free electrons

Embedded Linux Experts

  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
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
/*
 *  Code extracted from drivers/block/genhd.c
 *  Copyright (C) 1991-1998  Linus Torvalds
 *  Re-organised Feb 1998 Russell King
 *
 *  We now have independent partition support from the
 *  block drivers, which allows all the partition code to
 *  be grouped in one location, and it to be mostly self
 *  contained.
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
#include <linux/dax.h>
#include <linux/blktrace_api.h>

#include "partitions/check.h"

#ifdef CONFIG_BLK_DEV_MD
extern void md_autodetect_dev(dev_t dev);
#endif
 
/*
 * disk_name() is used by partition check code and the genhd driver.
 * It formats the devicename of the indicated disk into
 * the supplied buffer (of size at least 32), and returns
 * a pointer to that same buffer (for convenience).
 */

char *disk_name(struct gendisk *hd, int partno, char *buf)
{
	if (!partno)
		snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
	else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
		snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
	else
		snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);

	return buf;
}

const char *bdevname(struct block_device *bdev, char *buf)
{
	return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
}

EXPORT_SYMBOL(bdevname);

/*
 * There's very little reason to use this, you should really
 * have a struct block_device just about everywhere and use
 * bdevname() instead.
 */
const char *__bdevname(dev_t dev, char *buffer)
{
	scnprintf(buffer, BDEVNAME_SIZE, "unknown-block(%u,%u)",
				MAJOR(dev), MINOR(dev));
	return buffer;
}

EXPORT_SYMBOL(__bdevname);

static ssize_t part_partition_show(struct device *dev,
				   struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);

	return sprintf(buf, "%d\n", p->partno);
}

static ssize_t part_start_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);

	return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect);
}

ssize_t part_size_show(struct device *dev,
		       struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);
	return sprintf(buf, "%llu\n",(unsigned long long)part_nr_sects_read(p));
}

static ssize_t part_ro_show(struct device *dev,
			    struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);
	return sprintf(buf, "%d\n", p->policy ? 1 : 0);
}

static ssize_t part_alignment_offset_show(struct device *dev,
					  struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);
	return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
}

static ssize_t part_discard_alignment_show(struct device *dev,
					   struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);
	return sprintf(buf, "%u\n", p->discard_alignment);
}

ssize_t part_stat_show(struct device *dev,
		       struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);
	int cpu;

	cpu = part_stat_lock();
	part_round_stats(cpu, p);
	part_stat_unlock();
	return sprintf(buf,
		"%8lu %8lu %8llu %8u "
		"%8lu %8lu %8llu %8u "
		"%8u %8u %8u"
		"\n",
		part_stat_read(p, ios[READ]),
		part_stat_read(p, merges[READ]),
		(unsigned long long)part_stat_read(p, sectors[READ]),
		jiffies_to_msecs(part_stat_read(p, ticks[READ])),
		part_stat_read(p, ios[WRITE]),
		part_stat_read(p, merges[WRITE]),
		(unsigned long long)part_stat_read(p, sectors[WRITE]),
		jiffies_to_msecs(part_stat_read(p, ticks[WRITE])),
		part_in_flight(p),
		jiffies_to_msecs(part_stat_read(p, io_ticks)),
		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
}

ssize_t part_inflight_show(struct device *dev,
			struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);

	return sprintf(buf, "%8u %8u\n", atomic_read(&p->in_flight[0]),
		atomic_read(&p->in_flight[1]));
}

#ifdef CONFIG_FAIL_MAKE_REQUEST
ssize_t part_fail_show(struct device *dev,
		       struct device_attribute *attr, char *buf)
{
	struct hd_struct *p = dev_to_part(dev);

	return sprintf(buf, "%d\n", p->make_it_fail);
}

ssize_t part_fail_store(struct device *dev,
			struct device_attribute *attr,
			const char *buf, size_t count)
{
	struct hd_struct *p = dev_to_part(dev);
	int i;

	if (count > 0 && sscanf(buf, "%d", &i) > 0)
		p->make_it_fail = (i == 0) ? 0 : 1;

	return count;
}
#endif

static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
static DEVICE_ATTR(ro, S_IRUGO, part_ro_show, NULL);
static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
		   NULL);
static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static struct device_attribute dev_attr_fail =
	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
#endif

