summaryrefslogtreecommitdiffstats
path: root/drivers/md/raid0.c
blob: d3a4ce06015a300e9d4df5e95ee63669613db17e (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
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
/*
   raid0.c : Multiple Devices driver for Linux
             Copyright (C) 1994-96 Marc ZYNGIER
	     <zyngier@ufr-info-p7.ibp.fr> or
	     <maz@gloups.fdn.fr>
             Copyright (C) 1999, 2000 Ingo Molnar, Red Hat


   RAID-0 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/seq_file.h>
#include "md.h"
#include "raid0.h"

static void raid0_unplug(struct request_queue *q)
{
	mddev_t *mddev = q->queuedata;
	raid0_conf_t *conf = mddev->private;
	mdk_rdev_t **devlist = conf->devlist;
	int i;

	for (i=0; i<mddev->raid_disks; i++) {
		struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev);

		blk_unplug(r_queue);
	}
}

static int raid0_congested(void *data, int bits)
{
	mddev_t *mddev = data;
	raid0_conf_t *conf = mddev->private;
	mdk_rdev_t **devlist = conf->devlist;
	int i, ret = 0;

	if (mddev_congested(mddev, bits))
		return 1;

	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);

		ret |= bdi_congested(&q->backing_dev_info, bits);
	}
	return ret;
}

/*
 * inform the user of the raid configuration
*/
static void dump_zones(mddev_t *mddev)
{
	int j, k, h;
	sector_t zone_size = 0;
	sector_t zone_start = 0;
	char b[BDEVNAME_SIZE];
	raid0_conf_t *conf = mddev->private;
	printk(KERN_INFO "******* %s configuration *********\n",
		mdname(mddev));
	h = 0;
	for (j = 0; j < conf->nr_strip_zones; j++) {
		printk(KERN_INFO "zone%d=[", j);
		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
			printk("%s/",
			bdevname(conf->devlist[j*mddev->raid_disks
						+ k]->bdev, b));
		printk("]\n");

		zone_size  = conf->strip_zone[j].zone_end - zone_start;
		printk(KERN_INFO "        zone offset=%llukb "
				"device offset=%llukb size=%llukb\n",
			(unsigned long long)zone_start>>1,
			(unsigned long long)conf->strip_zone[j].dev_start>>1,
			(unsigned long long)zone_size>>1);
		zone_start = conf->strip_zone[j].zone_end;
	}
	printk(KERN_INFO "**********************************\n\n");
}

static int create_strip_zones(mddev_t *mddev)
{
	int i, c, err;
	sector_t curr_zone_end, sectors;
	mdk_rdev_t *smallest, *rdev1, *rdev2, *rdev, **dev;
	struct strip_zone *zone;
	int cnt;
	char b[BDEVNAME_SIZE];
	raid0_conf_t *conf = kzalloc(sizeof(*conf), GFP_KERNEL);

	if (!conf)
		return -ENOMEM;
	list_for_each_entry(rdev1, &mddev->disks, same_set) {
		printk(KERN_INFO "raid0: looking at %s\n",
			bdevname(rdev1->bdev,b));
		c = 0;

		/* round size to chunk_size */
		sectors = rdev1->sectors;
		sector_div(sectors, mddev->chunk_sectors);
		rdev1->sectors = sectors * mddev->chunk_sectors;

		list_for_each_entry(rdev2, &mddev->disks, same_set) {
			printk(KERN_INFO "raid0:   comparing %s(%llu)",
			       bdevname(rdev1->bdev,b),
			       (unsigned long long)rdev1->sectors);
			printk(KERN_INFO " with %s(%llu)\n",
			       bdevname(rdev2->bdev,b),
			       (unsigned long long)rdev2->sectors);
			if (rdev2 == rdev1) {
				printk(KERN_INFO "raid0:   END\n");
				break;
			}
			if (rdev2->sectors == rdev1->sectors) {
				/*
				 * Not unique, don't count it as a new
				 * group
				 */
				printk(KERN_INFO "raid0:   EQUAL\n");
				c = 1;
				break;
			}
			printk(KERN_INFO "raid0:   NOT EQUAL\n");
		}
		if (!c) {
			printk(KERN_INFO "raid0:   ==> UNIQUE\n");
			conf->nr_strip_zones++;
			printk(KERN_INFO "raid0: %d zones\n",
				conf->nr_strip_zones);
		}
	}
	printk(KERN_INFO "raid0: FINAL %d zones\n", conf->nr_strip_zones);
	err = -ENOMEM;
	conf->strip_zone = kzalloc(sizeof(struct strip_zone)*
				conf->nr_strip_zones, GFP_KERNEL);
	if (!conf->strip_zone)
		goto abort;
	conf->devlist = kzalloc(sizeof(mdk_rdev_t*)*
				conf->nr_strip_zones*mddev->raid_disks,
				GFP_KERNEL);
	if (!conf->devlist)
		goto abort;

