summaryrefslogtreecommitdiff
path: root/fs/nfs/blocklayout/dev.c
blob: dec5880ac6de28aa393406e931c4a2f70d2a5fda (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2014-2016 Christoph Hellwig.
 */
#include <linux/sunrpc/svc.h>
#include <linux/blkdev.h>
#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_xdr.h>
#include <linux/pr.h>

#include "blocklayout.h"

#define NFSDBG_FACILITY		NFSDBG_PNFS_LD

static void
bl_free_device(struct pnfs_block_dev *dev)
{
	if (dev->nr_children) {
		int i;

		for (i = 0; i < dev->nr_children; i++)
			bl_free_device(&dev->children[i]);
		kfree(dev->children);
	} else {
		if (dev->pr_registered) {
			const struct pr_ops *ops =
				dev->bdev->bd_disk->fops->pr_ops;
			int error;

			error = ops->pr_register(dev->bdev, dev->pr_key, 0,
				false);
			if (error)
				pr_err("failed to unregister PR key.\n");
		}

		if (dev->bdev)
			blkdev_put(dev->bdev, FMODE_READ | FMODE_WRITE);
	}
}

void
bl_free_deviceid_node(struct nfs4_deviceid_node *d)
{
	struct pnfs_block_dev *dev =
		container_of(d, struct pnfs_block_dev, node);

	bl_free_device(dev);
	kfree_rcu(dev, node.rcu);
}

static int
nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
{
	__be32 *p;
	int i;

	p = xdr_inline_decode(xdr, 4);
	if (!p)
		return -EIO;
	b->type = be32_to_cpup(p++);

	switch (b->type) {
	case PNFS_BLOCK_VOLUME_SIMPLE:
		p = xdr_inline_decode(xdr, 4);
		if (!p)
			return -EIO;
		b->simple.nr_sigs = be32_to_cpup(p++);
		if (!b->simple.nr_sigs || b->simple.nr_sigs > PNFS_BLOCK_MAX_UUIDS) {
			dprintk("Bad signature count: %d\n", b->simple.nr_sigs);
			return -EIO;
		}

		b->simple.len = 4 + 4;
		for (i = 0; i < b->simple.nr_sigs; i++) {
			p = xdr_inline_decode(xdr, 8 + 4);
			if (!p)
				return -EIO;
			p = xdr_decode_hyper(p, &b->simple.sigs[i].offset);
			b->simple.sigs[i].sig_len = be32_to_cpup(p++);
			if (b->simple.sigs[i].sig_len > PNFS_BLOCK_UUID_LEN) {
				pr_info("signature too long: %d\n",
					b->simple.sigs[i].sig_len);
				return -EIO;
			}

			p = xdr_inline_decode(xdr, b->simple.sigs[i].sig_len);
			if (!p)
				return -EIO;
			memcpy(&b->simple.sigs[i].sig, p,
				b->simple.sigs[i].sig_len);

			b->simple.len += 8 + 4 + \
				(XDR_QUADLEN(b->simple.sigs[i].sig_len) << 2);
		}
		break;
	case PNFS_BLOCK_VOLUME_SLICE:
		p = xdr_inline_decode(xdr, 8 + 8 + 4);
		if (!p)
			return -EIO;
		p = xdr_decode_hyper(p, &b->slice.start);
		p = xdr_decode_hyper(p, &b->slice.len);
		b->slice.volume = be32_to_cpup(p++);
		break;
	case PNFS_BLOCK_VOLUME_CONCAT:
		p = xdr_inline_decode(xdr, 4);
		if (!p)
			return -EIO;

		b->concat.volumes_count = be32_to_cpup(p++);
		if (b->concat.volumes_count > PNFS_BLOCK_MAX_DEVICES) {
			dprintk("Too many volumes: %d\n", b->concat.volumes_count);
			return -EIO;
		}

		p = xdr_inline_decode(xdr, b->concat.volumes_count * 4);
		if (!p)
			return -EIO;
		for (i = 0; i < b->concat.volumes_count; i++)
			b->concat.volumes[i] = be32_to_cpup(p++);
		break;
	case PNFS_BLOCK_VOLUME_STRIPE:
		p = xdr_inline_decode(xdr, 8 + 4);
		if (!p)
			return -EIO;

