summaryrefslogtreecommitdiffstats
path: root/drivers/nvdimm/core.c
blob: be89764315c2b54d9bbe9548fc3f6183d6032ea4 (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
/*
 * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that 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/libnvdimm.h>
#include <linux/badblocks.h>
#include <linux/export.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/device.h>
#include <linux/ctype.h>
#include <linux/ndctl.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include "nd-core.h"
#include "nd.h"

LIST_HEAD(nvdimm_bus_list);
DEFINE_MUTEX(nvdimm_bus_list_mutex);
static DEFINE_IDA(nd_ida);

void nvdimm_bus_lock(struct device *dev)
{
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);

	if (!nvdimm_bus)
		return;
	mutex_lock(&nvdimm_bus->reconfig_mutex);
}
EXPORT_SYMBOL(nvdimm_bus_lock);

void nvdimm_bus_unlock(struct device *dev)
{
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);

	if (!nvdimm_bus)
		return;
	mutex_unlock(&nvdimm_bus->reconfig_mutex);
}
EXPORT_SYMBOL(nvdimm_bus_unlock);

bool is_nvdimm_bus_locked(struct device *dev)
{
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);

	if (!nvdimm_bus)
		return false;
	return mutex_is_locked(&nvdimm_bus->reconfig_mutex);
}
EXPORT_SYMBOL(is_nvdimm_bus_locked);

u64 nd_fletcher64(void *addr, size_t len, bool le)
{
	u32 *buf = addr;
	u32 lo32 = 0;
	u64 hi32 = 0;
	int i;

	for (i = 0; i < len / sizeof(u32); i++) {
		lo32 += le ? le32_to_cpu((__le32) buf[i]) : buf[i];
		hi32 += lo32;
	}

	return hi32 << 32 | lo32;
}
EXPORT_SYMBOL_GPL(nd_fletcher64);

static void nvdimm_bus_release(struct device *dev)
{
	struct nvdimm_bus *nvdimm_bus;

	nvdimm_bus = container_of(dev, struct nvdimm_bus, dev);
	ida_simple_remove(&nd_ida, nvdimm_bus->id);
	kfree(nvdimm_bus);
}

struct nvdimm_bus *to_nvdimm_bus(struct device *dev)
{
	struct nvdimm_bus *nvdimm_bus;

	nvdimm_bus = container_of(dev, struct nvdimm_bus, dev);
	WARN_ON(nvdimm_bus->dev.release != nvdimm_bus_release);
	return nvdimm_bus;
}
EXPORT_SYMBOL_GPL(to_nvdimm_bus);

struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus)
{
	/* struct nvdimm_bus definition is private to libnvdimm */
	return nvdimm_bus->nd_desc;
}
EXPORT_SYMBOL_GPL(to_nd_desc);

struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev)
{
	struct device *dev;

	for (dev = nd_dev; dev; dev = dev->parent)
		if (dev->release == nvdimm_bus_release)
			break;
	dev_WARN_ONCE(nd_dev, !dev, "invalid dev, not on nd bus\n");
	if (dev)
		return to_nvdimm_bus(dev);
	return NULL;
}

static bool is_uuid_sep(char sep)
{
	if (sep == '\n' || sep == '-' || sep == ':' || sep == '\0')
		return true;
	return false;
}

static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf,
		size_t len)
{
	const char *str = buf;
	u8 uuid[16];
	int i;

	for (i = 0; i < 16; i++) {
		if (!isxdigit(str[0]) || !isxdigit(str[1])) {
			dev_dbg(dev, "%s: pos: %d buf[%zd]: %c buf[%zd]: %c\n",
					__func__, i, str - buf, str[0],
					str + 1 - buf, str[1]);
			return -EINVAL;
		}

		uuid[i] = (hex_to_bin(str[0]) << 4) | hex_to_bin(str[1]);
		str += 2;
		if (is_uuid_sep(*str))
			str++;
	}

	memcpy(uuid_out, uuid, sizeof(uuid));
	return 0;
}

/**
 * nd_uuid_store: common implementation for writing 'uuid' sysfs attributes
 * @dev: container device for the uuid property
 * @uuid_out: uuid buffer to replace
 * @buf: raw sysfs buffer to parse
 *
 * Enforce that uuids can only be changed while the device is disabled
 * (driver detached)
 * LOCKING: expects device_lock() is held on entry
 */
int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
		size_t len)
{
	u8 uuid[16];
	int rc;

	if (dev->driver)
		return -EBUSY;

	rc = nd_uuid_parse(dev, uuid, buf, len);
	if (rc)
		return rc;

