Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: c464fb48039acf6a4039a535b91d0591c2d16cc2 (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
/*
   linear.c : Multiple Devices driver for Linux
	      Copyright (C) 1994-96 Marc ZYNGIER
	      <zyngier@ufr-info-p7.ibp.fr> or
	      <maz@gloups.fdn.fr>

   Linear mode management functions.

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2, or (at your option)
   any later version.

   You should have received a copy of the GNU General Public License
   (for example /usr/src/linux/COPYING); if not, write to the Free
   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/

#include <linux/blkdev.h>
#include <linux/raid/md_u.h>
#include <linux/seq_file.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <trace/events/block.h>
#include "md.h"
#include "linear.h"

/*
 * find which device holds a particular offset
 */
static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
{
	int lo, mid, hi;
	struct linear_conf *conf;

	lo = 0;
	hi = mddev->raid_disks - 1;
	conf = mddev->private;

	/*
	 * Binary Search
	 */

	while (hi > lo) {

		mid = (hi + lo) / 2;
		if (sector < conf->disks[mid].end_sector)
			hi = mid;
		else
			lo = mid + 1;
	}

	return conf->disks + lo;
}

/*
 * In linear_congested() conf->raid_disks is used as a copy of
 * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
 * and conf->disks[] are created in linear_conf(), they are always
 * consitent with each other, but mddev->raid_disks does not.
 */
static int linear_congested(struct mddev *mddev, int bits)
{
	struct linear_conf *conf;
	int i, ret = 0;

	rcu_read_lock();
	conf = rcu_dereference(mddev->private);

	for (i = 0; i < conf->raid_disks && !ret ; i++) {
		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
		ret |= bdi_congested(q->backing_dev_info, bits);
	}

	rcu_read_unlock();
	return ret;
}

static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
{
	struct linear_conf *conf;
	sector_t array_sectors;

	conf = mddev->private;
	WARN_ONCE(sectors || raid_disks,
		  "%s does not support generic reshape\n", __func__);
	array_sectors = conf->array_sectors;

	return array_sectors;
}

static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
{
	struct linear_conf *conf;
	struct md_rdev *rdev;
	int i, cnt;
	bool discard_supported = false;

	conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info),
			GFP_KERNEL);
	if (!conf)
		return NULL;

	cnt = 0;
	conf->array_sectors = 0;

	rdev_for_each(rdev, mddev) {
		int j = rdev->raid_disk;
		struct dev_info *disk = conf->disks + j;
		sector_t sectors;

		if (j < 0 || j >= raid_disks || disk->rdev) {
			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
				mdname(mddev));
			goto out;
		}

		disk->rdev = rdev;
		if (mddev->chunk_sectors) {
			sectors = rdev->sectors;
			sector_div(sectors, mddev->chunk_sectors);
			rdev->sectors = sectors * mddev->chunk_sectors;
		}

		disk_stack_limits(mddev->gendisk, rdev->bdev,
				  rdev->data_offset << 9);

		conf->array_sectors += rdev->sectors;
		cnt++;

		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
			discard_supported = true;
	}
	if (cnt != raid_disks) {
		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
			mdname(mddev));
		goto out;
	}

	if (!discard_supported)
		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
	else
		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);

	/*
	 * Here we calculate the device offsets.
	 */
	conf->disks[0].end_sector = conf->disks[0].rdev->sectors;

	for (i = 1; i < raid_disks; i++)
		conf->disks[i].end_sector =
			conf->disks[i-1].end_sector +
			conf->disks[i].rdev->sectors;

	/*
	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
	 * keep a copy of mddev->raid_disks in struct linear_conf is,
	 * mddev->raid_disks may not be consistent with pointers number of
	 * conf->disks[] when it is updated in linear_add() and used to
	 * iterate old conf->disks[] earray in linear_congested().
	 * Here conf->raid_disks is always consitent with number of
	 * pointers in conf->disks[] array, and mddev->private is updated
	 * with rcu_assign_pointer() in linear_addr(), such race can be
	 * avoided.
	 */
	conf->raid_disks = raid_disks;

	return conf;

out:
	kfree(conf);
	return NULL;
}

static int linear_run (struct mddev *mddev)
{
	struct linear_conf *conf;
	int ret;

	if (md_check_no_bitmap(mddev))
		return -EINVAL;
	conf = linear_conf(mddev, mddev->raid_disks);

	if (!conf)
		return 1;
	mddev->private = conf;
	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));

	ret =  md_integrity_register(mddev);
	if (ret) {
		kfree(conf);
		mddev->private = NULL;
	}
	return ret;
}

