summaryrefslogtreecommitdiffstats
path: root/drivers/md/md.h
blob: 10f98200e2f8a38a43d1dc158b84bf633f4d7e66 (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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
   md.h : kernel internal structure of the Linux MD driver
          Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman

*/

#ifndef _MD_MD_H
#define _MD_MD_H

#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/badblocks.h>
#include <linux/kobject.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/timer.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include "md-cluster.h"

#define MaxSector (~(sector_t)0)

/*
 * These flags should really be called "NO_RETRY" rather than
 * "FAILFAST" because they don't make any promise about time lapse,
 * only about the number of retries, which will be zero.
 * REQ_FAILFAST_DRIVER is not included because
 * Commit: 4a27446f3e39 ("[SCSI] modify scsi to handle new fail fast flags.")
 * seems to suggest that the errors it avoids retrying should usually
 * be retried.
 */
#define	MD_FAILFAST	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT)
/*
 * MD's 'extended' device
 */
struct md_rdev {
	struct list_head same_set;	/* RAID devices within the same set */

	sector_t sectors;		/* Device size (in 512bytes sectors) */
	struct mddev *mddev;		/* RAID array if running */
	int last_events;		/* IO event timestamp */

	/*
	 * If meta_bdev is non-NULL, it means that a separate device is
	 * being used to store the metadata (superblock/bitmap) which
	 * would otherwise be contained on the same device as the data (bdev).
	 */
	struct block_device *meta_bdev;
	struct block_device *bdev;	/* block device handle */

	struct page	*sb_page, *bb_page;
	int		sb_loaded;
	__u64		sb_events;
	sector_t	data_offset;	/* start of data in array */
	sector_t	new_data_offset;/* only relevant while reshaping */
	sector_t	sb_start;	/* offset of the super block (in 512byte sectors) */
	int		sb_size;	/* bytes in the superblock */
	int		preferred_minor;	/* autorun support */

	struct kobject	kobj;

	/* A device can be in one of three states based on two flags:
	 * Not working:   faulty==1 in_sync==0
	 * Fully working: faulty==0 in_sync==1
	 * Working, but not
	 * in sync with array
	 *                faulty==0 in_sync==0
	 *
	 * It can never have faulty==1, in_sync==1
	 * This reduces the burden of testing multiple flags in many cases
	 */

	unsigned long	flags;	/* bit set of 'enum flag_bits' bits. */
	wait_queue_head_t blocked_wait;

	int desc_nr;			/* descriptor index in the superblock */
	int raid_disk;			/* role of device in array */
	int new_raid_disk;		/* role that the device will have in
					 * the array after a level-change completes.
					 */
	int saved_raid_disk;		/* role that device used to have in the
					 * array and could again if we did a partial
					 * resync from the bitmap
					 */
	union {
		sector_t recovery_offset;/* If this device has been partially
					 * recovered, this is where we were
					 * up to.
					 */
		sector_t journal_tail;	/* If this device is a journal device,
					 * this is the journal tail (journal
					 * recovery start point)
					 */
	};

	atomic_t	nr_pending;	/* number of pending requests.
					 * only maintained for arrays that
					 * support hot removal
					 */
	atomic_t	read_errors;	/* number of consecutive read errors that
					 * we have tried to ignore.
					 */
	time64_t	last_read_error;	/* monotonic time since our
						 * last read error
						 */
	atomic_t	corrected_errors; /* number of corrected read errors,
					   * for reporting to userspace and storing
					   * in superblock.
					   */

	/*
	 * The members for check collision of write behind IOs.
	 */
	struct list_head wb_list;
	spinlock_t wb_list_lock;
	wait_queue_head_t wb_io_wait;

	struct work_struct del_work;	/* used for delayed sysfs removal */

	struct kernfs_node *sysfs_state; /* handle for 'state'
					   * sysfs entry */

	struct badblocks badblocks;

