aboutsummaryrefslogtreecommitdiffstats
path: root/block/genhd.c
blob: b431d65439429a91cca1e996464ad931d1b3eaf5 (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
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
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
/*
 *  gendisk handling
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/kdev_t.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/kobj_map.h>
#include <linux/buffer_head.h>
#include <linux/mutex.h>

#include "blk.h"

static DEFINE_MUTEX(block_class_lock);
#ifndef CONFIG_SYSFS_DEPRECATED
struct kobject *block_depr;
#endif

static struct device_type disk_type;

/**
 * disk_get_part - get partition
 * @disk: disk to look partition from
 * @partno: partition number
 *
 * Look for partition @partno from @disk.  If found, increment
 * reference count and return it.
 *
 * CONTEXT:
 * Don't care.
 *
 * RETURNS:
 * Pointer to the found partition on success, NULL if not found.
 */
struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
{
	struct hd_struct *part;

	if (unlikely(partno < 1 || partno > disk_max_parts(disk)))
		return NULL;
	rcu_read_lock();
	part = rcu_dereference(disk->__part[partno - 1]);
	if (part)
		get_device(&part->dev);
	rcu_read_unlock();

	return part;
}
EXPORT_SYMBOL_GPL(disk_get_part);

/**
 * disk_part_iter_init - initialize partition iterator
 * @piter: iterator to initialize
 * @disk: disk to iterate over
 * @flags: DISK_PITER_* flags
 *
 * Initialize @piter so that it iterates over partitions of @disk.
 *
 * CONTEXT:
 * Don't care.
 */
void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
			  unsigned int flags)
{
	piter->disk = disk;
	piter->part = NULL;

	if (flags & DISK_PITER_REVERSE)
		piter->idx = disk_max_parts(piter->disk) - 1;
	else
		piter->idx = 0;

	piter->flags = flags;
}
EXPORT_SYMBOL_GPL(disk_part_iter_init);

/**
 * disk_part_iter_next - proceed iterator to the next partition and return it
 * @piter: iterator of interest
 *
 * Proceed @piter to the next partition and return it.
 *
 * CONTEXT:
 * Don't care.
 */
struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
{
	int inc, end;

	/* put the last partition */
	disk_put_part(piter->part);
	piter->part = NULL;

	rcu_read_lock();

	/* determine iteration parameters */
	if (piter->flags & DISK_PITER_REVERSE) {
		inc = -1;
		end = -1;
	} else {
		inc = 1;
		end = disk_max_parts(piter->disk);
	}

	/* iterate to the next partition */
	for (; piter->idx != end; piter->idx += inc) {
		struct hd_struct *part;

		part = rcu_dereference(piter->disk->__part[piter->idx]);
		if (!part)
			continue;
		if (!(piter->flags & DISK_PITER_INCL_EMPTY) && !part->nr_sects)
			continue;

		get_device(&part->dev);
		piter->part = part;
		piter->idx += inc;
		break;
	}

	rcu_read_unlock();

	return piter->part;
}
EXPORT_SYMBOL_GPL(disk_part_iter_next);

/**
 * disk_part_iter_exit - finish up partition iteration
 * @piter: iter of interest
 *
 * Called when iteration is over.  Cleans up @piter.
 *
 * CONTEXT:
 * Don't care.
 */
void disk_part_iter_exit(struct disk_part_iter *piter)
{
	disk_put_part(piter->part);
	piter->part = NULL;
}
EXPORT_SYMBOL_GPL(disk_part_iter_exit);

/**
 * disk_map_sector_rcu - map sector to partition
 * @disk: gendisk of interest
 * @sector: sector to map
 *
 * Find out which partition @sector maps to on @disk.  This is
 * primarily used for stats accounting.
 *
 * CONTEXT:
 * RCU read locked.  The returned partition pointer is valid only
 * while preemption is disabled.
 *
 * RETURNS:
 * Found partition on success, NULL if there's no matching partition.
 */
struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
{
	int i;

	for (i = 0; i < disk_max_parts(disk); i++) {
		struct hd_struct *part = rcu_dereference(disk->__part[i]);

		if (part && part->start_sect <= sector &&
		    sector < part->start_sect + part->nr_sects)
			return part;
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(disk_map_sector_rcu);

/*
 * Can be deleted altogether. Later.
 *
 */
static struct blk_major_name {
	struct blk_major_name *next;
	int major;
	char name[16];
} *major_names[BLKDEV_MAJOR_HASH_SIZE];