static struct attribute *part_attrs[] = {
	&dev_attr_partition.attr,
	&dev_attr_start.attr,
	&dev_attr_size.attr,
	&dev_attr_ro.attr,
	&dev_attr_alignment_offset.attr,
	&dev_attr_discard_alignment.attr,
	&dev_attr_stat.attr,
	&dev_attr_inflight.attr,
#ifdef CONFIG_FAIL_MAKE_REQUEST
	&dev_attr_fail.attr,
#endif
	NULL
};

static struct attribute_group part_attr_group = {
	.attrs = part_attrs,
};

static const struct attribute_group *part_attr_groups[] = {
	&part_attr_group,
#ifdef CONFIG_BLK_DEV_IO_TRACE
	&blk_trace_attr_group,
#endif
	NULL
};

static void part_release(struct device *dev)
{
	struct hd_struct *p = dev_to_part(dev);
	blk_free_devt(dev->devt);
	hd_free_part(p);
	kfree(p);
}

static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
{
	struct hd_struct *part = dev_to_part(dev);

	add_uevent_var(env, "PARTN=%u", part->partno);
	if (part->info && part->info->volname[0])
		add_uevent_var(env, "PARTNAME=%s", part->info->volname);
	return 0;
}

struct device_type part_type = {
	.name		= "partition",
	.groups		= part_attr_groups,
	.release	= part_release,
	.uevent		= part_uevent,
};

static void delete_partition_rcu_cb(struct rcu_head *head)
{
	struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);

	part->start_sect = 0;
	part->nr_sects = 0;
	part_stat_set_all(part, 0);
	put_device(part_to_dev(part));
}

void __delete_partition(struct percpu_ref *ref)
{
	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
}

void delete_partition(struct gendisk *disk, int partno)
{
	struct disk_part_tbl *ptbl = disk->part_tbl;
	struct hd_struct *part;

	if (partno >= ptbl->len)
		return;

	part = ptbl->part[partno];
	if (!part)
		return;

	rcu_assign_pointer(ptbl->part[partno], NULL);
	rcu_assign_pointer(ptbl->last_lookup, NULL);
	kobject_put(part->holder_dir);
	device_del(part_to_dev(part));

	hd_struct_kill(part);
}

static ssize_t whole_disk_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	return 0;
}
static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
		   whole_disk_show, NULL);

struct hd_struct *add_partition(struct gendisk *disk, int partno,
				sector_t start, sector_t len, int flags,
				struct partition_meta_info *info)
{
	struct hd_struct *p;
	dev_t devt = MKDEV(0, 0);
	struct device *ddev = disk_to_dev(disk);
	struct device *pdev;
	struct disk_part_tbl *ptbl;
	const char *dname;
	int err;

	err = disk_expand_part_tbl(disk, partno);
	if (err)
		return ERR_PTR(err);
	ptbl = disk->part_tbl;

	if (ptbl->part[partno])
		return ERR_PTR(-EBUSY);

	p = kzalloc(sizeof(*p), GFP_KERNEL);
	if (!p)
		return ERR_PTR(-EBUSY);

	if (!init_part_stats(p)) {
		err = -ENOMEM;
		goto out_free;
	}

	seqcount_init(&p->nr_sects_seq);
	pdev = part_to_dev(p);

	p->start_sect = start;
	p->alignment_offset =
		queue_limit_alignment_offset(&disk->queue->limits, start);
	p->discard_alignment =
		queue_limit_discard_alignment(&disk->queue->limits, start);
	p->nr_sects = len;
	p->partno = partno;
	p->policy = get_disk_ro(disk);

	if (info) {
		struct partition_meta_info *pinfo = alloc_part_info(disk);
		if (!pinfo)
			goto out_free_stats;
		memcpy(pinfo, info, sizeof(*info));
		p->info = pinfo;
	}

	dname = dev_name(ddev);
	if (isdigit(dname[strlen(dname) - 1]))
		dev_set_name(pdev, "%sp%d", dname, partno);
	else
		dev_set_name(pdev, "%s%d", dname, partno);

	device_initialize(pdev);
	pdev->class = &block_class;
	pdev->type = &part_type;
	pdev->parent = ddev;

	err = blk_alloc_devt(p, &devt);
	if (err)
		goto out_free_info;
	pdev->devt = devt;