	struct {
		short offset;	/* Offset from superblock to start of PPL.
				 * Not used by external metadata. */
		unsigned int size;	/* Size in sectors of the PPL space */
		sector_t sector;	/* First sector of the PPL space */
	} ppl;
};
enum flag_bits {
	Faulty,			/* device is known to have a fault */
	In_sync,		/* device is in_sync with rest of array */
	Bitmap_sync,		/* ..actually, not quite In_sync.  Need a
				 * bitmap-based recovery to get fully in sync.
				 * The bit is only meaningful before device
				 * has been passed to pers->hot_add_disk.
				 */
	WriteMostly,		/* Avoid reading if at all possible */
	AutoDetected,		/* added by auto-detect */
	Blocked,		/* An error occurred but has not yet
				 * been acknowledged by the metadata
				 * handler, so don't allow writes
				 * until it is cleared */
	WriteErrorSeen,		/* A write error has been seen on this
				 * device
				 */
	FaultRecorded,		/* Intermediate state for clearing
				 * Blocked.  The Fault is/will-be
				 * recorded in the metadata, but that
				 * metadata hasn't been stored safely
				 * on disk yet.
				 */
	BlockedBadBlocks,	/* A writer is blocked because they
				 * found an unacknowledged bad-block.
				 * This can safely be cleared at any
				 * time, and the writer will re-check.
				 * It may be set at any time, and at
				 * worst the writer will timeout and
				 * re-check.  So setting it as
				 * accurately as possible is good, but
				 * not absolutely critical.
				 */
	WantReplacement,	/* This device is a candidate to be
				 * hot-replaced, either because it has
				 * reported some faults, or because
				 * of explicit request.
				 */
	Replacement,		/* This device is a replacement for
				 * a want_replacement device with same
				 * raid_disk number.
				 */
	Candidate,		/* For clustered environments only:
				 * This device is seen locally but not
				 * by the whole cluster
				 */
	Journal,		/* This device is used as journal for
				 * raid-5/6.
				 * Usually, this device should be faster
				 * than other devices in the array
				 */
	ClusterRemove,
	RemoveSynchronized,	/* synchronize_rcu() was called after
				 * this device was known to be faulty,
				 * so it is safe to remove without
				 * another synchronize_rcu() call.
				 */
	ExternalBbl,            /* External metadata provides bad
				 * block management for a disk
				 */
	FailFast,		/* Minimal retries should be attempted on
				 * this device, so use REQ_FAILFAST_DEV.
				 * Also don't try to repair failed reads.
				 * It is expects that no bad block log
				 * is present.
				 */
	LastDev,		/* Seems to be the last working dev as
				 * it didn't fail, so don't use FailFast
				 * any more for metadata
				 */
	WBCollisionCheck,	/*
				 * multiqueue device should check if there
				 * is collision between write behind bios.
				 */
};

static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
			      sector_t *first_bad, int *bad_sectors)
{
	if (unlikely(rdev->badblocks.count)) {
		int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s,
					sectors,
					first_bad, bad_sectors);
		if (rv)
			*first_bad -= rdev->data_offset;
		return rv;
	}
	return 0;
}
extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
			      int is_new);
extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
				int is_new);
struct md_cluster_info;

/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
enum mddev_flags {
	MD_ARRAY_FIRST_USE,	/* First use of array, needs initialization */
	MD_CLOSING,		/* If set, we are closing the array, do not open
				 * it then */
	MD_JOURNAL_CLEAN,	/* A raid with journal is already clean */
	MD_HAS_JOURNAL,		/* The raid array has journal feature set */
	MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node
				   * already took resync lock, need to
				   * release the lock */
	MD_FAILFAST_SUPPORTED,	/* Using MD_FAILFAST on metadata writes is
				 * supported as calls to md_error() will
				 * never cause the array to become failed.
				 */
	MD_HAS_PPL,		/* The raid array has PPL feature set */
	MD_HAS_MULTIPLE_PPLS,	/* The raid array has multiple PPLs feature set */
	MD_ALLOW_SB_UPDATE,	/* md_check_recovery is allowed to update
				 * the metadata without taking reconfig_mutex.
				 */
	MD_UPDATING_SB,		/* md_check_recovery is updating the metadata
				 * without explicitly holding reconfig_mutex.
				 */
};

enum mddev_sb_flags {
	MD_SB_CHANGE_DEVS,		/* Some device status has changed */
	MD_SB_CHANGE_CLEAN,	/* transition to or from 'clean' */
	MD_SB_CHANGE_PENDING,	/* switch from 'clean' to 'active' in progress */
	MD_SB_NEED_REWRITE,	/* metadata write needs to be repeated */
};

