summaryrefslogtreecommitdiffstats
path: root/drivers/nvdimm/pfn_devs.c
blob: ce9ef18282dd0491a21a273e5bd20fe5967bf04f (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
 */
#include <linux/memremap.h>
#include <linux/blkdev.h>
#include <linux/device.h>
#include <linux/genhd.h>
#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include "nd-core.h"
#include "pfn.h"
#include "nd.h"

static void nd_pfn_release(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);
	struct nd_pfn *nd_pfn = to_nd_pfn(dev);

	dev_dbg(dev, "trace\n");
	nd_detach_ndns(&nd_pfn->dev, &nd_pfn->ndns);
	ida_simple_remove(&nd_region->pfn_ida, nd_pfn->id);
	kfree(nd_pfn->uuid);
	kfree(nd_pfn);
}

static struct device_type nd_pfn_device_type = {
	.name = "nd_pfn",
	.release = nd_pfn_release,
};

bool is_nd_pfn(struct device *dev)
{
	return dev ? dev->type == &nd_pfn_device_type : false;
}
EXPORT_SYMBOL(is_nd_pfn);

struct nd_pfn *to_nd_pfn(struct device *dev)
{
	struct nd_pfn *nd_pfn = container_of(dev, struct nd_pfn, dev);

	WARN_ON(!is_nd_pfn(dev));
	return nd_pfn;
}
EXPORT_SYMBOL(to_nd_pfn);

static ssize_t mode_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);

	switch (nd_pfn->mode) {
	case PFN_MODE_RAM:
		return sprintf(buf, "ram\n");
	case PFN_MODE_PMEM:
		return sprintf(buf, "pmem\n");
	default:
		return sprintf(buf, "none\n");
	}
}

static ssize_t mode_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
	ssize_t rc = 0;

	nd_device_lock(dev);
	nvdimm_bus_lock(dev);
	if (dev->driver)
		rc = -EBUSY;
	else {
		size_t n = len - 1;

		if (strncmp(buf, "pmem\n", n) == 0
				|| strncmp(buf, "pmem", n) == 0) {
			nd_pfn->mode = PFN_MODE_PMEM;
		} else if (strncmp(buf, "ram\n", n) == 0
				|| strncmp(buf, "ram", n) == 0)
			nd_pfn->mode = PFN_MODE_RAM;
		else if (strncmp(buf, "none\n", n) == 0
				|| strncmp(buf, "none", n) == 0)
			nd_pfn->mode = PFN_MODE_NONE;
		else
			rc = -EINVAL;
	}
	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
			buf[len - 1] == '\n' ? "" : "\n");
	nvdimm_bus_unlock(dev);
	nd_device_unlock(dev);

	return rc ? rc : len;
}
static DEVICE_ATTR_RW(mode);

static ssize_t align_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);

	return sprintf(buf, "%ld\n", nd_pfn->align);
}

static const unsigned long *nd_pfn_supported_alignments(void)
{
	/*
	 * This needs to be a non-static variable because the *_SIZE
	 * macros aren't always constants.
	 */
	const unsigned long supported_alignments[] = {
		PAGE_SIZE,
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
		HPAGE_PMD_SIZE,
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
		HPAGE_PUD_SIZE,
#endif
#endif
		0,
	};
	static unsigned long data[ARRAY_SIZE(supported_alignments)];

	memcpy(data, supported_alignments, sizeof(data));

	return data;
}

static ssize_t align_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
	ssize_t rc;

	nd_device_lock(dev);
	nvdimm_bus_lock(dev);
	rc = nd_size_select_store(dev, buf, &nd_pfn->align,
			nd_pfn_supported_alignments());
	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
			buf[len - 1] == '\n' ? "" : "\n");
	nvdimm_bus_unlock(dev);
	nd_device_unlock(dev);

	return rc ? rc : len;
}
static DEVICE_ATTR_RW(align);

static ssize_t uuid_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);

	if (nd_pfn->uuid)
		return sprintf(buf, "%pUb\n", nd_pfn->uuid);
	return sprintf(buf, "\n");
}

static ssize_t uuid_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
	ssize_t rc;

	nd_device_lock(dev);
	rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len);
	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
			buf[len - 1] == '\n' ? "" : "\n");
	nd_device_unlock(dev);

	return rc ? rc : len;
}
static DEVICE_ATTR_RW(uuid);

static ssize_t namespace_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	rc = sprintf(buf, "%s\n", nd_pfn->ndns
			? dev_name(&nd_pfn->ndns->dev) : "");
	nvdimm_bus_unlock(dev);
	return rc;
}

