summaryrefslogtreecommitdiffstats
path: root/drivers/md/linear.c
blob: bb279fad2fd2788e9a8e0d8d8b322df77a76766a (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
382
383
/*
   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/module.h>

#include <linux/raid/md.h>
#include <linux/slab.h>
#include <linux/raid/linear.h>

#define MAJOR_NR MD_MAJOR
#define MD_DRIVER
#define MD_PERSONALITY

/*
 * find which device holds a particular offset 
 */
static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
{
	dev_info_t *hash;
	linear_conf_t *conf = mddev_to_conf(mddev);
	sector_t block = sector >> 1;

	/*
	 * sector_div(a,b) returns the remainer and sets a to a/b
	 */
	block >>= conf->preshift;
	(void)sector_div(block, conf->hash_spacing);
	hash = conf->hash_table[block];

	while ((sector>>1) >= (hash->size + hash->offset))
		hash++;
	return hash;
}

/**
 *	linear_mergeable_bvec -- tell bio layer if two requests can be merged
 *	@q: request queue
 *	@bio: the buffer head that's been built up so far
 *	@biovec: the request that could be merged to it.
 *
 *	Return amount of bytes we can take at this offset
 */
static int linear_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *biovec)
{
	mddev_t *mddev = q->queuedata;
	dev_info_t *dev0;
	unsigned long maxsectors, bio_sectors = bio->bi_size >> 9;
	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);

	dev0 = which_dev(mddev, sector);
	maxsectors = (dev0->size << 1) - (sector - (dev0->offset<<1));

	if (maxsectors < bio_sectors)
		maxsectors = 0;
	else
		maxsectors -= bio_sectors;

	if (maxsectors <= (PAGE_SIZE >> 9 ) && bio_sectors == 0)
		return biovec->bv_len;
	/* The bytes available at this offset could be really big,
	 * so we cap at 2^31 to avoid overflow */
	if (maxsectors > (1 << (31-9)))
		return 1<<31;
	return maxsectors << 9;
}

static void linear_unplug(request_queue_t *q)
{
	mddev_t *mddev = q->queuedata;
	linear_conf_t *conf = mddev_to_conf(mddev);
	int i;

	for (i=0; i < mddev->raid_disks; i++) {
		request_queue_t *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev);
		if (r_queue->unplug_fn)
			r_queue->unplug_fn(r_queue);
	}
}

static int linear_issue_flush(request_queue_t *q, struct gendisk *disk,
			      sector_t *error_sector)
{
	mddev_t *mddev = q->queuedata;
	linear_conf_t *conf = mddev_to_conf(mddev);
	int i, ret = 0;

	for (i=0; i < mddev->raid_disks && ret == 0; i++) {
		struct block_device *bdev = conf->disks[i].rdev->bdev;
		request_queue_t *r_queue = bdev_get_queue(bdev);

		if (!r_queue->issue_flush_fn)
			ret = -EOPNOTSUPP;
		else
			ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk, error_sector);
	}
	return ret;
}

static int linear_run (mddev_t *mddev)
{
	linear_conf_t *conf;
	dev_info_t **table;
	mdk_rdev_t *rdev;
	int i, nb_zone, cnt;
	sector_t min_spacing;
	sector_t curr_offset;
	struct list_head *tmp;

	conf = kmalloc (sizeof (*conf) + mddev->raid_disks*sizeof(dev_info_t),
			GFP_KERNEL);
	if (!conf)
		goto out;
	memset(conf, 0, sizeof(*conf) + mddev->raid_disks*sizeof(dev_info_t));
	mddev->private = conf;

	cnt = 0;
	mddev->array_size = 0;

	ITERATE_RDEV(mddev,rdev,tmp) {
		int j = rdev->raid_disk;
		dev_info_t *disk = conf->disks + j;

		if (j < 0 || j > mddev->raid_disks || disk->rdev) {
			printk("linear: disk numbering problem. Aborting!\n");
			goto out;
		}

		disk->rdev = rdev;

		blk_queue_stack_limits(mddev->queue,
				       rdev->bdev->bd_disk->queue);
		/* as we don't honour merge_bvec_fn, we must never risk
		 * violating it, so limit ->max_sector to one PAGE, as
		 * a one page request is never in violation.
		 */
		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);

		disk->size = rdev->size;
		mddev->array_size += rdev->size;

		cnt++;
	}
	if (cnt != mddev->raid_disks) {
		printk("linear: not enough drives present. Aborting!\n");
		goto out;
	}

	min_spacing = mddev->array_size;
	sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));

	/* min_spacing is the minimum spacing that will fit the hash
	 * table in one PAGE.  This may be much smaller than needed.
	 * We find the smallest non-terminal set of consecutive devices
	 * that is larger than min_spacing as use the size of that as
	 * the actual spacing
	 */
	conf->hash_spacing = mddev->array_size;
	for (i=0; i < cnt-1 ; i++) {
		sector_t sz = 0;
		int j;
		for (j=i; i<cnt-1 && sz < min_spacing ; j++)
			sz += conf->disks[j].size;
		if (sz >= min_spacing && sz < conf->hash_spacing)
			conf->hash_spacing = sz;
	}