	/* delay uevent until 'holders' subdir is created */
	dev_set_uevent_suppress(pdev, 1);
	err = device_add(pdev);
	if (err)
		goto out_put;

	err = -ENOMEM;
	p->holder_dir = kobject_create_and_add("holders", &pdev->kobj);
	if (!p->holder_dir)
		goto out_del;

	dev_set_uevent_suppress(pdev, 0);
	if (flags & ADDPART_FLAG_WHOLEDISK) {
		err = device_create_file(pdev, &dev_attr_whole_disk);
		if (err)
			goto out_del;
	}

	err = hd_ref_init(p);
	if (err) {
		if (flags & ADDPART_FLAG_WHOLEDISK)
			goto out_remove_file;
		goto out_del;
	}

	/* everything is up and running, commence */
	rcu_assign_pointer(ptbl->part[partno], p);

	/* suppress uevent if the disk suppresses it */
	if (!dev_get_uevent_suppress(ddev))
		kobject_uevent(&pdev->kobj, KOBJ_ADD);
	return p;

out_free_info:
	free_part_info(p);
out_free_stats:
	free_part_stats(p);
out_free:
	kfree(p);
	return ERR_PTR(err);
out_remove_file:
	device_remove_file(pdev, &dev_attr_whole_disk);
out_del:
	kobject_put(p->holder_dir);
	device_del(pdev);
out_put:
	put_device(pdev);
	blk_free_devt(devt);
	return ERR_PTR(err);
}

static bool disk_unlock_native_capacity(struct gendisk *disk)
{
	const struct block_device_operations *bdops = disk->fops;

	if (bdops->unlock_native_capacity &&
	    !(disk->flags & GENHD_FL_NATIVE_CAPACITY)) {
		printk(KERN_CONT "enabling native capacity\n");
		bdops->unlock_native_capacity(disk);
		disk->flags |= GENHD_FL_NATIVE_CAPACITY;
		return true;
	} else {
		printk(KERN_CONT "truncated\n");
		return false;
	}
}

static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
{
	struct disk_part_iter piter;
	struct hd_struct *part;
	int res;

	if (bdev->bd_part_count || bdev->bd_super)
		return -EBUSY;
	res = invalidate_partition(disk, 0);
	if (res)
		return res;

	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
	while ((part = disk_part_iter_next(&piter)))
		delete_partition(disk, part->partno);
	disk_part_iter_exit(&piter);

	return 0;
}

static bool part_zone_aligned(struct gendisk *disk,
			      struct block_device *bdev,
			      sector_t from, sector_t size)
{
	unsigned int zone_sectors = bdev_zone_sectors(bdev);

	/*
	 * If this function is called, then the disk is a zoned block device
	 * (host-aware or host-managed). This can be detected even if the
	 * zoned block device support is disabled (CONFIG_BLK_DEV_ZONED not
	 * set). In this case, however, only host-aware devices will be seen
	 * as a block device is not created for host-managed devices. Without
	 * zoned block device support, host-aware drives can still be used as
	 * regular block devices (no zone operation) and their zone size will
	 * be reported as 0. Allow this case.
	 */
	if (!zone_sectors)
		return true;

	/*
	 * Check partition start and size alignement. If the drive has a
	 * smaller last runt zone, ignore it and allow the partition to
	 * use it. Check the zone size too: it should be a power of 2 number
	 * of sectors.
	 */
	if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) {
		u32 rem;

		div_u64_rem(from, zone_sectors, &rem);
		if (rem)
			return false;
		if ((from + size) < get_capacity(disk)) {
			div_u64_rem(size, zone_sectors, &rem);
			if (rem)
				return false;
		}

	} else {

		if (from & (zone_sectors - 1))
			return false;
		if ((from + size) < get_capacity(disk) &&
		    (size & (zone_sectors - 1)))
			return false;

	}

	return true;
}

int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
{
	struct parsed_partitions *state = NULL;
	struct hd_struct *part;
	int p, highest, res;
rescan:
	if (state && !IS_ERR(state)) {
		free_partitions(state);
		state = NULL;
	}

	res = drop_partitions(disk, bdev);
	if (res)
		return res;

