summaryrefslogtreecommitdiff
path: root/drivers/nvdimm/blk.c
blob: 26d039879ba2c7cf9c4cc27e23b2a751a4dee99c (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
/*
 * NVDIMM Block Window Driver
 * Copyright (c) 2014, Intel Corporation.
 *
 * 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/blkdev.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/nd.h>
#include <linux/sizes.h>
#include "nd.h"

struct nd_blk_device {
	struct nd_namespace_blk *nsblk;
	struct nd_blk_region *ndbr;
	size_t disk_size;
	u32 sector_size;
	u32 internal_lbasize;
};

static u32 nd_blk_meta_size(struct nd_blk_device *blk_dev)
{
	return blk_dev->nsblk->lbasize - blk_dev->sector_size;
}

static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
				resource_size_t ns_offset, unsigned int len)
{
	int i;

	for (i = 0; i < nsblk->num_resources; i++) {
		if (ns_offset < resource_size(nsblk->res[i])) {
			if (ns_offset + len > resource_size(nsblk->res[i])) {
				dev_WARN_ONCE(&nsblk->common.dev, 1,
					"illegal request\n");
				return SIZE_MAX;
			}
			return nsblk->res[i]->start + ns_offset;
		}
		ns_offset -= resource_size(nsblk->res[i]);
	}

	dev_WARN_ONCE(&nsblk->common.dev, 1, "request out of range\n");
	return SIZE_MAX;
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
				struct bio_integrity_payload *bip, u64 lba,
				int rw)
{
	unsigned int len = nd_blk_meta_size(blk_dev);
	resource_size_t	dev_offset, ns_offset;
	struct nd_namespace_blk *nsblk;
	struct nd_blk_region *ndbr;
	int err = 0;

	nsblk = blk_dev->nsblk;
	ndbr = blk_dev->ndbr;
	ns_offset = lba * blk_dev->internal_lbasize + blk_dev->sector_size;
	dev_offset = to_dev_offset(nsblk, ns_offset, len);
	if (dev_offset == SIZE_MAX)
		return -EIO;

	while (len) {
		unsigned int cur_len;
		struct bio_vec bv;
		void *iobuf;

		bv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter);
		/*
		 * The 'bv' obtained from bvec_iter_bvec has its .bv_len and
		 * .bv_offset already adjusted for iter->bi_bvec_done, and we
		 * can use those directly
		 */

		cur_len = min(len, bv.bv_len);
		iobuf = kmap_atomic(bv.bv_page);
		err = ndbr->do_io(ndbr, dev_offset, iobuf + bv.bv_offset,
				cur_len, rw);
		kunmap_atomic(iobuf);
		if (err)
			return err;

		len -= cur_len;
		dev_offset += cur_len;
		bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len);
	}

	return err;
}

#else /* CONFIG_BLK_DEV_INTEGRITY */
static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
				struct bio_integrity_payload *bip, u64 lba,
				int rw)
{
	return 0;
}
#endif

static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
			struct bio_integrity_payload *bip, struct page *page,
			unsigned int len, unsigned int off, int rw,
			sector_t sector)
{
	struct nd_blk_region *ndbr = blk_dev->ndbr;
	resource_size_t	dev_offset, ns_offset;
	int err = 0;
	void *iobuf;
	u64 lba;

	while (len) {
		unsigned int cur_len;

		/*
		 * If we don't have an integrity payload, we don't have to
		 * split the bvec into sectors, as this would cause unnecessary
		 * Block Window setup/move steps. the do_io routine is capable
		 * of handling len <= PAGE_SIZE.
		 */
		cur_len = bip ? min(len, blk_dev->sector_size) : len;

		lba = div_u64(sector << SECTOR_SHIFT, blk_dev->sector_size);
		ns_offset = lba * blk_dev->internal_lbasize;
		dev_offset = to_dev_offset(blk_dev->nsblk, ns_offset, cur_len);
		if (dev_offset == SIZE_MAX)
			return -EIO;

		iobuf = kmap_atomic(page);
		err = ndbr->do_io(ndbr, dev_offset, iobuf + off, cur_len, rw);
		kunmap_atomic(iobuf);
		if (err)
			return err;

		if (bip) {
			err = nd_blk_rw_integrity(blk_dev, bip, lba, rw);
			if (err)
				return err;
		}
		len -= cur_len;
		off += cur_len;
		sector += blk_dev->sector_size >> SECTOR_SHIFT;
	}

	return err;
}

static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
{
	struct bio_integrity_payload *bip;
	struct nd_blk_device *blk_dev;
	struct bvec_iter iter;
	unsigned long start;
	struct bio_vec bvec;
	int err = 0, rw;
	bool do_acct;

	/*
	 * bio_integrity_enabled also checks if the bio already has an
	 * integrity payload attached. If it does, we *don't* do a
	 * bio_integrity_prep here - the payload has been generated by
	 * another kernel subsystem, and we just pass it through.
	 */
	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
		bio->bi_error = -EIO;
		goto out;
	}

	bip = bio_integrity(bio);
	blk_dev = q->queuedata;
	rw = bio_data_dir(bio);
	do_acct = nd_iostat_start(bio, &start);
	bio_for_each_segment(bvec, bio, iter) {
		unsigned int len = bvec.bv_len;