#define NR_WB_INFOS	8
/* record current range of write behind IOs */
struct wb_info {
	sector_t lo;
	sector_t hi;
	struct list_head list;
};

struct mddev {
	void				*private;
	struct md_personality		*pers;
	dev_t				unit;
	int				md_minor;
	struct list_head		disks;
	unsigned long			flags;
	unsigned long			sb_flags;

	int				suspended;
	atomic_t			active_io;
	int				ro;
	int				sysfs_active; /* set when sysfs deletes
						       * are happening, so run/
						       * takeover/stop are not safe
						       */
	struct gendisk			*gendisk;

	struct kobject			kobj;
	int				hold_active;
#define	UNTIL_IOCTL	1
#define	UNTIL_STOP	2

	/* Superblock information */
	int				major_version,
					minor_version,
					patch_version;
	int				persistent;
	int				external;	/* metadata is
							 * managed externally */
	char				metadata_type[17]; /* externally set*/
	int				chunk_sectors;
	time64_t			ctime, utime;
	int				level, layout;
	char				clevel[16];
	int				raid_disks;
	int				max_disks;
	sector_t			dev_sectors;	/* used size of
							 * component devices */
	sector_t			array_sectors; /* exported array size */
	int				external_size; /* size managed
							* externally */
	__u64				events;
	/* If the last 'event' was simply a clean->dirty transition, and
	 * we didn't write it to the spares, then it is safe and simple
	 * to just decrement the event count on a dirty->clean transition.
	 * So we record that possibility here.
	 */
	int				can_decrease_events;

	char				uuid[16];

	/* If the array is being reshaped, we need to record the
	 * new shape and an indication of where we are up to.
	 * This is written to the superblock.
	 * If reshape_position is MaxSector, then no reshape is happening (yet).
	 */
	sector_t			reshape_position;
	int				delta_disks, new_level, new_layout;
	int				new_chunk_sectors;
	int				reshape_backwards;

	struct md_thread		*thread;	/* management thread */
	struct md_thread		*sync_thread;	/* doing resync or reconstruct */

	/* 'last_sync_action' is initialized to "none".  It is set when a
	 * sync operation (i.e "data-check", "requested-resync", "resync",
	 * "recovery", or "reshape") is started.  It holds this value even
	 * when the sync thread is "frozen" (interrupted) or "idle" (stopped
	 * or finished).  It is overwritten when a new sync operation is begun.
	 */
	char				*last_sync_action;
	sector_t			curr_resync;	/* last block scheduled */
	/* As resync requests can complete out of order, we cannot easily track
	 * how much resync has been completed.  So we occasionally pause until
	 * everything completes, then set curr_resync_completed to curr_resync.
	 * As such it may be well behind the real resync mark, but it is a value
	 * we are certain of.
	 */
	sector_t			curr_resync_completed;
	unsigned long			resync_mark;	/* a recent timestamp */
	sector_t			resync_mark_cnt;/* blocks written at resync_mark */
	sector_t			curr_mark_cnt; /* blocks scheduled now */

	sector_t			resync_max_sectors; /* may be set by personality */

	atomic64_t			resync_mismatches; /* count of sectors where
							    * parity/replica mismatch found
							    */

	/* allow user-space to request suspension of IO to regions of the array */
	sector_t			suspend_lo;
	sector_t			suspend_hi;
	/* if zero, use the system-wide default */
	int				sync_speed_min;
	int				sync_speed_max;

	/* resync even though the same disks are shared among md-devices */
	int				parallel_resync;

	int				ok_start_degraded;

	unsigned long			recovery;
	/* If a RAID personality determines that recovery (of a particular
	 * device) will fail due to a read error on the source device, it
	 * takes a copy of this number and does not attempt recovery again
	 * until this number changes.
	 */
	int				recovery_disabled;

	int				in_sync;	/* know to not need resync */
	/* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so
	 * that we are never stopping an array while it is open.
	 * 'reconfig_mutex' protects all other reconfiguration.
	 * These locks are separate due to conflicting interactions
	 * with bdev->bd_mutex.
	 * Lock ordering is:
	 *  reconfig_mutex -> bd_mutex : e.g. do_md_run -> revalidate_disk
	 *  bd_mutex -> open_mutex:  e.g. __blkdev_get -> md_open
	 */
	struct mutex			open_mutex;
	struct mutex			reconfig_mutex;
	atomic_t			active;		/* general refcount */
	atomic_t			openers;	/* number of active opens */

