summaryrefslogtreecommitdiff
path: root/block/blk-lib.c
blob: 715e948f58a4e8e1cad659a71b61c6f6920fd207 (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
/*
 * 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"

struct bio_batch {
	atomic_t		done;
	unsigned long		flags;
	struct completion	*wait;
};

static void bio_batch_end_io(struct bio *bio, int err)
{
	struct bio_batch *bb = bio->bi_private;

	if (err && (err != -EOPNOTSUPP))
		clear_bit(BIO_UPTODATE, &bb->flags);
	if (atomic_dec_and_test(&bb->done))
		complete(bb->wait);
	bio_put(bio);
}

/**
 * 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)
 * @flags:	BLKDEV_IFL_* flags to control behaviour
 *
 * 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, unsigned long flags)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	struct request_queue *q = bdev_get_queue(bdev);
	int type = REQ_WRITE | REQ_DISCARD;
	unsigned int max_discard_sectors, granularity;
	int alignment;
	struct bio_batch bb;
	struct bio *bio;
	int ret = 0;
	struct blk_plug plug;

	if (!q)
		return -ENXIO;

	if (!blk_queue_discard(q))
		return -EOPNOTSUPP;

	/* Zero-sector (unknown) and one-sector granularities are the same.  */
	granularity = max(q->limits.discard_granularity >> 9, 1U);
	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;

	/*
	 * Ensure that max_discard_sectors is of the proper
	 * granularity, so that requests stay aligned after a split.
	 */
	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
	max_discard_sectors -= max_discard_sectors % granularity;
	if (unlikely(!max_discard_sectors)) {
		/* Avoid infinite loop below. Being cautious never hurts. */
		return -EOPNOTSUPP;
	}

	if (flags & BLKDEV_DISCARD_SECURE) {
		if (!blk_queue_secdiscard(q))
			return -EOPNOTSUPP;
		type |= REQ_SECURE;
	}

	atomic_set(&bb.done, 1);
	bb.flags = 1 << BIO_UPTODATE;
	bb.wait = &wait;

	blk_start_plug(&plug);
	while (nr_sects) {
		unsigned int req_sects;
		sector_t end_sect, tmp;

		bio = bio_alloc(gfp_mask, 1);
		if (!bio) {
			ret = -ENOMEM;
			break;
		}

		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);

		/*
		 * If splitting a request, and the next starting sector would be
		 * misaligned, stop the discard at the previous aligned sector.
		 */
		end_sect = sector + req_sects;
		tmp = end_sect;
		if (req_sects < nr_sects &&
		    sector_div(tmp, granularity) != alignment) {
			end_sect = end_sect - alignment;
			sector_div(end_sect, granularity);
			end_sect = end_sect * granularity + alignment;
			req_sects = end_sect - sector;
		}

		bio->bi_iter.bi_sector = sector;
		bio->bi_end_io = bio_batch_end_io;
		bio->bi_bdev = bdev;
		bio->bi_private = &bb;

		bio->bi_iter.bi_size = req_sects << 9;
		nr_sects -= req_sects;
		sector = end_sect;

		atomic_inc(&bb.done);
		submit_bio(type, bio);

		/*
		 * 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();
	}
	blk_finish_plug(&plug);

	/* Wait for bios in-flight */
	if (!atomic_dec_and_test(&bb.done))
		wait_for_completion_io(&wait);

	if (!test_bit(BIO_UPTODATE, &bb.flags))
		ret = -EIO;

	return ret;
}
EXPORT_SYMBOL(blkdev_issue_discard);

/**
 * blkdev_issue_write_same - queue a write same operation
 * @bdev:	target blockdev
 * @sector:	start sector
 * @nr_sects:	number of sectors to write
 * @gfp_mask:	memory allocation flags (for bio_alloc)
 * @page:	page containing data to write
 *
 * Description:
 *    Issue a write same request for the sectors in question.
 */
int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
			    sector_t nr_sects, gfp_t gfp_mask,
			    struct page *page)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	struct request_queue *q = bdev_get_queue(bdev);
	unsigned int max_write_same_sectors;
	struct bio_batch bb;
	struct bio *bio;
	int ret = 0;

	if (!q)
		return -ENXIO;