	kfree(*uuid_out);
	*uuid_out = kmemdup(uuid, sizeof(uuid), GFP_KERNEL);
	if (!(*uuid_out))
		return -ENOMEM;

	return 0;
}

ssize_t nd_sector_size_show(unsigned long current_lbasize,
		const unsigned long *supported, char *buf)
{
	ssize_t len = 0;
	int i;

	for (i = 0; supported[i]; i++)
		if (current_lbasize == supported[i])
			len += sprintf(buf + len, "[%ld] ", supported[i]);
		else
			len += sprintf(buf + len, "%ld ", supported[i]);
	len += sprintf(buf + len, "\n");
	return len;
}

ssize_t nd_sector_size_store(struct device *dev, const char *buf,
		unsigned long *current_lbasize, const unsigned long *supported)
{
	unsigned long lbasize;
	int rc, i;

	if (dev->driver)
		return -EBUSY;

	rc = kstrtoul(buf, 0, &lbasize);
	if (rc)
		return rc;

	for (i = 0; supported[i]; i++)
		if (lbasize == supported[i])
			break;

	if (supported[i]) {
		*current_lbasize = lbasize;
		return 0;
	} else {
		return -EINVAL;
	}
}

void __nd_iostat_start(struct bio *bio, unsigned long *start)
{
	struct gendisk *disk = bio->bi_bdev->bd_disk;
	const int rw = bio_data_dir(bio);
	int cpu = part_stat_lock();

	*start = jiffies;
	part_round_stats(cpu, &disk->part0);
	part_stat_inc(cpu, &disk->part0, ios[rw]);
	part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio));
	part_inc_in_flight(&disk->part0, rw);
	part_stat_unlock();
}
EXPORT_SYMBOL(__nd_iostat_start);

void nd_iostat_end(struct bio *bio, unsigned long start)
{
	struct gendisk *disk = bio->bi_bdev->bd_disk;
	unsigned long duration = jiffies - start;
	const int rw = bio_data_dir(bio);
	int cpu = part_stat_lock();

	part_stat_add(cpu, &disk->part0, ticks[rw], duration);
	part_round_stats(cpu, &disk->part0);
	part_dec_in_flight(&disk->part0, rw);
	part_stat_unlock();
}
EXPORT_SYMBOL(nd_iostat_end);

static ssize_t commands_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	int cmd, len = 0;
	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;

	for_each_set_bit(cmd, &nd_desc->cmd_mask, BITS_PER_LONG)
		len += sprintf(buf + len, "%s ", nvdimm_bus_cmd_name(cmd));
	len += sprintf(buf + len, "\n");
	return len;
}
static DEVICE_ATTR_RO(commands);

static const char *nvdimm_bus_provider(struct nvdimm_bus *nvdimm_bus)
{
	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
	struct device *parent = nvdimm_bus->dev.parent;

	if (nd_desc->provider_name)
		return nd_desc->provider_name;
	else if (parent)
		return dev_name(parent);
	else
		return "unknown";
}

static ssize_t provider_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);

	return sprintf(buf, "%s\n", nvdimm_bus_provider(nvdimm_bus));
}
static DEVICE_ATTR_RO(provider);

static int flush_namespaces(struct device *dev, void *data)
{
	device_lock(dev);
	device_unlock(dev);
	return 0;
}

static int flush_regions_dimms(struct device *dev, void *data)
{
	device_lock(dev);
	device_unlock(dev);
	device_for_each_child(dev, NULL, flush_namespaces);
	return 0;
}

static ssize_t wait_probe_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
	int rc;

	if (nd_desc->flush_probe) {
		rc = nd_desc->flush_probe(nd_desc);
		if (rc)
			return rc;
	}
	nd_synchronize();
	device_for_each_child(dev, NULL, flush_regions_dimms);
	return sprintf(buf, "1\n");
}
static DEVICE_ATTR_RO(wait_probe);

static struct attribute *nvdimm_bus_attributes[] = {
	&dev_attr_commands.attr,
	&dev_attr_wait_probe.attr,
	&dev_attr_provider.attr,
	NULL,
};

struct attribute_group nvdimm_bus_attribute_group = {
	.attrs = nvdimm_bus_attributes,
};
EXPORT_SYMBOL_GPL(nvdimm_bus_attribute_group);

struct nvdimm_bus *__nvdimm_bus_register(struct device *parent,
		struct nvdimm_bus_descriptor *nd_desc, struct module *module)
{
	struct nvdimm_bus *nvdimm_bus;
	int rc;