		p = xdr_decode_hyper(p, &b->stripe.chunk_size);
		b->stripe.volumes_count = be32_to_cpup(p++);
		if (b->stripe.volumes_count > PNFS_BLOCK_MAX_DEVICES) {
			dprintk("Too many volumes: %d\n", b->stripe.volumes_count);
			return -EIO;
		}

		p = xdr_inline_decode(xdr, b->stripe.volumes_count * 4);
		if (!p)
			return -EIO;
		for (i = 0; i < b->stripe.volumes_count; i++)
			b->stripe.volumes[i] = be32_to_cpup(p++);
		break;
	case PNFS_BLOCK_VOLUME_SCSI:
		p = xdr_inline_decode(xdr, 4 + 4 + 4);
		if (!p)
			return -EIO;
		b->scsi.code_set = be32_to_cpup(p++);
		b->scsi.designator_type = be32_to_cpup(p++);
		b->scsi.designator_len = be32_to_cpup(p++);
		p = xdr_inline_decode(xdr, b->scsi.designator_len);
		if (!p)
			return -EIO;
		if (b->scsi.designator_len > 256)
			return -EIO;
		memcpy(&b->scsi.designator, p, b->scsi.designator_len);
		p = xdr_inline_decode(xdr, 8);
		if (!p)
			return -EIO;
		p = xdr_decode_hyper(p, &b->scsi.pr_key);
		break;
	default:
		dprintk("unknown volume type!\n");
		return -EIO;
	}

	return 0;
}

static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset,
		struct pnfs_block_dev_map *map)
{
	map->start = dev->start;
	map->len = dev->len;
	map->disk_offset = dev->disk_offset;
	map->bdev = dev->bdev;
	return true;
}

static bool bl_map_concat(struct pnfs_block_dev *dev, u64 offset,
		struct pnfs_block_dev_map *map)
{
	int i;

	for (i = 0; i < dev->nr_children; i++) {
		struct pnfs_block_dev *child = &dev->children[i];

		if (child->start > offset ||
		    child->start + child->len <= offset)
			continue;

		child->map(child, offset - child->start, map);
		return true;
	}

	dprintk("%s: ran off loop!\n", __func__);
	return false;
}

static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
		struct pnfs_block_dev_map *map)
{
	struct pnfs_block_dev *child;
	u64 chunk;
	u32 chunk_idx;
	u64 disk_offset;

	chunk = div_u64(offset, dev->chunk_size);
	div_u64_rem(chunk, dev->nr_children, &chunk_idx);

	if (chunk_idx >= dev->nr_children) {
		dprintk("%s: invalid chunk idx %d (%lld/%lld)\n",
			__func__, chunk_idx, offset, dev->chunk_size);
		/* error, should not happen */
		return false;
	}

	/* truncate offset to the beginning of the stripe */
	offset = chunk * dev->chunk_size;

	/* disk offset of the stripe */
	disk_offset = div_u64(offset, dev->nr_children);

	child = &dev->children[chunk_idx];
	child->map(child, disk_offset, map);

	map->start += offset;
	map->disk_offset += disk_offset;
	map->len = dev->chunk_size;
	return true;
}

static int
bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask);


static int
bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
	struct pnfs_block_volume *v = &volumes[idx];
	struct block_device *bdev;
	dev_t dev;

	dev = bl_resolve_deviceid(server, v, gfp_mask);
	if (!dev)
		return -EIO;

	bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_WRITE, NULL);
	if (IS_ERR(bdev)) {
		printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
			MAJOR(dev), MINOR(dev), PTR_ERR(bdev));
		return PTR_ERR(bdev);
	}
	d->bdev = bdev;


	d->len = i_size_read(d->bdev->bd_inode);
	d->map = bl_map_simple;

	printk(KERN_INFO "pNFS: using block device %s\n",
		d->bdev->bd_disk->disk_name);
	return 0;
}

