summaryrefslogtreecommitdiff
path: root/drivers/md/raid1.h
blob: e0d676b4897498d22390600012da67e751b185ea (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
#ifndef _RAID1_H
#define _RAID1_H

typedef struct mirror_info mirror_info_t;

struct mirror_info {
	mdk_rdev_t	*rdev;
	sector_t	head_position;
};

/*
 * memory pools need a pointer to the mddev, so they can force an unplug
 * when memory is tight, and a count of the number of drives that the
 * pool was allocated for, so they know how much to allocate and free.
 * mddev->raid_disks cannot be used, as it can change while a pool is active
 * These two datums are stored in a kmalloced struct.
 */

struct pool_info {
	mddev_t *mddev;
	int	raid_disks;
};


typedef struct r1bio_s r1bio_t;

struct r1_private_data_s {
	mddev_t			*mddev;
	mirror_info_t		*mirrors;
	int			raid_disks;
	int			last_used;
	sector_t		next_seq_sect;
	spinlock_t		device_lock;

	struct list_head	retry_list;
	/* queue pending writes and submit them on unplug */
	struct bio_list		pending_bio_list;

	/* for use when syncing mirrors: */

	spinlock_t		resync_lock;
	int			nr_pending;
	int			nr_waiting;
	int			nr_queued;
	int			barrier;
	sector_t		next_resync;
	int			fullsync;  /* set to 1 if a full sync is needed,
					    * (fresh device added).
					    * Cleared when a sync completes.
					    */
	int			recovery_disabled; /* when the same as
						    * mddev->recovery_disabled
						    * we don't allow recovery
						    * to be attempted as we
						    * expect a read error
						    */

	wait_queue_head_t	wait_barrier;

	struct pool_info	*poolinfo;

	struct page		*tmppage;

	mempool_t *r1bio_pool;
	mempool_t *r1buf_pool;

	/* When taking over an array from a different personality, we store
	 * the new thread here until we fully activate the array.
	 */
	struct mdk_thread_s	*thread;
};

typedef struct r1_private_data_s conf_t;

/*
 * this is our 'private' RAID1 bio.
 *
 * it contains information about what kind of IO operations were started
 * for this RAID1 operation, and about their status:
 */

struct r1bio_s {
	atomic_t		remaining; /* 'have we finished' count,
					    * used from IRQ handlers
					    */
	atomic_t		behind_remaining; /* number of write-behind ios remaining
						 * in this BehindIO request
						 */
	sector_t		sector;
	int			sectors;
	unsigned long		state;
	mddev_t			*mddev;
	/*
	 * original bio going to /dev/mdx
	 */
	struct bio		*master_bio;
	/*
	 * if the IO is in READ direction, then this is where we read
	 */
	int			read_disk;

	struct list_head	retry_list;
	/* Next two are only valid when R1BIO_BehindIO is set */
	struct bio_vec		*behind_bvecs;
	int			behind_page_count;
	/*
	 * if the IO is in WRITE direction, then multiple bios are used.
	 * We choose the number when they are allocated.
	 */
	struct bio		*bios[0];
	/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
};

/* when we get a read error on a read-only array, we redirect to another
 * device without failing the first device, or trying to over-write to
 * correct the read error.  To keep track of bad blocks on a per-bio
 * level, we store IO_BLOCKED in the appropriate 'bios' pointer
 */
#define IO_BLOCKED ((struct bio *)1)
/* When we successfully write to a known bad-block, we need to remove the
 * bad-block marking which must be done from process context.  So we record
 * the success by setting bios[n] to IO_MADE_GOOD
 */
#define IO_MADE_GOOD ((struct bio *)2)

#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)

/* bits for r1bio.state */
#define	R1BIO_Uptodate	0
#define	R1BIO_IsSync	1
#define	R1BIO_Degraded	2
#define	R1BIO_BehindIO	3
/* Set ReadError on bios that experience a readerror so that
 * raid1d knows what to do with them.
 */
#define R1BIO_ReadError 4
/* For write-behind requests, we call bi_end_io when
 * the last non-write-behind device completes, providing
 * any write was successful.  Otherwise we call when
 * any write-behind write succeeds, otherwise we call
 * with failure when last write completes (and all failed).
 * Record that bi_end_io was called with this flag...
 */
#define	R1BIO_Returned 6
/* If a write for this request means we can clear some
 * known-bad-block records, we set this flag
 */
#define	R1BIO_MadeGood 7
#define	R1BIO_WriteError 8

extern int md_raid1_congested(mddev_t *mddev, int bits);

#endif