/* index in the above - for now: assume no multimajor ranges */
static inline int major_to_index(int major)
{
	return major % BLKDEV_MAJOR_HASH_SIZE;
}

#ifdef CONFIG_PROC_FS
void blkdev_show(struct seq_file *seqf, off_t offset)
{
	struct blk_major_name *dp;

	if (offset < BLKDEV_MAJOR_HASH_SIZE) {
		mutex_lock(&block_class_lock);
		for (dp = major_names[offset]; dp; dp = dp->next)
			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
		mutex_unlock(&block_class_lock);
	}
}
#endif /* CONFIG_PROC_FS */

int register_blkdev(unsigned int major, const char *name)
{
	struct blk_major_name **n, *p;
	int index, ret = 0;

	mutex_lock(&block_class_lock);

	/* temporary */
	if (major == 0) {
		for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) {
			if (major_names[index] == NULL)
				break;
		}

		if (index == 0) {
			printk("register_blkdev: failed to get major for %s\n",
			       name);
			ret = -EBUSY;
			goto out;
		}
		major = index;
		ret = major;
	}

	p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL);
	if (p == NULL) {
		ret = -ENOMEM;
		goto out;
	}

	p->major = major;
	strlcpy(p->name, name, sizeof(p->name));
	p->next = NULL;
	index = major_to_index(major);

	for (n = &major_names[index]; *n; n = &(*n)->next) {
		if ((*n)->major == major)
			break;
	}
	if (!*n)
		*n = p;
	else
		ret = -EBUSY;

	if (ret < 0) {
		printk("register_blkdev: cannot get major %d for %s\n",
		       major, name);
		kfree(p);
	}
out:
	mutex_unlock(&block_class_lock);
	return ret;
}

EXPORT_SYMBOL(register_blkdev);

void unregister_blkdev(unsigned int major, const char *name)
{
	struct blk_major_name **n;
	struct blk_major_name *p = NULL;
	int index = major_to_index(major);

	mutex_lock(&block_class_lock);
	for (n = &major_names[index]; *n; n = &(*n)->next)
		if ((*n)->major == major)
			break;
	if (!*n || strcmp((*n)->name, name)) {
		WARN_ON(1);
	} else {
		p = *n;
		*n = p->next;
	}
	mutex_unlock(&block_class_lock);
	kfree(p);
}

EXPORT_SYMBOL(unregister_blkdev);

static struct kobj_map *bdev_map;

/*
 * Register device numbers dev..(dev+range-1)
 * range must be nonzero
 * The hash chain is sorted on range, so that subranges can override.
 */
void blk_register_region(dev_t devt, unsigned long range, struct module *module,
			 struct kobject *(*probe)(dev_t, int *, void *),
			 int (*lock)(dev_t, void *), void *data)
{
	kobj_map(bdev_map, devt, range, module, probe, lock, data);
}

EXPORT_SYMBOL(blk_register_region);

void blk_unregister_region(dev_t devt, unsigned long range)
{
	kobj_unmap(bdev_map, devt, range);
}

EXPORT_SYMBOL(blk_unregister_region);

static struct kobject *exact_match(dev_t devt, int *partno, void *data)
{
	struct gendisk *p = data;

	return &p->dev.kobj;
}

static int exact_lock(dev_t devt, void *data)
{
	struct gendisk *p = data;

	if (!get_disk(p))
		return -1;
	return 0;
}

/**
 * add_disk - add partitioning information to kernel list
 * @disk: per-device partitioning information
 *
 * This function registers the partitioning information in @disk
 * with the kernel.
 */
void add_disk(struct gendisk *disk)
{
	struct backing_dev_info *bdi;
	int retval;

	disk->flags |= GENHD_FL_UP;
	disk->dev.devt = MKDEV(disk->major, disk->first_minor);
	blk_register_region(disk_devt(disk), disk->minors, NULL,
			    exact_match, exact_lock, disk);
	register_disk(disk);
	blk_register_queue(disk);

	bdi = &disk->queue->backing_dev_info;
	bdi_register_dev(bdi, disk_devt(disk));
	retval = sysfs_create_link(&disk->dev.kobj, &bdi->dev->kobj, "bdi");
	WARN_ON(retval);
}

EXPORT_SYMBOL(add_disk);
EXPORT_SYMBOL(del_gendisk);	/* in partitions/check.c */

void unlink_gendisk(struct gendisk *disk)
{
	sysfs_remove_link(&disk->dev.kobj, "bdi");
	bdi_unregister(&disk->queue->backing_dev_info);
	blk_unregister_queue(disk);
	blk_unregister_region(disk_devt(disk), disk->minors);
}