static bool
bl_validate_designator(struct pnfs_block_volume *v)
{
	switch (v->scsi.designator_type) {
	case PS_DESIGNATOR_EUI64:
		if (v->scsi.code_set != PS_CODE_SET_BINARY)
			return false;

		if (v->scsi.designator_len != 8 &&
		    v->scsi.designator_len != 10 &&
		    v->scsi.designator_len != 16)
			return false;

		return true;
	case PS_DESIGNATOR_NAA:
		if (v->scsi.code_set != PS_CODE_SET_BINARY)
			return false;

		if (v->scsi.designator_len != 8 &&
		    v->scsi.designator_len != 16)
			return false;

		return true;
	case PS_DESIGNATOR_T10:
	case PS_DESIGNATOR_NAME:
		pr_err("pNFS: unsupported designator "
			"(code set %d, type %d, len %d.\n",
			v->scsi.code_set,
			v->scsi.designator_type,
			v->scsi.designator_len);
		return false;
	default:
		pr_err("pNFS: invalid designator "
			"(code set %d, type %d, len %d.\n",
			v->scsi.code_set,
			v->scsi.designator_type,
			v->scsi.designator_len);
		return false;
	}
}

/*
 * Try to open the udev path for the WWN.  At least on Debian the udev
 * by-id path will always point to the dm-multipath device if one exists.
 */
static struct block_device *
bl_open_udev_path(struct pnfs_block_volume *v)
{
	struct block_device *bdev;
	const char *devname;

	devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%*phN",
				v->scsi.designator_len, v->scsi.designator);
	if (!devname)
		return ERR_PTR(-ENOMEM);

	bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL);
	if (IS_ERR(bdev)) {
		pr_warn("pNFS: failed to open device %s (%ld)\n",
			devname, PTR_ERR(bdev));
	}

	kfree(devname);
	return bdev;
}

/*
 * Try to open the RH/Fedora specific dm-mpath udev path for this WWN, as the
 * wwn- links will only point to the first discovered SCSI device there.
 */
static struct block_device *
bl_open_dm_mpath_udev_path(struct pnfs_block_volume *v)
{
	struct block_device *bdev;
	const char *devname;

	devname = kasprintf(GFP_KERNEL,
			"/dev/disk/by-id/dm-uuid-mpath-%d%*phN",
			v->scsi.designator_type,
			v->scsi.designator_len, v->scsi.designator);
	if (!devname)
		return ERR_PTR(-ENOMEM);

	bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL);
	kfree(devname);
	return bdev;
}

static int
bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
	struct pnfs_block_volume *v = &volumes[idx];
	struct block_device *bdev;
	const struct pr_ops *ops;
	int error;

	if (!bl_validate_designator(v))
		return -EINVAL;

	bdev = bl_open_dm_mpath_udev_path(v);
	if (IS_ERR(bdev))
		bdev = bl_open_udev_path(v);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);
	d->bdev = bdev;

	d->len = i_size_read(d->bdev->bd_inode);
	d->map = bl_map_simple;
	d->pr_key = v->scsi.pr_key;

	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
		d->bdev->bd_disk->disk_name, d->pr_key);

	ops = d->bdev->bd_disk->fops->pr_ops;
	if (!ops) {
		pr_err("pNFS: block device %s does not support reservations.",
				d->bdev->bd_disk->disk_name);
		error = -EINVAL;
		goto out_blkdev_put;
	}

	error = ops->pr_register(d->bdev, 0, d->pr_key, true);
	if (error) {
		pr_err("pNFS: failed to register key for block device %s.",
				d->bdev->bd_disk->disk_name);
		goto out_blkdev_put;
	}

	d->pr_registered = true;
	return 0;

out_blkdev_put:
	blkdev_put(d->bdev, FMODE_READ | FMODE_WRITE);
	return error;
}

static int
bl_parse_slice(struct nfs_server *server, struct pnfs_block_dev *d,
		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
	struct pnfs_block_volume *v = &volumes[idx];
	int ret;