	/* The first zone must contain all devices, so here we check that
	 * there is a proper alignment of slots to devices and find them all
	 */
	zone = &conf->strip_zone[0];
	cnt = 0;
	smallest = NULL;
	dev = conf->devlist;
	err = -EINVAL;
	list_for_each_entry(rdev1, &mddev->disks, same_set) {
		int j = rdev1->raid_disk;

		if (j < 0 || j >= mddev->raid_disks) {
			printk(KERN_ERR "raid0: bad disk number %d - "
				"aborting!\n", j);
			goto abort;
		}
		if (dev[j]) {
			printk(KERN_ERR "raid0: multiple devices for %d - "
				"aborting!\n", j);
			goto abort;
		}
		dev[j] = rdev1;

		disk_stack_limits(mddev->gendisk, rdev1->bdev,
				  rdev1->data_offset << 9);
		/* 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 (rdev1->bdev->bd_disk->queue->merge_bvec_fn &&
		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);

		if (!smallest || (rdev1->sectors < smallest->sectors))
			smallest = rdev1;
		cnt++;
	}
	if (cnt != mddev->raid_disks) {
		printk(KERN_ERR "raid0: too few disks (%d of %d) - "
			"aborting!\n", cnt, mddev->raid_disks);
		goto abort;
	}
	zone->nb_dev = cnt;
	zone->zone_end = smallest->sectors * cnt;

	curr_zone_end = zone->zone_end;

	/* now do the other zones */
	for (i = 1; i < conf->nr_strip_zones; i++)
	{
		int j;

		zone = conf->strip_zone + i;
		dev = conf->devlist + i * mddev->raid_disks;

		printk(KERN_INFO "raid0: zone %d\n", i);
		zone->dev_start = smallest->sectors;
		smallest = NULL;
		c = 0;

		for (j=0; j<cnt; j++) {
			rdev = conf->devlist[j];
			printk(KERN_INFO "raid0: checking %s ...",
				bdevname(rdev->bdev, b));
			if (rdev->sectors <= zone->dev_start) {
				printk(KERN_INFO " nope.\n");
				continue;
			}
			printk(KERN_INFO " contained as device %d\n", c);
			dev[c] = rdev;
			c++;
			if (!smallest || rdev->sectors < smallest->sectors) {
				smallest = rdev;
				printk(KERN_INFO "  (%llu) is smallest!.\n",
					(unsigned long long)rdev->sectors);
			}
		}

		zone->nb_dev = c;
		sectors = (smallest->sectors - zone->dev_start) * c;
		printk(KERN_INFO "raid0: zone->nb_dev: %d, sectors: %llu\n",
			zone->nb_dev, (unsigned long long)sectors);

		curr_zone_end += sectors;
		zone->zone_end = curr_zone_end;

		printk(KERN_INFO "raid0: current zone start: %llu\n",
			(unsigned long long)smallest->sectors);
	}
	mddev->queue->unplug_fn = raid0_unplug;
	mddev->queue->backing_dev_info.congested_fn = raid0_congested;
	mddev->queue->backing_dev_info.congested_data = mddev;

	/*
	 * now since we have the hard sector sizes, we can make sure
	 * chunk size is a multiple of that sector size
	 */
	if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
		printk(KERN_ERR "%s chunk_size of %d not valid\n",
		       mdname(mddev),
		       mddev->chunk_sectors << 9);
		goto abort;
	}

	blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
	blk_queue_io_opt(mddev->queue,
			 (mddev->chunk_sectors << 9) * mddev->raid_disks);

	printk(KERN_INFO "raid0: done.\n");
	mddev->private = conf;
	return 0;
abort:
	kfree(conf->strip_zone);
	kfree(conf->devlist);
	kfree(conf);
	mddev->private = NULL;
	return err;
}