static ssize_t namespace_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
	ssize_t rc;

	nd_device_lock(dev);
	nvdimm_bus_lock(dev);
	rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
			buf[len - 1] == '\n' ? "" : "\n");
	nvdimm_bus_unlock(dev);
	nd_device_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RW(namespace);

static ssize_t resource_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
	ssize_t rc;

	nd_device_lock(dev);
	if (dev->driver) {
		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
		u64 offset = __le64_to_cpu(pfn_sb->dataoff);
		struct nd_namespace_common *ndns = nd_pfn->ndns;
		u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
		struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);

		rc = sprintf(buf, "%#llx\n", (unsigned long long) nsio->res.start
				+ start_pad + offset);
	} else {
		/* no address to convey if the pfn instance is disabled */
		rc = -ENXIO;
	}
	nd_device_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(resource);

static ssize_t size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
	ssize_t rc;

	nd_device_lock(dev);
	if (dev->driver) {
		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
		u64 offset = __le64_to_cpu(pfn_sb->dataoff);
		struct nd_namespace_common *ndns = nd_pfn->ndns;
		u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
		u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
		struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);

		rc = sprintf(buf, "%llu\n", (unsigned long long)
				resource_size(&nsio->res) - start_pad
				- end_trunc - offset);
	} else {
		/* no size to convey if the pfn instance is disabled */
		rc = -ENXIO;
	}
	nd_device_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(size);

static ssize_t supported_alignments_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	return nd_size_select_show(0, nd_pfn_supported_alignments(), buf);
}
static DEVICE_ATTR_RO(supported_alignments);

static struct attribute *nd_pfn_attributes[] = {
	&dev_attr_mode.attr,
	&dev_attr_namespace.attr,
	&dev_attr_uuid.attr,
	&dev_attr_align.attr,
	&dev_attr_resource.attr,
	&dev_attr_size.attr,
	&dev_attr_supported_alignments.attr,
	NULL,
};

static umode_t pfn_visible(struct kobject *kobj, struct attribute *a, int n)
{
	if (a == &dev_attr_resource.attr)
		return 0400;
	return a->mode;
}

struct attribute_group nd_pfn_attribute_group = {
	.attrs = nd_pfn_attributes,
	.is_visible = pfn_visible,
};

static const struct attribute_group *nd_pfn_attribute_groups[] = {
	&nd_pfn_attribute_group,
	&nd_device_attribute_group,
	&nd_numa_attribute_group,
	NULL,
};

struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
		struct nd_namespace_common *ndns)
{
	struct device *dev;

	if (!nd_pfn)
		return NULL;

	nd_pfn->mode = PFN_MODE_NONE;
	nd_pfn->align = PFN_DEFAULT_ALIGNMENT;
	dev = &nd_pfn->dev;
	device_initialize(&nd_pfn->dev);
	if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
		dev_dbg(&ndns->dev, "failed, already claimed by %s\n",
				dev_name(ndns->claim));
		put_device(dev);
		return NULL;
	}
	return dev;
}

static struct nd_pfn *nd_pfn_alloc(struct nd_region *nd_region)
{
	struct nd_pfn *nd_pfn;
	struct device *dev;

	nd_pfn = kzalloc(sizeof(*nd_pfn), GFP_KERNEL);
	if (!nd_pfn)
		return NULL;

	nd_pfn->id = ida_simple_get(&nd_region->pfn_ida, 0, 0, GFP_KERNEL);
	if (nd_pfn->id < 0) {
		kfree(nd_pfn);
		return NULL;
	}

	dev = &nd_pfn->dev;
	dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id);
	dev->groups = nd_pfn_attribute_groups;
	dev->type = &nd_pfn_device_type;
	dev->parent = &nd_region->dev;

	return nd_pfn;
}

struct device *nd_pfn_create(struct nd_region *nd_region)
{
	struct nd_pfn *nd_pfn;
	struct device *dev;

	if (!is_memory(&nd_region->dev))
		return NULL;

	nd_pfn = nd_pfn_alloc(nd_region);
	dev = nd_pfn_devinit(nd_pfn, NULL);

