summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/bio.c
blob: b8fb7ef6b520600994a33e723d1c44993df13e24 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 * Copyright (C) 2022 Christoph Hellwig.
 */

#include <linux/bio.h>
#include "bio.h"
#include "ctree.h"
#include "volumes.h"
#include "raid56.h"
#include "async-thread.h"
#include "check-integrity.h"
#include "dev-replace.h"
#include "rcu-string.h"
#include "zoned.h"

static struct bio_set btrfs_bioset;

/*
 * Initialize a btrfs_bio structure.  This skips the embedded bio itself as it
 * is already initialized by the block layer.
 */
static inline void btrfs_bio_init(struct btrfs_bio *bbio,
				  btrfs_bio_end_io_t end_io, void *private)
{
	memset(bbio, 0, offsetof(struct btrfs_bio, bio));
	bbio->end_io = end_io;
	bbio->private = private;
}

/*
 * Allocate a btrfs_bio structure.  The btrfs_bio is the main I/O container for
 * btrfs, and is used for all I/O submitted through btrfs_submit_bio.
 *
 * Just like the underlying bio_alloc_bioset it will not fail as it is backed by
 * a mempool.
 */
struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
			    btrfs_bio_end_io_t end_io, void *private)
{
	struct bio *bio;

	bio = bio_alloc_bioset(NULL, nr_vecs, opf, GFP_NOFS, &btrfs_bioset);
	btrfs_bio_init(btrfs_bio(bio), end_io, private);
	return bio;
}

struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
				    btrfs_bio_end_io_t end_io, void *private)
{
	struct bio *bio;
	struct btrfs_bio *bbio;

	ASSERT(offset <= UINT_MAX && size <= UINT_MAX);

	bio = bio_alloc_clone(orig->bi_bdev, orig, GFP_NOFS, &btrfs_bioset);
	bbio = btrfs_bio(bio);
	btrfs_bio_init(bbio, end_io, private);

	bio_trim(bio, offset >> 9, size >> 9);
	bbio->iter = bio->bi_iter;
	return bio;
}

static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
{
	if (!dev || !dev->bdev)
		return;
	if (bio->bi_status != BLK_STS_IOERR && bio->bi_status != BLK_STS_TARGET)
		return;

	if (btrfs_op(bio) == BTRFS_MAP_WRITE)
		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
	if (!(bio->bi_opf & REQ_RAHEAD))
		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS);
	if (bio->bi_opf & REQ_PREFLUSH)
		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_FLUSH_ERRS);
}

static struct workqueue_struct *btrfs_end_io_wq(struct btrfs_fs_info *fs_info,
						struct bio *bio)
{
	if (bio->bi_opf & REQ_META)
		return fs_info->endio_meta_workers;
	return fs_info->endio_workers;
}

static void btrfs_end_bio_work(struct work_struct *work)
{
	struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work);

	bbio->end_io(bbio);
}

static void btrfs_simple_end_io(struct bio *bio)
{
	struct btrfs_fs_info *fs_info = bio->bi_private;
	struct btrfs_bio *bbio = btrfs_bio(bio);

	btrfs_bio_counter_dec(fs_info);

	if (bio->bi_status)
		btrfs_log_dev_io_error(bio, bbio->device);

	if (bio_op(bio) == REQ_OP_READ) {
		INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
		queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
	} else {
		bbio->end_io(bbio);
	}
}

static void btrfs_raid56_end_io(struct bio *bio)
{
	struct btrfs_io_context *bioc = bio->bi_private;
	struct btrfs_bio *bbio = btrfs_bio(bio);

	btrfs_bio_counter_dec(bioc->fs_info);
	bbio->mirror_num = bioc->mirror_num;
	bbio->end_io(bbio);

	btrfs_put_bioc(bioc);
}

static void btrfs_orig_write_end_io(struct bio *bio)
{
	struct btrfs_io_stripe *stripe = bio->bi_private;
	struct btrfs_io_context *bioc = stripe->bioc;
	struct btrfs_bio *bbio = btrfs_bio(bio);

	btrfs_bio_counter_dec(bioc->fs_info);

	if (bio->bi_status) {
		atomic_inc(&bioc->error);
		btrfs_log_dev_io_error(bio, stripe->dev);
	}

	/*
	 * Only send an error to the higher layers if it is beyond the tolerance
	 * threshold.
	 */
	if (atomic_read(&bioc->error) > bioc->max_errors)
		bio->bi_status = BLK_STS_IOERR;
	else
		bio->bi_status = BLK_STS_OK;

	bbio->end_io(bbio);
	btrfs_put_bioc(bioc);
}

static void btrfs_clone_write_end_io(struct bio *bio)
{
	struct btrfs_io_stripe *stripe = bio->bi_private;

	if (bio->bi_status) {
		atomic_inc(&stripe->bioc->error);
		btrfs_log_dev_io_error(bio, stripe->dev);
	}

	/* Pass on control to the original bio this one was cloned from */
	bio_endio(stripe->bioc->orig_bio);
	bio_put(bio);
}

static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio)
{
	if (!dev || !dev->bdev ||
	    test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) ||
	    (btrfs_op(bio) == BTRFS_MAP_WRITE &&
	     !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) {
		bio_io_error(bio);
		return;
	}

	bio_set_dev(bio, dev->bdev);

	/*
	 * For zone append writing, bi_sector must point the beginning of the
	 * zone
	 */
	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
		u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;

		if (btrfs_dev_is_sequential(dev, physical)) {
			u64 zone_start = round_down(physical,
						    dev->fs_info->zone_size);

			bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT;
		} else {
			bio->bi_opf &= ~REQ_OP_ZONE_APPEND;
			bio->bi_opf |= REQ_OP_WRITE;
		}
	}
	btrfs_debug_in_rcu(dev->fs_info,
	"%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
		__func__, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
		(unsigned long)dev->bdev->bd_dev, btrfs_dev_name(dev),
		dev->devid, bio->bi_iter.bi_size);

	btrfsic_check_bio(bio);
	submit_bio(bio);
}

static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr)
{
	struct bio *orig_bio = bioc->orig_bio, *bio;

