summaryrefslogtreecommitdiff
path: root/drivers/nvdimm/pmem.c
blob: 67d48e2e8ca21a9b9ef917a1e8110f02c11ca3e6 (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
/*
 * Persistent Memory Driver
 *
 * Copyright (c) 2014-2015, Intel Corporation.
 * Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
 * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
 *
 * 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 <asm/cacheflush.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/badblocks.h>
#include <linux/memremap.h>
#include <linux/vmalloc.h>
#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <linux/pmem.h>
#include <linux/nd.h>
#include "pfn.h"
#include "nd.h"

struct pmem_device {
	struct request_queue	*pmem_queue;
	struct gendisk		*pmem_disk;

	/* One contiguous memory region per device */
	phys_addr_t		phys_addr;
	/* when non-zero this device is hosting a 'pfn' instance */
	phys_addr_t		data_offset;
	u64			pfn_flags;
	void __pmem		*virt_addr;
	/* immutable base size of the namespace */
	size_t			size;
	/* trim size when namespace capacity has been section aligned */
	u32			pfn_pad;
	struct badblocks	bb;
};

static bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len)
{
	if (bb->count) {
		sector_t first_bad;
		int num_bad;

		return !!badblocks_check(bb, sector, len / 512, &first_bad,
				&num_bad);
	}

	return false;
}

static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
		unsigned int len)
{
	struct device *dev = disk_to_dev(pmem->pmem_disk);
	sector_t sector;
	long cleared;

	sector = (offset - pmem->data_offset) / 512;
	cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len);

	if (cleared > 0 && cleared / 512) {
		dev_dbg(dev, "%s: %llx clear %ld sector%s\n",
				__func__, (unsigned long long) sector,
				cleared / 512, cleared / 512 > 1 ? "s" : "");
		badblocks_clear(&pmem->bb, sector, cleared / 512);
	}
	invalidate_pmem(pmem->virt_addr + offset, len);
}

static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
			unsigned int len, unsigned int off, int rw,
			sector_t sector)
{
	int rc = 0;
	bool bad_pmem = false;
	void *mem = kmap_atomic(page);
	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
	void __pmem *pmem_addr = pmem->virt_addr + pmem_off;

	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
		bad_pmem = true;

	if (rw == READ) {
		if (unlikely(bad_pmem))
			rc = -EIO;
		else {
			rc = memcpy_from_pmem(mem + off, pmem_addr, len);
			flush_dcache_page(page);
		}
	} else {
		/*
		 * Note that we write the data both before and after
		 * clearing poison.  The write before clear poison
		 * handles situations where the latest written data is
		 * preserved and the clear poison operation simply marks
		 * the address range as valid without changing the data.
		 * In this case application software can assume that an
		 * interrupted write will either return the new good
		 * data or an error.
		 *
		 * However, if pmem_clear_poison() leaves the data in an
		 * indeterminate state we need to perform the write
		 * after clear poison.
		 */
		flush_dcache_page(page);
		memcpy_to_pmem(pmem_addr, mem + off, len);
		if (unlikely(bad_pmem)) {
			pmem_clear_poison(pmem, pmem_off, len);
			memcpy_to_pmem(pmem_addr, mem + off, len);
		}
	}

	kunmap_atomic(mem);
	return rc;
}

static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
{
	int rc = 0;
	bool do_acct;
	unsigned long start;
	struct bio_vec bvec;
	struct bvec_iter iter;
	struct pmem_device *pmem = q->queuedata;

	do_acct = nd_iostat_start(bio, &start);
	bio_for_each_segment(bvec, bio, iter) {
		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
				bvec.bv_offset, bio_data_dir(bio),
				iter.bi_sector);
		if (rc) {
			bio->bi_error = rc;
			break;
		}
	}
	if (do_acct)
		nd_iostat_end(bio, start);

	if (bio_data_dir(bio))
		wmb_pmem();

	bio_endio(bio);
	return BLK_QC_T_NONE;
}

static int pmem_rw_page(struct block_device *bdev, sector_t sector,
		       struct page *page, int rw)
{
	struct pmem_device *pmem = bdev->bd_queue->queuedata;
	int rc;

	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, rw, sector);
	if (rw & WRITE)
		wmb_pmem();