	__nd_device_register(dev);
	return dev;
}

/*
 * nd_pfn_clear_memmap_errors() clears any errors in the volatile memmap
 * space associated with the namespace. If the memmap is set to DRAM, then
 * this is a no-op. Since the memmap area is freshly initialized during
 * probe, we have an opportunity to clear any badblocks in this area.
 */
static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn)
{
	struct nd_region *nd_region = to_nd_region(nd_pfn->dev.parent);
	struct nd_namespace_common *ndns = nd_pfn->ndns;
	void *zero_page = page_address(ZERO_PAGE(0));
	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
	int num_bad, meta_num, rc, bb_present;
	sector_t first_bad, meta_start;
	struct nd_namespace_io *nsio;

	if (nd_pfn->mode != PFN_MODE_PMEM)
		return 0;

	nsio = to_nd_namespace_io(&ndns->dev);
	meta_start = (SZ_4K + sizeof(*pfn_sb)) >> 9;
	meta_num = (le64_to_cpu(pfn_sb->dataoff) >> 9) - meta_start;

	do {
		unsigned long zero_len;
		u64 nsoff;

		bb_present = badblocks_check(&nd_region->bb, meta_start,
				meta_num, &first_bad, &num_bad);
		if (bb_present) {
			dev_dbg(&nd_pfn->dev, "meta: %x badblocks at %llx\n",
					num_bad, first_bad);
			nsoff = ALIGN_DOWN((nd_region->ndr_start
					+ (first_bad << 9)) - nsio->res.start,
					PAGE_SIZE);
			zero_len = ALIGN(num_bad << 9, PAGE_SIZE);
			while (zero_len) {
				unsigned long chunk = min(zero_len, PAGE_SIZE);

				rc = nvdimm_write_bytes(ndns, nsoff, zero_page,
							chunk, 0);
				if (rc)
					break;

				zero_len -= chunk;
				nsoff += chunk;
			}
			if (rc) {
				dev_err(&nd_pfn->dev,
					"error clearing %x badblocks at %llx\n",
					num_bad, first_bad);
				return rc;
			}
		}
	} while (bb_present);

	return 0;
}

/**
 * nd_pfn_validate - read and validate info-block
 * @nd_pfn: fsdax namespace runtime state / properties
 * @sig: 'devdax' or 'fsdax' signature
 *
 * Upon return the info-block buffer contents (->pfn_sb) are
 * indeterminate when validation fails, and a coherent info-block
 * otherwise.
 */
int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
{
	u64 checksum, offset;
	enum nd_pfn_mode mode;
	struct nd_namespace_io *nsio;
	unsigned long align, start_pad;
	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
	struct nd_namespace_common *ndns = nd_pfn->ndns;
	const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev);

	if (!pfn_sb || !ndns)
		return -ENODEV;

	if (!is_memory(nd_pfn->dev.parent))
		return -ENODEV;

	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0))
		return -ENXIO;

	if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
		return -ENODEV;

	checksum = le64_to_cpu(pfn_sb->checksum);
	pfn_sb->checksum = 0;
	if (checksum != nd_sb_checksum((struct nd_gen_sb *) pfn_sb))
		return -ENODEV;
	pfn_sb->checksum = cpu_to_le64(checksum);

	if (memcmp(pfn_sb->parent_uuid, parent_uuid, 16) != 0)
		return -ENODEV;

	if (__le16_to_cpu(pfn_sb->version_minor) < 1) {
		pfn_sb->start_pad = 0;
		pfn_sb->end_trunc = 0;
	}

	if (__le16_to_cpu(pfn_sb->version_minor) < 2)
		pfn_sb->align = 0;

	if (__le16_to_cpu(pfn_sb->version_minor) < 4) {
		pfn_sb->page_struct_size = cpu_to_le16(64);
		pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
	}

	switch (le32_to_cpu(pfn_sb->mode)) {
	case PFN_MODE_RAM:
	case PFN_MODE_PMEM:
		break;
	default:
		return -ENXIO;
	}

	align = le32_to_cpu(pfn_sb->align);
	offset = le64_to_cpu(pfn_sb->dataoff);
	start_pad = le32_to_cpu(pfn_sb->start_pad);
	if (align == 0)
		align = 1UL << ilog2(offset);
	mode = le32_to_cpu(pfn_sb->mode);

	if ((le32_to_cpu(pfn_sb->page_size) > PAGE_SIZE) &&
			(mode == PFN_MODE_PMEM)) {
		dev_err(&nd_pfn->dev,
				"init failed, page size mismatch %d\n",
				le32_to_cpu(pfn_sb->page_size));
		return -EOPNOTSUPP;
	}

	if ((le16_to_cpu(pfn_sb->page_struct_size) < sizeof(struct page)) &&
			(mode == PFN_MODE_PMEM)) {
		dev_err(&nd_pfn->dev,
				"init failed, struct page size mismatch %d\n",
				le16_to_cpu(pfn_sb->page_struct_size));
		return -EOPNOTSUPP;
	}

	if (!nd_pfn->uuid) {
		/*
		 * When probing a namepace via nd_pfn_probe() the uuid
		 * is NULL (see: nd_pfn_devinit()) we init settings from
		 * pfn_sb
		 */
		nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
		if (!nd_pfn->uuid)
			return -ENOMEM;
		nd_pfn->align = align;
		nd_pfn->mode = mode;
	} else {
		/*
		 * When probing a pfn / dax instance we validate the
		 * live settings against the pfn_sb
		 */
		if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
			return -ENODEV;