	ASSERT(bio_op(orig_bio) != REQ_OP_READ);

	/* Reuse the bio embedded into the btrfs_bio for the last mirror */
	if (dev_nr == bioc->num_stripes - 1) {
		bio = orig_bio;
		bio->bi_end_io = btrfs_orig_write_end_io;
	} else {
		bio = bio_alloc_clone(NULL, orig_bio, GFP_NOFS, &fs_bio_set);
		bio_inc_remaining(orig_bio);
		bio->bi_end_io = btrfs_clone_write_end_io;
	}

	bio->bi_private = &bioc->stripes[dev_nr];
	bio->bi_iter.bi_sector = bioc->stripes[dev_nr].physical >> SECTOR_SHIFT;
	bioc->stripes[dev_nr].bioc = bioc;
	btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio);
}

void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num)
{
	u64 logical = bio->bi_iter.bi_sector << 9;
	u64 length = bio->bi_iter.bi_size;
	u64 map_length = length;
	struct btrfs_io_context *bioc = NULL;
	struct btrfs_io_stripe smap;
	int ret;

	btrfs_bio_counter_inc_blocked(fs_info);
	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
				&bioc, &smap, &mirror_num, 1);
	if (ret) {
		btrfs_bio_counter_dec(fs_info);
		btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
		return;
	}

	if (map_length < length) {
		btrfs_crit(fs_info,
			   "mapping failed logical %llu bio len %llu len %llu",
			   logical, length, map_length);
		BUG();
	}

	if (!bioc) {
		/* Single mirror read/write fast path */
		btrfs_bio(bio)->mirror_num = mirror_num;
		btrfs_bio(bio)->device = smap.dev;
		bio->bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT;
		bio->bi_private = fs_info;
		bio->bi_end_io = btrfs_simple_end_io;
		btrfs_submit_dev_bio(smap.dev, bio);
	} else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
		/* Parity RAID write or read recovery */
		bio->bi_private = bioc;
		bio->bi_end_io = btrfs_raid56_end_io;
		if (bio_op(bio) == REQ_OP_READ)
			raid56_parity_recover(bio, bioc, mirror_num);
		else
			raid56_parity_write(bio, bioc);
	} else {
		/* Write to multiple mirrors */
		int total_devs = bioc->num_stripes;
		int dev_nr;

		bioc->orig_bio = bio;
		for (dev_nr = 0; dev_nr < total_devs; dev_nr++)
			btrfs_submit_mirrored_bio(bioc, dev_nr);
	}
}

/*
 * Submit a repair write.
 *
 * This bypasses btrfs_submit_bio deliberately, as that writes all copies in a
 * RAID setup.  Here we only want to write the one bad copy, so we do the
 * mapping ourselves and submit the bio directly.
 *
 * The I/O is issued sychronously to block the repair read completion from
 * freeing the bio.
 */
int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
			    u64 length, u64 logical, struct page *page,
			    unsigned int pg_offset, int mirror_num)
{
	struct btrfs_device *dev;
	struct bio_vec bvec;
	struct bio bio;
	u64 map_length = 0;
	u64 sector;
	struct btrfs_io_context *bioc = NULL;
	int ret = 0;

	ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
	BUG_ON(!mirror_num);

	if (btrfs_repair_one_zone(fs_info, logical))
		return 0;

	map_length = length;

	/*
	 * Avoid races with device replace and make sure our bioc has devices
	 * associated to its stripes that don't go away while we are doing the
	 * read repair operation.
	 */
	btrfs_bio_counter_inc_blocked(fs_info);
	if (btrfs_is_parity_mirror(fs_info, logical, length)) {
		/*
		 * Note that we don't use BTRFS_MAP_WRITE because it's supposed
		 * to update all raid stripes, but here we just want to correct
		 * bad stripe, thus BTRFS_MAP_READ is abused to only get the bad
		 * stripe's dev and sector.
		 */
		ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
				      &map_length, &bioc, 0);
		if (ret)
			goto out_counter_dec;
		ASSERT(bioc->mirror_num == 1);
	} else {
		ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
				      &map_length, &bioc, mirror_num);
		if (ret)
			goto out_counter_dec;
		BUG_ON(mirror_num != bioc->mirror_num);
	}

	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
	dev = bioc->stripes[bioc->mirror_num - 1].dev;
	btrfs_put_bioc(bioc);

	if (!dev || !dev->bdev ||
	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
		ret = -EIO;
		goto out_counter_dec;
	}

	bio_init(&bio, dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC);
	bio.bi_iter.bi_sector = sector;
	__bio_add_page(&bio, page, length, pg_offset);

	btrfsic_check_bio(&bio);
	ret = submit_bio_wait(&bio);
	if (ret) {
		/* try to remap that extent elsewhere? */
		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
		goto out_bio_uninit;
	}

	btrfs_info_rl_in_rcu(fs_info,
		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
			     ino, start, btrfs_dev_name(dev), sector);
	ret = 0;

out_bio_uninit:
	bio_uninit(&bio);
out_counter_dec:
	btrfs_bio_counter_dec(fs_info);
	return ret;
}

int __init btrfs_bioset_init(void)
{
	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
			offsetof(struct btrfs_bio, bio),
			BIOSET_NEED_BVECS))
		return -ENOMEM;
	return 0;
}

void __cold btrfs_bioset_exit(void)
{
	bioset_exit(&btrfs_bioset);
}