	/*
	 * The ->rw_page interface is subtle and tricky.  The core
	 * retries on any error, so we can only invoke page_endio() in
	 * the successful completion case.  Otherwise, we'll see crashes
	 * caused by double completion.
	 */
	if (rc == 0)
		page_endio(page, rw & WRITE, 0);

	return rc;
}

static long pmem_direct_access(struct block_device *bdev, sector_t sector,
		      void __pmem **kaddr, pfn_t *pfn)
{
	struct pmem_device *pmem = bdev->bd_queue->queuedata;
	resource_size_t offset = sector * 512 + pmem->data_offset;

	*kaddr = pmem->virt_addr + offset;
	*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);

	return pmem->size - pmem->pfn_pad - offset;
}

static const struct block_device_operations pmem_fops = {
	.owner =		THIS_MODULE,
	.rw_page =		pmem_rw_page,
	.direct_access =	pmem_direct_access,
	.revalidate_disk =	nvdimm_revalidate_disk,
};

static void pmem_release_queue(void *q)
{
	blk_cleanup_queue(q);
}

void pmem_release_disk(void *disk)
{
	del_gendisk(disk);
	put_disk(disk);
}

static struct pmem_device *pmem_alloc(struct device *dev,
		struct resource *res, int id)
{
	struct pmem_device *pmem;
	struct request_queue *q;

	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
	if (!pmem)
		return ERR_PTR(-ENOMEM);

	pmem->phys_addr = res->start;
	pmem->size = resource_size(res);
	if (!arch_has_wmb_pmem())
		dev_warn(dev, "unable to guarantee persistence of writes\n");

	if (!devm_request_mem_region(dev, res->start, resource_size(res),
				dev_name(dev))) {
		dev_warn(dev, "could not reserve region %pR\n", res);
		return ERR_PTR(-EBUSY);
	}

	q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev));
	if (!q)
		return ERR_PTR(-ENOMEM);

	pmem->pfn_flags = PFN_DEV;
	if (pmem_should_map_pages(dev)) {
		pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res,
				&q->q_usage_counter, NULL);
		pmem->pfn_flags |= PFN_MAP;
	} else
		pmem->virt_addr = (void __pmem *) devm_memremap(dev,
				pmem->phys_addr, pmem->size,
				ARCH_MEMREMAP_PMEM);

	/*
	 * At release time the queue must be dead before
	 * devm_memremap_pages is unwound
	 */
	if (devm_add_action(dev, pmem_release_queue, q)) {
		blk_cleanup_queue(q);
		return ERR_PTR(-ENOMEM);
	}

	if (IS_ERR(pmem->virt_addr))
		return (void __force *) pmem->virt_addr;

	pmem->pmem_queue = q;
	return pmem;
}

static int pmem_attach_disk(struct device *dev,
		struct nd_namespace_common *ndns, struct pmem_device *pmem)
{
	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
	int nid = dev_to_node(dev);
	struct resource bb_res;
	struct gendisk *disk;

	blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
	blk_queue_physical_block_size(pmem->pmem_queue, PAGE_SIZE);
	blk_queue_max_hw_sectors(pmem->pmem_queue, UINT_MAX);
	blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, pmem->pmem_queue);
	pmem->pmem_queue->queuedata = pmem;

	disk = alloc_disk_node(0, nid);
	if (!disk)
		return -ENOMEM;
	if (devm_add_action(dev, pmem_release_disk, disk)) {
		put_disk(disk);
		return -ENOMEM;
	}

	disk->fops		= &pmem_fops;
	disk->queue		= pmem->pmem_queue;
	disk->flags		= GENHD_FL_EXT_DEVT;
	nvdimm_namespace_disk_name(ndns, disk->disk_name);
	disk->driverfs_dev = dev;
	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
			/ 512);
	pmem->pmem_disk = disk;
	devm_exit_badblocks(dev, &pmem->bb);
	if (devm_init_badblocks(dev, &pmem->bb))
		return -ENOMEM;
	bb_res.start = nsio->res.start + pmem->data_offset;
	bb_res.end = nsio->res.end;
	if (is_nd_pfn(dev)) {
		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;

		bb_res.start += __le32_to_cpu(pfn_sb->start_pad);
		bb_res.end -= __le32_to_cpu(pfn_sb->end_trunc);
	}
	nvdimm_badblocks_populate(to_nd_region(dev->parent), &pmem->bb,
			&bb_res);
	disk->bb = &pmem->bb;
	add_disk(disk);
	revalidate_disk(disk);