	int				changed;	/* True if we might need to
							 * reread partition info */
	int				degraded;	/* whether md should consider
							 * adding a spare
							 */

	atomic_t			recovery_active; /* blocks scheduled, but not written */
	wait_queue_head_t		recovery_wait;
	sector_t			recovery_cp;
	sector_t			resync_min;	/* user requested sync
							 * starts here */
	sector_t			resync_max;	/* resync should pause
							 * when it gets here */

	struct kernfs_node		*sysfs_state;	/* handle for 'array_state'
							 * file in sysfs.
							 */
	struct kernfs_node		*sysfs_action;  /* handle for 'sync_action' */

	struct work_struct del_work;	/* used for delayed sysfs removal */

	/* "lock" protects:
	 *   flush_bio transition from NULL to !NULL
	 *   rdev superblocks, events
	 *   clearing MD_CHANGE_*
	 *   in_sync - and related safemode and MD_CHANGE changes
	 *   pers (also protected by reconfig_mutex and pending IO).
	 *   clearing ->bitmap
	 *   clearing ->bitmap_info.file
	 *   changing ->resync_{min,max}
	 *   setting MD_RECOVERY_RUNNING (which interacts with resync_{min,max})
	 */
	spinlock_t			lock;
	wait_queue_head_t		sb_wait;	/* for waiting on superblock updates */
	atomic_t			pending_writes;	/* number of active superblock writes */

	unsigned int			safemode;	/* if set, update "clean" superblock
							 * when no writes pending.
							 */
	unsigned int			safemode_delay;
	struct timer_list		safemode_timer;
	struct percpu_ref		writes_pending;
	int				sync_checkers;	/* # of threads checking writes_pending */
	struct request_queue		*queue;	/* for plugging ... */

	struct bitmap			*bitmap; /* the bitmap for the device */
	struct {
		struct file		*file; /* the bitmap file */
		loff_t			offset; /* offset from superblock of
						 * start of bitmap. May be
						 * negative, but not '0'
						 * For external metadata, offset
						 * from start of device.
						 */
		unsigned long		space; /* space available at this offset */
		loff_t			default_offset; /* this is the offset to use when
							 * hot-adding a bitmap.  It should
							 * eventually be settable by sysfs.
							 */
		unsigned long		default_space; /* space available at
							* default offset */
		struct mutex		mutex;
		unsigned long		chunksize;
		unsigned long		daemon_sleep; /* how many jiffies between updates? */
		unsigned long		max_write_behind; /* write-behind mode */
		int			external;
		int			nodes; /* Maximum number of nodes in the cluster */
		char                    cluster_name[64]; /* Name of the cluster */
	} bitmap_info;

	atomic_t			max_corr_read_errors; /* max read retries */
	struct list_head		all_mddevs;

	struct attribute_group		*to_remove;

	struct bio_set			bio_set;
	struct bio_set			sync_set; /* for sync operations like
						   * metadata and bitmap writes
						   */

	/* Generic flush handling.
	 * The last to finish preflush schedules a worker to submit
	 * the rest of the request (without the REQ_PREFLUSH flag).
	 */
	struct bio *flush_bio;
	atomic_t flush_pending;
	ktime_t start_flush, last_flush; /* last_flush is when the last completed
					  * flush was started.
					  */
	struct work_struct flush_work;
	struct work_struct event_work;	/* used by dm to report failure event */
	mempool_t *wb_info_pool;
	void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);
	struct md_cluster_info		*cluster_info;
	unsigned int			good_device_nr;	/* good device num within cluster raid */

	bool	has_superblocks:1;
};

enum recovery_flags {
	/*
	 * If neither SYNC or RESHAPE are set, then it is a recovery.
	 */
	MD_RECOVERY_RUNNING,	/* a thread is running, or about to be started */
	MD_RECOVERY_SYNC,	/* actually doing a resync, not a recovery */
	MD_RECOVERY_RECOVER,	/* doing recovery, or need to try it. */
	MD_RECOVERY_INTR,	/* resync needs to be aborted for some reason */
	MD_RECOVERY_DONE,	/* thread is done and is waiting to be reaped */
	MD_RECOVERY_NEEDED,	/* we might need to start a resync/recover */
	MD_RECOVERY_REQUESTED,	/* user-space has requested a sync (used with SYNC) */
	MD_RECOVERY_CHECK,	/* user-space request for check-only, no repair */
	MD_RECOVERY_RESHAPE,	/* A reshape is happening */
	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
};

static inline int __must_check mddev_lock(struct mddev *mddev)
{
	return mutex_lock_interruptible(&mddev->reconfig_mutex);
}