static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
{
	/* Adding a drive to a linear array allows the array to grow.
	 * It is permitted if the new drive has a matching superblock
	 * already on it, with raid_disk equal to raid_disks.
	 * It is achieved by creating a new linear_private_data structure
	 * and swapping it in in-place of the current one.
	 * The current one is never freed until the array is stopped.
	 * This avoids races.
	 */
	struct linear_conf *newconf, *oldconf;

	if (rdev->saved_raid_disk != mddev->raid_disks)
		return -EINVAL;

	rdev->raid_disk = rdev->saved_raid_disk;
	rdev->saved_raid_disk = -1;

	newconf = linear_conf(mddev,mddev->raid_disks+1);

	if (!newconf)
		return -ENOMEM;

	/* newconf->raid_disks already keeps a copy of * the increased
	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
	 * sure of this. It is possible that oldconf is still referenced
	 * in linear_congested(), therefore kfree_rcu() is used to free
	 * oldconf until no one uses it anymore.
	 */
	mddev_suspend(mddev);
	oldconf = rcu_dereference_protected(mddev->private,
			lockdep_is_held(&mddev->reconfig_mutex));
	mddev->raid_disks++;
	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
		"copied raid_disks doesn't match mddev->raid_disks");
	rcu_assign_pointer(mddev->private, newconf);
	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
	set_capacity(mddev->gendisk, mddev->array_sectors);
	mddev_resume(mddev);
	revalidate_disk(mddev->gendisk);
	kfree_rcu(oldconf, rcu);
	return 0;
}

static void linear_free(struct mddev *mddev, void *priv)
{
	struct linear_conf *conf = priv;

	kfree(conf);
}

static bool linear_make_request(struct mddev *mddev, struct bio *bio)
{
	char b[BDEVNAME_SIZE];
	struct dev_info *tmp_dev;
	sector_t start_sector, end_sector, data_offset;
	sector_t bio_sector = bio->bi_iter.bi_sector;

	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
		md_flush_request(mddev, bio);
		return true;
	}

	tmp_dev = which_dev(mddev, bio_sector);
	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
	end_sector = tmp_dev->end_sector;
	data_offset = tmp_dev->rdev->data_offset;

	if (unlikely(bio_sector >= end_sector ||
		     bio_sector < start_sector))
		goto out_of_bounds;

	if (unlikely(bio_end_sector(bio) > end_sector)) {
		/* This bio crosses a device boundary, so we have to split it */
		struct bio *split = bio_split(bio, end_sector - bio_sector,
					      GFP_NOIO, mddev->bio_set);
		bio_chain(split, bio);
		generic_make_request(bio);
		bio = split;
	}

	bio_set_dev(bio, tmp_dev->rdev->bdev);
	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
		start_sector + data_offset;

	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
		     !blk_queue_discard(bio->bi_disk->queue))) {
		/* Just ignore it */
		bio_endio(bio);
	} else {
		if (mddev->gendisk)
			trace_block_bio_remap(bio->bi_disk->queue,
					      bio, disk_devt(mddev->gendisk),
					      bio_sector);
		mddev_check_writesame(mddev, bio);
		mddev_check_write_zeroes(mddev, bio);
		generic_make_request(bio);
	}
	return true;

out_of_bounds:
	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n",
	       mdname(mddev),
	       (unsigned long long)bio->bi_iter.bi_sector,
	       bdevname(tmp_dev->rdev->bdev, b),
	       (unsigned long long)tmp_dev->rdev->sectors,
	       (unsigned long long)start_sector);
	bio_io_error(bio);
	return true;
}

static void linear_status (struct seq_file *seq, struct mddev *mddev)
{
	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
}

static void linear_quiesce(struct mddev *mddev, int state)
{
}

static struct md_personality linear_personality =
{
	.name		= "linear",
	.level		= LEVEL_LINEAR,
	.owner		= THIS_MODULE,
	.make_request	= linear_make_request,
	.run		= linear_run,
	.free		= linear_free,
	.status		= linear_status,
	.hot_add_disk	= linear_add,
	.size		= linear_size,
	.quiesce	= linear_quiesce,
	.congested	= linear_congested,
};

static int __init linear_init (void)
{
	return register_md_personality (&linear_personality);
}

static void linear_exit (void)
{
	unregister_md_personality (&linear_personality);
}

module_init(linear_init);
module_exit(linear_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Linear device concatenation personality for MD");
MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
MODULE_ALIAS("md-linear");
MODULE_ALIAS("md-level--1");