	return 0;
}

static int pmem_rw_bytes(struct nd_namespace_common *ndns,
		resource_size_t offset, void *buf, size_t size, int rw)
{
	struct pmem_device *pmem = dev_get_drvdata(ndns->claim);

	if (unlikely(offset + size > pmem->size)) {
		dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
		return -EFAULT;
	}

	if (rw == READ) {
		unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);

		if (unlikely(is_bad_pmem(&pmem->bb, offset / 512, sz_align)))
			return -EIO;
		return memcpy_from_pmem(buf, pmem->virt_addr + offset, size);
	} else {
		memcpy_to_pmem(pmem->virt_addr + offset, buf, size);
		wmb_pmem();
	}

	return 0;
}

static int nd_pfn_init(struct nd_pfn *nd_pfn)
{
	struct pmem_device *pmem = dev_get_drvdata(&nd_pfn->dev);
	struct nd_namespace_common *ndns = nd_pfn->ndns;
	u32 start_pad = 0, end_trunc = 0;
	resource_size_t start, size;
	struct nd_namespace_io *nsio;
	struct nd_region *nd_region;
	struct nd_pfn_sb *pfn_sb;
	unsigned long npfns;
	phys_addr_t offset;
	u64 checksum;
	int rc;

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

	nd_pfn->pfn_sb = pfn_sb;
	rc = nd_pfn_validate(nd_pfn);
	if (rc == -ENODEV)
		/* no info block, do init */;
	else
		return rc;

	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;
	}

	memset(pfn_sb, 0, sizeof(*pfn_sb));

	/*
	 * Check if pmem collides with 'System RAM' when section aligned and
	 * trim it accordingly
	 */
	nsio = to_nd_namespace_io(&ndns->dev);
	start = PHYS_SECTION_ALIGN_DOWN(nsio->res.start);
	size = resource_size(&nsio->res);
	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
				IORES_DESC_NONE) == REGION_MIXED) {

		start = nsio->res.start;
		start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
	}

	start = nsio->res.start;
	size = PHYS_SECTION_ALIGN_UP(start + size) - start;
	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
				IORES_DESC_NONE) == REGION_MIXED) {
		size = resource_size(&nsio->res);
		end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size);
	}

	if (start_pad + end_trunc)
		dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n",
				dev_name(&ndns->dev), start_pad + end_trunc);

	/*
	 * 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 += start_pad;
	npfns = (pmem->size - start_pad - end_trunc - SZ_8K) / SZ_4K;
	if (nd_pfn->mode == PFN_MODE_PMEM)
		offset = ALIGN(start + SZ_8K + 64 * npfns, nd_pfn->align)
			- start;
	else if (nd_pfn->mode == PFN_MODE_RAM)
		offset = ALIGN(start + SZ_8K, nd_pfn->align) - start;
	else
		return -ENXIO;

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

	npfns = (pmem->size - offset - start_pad - end_trunc) / SZ_4K;
	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, PFN_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(1);
	pfn_sb->start_pad = cpu_to_le32(start_pad);
	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
	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));
}

/*
 * We hotplug memory at 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 PFN_SECTION_ALIGN_DOWN(base_pfn);
}

static unsigned long init_altmap_reserve(resource_size_t base)
{
	unsigned long reserve = PHYS_PFN(SZ_8K);
	unsigned long base_pfn = PHYS_PFN(base);

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

static int __nvdimm_namespace_attach_pfn(struct nd_pfn *nd_pfn)
{
	struct resource res;
	struct request_queue *q;
	struct pmem_device *pmem;
	struct vmem_altmap *altmap;
	struct device *dev = &nd_pfn->dev;
	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
	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);
	resource_size_t base = nsio->res.start + start_pad;
	struct vmem_altmap __altmap = {
		.base_pfn = init_altmap_base(base),
		.reserve = init_altmap_reserve(base),
	};

	pmem = dev_get_drvdata(dev);
	pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
	pmem->pfn_pad = start_pad + end_trunc;
	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
	if (nd_pfn->mode == PFN_MODE_RAM) {
		if (pmem->data_offset < SZ_8K)
			return -EINVAL;
		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
		altmap = NULL;
	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
		nd_pfn->npfns = (pmem->size - pmem->pfn_pad - pmem->data_offset)
			/ PAGE_SIZE;
		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);
		altmap = & __altmap;
		altmap->free = PHYS_PFN(pmem->data_offset - SZ_8K);
		altmap->alloc = 0;
	} else
		return -ENXIO;