/**
 * get_gendisk - get partitioning information for a given device
 * @devt: device to get partitioning information for
 * @part: returned partition index
 *
 * This function gets the structure containing partitioning
 * information for the given device @devt.
 */
struct gendisk *get_gendisk(dev_t devt, int *partno)
{
	struct kobject *kobj = kobj_lookup(bdev_map, devt, partno);
	struct device *dev = kobj_to_dev(kobj);

	return  kobj ? dev_to_disk(dev) : NULL;
}

/**
 * bdget_disk - do bdget() by gendisk and partition number
 * @disk: gendisk of interest
 * @partno: partition number
 *
 * Find partition @partno from @disk, do bdget() on it.
 *
 * CONTEXT:
 * Don't care.
 *
 * RETURNS:
 * Resulting block_device on success, NULL on failure.
 */
extern struct block_device *bdget_disk(struct gendisk *disk, int partno)
{
	dev_t devt = MKDEV(0, 0);

	if (partno == 0)
		devt = disk_devt(disk);
	else {
		struct hd_struct *part;

		part = disk_get_part(disk, partno);
		if (part && part->nr_sects)
			devt = part_devt(part);
		disk_put_part(part);
	}

	if (likely(devt != MKDEV(0, 0)))
		return bdget(devt);
	return NULL;
}
EXPORT_SYMBOL(bdget_disk);

/*
 * print a full list of all partitions - intended for places where the root
 * filesystem can't be mounted and thus to give the victim some idea of what
 * went wrong
 */
void __init printk_all_partitions(void)
{
	struct class_dev_iter iter;
	struct device *dev;

	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
	while ((dev = class_dev_iter_next(&iter))) {
		struct gendisk *disk = dev_to_disk(dev);
		struct disk_part_iter piter;
		struct hd_struct *part;
		char buf[BDEVNAME_SIZE];

		/*
		 * Don't show empty devices or things that have been
		 * surpressed
		 */
		if (get_capacity(disk) == 0 ||
		    (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO))
			continue;

		/*
		 * Note, unlike /proc/partitions, I am showing the
		 * numbers in hex - the same format as the root=
		 * option takes.
		 */
		printk("%02x%02x %10llu %s",
		       MAJOR(disk_devt(disk)), MINOR(disk_devt(disk)),
		       (unsigned long long)get_capacity(disk) >> 1,
		       disk_name(disk, 0, buf));
		if (disk->driverfs_dev != NULL &&
		    disk->driverfs_dev->driver != NULL)
			printk(" driver: %s\n",
			       disk->driverfs_dev->driver->name);
		else
			printk(" (driver?)\n");

		/* now show the partitions */
		disk_part_iter_init(&piter, disk, 0);
		while ((part = disk_part_iter_next(&piter)))
			printk("  %02x%02x %10llu %s\n",
			       MAJOR(part_devt(part)), MINOR(part_devt(part)),
			       (unsigned long long)part->nr_sects >> 1,
			       disk_name(disk, part->partno, buf));
		disk_part_iter_exit(&piter);
	}
	class_dev_iter_exit(&iter);
}

#ifdef CONFIG_PROC_FS
/* iterator */
static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos)
{
	loff_t skip = *pos;
	struct class_dev_iter *iter;
	struct device *dev;

	iter = kmalloc(GFP_KERNEL, sizeof(*iter));
	if (!iter)
		return ERR_PTR(-ENOMEM);

	seqf->private = iter;
	class_dev_iter_init(iter, &block_class, NULL, &disk_type);
	do {
		dev = class_dev_iter_next(iter);
		if (!dev)
			return NULL;
	} while (skip--);

	return dev_to_disk(dev);
}

static void *disk_seqf_next(struct seq_file *seqf, void *v, loff_t *pos)
{
	struct device *dev;

	(*pos)++;
	dev = class_dev_iter_next(seqf->private);
	if (dev)
		return dev_to_disk(dev);

	return NULL;
}

static void disk_seqf_stop(struct seq_file *seqf, void *v)
{
	struct class_dev_iter *iter = seqf->private;

	/* stop is called even after start failed :-( */
	if (iter) {
		class_dev_iter_exit(iter);
		kfree(iter);
	}
}

static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
{
	static void *p;

	p = disk_seqf_start(seqf, pos);
	if (!IS_ERR(p) && p)
		seq_puts(seqf, "major minor  #blocks  name\n\n");
	return p;
}

static int show_partition(struct seq_file *seqf, void *v)
{
	struct gendisk *sgp = v;
	struct disk_part_iter piter;
	struct hd_struct *part;
	char buf[BDEVNAME_SIZE];