	ret = bl_parse_deviceid(server, d, volumes, v->slice.volume, gfp_mask);
	if (ret)
		return ret;

	d->disk_offset = v->slice.start;
	d->len = v->slice.len;
	return 0;
}

static int
bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d,
		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
	struct pnfs_block_volume *v = &volumes[idx];
	u64 len = 0;
	int ret, i;

	d->children = kcalloc(v->concat.volumes_count,
			sizeof(struct pnfs_block_dev), GFP_KERNEL);
	if (!d->children)
		return -ENOMEM;

	for (i = 0; i < v->concat.volumes_count; i++) {
		ret = bl_parse_deviceid(server, &d->children[i],
				volumes, v->concat.volumes[i], gfp_mask);
		if (ret)
			return ret;

		d->nr_children++;
		d->children[i].start += len;
		len += d->children[i].len;
	}

	d->len = len;
	d->map = bl_map_concat;
	return 0;
}

static int
bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d,
		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
	struct pnfs_block_volume *v = &volumes[idx];
	u64 len = 0;
	int ret, i;

	d->children = kcalloc(v->stripe.volumes_count,
			sizeof(struct pnfs_block_dev), GFP_KERNEL);
	if (!d->children)
		return -ENOMEM;

	for (i = 0; i < v->stripe.volumes_count; i++) {
		ret = bl_parse_deviceid(server, &d->children[i],
				volumes, v->stripe.volumes[i], gfp_mask);
		if (ret)
			return ret;

		d->nr_children++;
		len += d->children[i].len;
	}

	d->len = len;
	d->chunk_size = v->stripe.chunk_size;
	d->map = bl_map_stripe;
	return 0;
}

static int
bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
	switch (volumes[idx].type) {
	case PNFS_BLOCK_VOLUME_SIMPLE:
		return bl_parse_simple(server, d, volumes, idx, gfp_mask);
	case PNFS_BLOCK_VOLUME_SLICE:
		return bl_parse_slice(server, d, volumes, idx, gfp_mask);
	case PNFS_BLOCK_VOLUME_CONCAT:
		return bl_parse_concat(server, d, volumes, idx, gfp_mask);
	case PNFS_BLOCK_VOLUME_STRIPE:
		return bl_parse_stripe(server, d, volumes, idx, gfp_mask);
	case PNFS_BLOCK_VOLUME_SCSI:
		return bl_parse_scsi(server, d, volumes, idx, gfp_mask);
	default:
		dprintk("unsupported volume type: %d\n", volumes[idx].type);
		return -EIO;
	}
}

struct nfs4_deviceid_node *
bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
		gfp_t gfp_mask)
{
	struct nfs4_deviceid_node *node = NULL;
	struct pnfs_block_volume *volumes;
	struct pnfs_block_dev *top;
	struct xdr_stream xdr;
	struct xdr_buf buf;
	struct page *scratch;
	int nr_volumes, ret, i;
	__be32 *p;

	scratch = alloc_page(gfp_mask);
	if (!scratch)
		goto out;

	xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen);
	xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);

	p = xdr_inline_decode(&xdr, sizeof(__be32));
	if (!p)
		goto out_free_scratch;
	nr_volumes = be32_to_cpup(p++);

	volumes = kcalloc(nr_volumes, sizeof(struct pnfs_block_volume),
			  gfp_mask);
	if (!volumes)
		goto out_free_scratch;

	for (i = 0; i < nr_volumes; i++) {
		ret = nfs4_block_decode_volume(&xdr, &volumes[i]);
		if (ret < 0)
			goto out_free_volumes;
	}

	top = kzalloc(sizeof(*top), gfp_mask);
	if (!top)
		goto out_free_volumes;

	ret = bl_parse_deviceid(server, top, volumes, nr_volumes - 1, gfp_mask);

	node = &top->node;
	nfs4_init_deviceid_node(node, server, &pdev->dev_id);
	if (ret)
		nfs4_mark_deviceid_unavailable(node);

out_free_volumes:
	kfree(volumes);
out_free_scratch:
	__free_page(scratch);
out:
	return node;
}