node_id();
	struct nvme_ns *ns;

	ns = srcu_dereference(head->current_path[node], &head->srcu);
	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
		ns = __nvme_find_path(head, node);
	return ns;
}

static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
		struct bio *bio)
{
	struct nvme_ns_head *head = q->queuedata;
	struct device *dev = disk_to_dev(head->disk);
	struct nvme_ns *ns;
	blk_qc_t ret = BLK_QC_T_NONE;
	int srcu_idx;

	srcu_idx = srcu_read_lock(&head->srcu);
	ns = nvme_find_path(head);
	if (likely(ns)) {
		bio->bi_disk = ns->disk;
		bio->bi_opf |= REQ_NVME_MPATH;
		trace_block_bio_remap(bio->bi_disk->queue, bio,
				      disk_devt(ns->head->disk),
				      bio->bi_iter.bi_sector);
		ret = direct_make_request(bio);
	} else if (!list_empty_careful(&head->list)) {
		dev_warn_ratelimited(dev, "no path available - requeuing I/O\n");

		spin_lock_irq(&head->requeue_lock);
		bio_list_add(&head->requeue_list, bio);
		spin_unlock_irq(&head->requeue_lock);
	} else {
		dev_warn_ratelimited(dev, "no path - failing I/O\n");

		bio->bi_status = BLK_STS_IOERR;
		bio_endio(bio);
	}

	srcu_read_unlock(&head->srcu, srcu_idx);
	return ret;
}

static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
{
	struct nvme_ns_head *head = q->queuedata;
	struct nvme_ns *ns;
	bool found = false;
	int srcu_idx;

	srcu_idx = srcu_read_lock(&head->srcu);
	ns = srcu_dereference(head->current_path[numa_node_id()], &head->srcu);
	if (likely(ns && nvme_path_is_optimized(ns)))
		found = ns->queue->poll_fn(q, qc);
	srcu_read_unlock(&head->srcu, srcu_idx);
	return found;
}

static void nvme_requeue_work(struct work_struct *work)
{
	struct nvme_ns_head *head =
		container_of(work, struct nvme_ns_head, requeue_work);
	struct bio *bio, *next;

	spin_lock_irq(&head->requeue_lock);
	next = bio_list_get(&head->requeue_list);
	spin_unlock_irq(&head->requeue_lock);

	while ((bio = next) != NULL) {
		next = bio->bi_next;
		bio->bi_next = NULL;

		/*
		 * Reset disk to the mpath node and resubmit to select a new
		 * path.
		 */
		bio->bi_disk = head->disk;
		generic_make_request(bio);
	}
}

int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
{
	struct request_queue *q;
	bool vwc = false;

	mutex_init(&head->lock);
	bio_list_init(&head->requeue_list);
	spin_lock_init(&head->requeue_lock);
	INIT_WORK(&head->requeue_work, nvme_requeue_work);

	/*
	 * Add a multipath node if the subsystems supports multiple controllers.
	 * We also do this for private namespaces as the namespace sharing data could
	 * change after a rescan.
	 */
	if (!(ctrl->subsys->cmic & (1 << 1)) || !multipath)
		return 0;

	q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE, NULL);
	if (!q)
		goto out;
	q->queuedata = head;
	blk_queue_make_request(q, nvme_ns_head_make_request);
	q->poll_fn = nvme_ns_head_poll;
	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
	/* set to a default value for 512 until disk is validated */
	blk_queue_logical_block_size(q, 512);

	/* we need to propagate up the VMC settings */
	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
		vwc = true;
	blk_queue_write_cache(q, vwc, vwc);

	head->disk = alloc_disk(0);
	if (!head->disk)
		goto out_cleanup_queue;
	head->disk->fops = &nvme_ns_head_ops;
	head->disk->private_data = head;
	head->disk->queue = q;
	head->disk->flags = GENHD_FL_EXT_DEVT;
	sprintf(head->disk->disk_name, "nvme%dn%d",
			ctrl->subsys->instance, head->instance);
	return 0;

out_cleanup_queue:
	blk_cleanup_queue(q);
out:
	return -ENOMEM;
}

static void nvme_mpath_set_live(struct nvme_ns *ns)
{
	struct nvme_ns_head *head = ns->head;

	lockdep_assert_held(&ns->head->lock);

	if (!head->disk)
		return;

	if (!(head->disk->flags & GENHD_FL_UP))
		device_add_disk(&head->subsys->dev, head->disk,
				nvme_ns_id_attr_groups);

	if (nvme_path_is_optimized(ns)) {
		int node, srcu_idx;

		srcu_idx = srcu_read_lock(&head->srcu);
		for_each_node(node)
			__nvme_find_path(head, node);
		srcu_read_unlock(&head->srcu, srcu_idx);
	}

	kblockd_schedule_work(&ns->head->requeue_work);
}

static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
		int (*cb)(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *,
			void *))
{
	void *base = ctrl->ana_log_buf;
	size_t offset = sizeof(struct nvme_ana_rsp_hdr);
	int error, i;

	lockdep_assert_held(&ctrl->ana_lock);

	for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
		struct nvme_ana_group_desc *desc = base + offset;
		u32 nr_nsids = le32_to_cpu(desc->nnsids);
		size_t nsid_buf_size = nr_nsids * sizeof(__le32);

		if (WARN_ON_ONCE(desc->grpid == 0))
			return -EINVAL;
		if (WARN_ON_ONCE(le32_to_cpu(desc->grpid) > ctrl->anagrpmax))
			return -EINVAL;
		if (WARN_ON_ONCE(desc->state == 0))
			return -EINVAL;
		if (WARN_ON_ONCE(desc->state > NVME_ANA_CHANGE))
			return -EINVAL;

		offset += sizeof(*desc);
		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - nsid_buf_size))
			return -EINVAL;

