summaryrefslogtreecommitdiff
path: root/block/blk-lib.c
blob: 4c9f20a689f7bbea999eaa614f1e2b1c83f5d984 (plain) (blame)
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
// SPDX-License-Identifier: GPL-2.0
/*
 * Functions related to generic helpers functions
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>

#include "blk.h"

static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
{
	unsigned int discard_granularity = bdev_discard_granularity(bdev);
	sector_t granularity_aligned_sector;

	if (bdev_is_partition(bdev))
		sector += bdev->bd_start_sect;

	granularity_aligned_sector =
		round_up(sector, discard_granularity >> SECTOR_SHIFT);

	/*
	 * Make sure subsequent bios start aligned to the discard granularity if
	 * it needs to be split.
	 */
	if (granularity_aligned_sector != sector)
		return granularity_aligned_sector - sector;

	/*
	 * Align the bio size to the discard granularity to make splitting the bio
	 * at discard granularity boundaries easier in the driver if needed.
	 */
	return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT;
}

struct bio *blk_alloc_discard_bio(struct block_device *bdev,
		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask)
{
	sector_t bio_sects = min(*nr_sects, bio_discard_limit(bdev, *sector));
	struct bio *bio;

	if (!bio_sects)
		return NULL;

	bio = bio_alloc(bdev, 0, REQ_OP_DISCARD, gfp_mask);
	if (!bio)
		return NULL;
	bio->bi_iter.bi_sector = *sector;
	bio->bi_iter.bi_size = bio_sects << SECTOR_SHIFT;
	*sector += bio_sects;
	*nr_sects -= bio_sects;
	/*
	 * We can loop for a long time in here if someone does full device
	 * discards (like mkfs).  Be nice and allow us to schedule out to avoid
	 * softlocking if preempt is disabled.
	 */
	cond_resched();
	return bio;
}

int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
{
	struct bio *bio;

	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
			gfp_mask)))
		*biop = bio_chain_and_submit(*biop, bio);
	return 0;
}
EXPORT_SYMBOL(__blkdev_issue_discard);

/**
 * blkdev_issue_discard - queue a discard
 * @bdev:	blockdev to issue discard for
 * @sector:	start sector
 * @nr_sects:	number of sectors to discard
 * @gfp_mask:	memory allocation flags (for bio_alloc)
 *
 * Description:
 *    Issue a discard request for the sectors in question.
 */
int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask)
{
	struct bio *bio = NULL;
	struct blk_plug plug;
	int ret;

	blk_start_plug(&plug);
	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio);
	if (!ret && bio) {
		ret = submit_bio_wait(bio);
		if (ret == -EOPNOTSUPP)
			ret = 0;
		bio_put(bio);
	}
	blk_finish_plug(&plug);

	return ret;
}
EXPORT_SYMBOL(blkdev_issue_discard);

static sector_t bio_write_zeroes_limit(struct block_device *bdev)
{
	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;

	return min(bdev_write_zeroes_sectors(bdev),
		(UINT_MAX >> SECTOR_SHIFT) & ~bs_mask);
}

/*
 * There is no reliable way for the SCSI subsystem to determine whether a
 * device supports a WRITE SAME operation without actually performing a write
 * to media. As a result, write_zeroes is enabled by default and will be
 * disabled if a zeroing operation subsequently fails. This means that this
 * queue limit is likely to change at runtime.
 */
static void __blkdev_issue_write_zeroes(struct block_device *bdev,
		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
		struct bio **biop, unsigned flags, sector_t limit)
{

	while (nr_sects) {
		unsigned int len = min(nr_sects, limit);
		struct bio *bio;

		if ((flags & BLKDEV_ZERO_KILLABLE) &&
		    fatal_signal_pending(current))
			break;

		bio = bio_alloc(bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
		bio->bi_iter.bi_sector = sector;
		if (flags & BLKDEV_ZERO_NOUNMAP)
			bio->bi_opf |= REQ_NOUNMAP;

		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
		*biop = bio_chain_and_submit(*biop, bio);

		nr_sects -= len;
		sector += len;
		cond_resched();
	}
}

static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp, unsigned flags)
{
	sector_t limit = bio_write_zeroes_limit(bdev);
	struct bio *bio = NULL;
	struct blk_plug plug;
	int ret = 0;

	blk_start_plug(&plug);
	__blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio,
			flags, limit);
	if (bio) {
		if ((flags & BLKDEV_ZERO_KILLABLE) &&
		    fatal_signal_pending(current)) {
			bio_await_chain(bio);
			blk_finish_plug(&plug);
			return -EINTR;
		}
		ret = submit_bio_wait(bio);
		bio_put(bio);
	}
	blk_finish_plug(&plug);

	/*
	 * For some devices there is no non-destructive way to verify whether
	 * WRITE ZEROES is actually supported.  These will clear the capability
	 * on an I/O error, in which case we'll turn any error into
	 * "not supported" here.
	 */
	if (ret && !bdev_write_zeroes_sectors(bdev))
		return -EOPNOTSUPP;
	return ret;
}