	/* establish pfn range for lookup, and switch to direct map */
	q = pmem->pmem_queue;
	memcpy(&res, &nsio->res, sizeof(res));
	res.start += start_pad;
	res.end -= end_trunc;
	devm_remove_action(dev, pmem_release_queue, q);
	devm_memunmap(dev, (void __force *) pmem->virt_addr);
	pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &res,
			&q->q_usage_counter, altmap);
	pmem->pfn_flags |= PFN_MAP;

	/*
	 * At release time the queue must be dead before
	 * devm_memremap_pages is unwound
	 */
	if (devm_add_action(dev, pmem_release_queue, q)) {
		blk_cleanup_queue(q);
		return -ENOMEM;
	}
	if (IS_ERR(pmem->virt_addr))
		return PTR_ERR(pmem->virt_addr);

	/* attach pmem disk in "pfn-mode" */
	return pmem_attach_disk(dev, ndns, pmem);
}

static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
{
	struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
	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 vmem_altmap */
	return __nvdimm_namespace_attach_pfn(nd_pfn);
}

static int nd_pmem_probe(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);
	struct nd_namespace_common *ndns;
	struct nd_namespace_io *nsio;
	struct pmem_device *pmem;

	ndns = nvdimm_namespace_common_probe(dev);
	if (IS_ERR(ndns))
		return PTR_ERR(ndns);

	nsio = to_nd_namespace_io(&ndns->dev);
	pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
	if (IS_ERR(pmem))
		return PTR_ERR(pmem);

	dev_set_drvdata(dev, pmem);
	ndns->rw_bytes = pmem_rw_bytes;
	if (devm_init_badblocks(dev, &pmem->bb))
		return -ENOMEM;
	nvdimm_badblocks_populate(nd_region, &pmem->bb, &nsio->res);

	if (is_nd_btt(dev)) {
		/* btt allocates its own request_queue */
		devm_remove_action(dev, pmem_release_queue, pmem->pmem_queue);
		blk_cleanup_queue(pmem->pmem_queue);
		return nvdimm_namespace_attach_btt(ndns);
	}

	if (is_nd_pfn(dev))
		return nvdimm_namespace_attach_pfn(ndns);

	if (nd_btt_probe(dev, ndns, pmem) == 0
			|| nd_pfn_probe(dev, ndns, pmem) == 0) {
		/*
		 * We'll come back as either btt-pmem, or pfn-pmem, so
		 * drop the queue allocation for now.
		 */
		return -ENXIO;
	}

	return pmem_attach_disk(dev, ndns, pmem);
}

static int nd_pmem_remove(struct device *dev)
{
	if (is_nd_btt(dev))
		nvdimm_namespace_detach_btt(to_nd_btt(dev));
	return 0;
}

static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);
	struct pmem_device *pmem = dev_get_drvdata(dev);
	resource_size_t offset = 0, end_trunc = 0;
	struct nd_namespace_common *ndns;
	struct nd_namespace_io *nsio;
	struct resource res;

	if (event != NVDIMM_REVALIDATE_POISON)
		return;

	if (is_nd_btt(dev)) {
		struct nd_btt *nd_btt = to_nd_btt(dev);

		ndns = nd_btt->ndns;
	} else if (is_nd_pfn(dev)) {
		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;

		ndns = nd_pfn->ndns;
		offset = pmem->data_offset + __le32_to_cpu(pfn_sb->start_pad);
		end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
	} else
		ndns = to_ndns(dev);

	nsio = to_nd_namespace_io(&ndns->dev);
	res.start = nsio->res.start + offset;
	res.end = nsio->res.end - end_trunc;
	nvdimm_badblocks_populate(nd_region, &pmem->bb, &res);
}

MODULE_ALIAS("pmem");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
static struct nd_device_driver nd_pmem_driver = {
	.probe = nd_pmem_probe,
	.remove = nd_pmem_remove,
	.notify = nd_pmem_notify,
	.drv = {
		.name = "nd_pmem",
	},
	.type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
};

static int __init pmem_init(void)
{
	return nd_driver_register(&nd_pmem_driver);
}
module_init(pmem_init);

static void pmem_exit(void)
{
	driver_unregister(&nd_pmem_driver.drv);
}
module_exit(pmem_exit);

MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
MODULE_LICENSE("GPL v2");