	/* Don't show non-partitionable removeable devices or empty devices */
	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
				   (sgp->flags & GENHD_FL_REMOVABLE)))
		return 0;
	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
		return 0;

	/* show the full disk and all non-0 size partitions of it */
	seq_printf(seqf, "%4d  %4d %10llu %s\n",
		MAJOR(disk_devt(sgp)), MINOR(disk_devt(sgp)),
		(unsigned long long)get_capacity(sgp) >> 1,
		disk_name(sgp, 0, buf));

	disk_part_iter_init(&piter, sgp, 0);
	while ((part = disk_part_iter_next(&piter)))
		seq_printf(seqf, "%4d  %4d %10llu %s\n",
			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
			   (unsigned long long)part->nr_sects >> 1,
			   disk_name(sgp, part->partno, buf));
	disk_part_iter_exit(&piter);

	return 0;
}

const struct seq_operations partitions_op = {
	.start	= show_partition_start,
	.next	= disk_seqf_next,
	.stop	= disk_seqf_stop,
	.show	= show_partition
};
#endif


static struct kobject *base_probe(dev_t devt, int *partno, void *data)
{
	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
		/* Make old-style 2.4 aliases work */
		request_module("block-major-%d", MAJOR(devt));
	return NULL;
}

static int __init genhd_device_init(void)
{
	int error;

	block_class.dev_kobj = sysfs_dev_block_kobj;
	error = class_register(&block_class);
	if (unlikely(error))
		return error;
	bdev_map = kobj_map_init(base_probe, &block_class_lock);
	blk_dev_init();

#ifndef CONFIG_SYSFS_DEPRECATED
	/* create top-level block dir */
	block_depr = kobject_create_and_add("block", NULL);
#endif
	return 0;
}

subsys_initcall(genhd_device_init);

static ssize_t disk_range_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);

	return sprintf(buf, "%d\n", disk->minors);
}

static ssize_t disk_removable_show(struct device *dev,
				   struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);

	return sprintf(buf, "%d\n",
		       (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
}

static ssize_t disk_ro_show(struct device *dev,
				   struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);

	return sprintf(buf, "%d\n", disk->policy ? 1 : 0);
}

static ssize_t disk_size_show(struct device *dev,
			      struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);

	return sprintf(buf, "%llu\n", (unsigned long long)get_capacity(disk));
}

static ssize_t disk_capability_show(struct device *dev,
				    struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);

	return sprintf(buf, "%x\n", disk->flags);
}

static ssize_t disk_stat_show(struct device *dev,
			      struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);

	preempt_disable();
	disk_round_stats(disk);
	preempt_enable();
	return sprintf(buf,
		"%8lu %8lu %8llu %8u "
		"%8lu %8lu %8llu %8u "
		"%8u %8u %8u"
		"\n",
		disk_stat_read(disk, ios[READ]),
		disk_stat_read(disk, merges[READ]),
		(unsigned long long)disk_stat_read(disk, sectors[READ]),
		jiffies_to_msecs(disk_stat_read(disk, ticks[READ])),
		disk_stat_read(disk, ios[WRITE]),
		disk_stat_read(disk, merges[WRITE]),
		(unsigned long long)disk_stat_read(disk, sectors[WRITE]),
		jiffies_to_msecs(disk_stat_read(disk, ticks[WRITE])),
		disk->in_flight,
		jiffies_to_msecs(disk_stat_read(disk, io_ticks)),
		jiffies_to_msecs(disk_stat_read(disk, time_in_queue)));
}

#ifdef CONFIG_FAIL_MAKE_REQUEST
static ssize_t disk_fail_show(struct device *dev,
			      struct device_attribute *attr, char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);

	return sprintf(buf, "%d\n", disk->flags & GENHD_FL_FAIL ? 1 : 0);
}

static ssize_t disk_fail_store(struct device *dev,
			       struct device_attribute *attr,
			       const char *buf, size_t count)
{
	struct gendisk *disk = dev_to_disk(dev);
	int i;

	if (count > 0 && sscanf(buf, "%d", &i) > 0) {
		if (i == 0)
			disk->flags &= ~GENHD_FL_FAIL;
		else
			disk->flags |= GENHD_FL_FAIL;
	}