		/*
		 * If the uuid validates, but other settings mismatch
		 * return EINVAL because userspace has managed to change
		 * the configuration without specifying new
		 * identification.
		 */
		if (nd_pfn->align != align || nd_pfn->mode != mode) {
			dev_err(&nd_pfn->dev,
					"init failed, settings mismatch\n");
			dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
					nd_pfn->align, align, nd_pfn->mode,
					mode);
			return -EINVAL;
		}
	}

	if (align > nvdimm_namespace_capacity(ndns)) {
		dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
				align, nvdimm_namespace_capacity(ndns));
		return -EINVAL;
	}

	/*
	 * These warnings are verbose because they can only trigger in
	 * the case where the physical address alignment of the
	 * namespace has changed since the pfn superblock was
	 * established.
	 */
	nsio = to_nd_namespace_io(&ndns->dev);
	if (offset >= resource_size(&nsio->res)) {
		dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
				dev_name(&ndns->dev));
		return -EBUSY;
	}

	if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align))
			|| !IS_ALIGNED(offset, PAGE_SIZE)) {
		dev_err(&nd_pfn->dev,
				"bad offset: %#llx dax disabled align: %#lx\n",
				offset, align);
		return -ENXIO;
	}

	return nd_pfn_clear_memmap_errors(nd_pfn);
}
EXPORT_SYMBOL(nd_pfn_validate);

int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns)
{
	int rc;
	struct nd_pfn *nd_pfn;
	struct device *pfn_dev;
	struct nd_pfn_sb *pfn_sb;
	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);

	if (ndns->force_raw)
		return -ENODEV;

	switch (ndns->claim_class) {
	case NVDIMM_CCLASS_NONE:
	case NVDIMM_CCLASS_PFN:
		break;
	default:
		return -ENODEV;
	}

	nvdimm_bus_lock(&ndns->dev);
	nd_pfn = nd_pfn_alloc(nd_region);
	pfn_dev = nd_pfn_devinit(nd_pfn, ndns);
	nvdimm_bus_unlock(&ndns->dev);
	if (!pfn_dev)
		return -ENOMEM;
	pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
	nd_pfn = to_nd_pfn(pfn_dev);
	nd_pfn->pfn_sb = pfn_sb;
	rc = nd_pfn_validate(nd_pfn, PFN_SIG);
	dev_dbg(dev, "pfn: %s\n", rc == 0 ? dev_name(pfn_dev) : "<none>");
	if (rc < 0) {
		nd_detach_ndns(pfn_dev, &nd_pfn->ndns);
		put_device(pfn_dev);
	} else
		__nd_device_register(pfn_dev);

	return rc;
}
EXPORT_SYMBOL(nd_pfn_probe);

static u32 info_block_reserve(void)
{
	return ALIGN(SZ_8K, PAGE_SIZE);
}

/*
 * We hotplug memory at sub-section granularity, pad the reserved area
 * from the previous section base to the namespace base address.
 */
static unsigned long init_altmap_base(resource_size_t base)
{
	unsigned long base_pfn = PHYS_PFN(base);

	return SUBSECTION_ALIGN_DOWN(base_pfn);
}

static unsigned long init_altmap_reserve(resource_size_t base)
{
	unsigned long reserve = info_block_reserve() >> PAGE_SHIFT;
	unsigned long base_pfn = PHYS_PFN(base);

	reserve += base_pfn - SUBSECTION_ALIGN_DOWN(base_pfn);
	return reserve;
}

static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
{
	struct resource *res = &pgmap->res;
	struct vmem_altmap *altmap = &pgmap->altmap;
	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
	u64 offset = le64_to_cpu(pfn_sb->dataoff);
	u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
	u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
	u32 reserve = info_block_reserve();
	struct nd_namespace_common *ndns = nd_pfn->ndns;
	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
	resource_size_t base = nsio->res.start + start_pad;
	struct vmem_altmap __altmap = {
		.base_pfn = init_altmap_base(base),
		.reserve = init_altmap_reserve(base),
	};