	nvdimm_bus = kzalloc(sizeof(*nvdimm_bus), GFP_KERNEL);
	if (!nvdimm_bus)
		return NULL;
	INIT_LIST_HEAD(&nvdimm_bus->list);
	INIT_LIST_HEAD(&nvdimm_bus->poison_list);
	init_waitqueue_head(&nvdimm_bus->probe_wait);
	nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
	mutex_init(&nvdimm_bus->reconfig_mutex);
	if (nvdimm_bus->id < 0) {
		kfree(nvdimm_bus);
		return NULL;
	}
	nvdimm_bus->nd_desc = nd_desc;
	nvdimm_bus->module = module;
	nvdimm_bus->dev.parent = parent;
	nvdimm_bus->dev.release = nvdimm_bus_release;
	nvdimm_bus->dev.groups = nd_desc->attr_groups;
	dev_set_name(&nvdimm_bus->dev, "ndbus%d", nvdimm_bus->id);
	rc = device_register(&nvdimm_bus->dev);
	if (rc) {
		dev_dbg(&nvdimm_bus->dev, "registration failed: %d\n", rc);
		goto err;
	}

	rc = nvdimm_bus_create_ndctl(nvdimm_bus);
	if (rc)
		goto err;

	mutex_lock(&nvdimm_bus_list_mutex);
	list_add_tail(&nvdimm_bus->list, &nvdimm_bus_list);
	mutex_unlock(&nvdimm_bus_list_mutex);

	return nvdimm_bus;
 err:
	put_device(&nvdimm_bus->dev);
	return NULL;
}
EXPORT_SYMBOL_GPL(__nvdimm_bus_register);

static void set_badblock(struct badblocks *bb, sector_t s, int num)
{
	dev_dbg(bb->dev, "Found a poison range (0x%llx, 0x%llx)\n",
			(u64) s * 512, (u64) num * 512);
	/* this isn't an error as the hardware will still throw an exception */
	if (badblocks_set(bb, s, num, 1))
		dev_info_once(bb->dev, "%s: failed for sector %llx\n",
				__func__, (u64) s);
}

/**
 * __add_badblock_range() - Convert a physical address range to bad sectors
 * @bb:		badblocks instance to populate
 * @ns_offset:	namespace offset where the error range begins (in bytes)
 * @len:	number of bytes of poison to be added
 *
 * This assumes that the range provided with (ns_offset, len) is within
 * the bounds of physical addresses for this namespace, i.e. lies in the
 * interval [ns_start, ns_start + ns_size)
 */
static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
{
	const unsigned int sector_size = 512;
	sector_t start_sector;
	u64 num_sectors;
	u32 rem;

	start_sector = div_u64(ns_offset, sector_size);
	num_sectors = div_u64_rem(len, sector_size, &rem);
	if (rem)
		num_sectors++;

	if (unlikely(num_sectors > (u64)INT_MAX)) {
		u64 remaining = num_sectors;
		sector_t s = start_sector;

		while (remaining) {
			int done = min_t(u64, remaining, INT_MAX);

			set_badblock(bb, s, done);
			remaining -= done;
			s += done;
		}
	} else
		set_badblock(bb, start_sector, num_sectors);
}

static void badblocks_populate(struct list_head *poison_list,
		struct badblocks *bb, const struct resource *res)
{
	struct nd_poison *pl;

	if (list_empty(poison_list))
		return;

	list_for_each_entry(pl, poison_list, list) {
		u64 pl_end = pl->start + pl->length - 1;

		/* Discard intervals with no intersection */
		if (pl_end < res->start)
			continue;
		if (pl->start >  res->end)
			continue;
		/* Deal with any overlap after start of the namespace */
		if (pl->start >= res->start) {
			u64 start = pl->start;
			u64 len;

			if (pl_end <= res->end)
				len = pl->length;
			else
				len = res->start + resource_size(res)
					- pl->start;
			__add_badblock_range(bb, start - res->start, len);
			continue;
		}
		/* Deal with overlap for poison starting before the namespace */
		if (pl->start < res->start) {
			u64 len;

			if (pl_end < res->end)
				len = pl->start + pl->length - res->start;
			else
				len = resource_size(res);
			__add_badblock_range(bb, 0, len);
		}
	}
}