	/* hash_spacing may be too large for sector_div to work with,
	 * so we might need to pre-shift
	 */
	conf->preshift = 0;
	if (sizeof(sector_t) > sizeof(u32)) {
		sector_t space = conf->hash_spacing;
		while (space > (sector_t)(~(u32)0)) {
			space >>= 1;
			conf->preshift++;
		}
	}
	/*
	 * This code was restructured to work around a gcc-2.95.3 internal
	 * compiler error.  Alter it with care.
	 */
	{
		sector_t sz;
		unsigned round;
		unsigned long base;

		sz = mddev->array_size >> conf->preshift;
		sz += 1; /* force round-up */
		base = conf->hash_spacing >> conf->preshift;
		round = sector_div(sz, base);
		nb_zone = sz + (round ? 1 : 0);
	}
	BUG_ON(nb_zone > PAGE_SIZE / sizeof(struct dev_info *));

	conf->hash_table = kmalloc (sizeof (struct dev_info *) * nb_zone,
					GFP_KERNEL);
	if (!conf->hash_table)
		goto out;

	/*
	 * Here we generate the linear hash table
	 * First calculate the device offsets.
	 */
	conf->disks[0].offset = 0;
	for (i=1; i<mddev->raid_disks; i++)
		conf->disks[i].offset =
			conf->disks[i-1].offset +
			conf->disks[i-1].size;

	table = conf->hash_table;
	curr_offset = 0;
	i = 0;
	for (curr_offset = 0;
	     curr_offset < mddev->array_size;
	     curr_offset += conf->hash_spacing) {

		while (i < mddev->raid_disks-1 &&
		       curr_offset >= conf->disks[i+1].offset)
			i++;

		*table ++ = conf->disks + i;
	}

	if (conf->preshift) {
		conf->hash_spacing >>= conf->preshift;
		/* round hash_spacing up so that when we divide by it,
		 * we err on the side of "too-low", which is safest.
		 */
		conf->hash_spacing++;
	}

	BUG_ON(table - conf->hash_table > nb_zone);

	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
	mddev->queue->unplug_fn = linear_unplug;
	mddev->queue->issue_flush_fn = linear_issue_flush;
	return 0;

out:
	kfree(conf);
	return 1;
}

static int linear_stop (mddev_t *mddev)
{
	linear_conf_t *conf = mddev_to_conf(mddev);
  
	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
	kfree(conf->hash_table);
	kfree(conf);

	return 0;
}

static int linear_make_request (request_queue_t *q, struct bio *bio)
{
	mddev_t *mddev = q->queuedata;
	dev_info_t *tmp_dev;
	sector_t block;

	if (unlikely(bio_barrier(bio))) {
		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
		return 0;
	}

	if (bio_data_dir(bio)==WRITE) {
		disk_stat_inc(mddev->gendisk, writes);
		disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio));
	} else {
		disk_stat_inc(mddev->gendisk, reads);
		disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio));
	}

	tmp_dev = which_dev(mddev, bio->bi_sector);
	block = bio->bi_sector >> 1;
    
	if (unlikely(block >= (tmp_dev->size + tmp_dev->offset)
		     || block < tmp_dev->offset)) {
		char b[BDEVNAME_SIZE];

		printk("linear_make_request: Block %llu out of bounds on "
			"dev %s size %llu offset %llu\n",
			(unsigned long long)block,
			bdevname(tmp_dev->rdev->bdev, b),
			(unsigned long long)tmp_dev->size,
		        (unsigned long long)tmp_dev->offset);
		bio_io_error(bio, bio->bi_size);
		return 0;
	}
	if (unlikely(bio->bi_sector + (bio->bi_size >> 9) >
		     (tmp_dev->offset + tmp_dev->size)<<1)) {
		/* This bio crosses a device boundary, so we have to
		 * split it.
		 */
		struct bio_pair *bp;
		bp = bio_split(bio, bio_split_pool,
			       ((tmp_dev->offset + tmp_dev->size)<<1) - bio->bi_sector);
		if (linear_make_request(q, &bp->bio1))
			generic_make_request(&bp->bio1);
		if (linear_make_request(q, &bp->bio2))
			generic_make_request(&bp->bio2);
		bio_pair_release(bp);
		return 0;
	}
		    
	bio->bi_bdev = tmp_dev->rdev->bdev;
	bio->bi_sector = bio->bi_sector - (tmp_dev->offset << 1) + tmp_dev->rdev->data_offset;

	return 1;
}

static void linear_status (struct seq_file *seq, mddev_t *mddev)
{

#undef MD_DEBUG
#ifdef MD_DEBUG
	int j;
	linear_conf_t *conf = mddev_to_conf(mddev);
	sector_t s = 0;
  
	seq_printf(seq, "      ");
	for (j = 0; j < mddev->raid_disks; j++)
	{
		char b[BDEVNAME_SIZE];
		s += conf->smallest_size;
		seq_printf(seq, "[%s",
			   bdevname(conf->hash_table[j][0].rdev->bdev,b));

		while (s > conf->hash_table[j][0].offset +
		           conf->hash_table[j][0].size)
			seq_printf(seq, "/%s] ",
				   bdevname(conf->hash_table[j][1].rdev->bdev,b));
		else
			seq_printf(seq, "] ");
	}
	seq_printf(seq, "\n");
#endif
	seq_printf(seq, " %dk rounding", mddev->chunk_size/1024);
}


static mdk_personality_t linear_personality=
{
	.name		= "linear",
	.owner		= THIS_MODULE,
	.make_request	= linear_make_request,
	.run		= linear_run,
	.stop		= linear_stop,
	.status		= linear_status,
};

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

static void linear_exit (void)
{
	unregister_md_personality (LINEAR);
}


module_init(linear_init);
module_exit(linear_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-1"); /* LINEAR */
OpenPOWER on IntegriCloud