		error = cb(ctrl, desc, data);
		if (error)
			return error;

		offset += nsid_buf_size;
		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
			return -EINVAL;
	}

	return 0;
}

static inline bool nvme_state_is_live(enum nvme_ana_state state)
{
	return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
}

static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
		struct nvme_ns *ns)
{
	enum nvme_ana_state old;

	mutex_lock(&ns->head->lock);
	old = ns->ana_state;
	ns->ana_grpid = le32_to_cpu(desc->grpid);
	ns->ana_state = desc->state;
	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);

	if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
		nvme_mpath_set_live(ns);
	mutex_unlock(&ns->head->lock);
}

static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
		struct nvme_ana_group_desc *desc, void *data)
{
	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
	unsigned *nr_change_groups = data;
	struct nvme_ns *ns;

	dev_info(ctrl->device, "ANA group %d: %s.\n",
			le32_to_cpu(desc->grpid),
			nvme_ana_state_names[desc->state]);

	if (desc->state == NVME_ANA_CHANGE)
		(*nr_change_groups)++;

	if (!nr_nsids)
		return 0;

	down_write(&ctrl->namespaces_rwsem);
	list_for_each_entry(ns, &ctrl->namespaces, list) {
		if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
			continue;
		nvme_update_ns_ana_state(desc, ns);
		if (++n == nr_nsids)
			break;
	}
	up_write(&ctrl->namespaces_rwsem);
	WARN_ON_ONCE(n < nr_nsids);
	return 0;
}

static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
{
	u32 nr_change_groups = 0;
	int error;

	mutex_lock(&ctrl->ana_lock);
	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
			groups_only ? NVME_ANA_LOG_RGO : 0,
			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
	if (error) {
		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
		goto out_unlock;
	}

	error = nvme_parse_ana_log(ctrl, &nr_change_groups,
			nvme_update_ana_state);
	if (error)
		goto out_unlock;

	/*
	 * In theory we should have an ANATT timer per group as they might enter
	 * the change state at different times.  But that is a lot of overhead
	 * just to protect against a target that keeps entering new changes
	 * states while never finishing previous ones.  But we'll still
	 * eventually time out once all groups are in change state, so this
	 * isn't a big deal.
	 *
	 * We also double the ANATT value to provide some slack for transports
	 * or AEN processing overhead.
	 */
	if (nr_change_groups)
		mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies);
	else
		del_timer_sync(&ctrl->anatt_timer);
out_unlock:
	mutex_unlock(&ctrl->ana_lock);
	return error;
}

static void nvme_ana_work(struct work_struct *work)
{
	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);

	nvme_read_ana_log(ctrl, false);
}

static void nvme_anatt_timeout(struct timer_list *t)
{
	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);

	dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
	nvme_reset_ctrl(ctrl);
}

void nvme_mpath_stop(struct nvme_ctrl *ctrl)
{
	if (!nvme_ctrl_use_ana(ctrl))
		return;
	del_timer_sync(&ctrl->anatt_timer);
	cancel_work_sync(&ctrl->ana_work);
}

static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr,
		char *buf)
{
	return sprintf(buf, "%d\n", nvme_get_ns_from_dev(dev)->ana_grpid);
}
DEVICE_ATTR_RO(ana_grpid);

static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
		char *buf)
{
	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);

	return sprintf(buf, "%s\n", nvme_ana_state_names[ns->ana_state]);
}
DEVICE_ATTR_RO(ana_state);

static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
		struct nvme_ana_group_desc *desc, void *data)
{
	struct nvme_ns *ns = data;

	if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
		nvme_update_ns_ana_state(desc, ns);
		return -ENXIO; /* just break out of the loop */
	}

	return 0;
}

void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
{
	if (nvme_ctrl_use_ana(ns->ctrl)) {
		mutex_lock(&ns->ctrl->ana_lock);
		ns->ana_grpid = le32_to_cpu(id->anagrpid);
		nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
		mutex_unlock(&ns->ctrl->ana_lock);
	} else {
		mutex_lock(&ns->head->lock);
		ns->ana_state = NVME_ANA_OPTIMIZED; 
		nvme_mpath_set_live(ns);
		mutex_unlock(&ns->head->lock);
	}
}

void nvme_mpath_remove_disk(struct nvme_ns_head *head)
{
	if (!head->disk)
		return;
	if (head->disk->flags & GENHD_FL_UP)
		del_gendisk(head->disk);
	blk_set_queue_dying(head->disk->queue);
	/* make sure all pending bios are cleaned up */
	kblockd_schedule_work(&head->requeue_work);
	flush_work(&head->requeue_work);
	blk_cleanup_queue(head->disk->queue);
	put_disk(head->disk);
}

int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
{
	int error;

	if (!nvme_ctrl_use_ana(ctrl))
		return 0;

	ctrl->anacap = id->anacap;
	ctrl->anatt = id->anatt;
	ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
	ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);

	mutex_init(&ctrl->ana_lock);
	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
	if (!(ctrl->anacap & (1 << 6)))
		ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);

	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
		dev_err(ctrl->device,
			"ANA log page size (%zd) larger than MDTS (%d).\n",
			ctrl->ana_log_size,
			ctrl->max_hw_sectors << SECTOR_SHIFT);
		dev_err(ctrl->device, "disabling ANA support.\n");
		return 0;
	}

	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
	if (!ctrl->ana_log_buf) {
		error = -ENOMEM;
		goto out;
	}

	error = nvme_read_ana_log(ctrl, true);
	if (error)
		goto out_free_ana_log_buf;
	return 0;
out_free_ana_log_buf:
	kfree(ctrl->ana_log_buf);
out:
	return error;
}

void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
{
	kfree(ctrl->ana_log_buf);
}