	return count;
}

#endif

static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
static DEVICE_ATTR(size, S_IRUGO, disk_size_show, NULL);
static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
static DEVICE_ATTR(stat, S_IRUGO, disk_stat_show, NULL);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static struct device_attribute dev_attr_fail =
	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, disk_fail_show, disk_fail_store);
#endif

static struct attribute *disk_attrs[] = {
	&dev_attr_range.attr,
	&dev_attr_removable.attr,
	&dev_attr_ro.attr,
	&dev_attr_size.attr,
	&dev_attr_capability.attr,
	&dev_attr_stat.attr,
#ifdef CONFIG_FAIL_MAKE_REQUEST
	&dev_attr_fail.attr,
#endif
	NULL
};

static struct attribute_group disk_attr_group = {
	.attrs = disk_attrs,
};

static struct attribute_group *disk_attr_groups[] = {
	&disk_attr_group,
	NULL
};

static void disk_release(struct device *dev)
{
	struct gendisk *disk = dev_to_disk(dev);

	kfree(disk->random);
	kfree(disk->__part);
	free_disk_stats(disk);
	kfree(disk);
}
struct class block_class = {
	.name		= "block",
};

static struct device_type disk_type = {
	.name		= "disk",
	.groups		= disk_attr_groups,
	.release	= disk_release,
};

#ifdef CONFIG_PROC_FS
/*
 * aggregate disk stat collector.  Uses the same stats that the sysfs
 * entries do, above, but makes them available through one seq_file.
 *
 * The output looks suspiciously like /proc/partitions with a bunch of
 * extra fields.
 */
static int diskstats_show(struct seq_file *seqf, void *v)
{
	struct gendisk *gp = v;
	struct disk_part_iter piter;
	struct hd_struct *hd;
	char buf[BDEVNAME_SIZE];

	/*
	if (&gp->dev.kobj.entry == block_class.devices.next)
		seq_puts(seqf,	"major minor name"
				"     rio rmerge rsect ruse wio wmerge "
				"wsect wuse running use aveq"
				"\n\n");
	*/
 
	preempt_disable();
	disk_round_stats(gp);
	preempt_enable();
	seq_printf(seqf, "%4d %4d %s %lu %lu %llu %u %lu %lu %llu %u %u %u %u\n",
		MAJOR(disk_devt(gp)), MINOR(disk_devt(gp)),
		disk_name(gp, 0, buf),
		disk_stat_read(gp, ios[0]), disk_stat_read(gp, merges[0]),
		(unsigned long long)disk_stat_read(gp, sectors[0]),
		jiffies_to_msecs(disk_stat_read(gp, ticks[0])),
		disk_stat_read(gp, ios[1]), disk_stat_read(gp, merges[1]),
		(unsigned long long)disk_stat_read(gp, sectors[1]),
		jiffies_to_msecs(disk_stat_read(gp, ticks[1])),
		gp->in_flight,
		jiffies_to_msecs(disk_stat_read(gp, io_ticks)),
		jiffies_to_msecs(disk_stat_read(gp, time_in_queue)));

	/* now show all non-0 size partitions of it */
	disk_part_iter_init(&piter, gp, 0);
	while ((hd = disk_part_iter_next(&piter))) {
		preempt_disable();
		part_round_stats(hd);
		preempt_enable();
		seq_printf(seqf, "%4d %4d %s %lu %lu %llu "
			   "%u %lu %lu %llu %u %u %u %u\n",
			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
			   disk_name(gp, hd->partno, buf),
			   part_stat_read(hd, ios[0]),
			   part_stat_read(hd, merges[0]),
			   (unsigned long long)part_stat_read(hd, sectors[0]),
			   jiffies_to_msecs(part_stat_read(hd, ticks[0])),
			   part_stat_read(hd, ios[1]),
			   part_stat_read(hd, merges[1]),
			   (unsigned long long)part_stat_read(hd, sectors[1]),
			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
			   hd->in_flight,
			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
			);
	}
	disk_part_iter_exit(&piter);
 
	return 0;
}

const struct seq_operations diskstats_op = {
	.start	= disk_seqf_start,
	.next	= disk_seqf_next,
	.stop	= disk_seqf_stop,
	.show	= diskstats_show
};
#endif /* CONFIG_PROC_FS */

static void media_change_notify_thread(struct work_struct *work)
{
	struct gendisk *gd = container_of(work, struct gendisk, async_notify);
	char event[] = "MEDIA_CHANGE=1";
	char *envp[] = { event, NULL };