/*
 * Convert a number of 512B sectors to a number of pages.
 * The result is limited to a number of pages that can fit into a BIO.
 * Also make sure that the result is always at least 1 (page) for the cases
 * where nr_sects is lower than the number of sectors in a page.
 */
static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
{
	sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512);

	return min(pages, (sector_t)BIO_MAX_VECS);
}

static void __blkdev_issue_zero_pages(struct block_device *bdev,
		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
		struct bio **biop, unsigned int flags)
{
	while (nr_sects) {
		unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects);
		struct bio *bio;

		bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask);
		bio->bi_iter.bi_sector = sector;

		if ((flags & BLKDEV_ZERO_KILLABLE) &&
		    fatal_signal_pending(current))
			break;

		do {
			unsigned int len, added;

			len = min_t(sector_t,
				PAGE_SIZE, nr_sects << SECTOR_SHIFT);
			added = bio_add_page(bio, ZERO_PAGE(0), len, 0);
			if (added < len)
				break;
			nr_sects -= added >> SECTOR_SHIFT;
			sector += added >> SECTOR_SHIFT;
		} while (nr_sects);

		*biop = bio_chain_and_submit(*biop, bio);
		cond_resched();
	}
}

static int blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp, unsigned flags)
{
	struct bio *bio = NULL;
	struct blk_plug plug;
	int ret = 0;

	if (flags & BLKDEV_ZERO_NOFALLBACK)
		return -EOPNOTSUPP;

	blk_start_plug(&plug);
	__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp, &bio, flags);
	if (bio) {
		if ((flags & BLKDEV_ZERO_KILLABLE) &&
		    fatal_signal_pending(current)) {
			bio_await_chain(bio);
			blk_finish_plug(&plug);
			return -EINTR;
		}
		ret = submit_bio_wait(bio);
		bio_put(bio);
	}
	blk_finish_plug(&plug);

	return ret;
}

/**
 * __blkdev_issue_zeroout - generate number of zero filed write bios
 * @bdev:	blockdev to issue
 * @sector:	start sector
 * @nr_sects:	number of sectors to write
 * @gfp_mask:	memory allocation flags (for bio_alloc)
 * @biop:	pointer to anchor bio
 * @flags:	controls detailed behavior
 *
 * Description:
 *  Zero-fill a block range, either using hardware offload or by explicitly
 *  writing zeroes to the device.
 *
 *  If a device is using logical block provisioning, the underlying space will
 *  not be released if %flags contains BLKDEV_ZERO_NOUNMAP.
 *
 *  If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return
 *  -EOPNOTSUPP if no explicit hardware offload for zeroing is provided.
 */
int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
		unsigned flags)
{
	sector_t limit = bio_write_zeroes_limit(bdev);

	if (bdev_read_only(bdev))
		return -EPERM;

	if (limit) {
		__blkdev_issue_write_zeroes(bdev, sector, nr_sects,
				gfp_mask, biop, flags, limit);
	} else {
		if (flags & BLKDEV_ZERO_NOFALLBACK)
			return -EOPNOTSUPP;
		__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask,
				biop, flags);
	}
	return 0;
}
EXPORT_SYMBOL(__blkdev_issue_zeroout);

/**
 * blkdev_issue_zeroout - zero-fill a block range
 * @bdev:	blockdev to write
 * @sector:	start sector
 * @nr_sects:	number of sectors to write
 * @gfp_mask:	memory allocation flags (for bio_alloc)
 * @flags:	controls detailed behavior
 *
 * Description:
 *  Zero-fill a block range, either using hardware offload or by explicitly
 *  writing zeroes to the device.  See __blkdev_issue_zeroout() for the
 *  valid values for %flags.
 */
int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
{
	int ret;

	if ((sector | nr_sects) & ((bdev_logical_block_size(bdev) >> 9) - 1))
		return -EINVAL;
	if (bdev_read_only(bdev))
		return -EPERM;

	if (bdev_write_zeroes_sectors(bdev)) {
		ret = blkdev_issue_write_zeroes(bdev, sector, nr_sects,
				gfp_mask, flags);
		if (ret != -EOPNOTSUPP)
			return ret;
	}

	return blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, flags);
}
EXPORT_SYMBOL(blkdev_issue_zeroout);

int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
		sector_t nr_sects, gfp_t gfp)
{
	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
	unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev);
	struct bio *bio = NULL;
	struct blk_plug plug;
	int ret = 0;

	/* make sure that "len << SECTOR_SHIFT" doesn't overflow */
	if (max_sectors > UINT_MAX >> SECTOR_SHIFT)
		max_sectors = UINT_MAX >> SECTOR_SHIFT;
	max_sectors &= ~bs_mask;

	if (max_sectors == 0)
		return -EOPNOTSUPP;
	if ((sector | nr_sects) & bs_mask)
		return -EINVAL;
	if (bdev_read_only(bdev))
		return -EPERM;

	blk_start_plug(&plug);
	while (nr_sects) {
		unsigned int len = min_t(sector_t, nr_sects, max_sectors);

		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
		bio->bi_iter.bi_sector = sector;
		bio->bi_iter.bi_size = len << SECTOR_SHIFT;

		sector += len;
		nr_sects -= len;
		cond_resched();
	}
	if (bio) {
		ret = submit_bio_wait(bio);
		bio_put(bio);
	}
	blk_finish_plug(&plug);

	return ret;
}
EXPORT_SYMBOL(blkdev_issue_secure_erase);