/* Sometimes we need to take the lock in a situation where
 * failure due to interrupts is not acceptable.
 */
static inline void mddev_lock_nointr(struct mddev *mddev)
{
	mutex_lock(&mddev->reconfig_mutex);
}

static inline int mddev_trylock(struct mddev *mddev)
{
	return mutex_trylock(&mddev->reconfig_mutex);
}
extern void mddev_unlock(struct mddev *mddev);

static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
{
	atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
}

static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors)
{
	atomic_add(nr_sectors, &bio->bi_disk->sync_io);
}

struct md_personality
{
	char *name;
	int level;
	struct list_head list;
	struct module *owner;
	bool (*make_request)(struct mddev *mddev, struct bio *bio);
	/*
	 * start up works that do NOT require md_thread. tasks that
	 * requires md_thread should go into start()
	 */
	int (*run)(struct mddev *mddev);
	/* start up works that require md threads */
	int (*start)(struct mddev *mddev);
	void (*free)(struct mddev *mddev, void *priv);
	void (*status)(struct seq_file *seq, struct mddev *mddev);
	/* error_handler must set ->faulty and clear ->in_sync
	 * if appropriate, and should abort recovery if needed
	 */
	void (*error_handler)(struct mddev *mddev, struct md_rdev *rdev);
	int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev);
	int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev);
	int (*spare_active) (struct mddev *mddev);
	sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped);
	int (*resize) (struct mddev *mddev, sector_t sectors);
	sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks);
	int (*check_reshape) (struct mddev *mddev);
	int (*start_reshape) (struct mddev *mddev);
	void (*finish_reshape) (struct mddev *mddev);
	void (*update_reshape_pos) (struct mddev *mddev);
	/* quiesce suspends or resumes internal processing.
	 * 1 - stop new actions and wait for action io to complete
	 * 0 - return to normal behaviour
	 */
	void (*quiesce) (struct mddev *mddev, int quiesce);
	/* takeover is used to transition an array from one
	 * personality to another.  The new personality must be able
	 * to handle the data in the current layout.
	 * e.g. 2drive raid1 -> 2drive raid5
	 *      ndrive raid5 -> degraded n+1drive raid6 with special layout
	 * If the takeover succeeds, a new 'private' structure is returned.
	 * This needs to be installed and then ->run used to activate the
	 * array.
	 */
	void *(*takeover) (struct mddev *mddev);
	/* congested implements bdi.congested_fn().
	 * Will not be called while array is 'suspended' */
	int (*congested)(struct mddev *mddev, int bits);
	/* Changes the consistency policy of an active array. */
	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
};

struct md_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct mddev *, char *);
	ssize_t (*store)(struct mddev *, const char *, size_t);
};
extern struct attribute_group md_bitmap_group;

static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name)
{
	if (sd)
		return sysfs_get_dirent(sd, name);
	return sd;
}
static inline void sysfs_notify_dirent_safe(struct kernfs_node *sd)
{
	if (sd)
		sysfs_notify_dirent(sd);
}

static inline char * mdname (struct mddev * mddev)
{
	return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
}

static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev)
{
	char nm[20];
	if (!test_bit(Replacement, &rdev->flags) &&
	    !test_bit(Journal, &rdev->flags) &&
	    mddev->kobj.sd) {
		sprintf(nm, "rd%d", rdev->raid_disk);
		return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
	} else
		return 0;
}

static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev)
{
	char nm[20];
	if (!test_bit(Replacement, &rdev->flags) &&
	    !test_bit(Journal, &rdev->flags) &&
	    mddev->kobj.sd) {
		sprintf(nm, "rd%d", rdev->raid_disk);
		sysfs_remove_link(&mddev->kobj, nm);
	}
}

/*
 * iterates through some rdev ringlist. It's safe to remove the
 * current 'rdev'. Dont touch 'tmp' though.
 */
#define rdev_for_each_list(rdev, tmp, head)				\
	list_for_each_entry_safe(rdev, tmp, head, same_set)

/*
 * iterates through the 'same array disks' ringlist
 */
#define rdev_for_each(rdev, mddev)				\
	list_for_each_entry(rdev, &((mddev)->disks), same_set)

