summaryrefslogtreecommitdiffstats
path: root/drivers/md/raid10.h
blob: 7c615613c3818c59264e34ebc2c6d91879c3d776 (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
#ifndef _RAID10_H
#define _RAID10_H

struct mirror_info {
	struct md_rdev	*rdev, *replacement;
	sector_t	head_position;
	int		recovery_disabled;	/* matches
						 * mddev->recovery_disabled
						 * when we shouldn't try
						 * recovering this device.
						 */
};

struct r10conf {
	struct mddev		*mddev;
	struct mirror_info	*mirrors;
	int			raid_disks;
	spinlock_t		device_lock;

	/* geometry */
	int			near_copies;  /* number of copies laid out
					       * raid0 style */
	int 			far_copies;   /* number of copies laid out
					       * at large strides across drives
					       */
	int			far_offset;   /* far_copies are offset by 1
					       * stripe instead of many
					       */
	int			copies;	      /* near_copies * far_copies.
					       * must be <= raid_disks
					       */
	sector_t		stride;	      /* distance between far copies.
					       * This is size / far_copies unless
					       * far_offset, in which case it is
					       * 1 stripe.
					       */

	sector_t		dev_sectors;  /* temp copy of
					       * mddev->dev_sectors */

	int			chunk_shift; /* shift from chunks to sectors */
	sector_t		chunk_mask;

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

	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			have_replacement; /* There is at least one
						   * replacement device.
						   */
	wait_queue_head_t	wait_barrier;

	mempool_t		*r10bio_pool;
	mempool_t		*r10buf_pool;
	struct page		*tmppage;

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

/*
 * this is our 'private' RAID10 bio.
 *
 * it contains information about what kind of IO operations were started
 * for this RAID10 operation, and about their status:
 */

struct r10bio {
	atomic_t		remaining; /* 'have we finished' count,
					    * used from IRQ handlers
					    */
	sector_t		sector;	/* virtual sector number */
	int			sectors;
	unsigned long		state;
	struct mddev		*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_slot;

	struct list_head	retry_list;
	/*
	 * if the IO is in WRITE direction, then multiple bios are used,
	 * one for each copy.
	 * When resyncing we also use one for each copy.
	 * When reconstructing, we use 2 bios, one for read, one for write.
	 * We choose the number when they are allocated.
	 * We sometimes need an extra bio to write to the replacement.
	 */
	struct {
		struct bio	*bio;
		union {
			struct bio	*repl_bio; /* used for resync and
						    * writes */
			struct md_rdev	*rdev;	   /* used for reads
						    * (read_slot >= 0) */
		};
		sector_t	addr;
		int		devnum;
	} devs[0];
};

/* 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 devs[n].bio to IO_MADE_GOOD
 */
#define IO_MADE_GOOD ((struct bio *)2)

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

/* bits for r10bio.state */
enum r10bio_state {
	R10BIO_Uptodate,
	R10BIO_IsSync,
	R10BIO_IsRecover,
	R10BIO_Degraded,
/* Set ReadError on bios that experience a read error
 * so that raid10d knows what to do with them.
 */
	R10BIO_ReadError,
/* If a write for this request means we can clear some
 * known-bad-block records, we set this flag.
 */
	R10BIO_MadeGood,
	R10BIO_WriteError,
};
#endif
OpenPOWER on IntegriCloud