		BUG_ON(len > PAGE_SIZE);
		err = nd_blk_do_bvec(blk_dev, bip, bvec.bv_page, len,
					bvec.bv_offset, rw, iter.bi_sector);
		if (err) {
			dev_dbg(&blk_dev->nsblk->common.dev,
					"io error in %s sector %lld, len %d,\n",
					(rw == READ) ? "READ" : "WRITE",
					(unsigned long long) iter.bi_sector, len);
			bio->bi_error = err;
			break;
		}
	}
	if (do_acct)
		nd_iostat_end(bio, start);

 out:
	bio_endio(bio);
	return BLK_QC_T_NONE;
}

static int nd_blk_rw_bytes(struct nd_namespace_common *ndns,
		resource_size_t offset, void *iobuf, size_t n, int rw)
{
	struct nd_blk_device *blk_dev = dev_get_drvdata(ndns->claim);
	struct nd_namespace_blk *nsblk = blk_dev->nsblk;
	struct nd_blk_region *ndbr = blk_dev->ndbr;
	resource_size_t	dev_offset;

	dev_offset = to_dev_offset(nsblk, offset, n);

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

	if (dev_offset == SIZE_MAX)
		return -EIO;

	return ndbr->do_io(ndbr, dev_offset, iobuf, n, rw);
}

static const struct block_device_operations nd_blk_fops = {
	.owner = THIS_MODULE,
	.revalidate_disk = nvdimm_revalidate_disk,
};

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

static void nd_blk_release_disk(void *disk)
{
	del_gendisk(disk);
	put_disk(disk);
}

static int nd_blk_attach_disk(struct device *dev,
		struct nd_namespace_common *ndns, struct nd_blk_device *blk_dev)
{
	resource_size_t available_disk_size;
	struct request_queue *q;
	struct gendisk *disk;
	u64 internal_nlba;

	internal_nlba = div_u64(blk_dev->disk_size, blk_dev->internal_lbasize);
	available_disk_size = internal_nlba * blk_dev->sector_size;

	q = blk_alloc_queue(GFP_KERNEL);
	if (!q)
		return -ENOMEM;
	if (devm_add_action(dev, nd_blk_release_queue, q)) {
		blk_cleanup_queue(q);
		return -ENOMEM;
	}

	blk_queue_make_request(q, nd_blk_make_request);
	blk_queue_max_hw_sectors(q, UINT_MAX);
	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
	blk_queue_logical_block_size(q, blk_dev->sector_size);
	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
	q->queuedata = blk_dev;

	disk = alloc_disk(0);
	if (!disk)
		return -ENOMEM;
	if (devm_add_action(dev, nd_blk_release_disk, disk)) {
		put_disk(disk);
		return -ENOMEM;
	}

	disk->driverfs_dev	= &ndns->dev;
	disk->first_minor	= 0;
	disk->fops		= &nd_blk_fops;
	disk->queue		= q;
	disk->flags		= GENHD_FL_EXT_DEVT;
	nvdimm_namespace_disk_name(ndns, disk->disk_name);
	set_capacity(disk, 0);
	add_disk(disk);

	if (nd_blk_meta_size(blk_dev)) {
		int rc = nd_integrity_init(disk, nd_blk_meta_size(blk_dev));

		if (rc)
			return rc;
	}

	set_capacity(disk, available_disk_size >> SECTOR_SHIFT);
	revalidate_disk(disk);
	return 0;
}

static int nd_blk_probe(struct device *dev)
{
	struct nd_namespace_common *ndns;
	struct nd_namespace_blk *nsblk;
	struct nd_blk_device *blk_dev;

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

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

	nsblk = to_nd_namespace_blk(&ndns->dev);
	blk_dev->disk_size = nvdimm_namespace_capacity(ndns);
	blk_dev->ndbr = to_nd_blk_region(dev->parent);
	blk_dev->nsblk = to_nd_namespace_blk(&ndns->dev);
	blk_dev->internal_lbasize = roundup(nsblk->lbasize,
						INT_LBASIZE_ALIGNMENT);
	blk_dev->sector_size = ((nsblk->lbasize >= 4096) ? 4096 : 512);
	dev_set_drvdata(dev, blk_dev);

	ndns->rw_bytes = nd_blk_rw_bytes;
	if (is_nd_btt(dev))
		return nvdimm_namespace_attach_btt(ndns);
	else if (nd_btt_probe(dev, ndns, blk_dev) == 0) {
		/* we'll come back as btt-blk */
		return -ENXIO;
	} else
		return nd_blk_attach_disk(dev, ndns, blk_dev);
}

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

static struct nd_device_driver nd_blk_driver = {
	.probe = nd_blk_probe,
	.remove = nd_blk_remove,
	.drv = {
		.name = "nd_blk",
	},
	.type = ND_DRIVER_NAMESPACE_BLK,
};

static int __init nd_blk_init(void)
{
	return nd_driver_register(&nd_blk_driver);
}

static void __exit nd_blk_exit(void)
{
	driver_unregister(&nd_blk_driver.drv);
}

MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_BLK);
module_init(nd_blk_init);
module_exit(nd_blk_exit);