#define rdev_for_each_safe(rdev, tmp, mddev)				\
	list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set)

#define rdev_for_each_rcu(rdev, mddev)				\
	list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set)

struct md_thread {
	void			(*run) (struct md_thread *thread);
	struct mddev		*mddev;
	wait_queue_head_t	wqueue;
	unsigned long		flags;
	struct task_struct	*tsk;
	unsigned long		timeout;
	void			*private;
};

#define THREAD_WAKEUP  0

static inline void safe_put_page(struct page *p)
{
	if (p) put_page(p);
}

extern int register_md_personality(struct md_personality *p);
extern int unregister_md_personality(struct md_personality *p);
extern int register_md_cluster_operations(struct md_cluster_operations *ops,
		struct module *module);
extern int unregister_md_cluster_operations(void);
extern int md_setup_cluster(struct mddev *mddev, int nodes);
extern void md_cluster_stop(struct mddev *mddev);
extern struct md_thread *md_register_thread(
	void (*run)(struct md_thread *thread),
	struct mddev *mddev,
	const char *name);
extern void md_unregister_thread(struct md_thread **threadp);
extern void md_wakeup_thread(struct md_thread *thread);
extern void md_check_recovery(struct mddev *mddev);
extern void md_reap_sync_thread(struct mddev *mddev);
extern int mddev_init_writes_pending(struct mddev *mddev);
extern bool md_write_start(struct mddev *mddev, struct bio *bi);
extern void md_write_inc(struct mddev *mddev, struct bio *bi);
extern void md_write_end(struct mddev *mddev);
extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
extern void md_finish_reshape(struct mddev *mddev);

extern int mddev_congested(struct mddev *mddev, int bits);
extern void md_flush_request(struct mddev *mddev, struct bio *bio);
extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
			   sector_t sector, int size, struct page *page);
extern int md_super_wait(struct mddev *mddev);
extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
			struct page *page, int op, int op_flags,
			bool metadata_op);
extern void md_do_sync(struct md_thread *thread);
extern void md_new_event(struct mddev *mddev);
extern void md_allow_write(struct mddev *mddev);
extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
extern int md_check_no_bitmap(struct mddev *mddev);
extern int md_integrity_register(struct mddev *mddev);
extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);

extern void mddev_init(struct mddev *mddev);
extern int md_run(struct mddev *mddev);
extern int md_start(struct mddev *mddev);
extern void md_stop(struct mddev *mddev);
extern void md_stop_writes(struct mddev *mddev);
extern int md_rdev_init(struct md_rdev *rdev);
extern void md_rdev_clear(struct md_rdev *rdev);

extern void md_handle_request(struct mddev *mddev, struct bio *bio);
extern void mddev_suspend(struct mddev *mddev);
extern void mddev_resume(struct mddev *mddev);
extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
				   struct mddev *mddev);

extern void md_reload_sb(struct mddev *mddev, int raid_disk);
extern void md_update_sb(struct mddev *mddev, int force);
extern void md_kick_rdev_from_array(struct md_rdev * rdev);
extern void mddev_create_wb_pool(struct mddev *mddev, struct md_rdev *rdev,
				 bool is_suspend);
struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev);

static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
{
	int faulty = test_bit(Faulty, &rdev->flags);
	if (atomic_dec_and_test(&rdev->nr_pending) && faulty) {
		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
		md_wakeup_thread(mddev->thread);
	}
}

extern struct md_cluster_operations *md_cluster_ops;
static inline int mddev_is_clustered(struct mddev *mddev)
{
	return mddev->cluster_info && mddev->bitmap_info.nodes > 1;
}

/* clear unsupported mddev_flags */
static inline void mddev_clear_unsupported_flags(struct mddev *mddev,
	unsigned long unsupported_flags)
{
	mddev->flags &= ~unsupported_flags;
}

static inline void mddev_check_writesame(struct mddev *mddev, struct bio *bio)
{
	if (bio_op(bio) == REQ_OP_WRITE_SAME &&
	    !bio->bi_disk->queue->limits.max_write_same_sectors)
		mddev->queue->limits.max_write_same_sectors = 0;
}

static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio)
{
	if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
	    !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
		mddev->queue->limits.max_write_zeroes_sectors = 0;
}
#endif /* _MD_MD_H */