	if (disk->fops->revalidate_disk)
		disk->fops->revalidate_disk(disk);
	check_disk_size_change(disk, bdev);
	bdev->bd_invalidated = 0;
	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
		return 0;
	if (IS_ERR(state)) {
		/*
		 * I/O error reading the partition table.  If any
		 * partition code tried to read beyond EOD, retry
		 * after unlocking native capacity.
		 */
		if (PTR_ERR(state) == -ENOSPC) {
			printk(KERN_WARNING "%s: partition table beyond EOD, ",
			       disk->disk_name);
			if (disk_unlock_native_capacity(disk))
				goto rescan;
		}
		return -EIO;
	}
	/*
	 * If any partition code tried to read beyond EOD, try
	 * unlocking native capacity even if partition table is
	 * successfully read as we could be missing some partitions.
	 */
	if (state->access_beyond_eod) {
		printk(KERN_WARNING
		       "%s: partition table partially beyond EOD, ",
		       disk->disk_name);
		if (disk_unlock_native_capacity(disk))
			goto rescan;
	}

	/* tell userspace that the media / partition table may have changed */
	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);

	/* Detect the highest partition number and preallocate
	 * disk->part_tbl.  This is an optimization and not strictly
	 * necessary.
	 */
	for (p = 1, highest = 0; p < state->limit; p++)
		if (state->parts[p].size)
			highest = p;

	disk_expand_part_tbl(disk, highest);

	/* add partitions */
	for (p = 1; p < state->limit; p++) {
		sector_t size, from;

		size = state->parts[p].size;
		if (!size)
			continue;

		from = state->parts[p].from;
		if (from >= get_capacity(disk)) {
			printk(KERN_WARNING
			       "%s: p%d start %llu is beyond EOD, ",
			       disk->disk_name, p, (unsigned long long) from);
			if (disk_unlock_native_capacity(disk))
				goto rescan;
			continue;
		}

		if (from + size > get_capacity(disk)) {
			printk(KERN_WARNING
			       "%s: p%d size %llu extends beyond EOD, ",
			       disk->disk_name, p, (unsigned long long) size);

			if (disk_unlock_native_capacity(disk)) {
				/* free state and restart */
				goto rescan;
			} else {
				/*
				 * we can not ignore partitions of broken tables
				 * created by for example camera firmware, but
				 * we limit them to the end of the disk to avoid
				 * creating invalid block devices
				 */
				size = get_capacity(disk) - from;
			}
		}

		/*
		 * On a zoned block device, partitions should be aligned on the
		 * device zone size (i.e. zone boundary crossing not allowed).
		 * Otherwise, resetting the write pointer of the last zone of
		 * one partition may impact the following partition.
		 */
		if (bdev_is_zoned(bdev) &&
		    !part_zone_aligned(disk, bdev, from, size)) {
			printk(KERN_WARNING
			       "%s: p%d start %llu+%llu is not zone aligned\n",
			       disk->disk_name, p, (unsigned long long) from,
			       (unsigned long long) size);
			continue;
		}

		part = add_partition(disk, p, from, size,
				     state->parts[p].flags,
				     &state->parts[p].info);
		if (IS_ERR(part)) {
			printk(KERN_ERR " %s: p%d could not be added: %ld\n",
			       disk->disk_name, p, -PTR_ERR(part));
			continue;
		}
#ifdef CONFIG_BLK_DEV_MD
		if (state->parts[p].flags & ADDPART_FLAG_RAID)
			md_autodetect_dev(part_to_dev(part)->devt);
#endif
	}
	free_partitions(state);
	return 0;
}

int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
{
	int res;

	if (!bdev->bd_invalidated)
		return 0;

	res = drop_partitions(disk, bdev);
	if (res)
		return res;

	set_capacity(disk, 0);
	check_disk_size_change(disk, bdev);
	bdev->bd_invalidated = 0;
	/* tell userspace that the media / partition table may have changed */
	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);

	return 0;
}

static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n)
{
	struct address_space *mapping = bdev->bd_inode->i_mapping;

	return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_SHIFT-9)),
				 NULL);
}

unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
{
	struct page *page;

	/* don't populate page cache for dax capable devices */
	if (IS_DAX(bdev->bd_inode))
		page = read_dax_sector(bdev, n);
	else
		page = read_pagecache_sector(bdev, n);

	if (!IS_ERR(page)) {
		if (PageError(page))
			goto fail;
		p->v = page;
		return (unsigned char *)page_address(page) +  ((n & ((1 << (PAGE_SHIFT - 9)) - 1)) << 9);
fail:
		put_page(page);
	}
	p->v = NULL;
	return NULL;
}

EXPORT_SYMBOL(read_dev_sector);