	memcpy(res, &nsio->res, sizeof(*res));
	res->start += start_pad;
	res->end -= end_trunc;

	if (nd_pfn->mode == PFN_MODE_RAM) {
		if (offset < reserve)
			return -EINVAL;
		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
		nd_pfn->npfns = PHYS_PFN((resource_size(res) - offset));
		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
			dev_info(&nd_pfn->dev,
					"number of pfns truncated from %lld to %ld\n",
					le64_to_cpu(nd_pfn->pfn_sb->npfns),
					nd_pfn->npfns);
		memcpy(altmap, &__altmap, sizeof(*altmap));
		altmap->free = PHYS_PFN(offset - reserve);
		altmap->alloc = 0;
		pgmap->flags |= PGMAP_ALTMAP_VALID;
	} else
		return -ENXIO;

	return 0;
}

static int nd_pfn_init(struct nd_pfn *nd_pfn)
{
	struct nd_namespace_common *ndns = nd_pfn->ndns;
	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
	resource_size_t start, size;
	struct nd_region *nd_region;
	unsigned long npfns, align;
	struct nd_pfn_sb *pfn_sb;
	phys_addr_t offset;
	const char *sig;
	u64 checksum;
	int rc;

	pfn_sb = devm_kmalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
	if (!pfn_sb)
		return -ENOMEM;

	nd_pfn->pfn_sb = pfn_sb;
	if (is_nd_dax(&nd_pfn->dev))
		sig = DAX_SIG;
	else
		sig = PFN_SIG;

	rc = nd_pfn_validate(nd_pfn, sig);
	if (rc != -ENODEV)
		return rc;

	/* no info block, do init */;
	memset(pfn_sb, 0, sizeof(*pfn_sb));

	nd_region = to_nd_region(nd_pfn->dev.parent);
	if (nd_region->ro) {
		dev_info(&nd_pfn->dev,
				"%s is read-only, unable to init metadata\n",
				dev_name(&nd_region->dev));
		return -ENXIO;
	}

	/*
	 * Note, we use 64 here for the standard size of struct page,
	 * debugging options may cause it to be larger in which case the
	 * implementation will limit the pfns advertised through
	 * ->direct_access() to those that are included in the memmap.
	 */
	start = nsio->res.start;
	size = resource_size(&nsio->res);
	npfns = PHYS_PFN(size - SZ_8K);
	align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT));
	if (nd_pfn->mode == PFN_MODE_PMEM) {
		/*
		 * The altmap should be padded out to the block size used
		 * when populating the vmemmap. This *should* be equal to
		 * PMD_SIZE for most architectures.
		 *
		 * Also make sure size of struct page is less than 64. We
		 * want to make sure we use large enough size here so that
		 * we don't have a dynamic reserve space depending on
		 * struct page size. But we also want to make sure we notice
		 * when we end up adding new elements to struct page.
		 */
		BUILD_BUG_ON(sizeof(struct page) > MAX_STRUCT_PAGE_SIZE);
		offset = ALIGN(start + SZ_8K + MAX_STRUCT_PAGE_SIZE * npfns, align)
			- start;
	} else if (nd_pfn->mode == PFN_MODE_RAM)
		offset = ALIGN(start + SZ_8K, align) - start;
	else
		return -ENXIO;

	if (offset >= size) {
		dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
				dev_name(&ndns->dev));
		return -ENXIO;
	}

	npfns = PHYS_PFN(size - offset);
	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
	pfn_sb->dataoff = cpu_to_le64(offset);
	pfn_sb->npfns = cpu_to_le64(npfns);
	memcpy(pfn_sb->signature, sig, PFN_SIG_LEN);
	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
	pfn_sb->version_major = cpu_to_le16(1);
	pfn_sb->version_minor = cpu_to_le16(4);
	pfn_sb->align = cpu_to_le32(nd_pfn->align);
	pfn_sb->page_struct_size = cpu_to_le16(MAX_STRUCT_PAGE_SIZE);
	pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
	pfn_sb->checksum = cpu_to_le64(checksum);

	return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0);
}

/*
 * Determine the effective resource range and vmem_altmap from an nd_pfn
 * instance.
 */
int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
{
	int rc;

	if (!nd_pfn->uuid || !nd_pfn->ndns)
		return -ENODEV;

	rc = nd_pfn_init(nd_pfn);
	if (rc)
		return rc;

	/* we need a valid pfn_sb before we can init a dev_pagemap */
	return __nvdimm_setup_pfn(nd_pfn, pgmap);
}
EXPORT_SYMBOL_GPL(nvdimm_setup_pfn);