/**
 * nvdimm_badblocks_populate() - Convert a list of poison ranges to badblocks
 * @region: parent region of the range to interrogate
 * @bb: badblocks instance to populate
 * @res: resource range to consider
 *
 * The poison list generated during bus initialization may contain
 * multiple, possibly overlapping physical address ranges.  Compare each
 * of these ranges to the resource range currently being initialized,
 * and add badblocks entries for all matching sub-ranges
 */
void nvdimm_badblocks_populate(struct nd_region *nd_region,
		struct badblocks *bb, const struct resource *res)
{
	struct nvdimm_bus *nvdimm_bus;
	struct list_head *poison_list;

	if (!is_nd_pmem(&nd_region->dev)) {
		dev_WARN_ONCE(&nd_region->dev, 1,
				"%s only valid for pmem regions\n", __func__);
		return;
	}
	nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
	poison_list = &nvdimm_bus->poison_list;

	nvdimm_bus_lock(&nvdimm_bus->dev);
	badblocks_populate(poison_list, bb, res);
	nvdimm_bus_unlock(&nvdimm_bus->dev);
}
EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);

static int add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
{
	struct nd_poison *pl;

	pl = kzalloc(sizeof(*pl), GFP_KERNEL);
	if (!pl)
		return -ENOMEM;

	pl->start = addr;
	pl->length = length;
	list_add_tail(&pl->list, &nvdimm_bus->poison_list);

	return 0;
}

static int bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
{
	struct nd_poison *pl;

	if (list_empty(&nvdimm_bus->poison_list))
		return add_poison(nvdimm_bus, addr, length);

	/*
	 * There is a chance this is a duplicate, check for those first.
	 * This will be the common case as ARS_STATUS returns all known
	 * errors in the SPA space, and we can't query it per region
	 */
	list_for_each_entry(pl, &nvdimm_bus->poison_list, list)
		if (pl->start == addr) {
			/* If length has changed, update this list entry */
			if (pl->length != length)
				pl->length = length;
			return 0;
		}

	/*
	 * If not a duplicate or a simple length update, add the entry as is,
	 * as any overlapping ranges will get resolved when the list is consumed
	 * and converted to badblocks
	 */
	return add_poison(nvdimm_bus, addr, length);
}

int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
{
	int rc;

	nvdimm_bus_lock(&nvdimm_bus->dev);
	rc = bus_add_poison(nvdimm_bus, addr, length);
	nvdimm_bus_unlock(&nvdimm_bus->dev);

	return rc;
}
EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison);

static void free_poison_list(struct list_head *poison_list)
{
	struct nd_poison *pl, *next;

	list_for_each_entry_safe(pl, next, poison_list, list) {
		list_del(&pl->list);
		kfree(pl);
	}
	list_del_init(poison_list);
}

static int child_unregister(struct device *dev, void *data)
{
	/*
	 * the singular ndctl class device per bus needs to be
	 * "device_destroy"ed, so skip it here
	 *
	 * i.e. remove classless children
	 */
	if (dev->class)
		/* pass */;
	else
		nd_device_unregister(dev, ND_SYNC);
	return 0;
}

void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
{
	if (!nvdimm_bus)
		return;

	mutex_lock(&nvdimm_bus_list_mutex);
	list_del_init(&nvdimm_bus->list);
	mutex_unlock(&nvdimm_bus_list_mutex);

	nd_synchronize();
	device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);

	nvdimm_bus_lock(&nvdimm_bus->dev);
	free_poison_list(&nvdimm_bus->poison_list);
	nvdimm_bus_unlock(&nvdimm_bus->dev);

	nvdimm_bus_destroy_ndctl(nvdimm_bus);

	device_unregister(&nvdimm_bus->dev);
}
EXPORT_SYMBOL_GPL(nvdimm_bus_unregister);

#ifdef CONFIG_BLK_DEV_INTEGRITY
int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
{
	struct blk_integrity bi;

	if (meta_size == 0)
		return 0;

	bi.profile = NULL;
	bi.tuple_size = meta_size;
	bi.tag_size = meta_size;

	blk_integrity_register(disk, &bi);
	blk_queue_max_integrity_segments(disk->queue, 1);

	return 0;
}
EXPORT_SYMBOL(nd_integrity_init);

#else /* CONFIG_BLK_DEV_INTEGRITY */
int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
{
	return 0;
}
EXPORT_SYMBOL(nd_integrity_init);

#endif

static __init int libnvdimm_init(void)
{
	int rc;

	rc = nvdimm_bus_init();
	if (rc)
		return rc;
	rc = nvdimm_init();
	if (rc)
		goto err_dimm;
	rc = nd_region_init();
	if (rc)
		goto err_region;
	return 0;
 err_region:
	nvdimm_exit();
 err_dimm:
	nvdimm_bus_exit();
	return rc;
}

static __exit void libnvdimm_exit(void)
{
	WARN_ON(!list_empty(&nvdimm_bus_list));
	nd_region_exit();
	nvdimm_exit();
	nvdimm_bus_exit();
	nd_region_devs_exit();
	nvdimm_devs_exit();
	ida_destroy(&nd_ida);
}

MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Intel Corporation");
subsys_initcall(libnvdimm_init);
module_exit(libnvdimm_exit);
OpenPOWER on IntegriCloud