/**
 *	raid0_mergeable_bvec -- tell bio layer if a two requests can be merged
 *	@q: request queue
 *	@bvm: properties of new bio
 *	@biovec: the request that could be merged to it.
 *
 *	Return amount of bytes we can accept at this offset
 */
static int raid0_mergeable_bvec(struct request_queue *q,
				struct bvec_merge_data *bvm,
				struct bio_vec *biovec)
{
	mddev_t *mddev = q->queuedata;
	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
	int max;
	unsigned int chunk_sectors = mddev->chunk_sectors;
	unsigned int bio_sectors = bvm->bi_size >> 9;

	if (is_power_of_2(chunk_sectors))
		max =  (chunk_sectors - ((sector & (chunk_sectors-1))
						+ bio_sectors)) << 9;
	else
		max =  (chunk_sectors - (sector_div(sector, chunk_sectors)
						+ bio_sectors)) << 9;
	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
	if (max <= biovec->bv_len && bio_sectors == 0)
		return biovec->bv_len;
	else 
		return max;
}

static sector_t raid0_size(mddev_t *mddev, sector_t sectors, int raid_disks)
{
	sector_t array_sectors = 0;
	mdk_rdev_t *rdev;

	WARN_ONCE(sectors || raid_disks,
		  "%s does not support generic reshape\n", __func__);

	list_for_each_entry(rdev, &mddev->disks, same_set)
		array_sectors += rdev->sectors;

	return array_sectors;
}

static int raid0_run(mddev_t *mddev)
{
	int ret;

	if (mddev->chunk_sectors == 0) {
		printk(KERN_ERR "md/raid0: chunk size must be set.\n");
		return -EINVAL;
	}
	if (md_check_no_bitmap(mddev))
		return -EINVAL;
	blk_queue_max_sectors(mddev->queue, mddev->chunk_sectors);
	mddev->queue->queue_lock = &mddev->queue->__queue_lock;

	ret = create_strip_zones(mddev);
	if (ret < 0)
		return ret;

	/* calculate array device size */
	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));

	printk(KERN_INFO "raid0 : md_size is %llu sectors.\n",
		(unsigned long long)mddev->array_sectors);
	/* calculate the max read-ahead size.
	 * For read-ahead of large files to be effective, we need to
	 * readahead at least twice a whole stripe. i.e. number of devices
	 * multiplied by chunk size times 2.
	 * If an individual device has an ra_pages greater than the
	 * chunk size, then we will not drive that device as hard as it
	 * wants.  We consider this a configuration error: a larger
	 * chunksize should be used in that case.
	 */
	{
		int stripe = mddev->raid_disks *
			(mddev->chunk_sectors << 9) / PAGE_SIZE;
		if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
	}

	blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
	dump_zones(mddev);
	md_integrity_register(mddev);
	return 0;
}

static int raid0_stop(mddev_t *mddev)
{
	raid0_conf_t *conf = mddev->private;

	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
	kfree(conf->strip_zone);
	kfree(conf->devlist);
	kfree(conf);
	mddev->private = NULL;
	return 0;
}

/* Find the zone which holds a particular offset
 * Update *sectorp to be an offset in that zone
 */
static struct strip_zone *find_zone(struct raid0_private_data *conf,
				    sector_t *sectorp)
{
	int i;
	struct strip_zone *z = conf->strip_zone;
	sector_t sector = *sectorp;

	for (i = 0; i < conf->nr_strip_zones; i++)
		if (sector < z[i].zone_end) {
			if (i)
				*sectorp = sector - z[i-1].zone_end;
			return z + i;
		}
	BUG();
}

/*
 * remaps the bio to the target device. we separate two flows.
 * power 2 flow and a general flow for the sake of perfromance
*/
static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone,
				sector_t sector, sector_t *sector_offset)
{
	unsigned int sect_in_chunk;
	sector_t chunk;
	raid0_conf_t *conf = mddev->private;
	unsigned int chunk_sects = mddev->chunk_sectors;

	if (is_power_of_2(chunk_sects)) {
		int chunksect_bits = ffz(~chunk_sects);
		/* find the sector offset inside the chunk */
		sect_in_chunk  = sector & (chunk_sects - 1);
		sector >>= chunksect_bits;
		/* chunk in zone */
		chunk = *sector_offset;
		/* quotient is the chunk in real device*/
		sector_div(chunk, zone->nb_dev << chunksect_bits);
	} else{
		sect_in_chunk = sector_div(sector, chunk_sects);
		chunk = *sector_offset;
		sector_div(chunk, chunk_sects * zone->nb_dev);
	}
	/*
	*  position the bio over the real device
	*  real sector = chunk in device + starting of zone
	*	+ the position in the chunk
	*/
	*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
	return conf->devlist[(zone - conf->strip_zone)*mddev->raid_disks
			     + sector_div(sector, zone->nb_dev)];
}