	max_write_same_sectors = q->limits.max_write_same_sectors;

	if (max_write_same_sectors == 0)
		return -EOPNOTSUPP;

	atomic_set(&bb.done, 1);
	bb.flags = 1 << BIO_UPTODATE;
	bb.wait = &wait;

	while (nr_sects) {
		bio = bio_alloc(gfp_mask, 1);
		if (!bio) {
			ret = -ENOMEM;
			break;
		}

		bio->bi_iter.bi_sector = sector;
		bio->bi_end_io = bio_batch_end_io;
		bio->bi_bdev = bdev;
		bio->bi_private = &bb;
		bio->bi_vcnt = 1;
		bio->bi_io_vec->bv_page = page;
		bio->bi_io_vec->bv_offset = 0;
		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);

		if (nr_sects > max_write_same_sectors) {
			bio->bi_iter.bi_size = max_write_same_sectors << 9;
			nr_sects -= max_write_same_sectors;
			sector += max_write_same_sectors;
		} else {
			bio->bi_iter.bi_size = nr_sects << 9;
			nr_sects = 0;
		}

		atomic_inc(&bb.done);
		submit_bio(REQ_WRITE | REQ_WRITE_SAME, bio);
	}

	/* Wait for bios in-flight */
	if (!atomic_dec_and_test(&bb.done))
		wait_for_completion_io(&wait);

	if (!test_bit(BIO_UPTODATE, &bb.flags))
		ret = -ENOTSUPP;

	return ret;
}
EXPORT_SYMBOL(blkdev_issue_write_same);

/**
 * 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)
 *
 * Description:
 *  Generate and issue number of bios with zerofiled pages.
 */

static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
				  sector_t nr_sects, gfp_t gfp_mask)
{
	int ret;
	struct bio *bio;
	struct bio_batch bb;
	unsigned int sz;
	DECLARE_COMPLETION_ONSTACK(wait);

	atomic_set(&bb.done, 1);
	bb.flags = 1 << BIO_UPTODATE;
	bb.wait = &wait;

	ret = 0;
	while (nr_sects != 0) {
		bio = bio_alloc(gfp_mask,
				min(nr_sects, (sector_t)BIO_MAX_PAGES));
		if (!bio) {
			ret = -ENOMEM;
			break;
		}

		bio->bi_iter.bi_sector = sector;
		bio->bi_bdev   = bdev;
		bio->bi_end_io = bio_batch_end_io;
		bio->bi_private = &bb;

		while (nr_sects != 0) {
			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
			ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
			nr_sects -= ret >> 9;
			sector += ret >> 9;
			if (ret < (sz << 9))
				break;
		}
		ret = 0;
		atomic_inc(&bb.done);
		submit_bio(WRITE, bio);
	}

	/* Wait for bios in-flight */
	if (!atomic_dec_and_test(&bb.done))
		wait_for_completion_io(&wait);

	if (!test_bit(BIO_UPTODATE, &bb.flags))
		/* One of bios in the batch was completed with error.*/
		ret = -EIO;

	return ret;
}

/**
 * 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)
 * @discard:	whether to discard the block range
 *
 * Description:

 *  Zero-fill a block range.  If the discard flag is set and the block
 *  device guarantees that subsequent READ operations to the block range
 *  in question will return zeroes, the blocks will be discarded. Should
 *  the discard request fail, if the discard flag is not set, or if
 *  discard_zeroes_data is not supported, this function will resort to
 *  zeroing the blocks manually, thus provisioning (allocating,
 *  anchoring) them. If the block device supports the WRITE SAME command
 *  blkdev_issue_zeroout() will use it to optimize the process of
 *  clearing the block range. Otherwise the zeroing will be performed
 *  using regular WRITE calls.
 */

int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
{
	struct request_queue *q = bdev_get_queue(bdev);
	unsigned char bdn[BDEVNAME_SIZE];

	if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data) {

		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0))
			return 0;

		bdevname(bdev, bdn);
		pr_warn("%s: DISCARD failed. Manually zeroing.\n", bdn);
	}

	if (bdev_write_same(bdev)) {

		if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
					     ZERO_PAGE(0)))
			return 0;

		bdevname(bdev, bdn);
		pr_warn("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
	}

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