	/*
	 * set enviroment vars to indicate which event this is for
	 * so that user space will know to go check the media status.
	 */
	kobject_uevent_env(&gd->dev.kobj, KOBJ_CHANGE, envp);
	put_device(gd->driverfs_dev);
}

#if 0
void genhd_media_change_notify(struct gendisk *disk)
{
	get_device(disk->driverfs_dev);
	schedule_work(&disk->async_notify);
}
EXPORT_SYMBOL_GPL(genhd_media_change_notify);
#endif  /*  0  */

dev_t blk_lookup_devt(const char *name, int partno)
{
	dev_t devt = MKDEV(0, 0);
	struct class_dev_iter iter;
	struct device *dev;

	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
	while ((dev = class_dev_iter_next(&iter))) {
		struct gendisk *disk = dev_to_disk(dev);

		if (strcmp(dev->bus_id, name))
			continue;
		if (partno < 0 || partno > disk_max_parts(disk))
			continue;

		if (partno == 0)
			devt = disk_devt(disk);
		else {
			struct hd_struct *part;

			part = disk_get_part(disk, partno);
			if (!part || !part->nr_sects) {
				disk_put_part(part);
				continue;
			}

			devt = part_devt(part);
			disk_put_part(part);
		}
		break;
	}
	class_dev_iter_exit(&iter);
	return devt;
}
EXPORT_SYMBOL(blk_lookup_devt);

struct gendisk *alloc_disk(int minors)
{
	return alloc_disk_node(minors, -1);
}

struct gendisk *alloc_disk_node(int minors, int node_id)
{
	struct gendisk *disk;

	disk = kmalloc_node(sizeof(struct gendisk),
				GFP_KERNEL | __GFP_ZERO, node_id);
	if (disk) {
		if (!init_disk_stats(disk)) {
			kfree(disk);
			return NULL;
		}
		if (minors > 1) {
			int size = (minors - 1) * sizeof(struct hd_struct *);
			disk->__part = kmalloc_node(size,
				GFP_KERNEL | __GFP_ZERO, node_id);
			if (!disk->__part) {
				free_disk_stats(disk);
				kfree(disk);
				return NULL;
			}
		}
		disk->minors = minors;
		rand_initialize_disk(disk);
		disk->dev.class = &block_class;
		disk->dev.type = &disk_type;
		device_initialize(&disk->dev);
		INIT_WORK(&disk->async_notify,
			media_change_notify_thread);
	}
	return disk;
}

EXPORT_SYMBOL(alloc_disk);
EXPORT_SYMBOL(alloc_disk_node);

struct kobject *get_disk(struct gendisk *disk)
{
	struct module *owner;
	struct kobject *kobj;

	if (!disk->fops)
		return NULL;
	owner = disk->fops->owner;
	if (owner && !try_module_get(owner))
		return NULL;
	kobj = kobject_get(&disk->dev.kobj);
	if (kobj == NULL) {
		module_put(owner);
		return NULL;
	}
	return kobj;

}

EXPORT_SYMBOL(get_disk);

void put_disk(struct gendisk *disk)
{
	if (disk)
		kobject_put(&disk->dev.kobj);
}

EXPORT_SYMBOL(put_disk);

void set_device_ro(struct block_device *bdev, int flag)
{
	if (bdev->bd_contains != bdev)
		bdev->bd_part->policy = flag;
	else
		bdev->bd_disk->policy = flag;
}

EXPORT_SYMBOL(set_device_ro);

void set_disk_ro(struct gendisk *disk, int flag)
{
	struct disk_part_iter piter;
	struct hd_struct *part;

	disk->policy = flag;
	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
	while ((part = disk_part_iter_next(&piter)))
		part->policy = flag;
	disk_part_iter_exit(&piter);
}

EXPORT_SYMBOL(set_disk_ro);

int bdev_read_only(struct block_device *bdev)
{
	if (!bdev)
		return 0;
	else if (bdev->bd_contains != bdev)
		return bdev->bd_part->policy;
	else
		return bdev->bd_disk->policy;
}

EXPORT_SYMBOL(bdev_read_only);

int invalidate_partition(struct gendisk *disk, int partno)
{
	int res = 0;
	struct block_device *bdev = bdget_disk(disk, partno);
	if (bdev) {
		fsync_bdev(bdev);
		res = __invalidate_device(bdev);
		bdput(bdev);
	}
	return res;
}

EXPORT_SYMBOL(invalidate_partition);