/*
 * Is io distribute over 1 or more chunks ?
*/
static inline int is_io_in_chunk_boundary(mddev_t *mddev,
			unsigned int chunk_sects, struct bio *bio)
{
	if (likely(is_power_of_2(chunk_sects))) {
		return chunk_sects >= ((bio->bi_sector & (chunk_sects-1))
					+ (bio->bi_size >> 9));
	} else{
		sector_t sector = bio->bi_sector;
		return chunk_sects >= (sector_div(sector, chunk_sects)
						+ (bio->bi_size >> 9));
	}
}

static int raid0_make_request(struct request_queue *q, struct bio *bio)
{
	mddev_t *mddev = q->queuedata;
	unsigned int chunk_sects;
	sector_t sector_offset;
	struct strip_zone *zone;
	mdk_rdev_t *tmp_dev;
	const int rw = bio_data_dir(bio);
	int cpu;

	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
		bio_endio(bio, -EOPNOTSUPP);
		return 0;
	}

	cpu = part_stat_lock();
	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
		      bio_sectors(bio));
	part_stat_unlock();

	chunk_sects = mddev->chunk_sectors;
	if (unlikely(!is_io_in_chunk_boundary(mddev, chunk_sects, bio))) {
		sector_t sector = bio->bi_sector;
		struct bio_pair *bp;
		/* Sanity check -- queue functions should prevent this happening */
		if (bio->bi_vcnt != 1 ||
		    bio->bi_idx != 0)
			goto bad_map;
		/* This is a one page bio that upper layers
		 * refuse to split for us, so we need to split it.
		 */
		if (likely(is_power_of_2(chunk_sects)))
			bp = bio_split(bio, chunk_sects - (sector &
							   (chunk_sects-1)));
		else
			bp = bio_split(bio, chunk_sects -
				       sector_div(sector, chunk_sects));
		if (raid0_make_request(q, &bp->bio1))
			generic_make_request(&bp->bio1);
		if (raid0_make_request(q, &bp->bio2))
			generic_make_request(&bp->bio2);

		bio_pair_release(bp);
		return 0;
	}

	sector_offset = bio->bi_sector;
	zone =  find_zone(mddev->private, &sector_offset);
	tmp_dev = map_sector(mddev, zone, bio->bi_sector,
			     &sector_offset);
	bio->bi_bdev = tmp_dev->bdev;
	bio->bi_sector = sector_offset + zone->dev_start +
		tmp_dev->data_offset;
	/*
	 * Let the main block layer submit the IO and resolve recursion:
	 */
	return 1;

bad_map:
	printk("raid0_make_request bug: can't convert block across chunks"
		" or bigger than %dk %llu %d\n", chunk_sects / 2,
		(unsigned long long)bio->bi_sector, bio->bi_size >> 10);

	bio_io_error(bio);
	return 0;
}

static void raid0_status(struct seq_file *seq, mddev_t *mddev)
{
#undef MD_DEBUG
#ifdef MD_DEBUG
	int j, k, h;
	char b[BDEVNAME_SIZE];
	raid0_conf_t *conf = mddev->private;

	sector_t zone_size;
	sector_t zone_start = 0;
	h = 0;

	for (j = 0; j < conf->nr_strip_zones; j++) {
		seq_printf(seq, "      z%d", j);
		seq_printf(seq, "=[");
		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
			seq_printf(seq, "%s/", bdevname(
				conf->devlist[j*mddev->raid_disks + k]
						->bdev, b));

		zone_size  = conf->strip_zone[j].zone_end - zone_start;
		seq_printf(seq, "] ze=%lld ds=%lld s=%lld\n",
			(unsigned long long)zone_start>>1,
			(unsigned long long)conf->strip_zone[j].dev_start>>1,
			(unsigned long long)zone_size>>1);
		zone_start = conf->strip_zone[j].zone_end;
	}
#endif
	seq_printf(seq, " %dk chunks", mddev->chunk_sectors / 2);
	return;
}

static struct mdk_personality raid0_personality=
{
	.name		= "raid0",
	.level		= 0,
	.owner		= THIS_MODULE,
	.make_request	= raid0_make_request,
	.run		= raid0_run,
	.stop		= raid0_stop,
	.status		= raid0_status,
	.size		= raid0_size,
};

static int __init raid0_init (void)
{
	return register_md_personality (&raid0_personality);
}

static void raid0_exit (void)
{
	unregister_md_personality (&raid0_personality);
}

module_init(raid0_init);
module_exit(raid0_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-2"); /* RAID0 */
MODULE_ALIAS("md-raid0");
MODULE_ALIAS("md-level-0");