aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/raid/raid5.h
blob: 55c738d50508e995cc4679901915753f0f663c99 (plain) (blame)
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
#ifndef _RAID5_H
#define _RAID5_H

#include <linux/raid/md.h>
#include <linux/raid/xor.h>

/*
 *
 * Each stripe contains one buffer per disc.  Each buffer can be in
 * one of a number of states stored in "flags".  Changes between
 * these states happen *almost* exclusively under a per-stripe
 * spinlock.  Some very specific changes can happen in bi_end_io, and
 * these are not protected by the spin lock.
 *
 * The flag bits that are used to represent these states are:
 *   R5_UPTODATE and R5_LOCKED
 *
 * State Empty == !UPTODATE, !LOCK
 *        We have no data, and there is no active request
 * State Want == !UPTODATE, LOCK
 *        A read request is being submitted for this block
 * State Dirty == UPTODATE, LOCK
 *        Some new data is in this buffer, and it is being written out
 * State Clean == UPTODATE, !LOCK
 *        We have valid data which is the same as on disc
 *
 * The possible state transitions are:
 *
 *  Empty -> Want   - on read or write to get old data for  parity calc
 *  Empty -> Dirty  - on compute_parity to satisfy write/sync request.(RECONSTRUCT_WRITE)
 *  Empty -> Clean  - on compute_block when computing a block for failed drive
 *  Want  -> Empty  - on failed read
 *  Want  -> Clean  - on successful completion of read request
 *  Dirty -> Clean  - on successful completion of write request
 *  Dirty -> Clean  - on failed write
 *  Clean -> Dirty  - on compute_parity to satisfy write/sync (RECONSTRUCT or RMW)
 *
 * The Want->Empty, Want->Clean, Dirty->Clean, transitions
 * all happen in b_end_io at interrupt time.
 * Each sets the Uptodate bit before releasing the Lock bit.
 * This leaves one multi-stage transition:
 *    Want->Dirty->Clean
 * This is safe because thinking that a Clean buffer is actually dirty
 * will at worst delay some action, and the stripe will be scheduled
 * for attention after the transition is complete.
 *
 * There is one possibility that is not covered by these states.  That
 * is if one drive has failed and there is a spare being rebuilt.  We
 * can't distinguish between a clean block that has been generated
 * from parity calculations, and a clean block that has been
 * successfully written to the spare ( or to parity when resyncing).
 * To distingush these states we have a stripe bit STRIPE_INSYNC that
 * is set whenever a write is scheduled to the spare, or to the parity
 * disc if there is no spare.  A sync request clears this bit, and
 * when we find it set with no buffers locked, we know the sync is
 * complete.
 *
 * Buffers for the md device that arrive via make_request are attached
 * to the appropriate stripe in one of two lists linked on b_reqnext.
 * One list (bh_read) for read requests, one (bh_write) for write.
 * There should never be more than one buffer on the two lists
 * together, but we are not guaranteed of that so we allow for more.
 *
 * If a buffer is on the read list when the associated cache buffer is
 * Uptodate, the data is copied into the read buffer and it's b_end_io
 * routine is called.  This may happen in the end_request routine only
 * if the buffer has just successfully been read.  end_request should
 * remove the buffers from the list and then set the Uptodate bit on
 * the buffer.  Other threads may do this only if they first check
 * that the Uptodate bit is set.  Once they have checked that they may
 * take buffers off the read queue.
 *
 * When a buffer on the write list is committed for write it is copied
 * into the cache buffer, which is then marked dirty, and moved onto a
 * third list, the written list (bh_written).  Once both the parity
 * block and the cached buffer are successfully written, any buffer on
 * a written list can be returned with b_end_io.
 *
 * The write list and read list both act as fifos.  The read list is
 * protected by the device_lock.  The write and written lists are
 * protected by the stripe lock.  The device_lock, which can be
 * claimed while the stipe lock is held, is only for list
 * manipulations and will only be held for a very short time.  It can
 * be claimed from interrupts.
 *
 *
 * Stripes in the stripe cache can be on one of two lists (or on
 * neither).  The "inactive_list" contains stripes which are not
 * currently being used for any request.  They can freely be reused
 * for another stripe.  The "handle_list" contains stripes that need
 * to be handled in some way.  Both of these are fifo queues.  Each
 * stripe is also (potentially) linked to a hash bucket in the hash
 * table so that it can be found by sector number.  Stripes that are
 * not hashed must be on the inactive_list, and will normally be at
 * the front.  All stripes start life this way.
 *
 * The inactive_list, handle_list and hash bucket lists are all protected by the
 * device_lock.
 *  - stripes on the inactive_list never have their stripe_lock held.
 *  - stripes have a reference counter. If count==0, they are on a list.
 *  - If a stripe might need handling, STRIPE_HANDLE is set.
 *  - When refcount reaches zero, then if STRIPE_HANDLE it is put on
 *    handle_list else inactive_list
 *
 * This, combined with the fact that STRIPE_HANDLE is only ever
 * cleared while a stripe has a non-zero count means that if the
 * refcount is 0 and STRIPE_HANDLE is set, then it is on the
 * handle_list and if recount is 0 and STRIPE_HANDLE is not set, then
 * the stripe is on inactive_list.
 *
 * The possible transitions are:
 *  activate an unhashed/inactive stripe (get_active_stripe())
 *     lockdev check-hash unlink-stripe cnt++ clean-stripe hash-stripe unlockdev
 *  activate a hashed, possibly active stripe (get_active_stripe())
 *     lockdev check-hash if(!cnt++)unlink-stripe unlockdev
 *  attach a request to an active stripe (add_stripe_bh())
 *     lockdev attach-buffer unlockdev
 *  handle a stripe (handle_stripe())
 *     lockstripe clrSTRIPE_HANDLE ... (lockdev check-buffers unlockdev) .. change-state .. record io needed unlockstripe schedule io
 *  release an active stripe (release_stripe())
 *     lockdev if (!--cnt) { if  STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev
 *
 * The refcount counts each thread that have activated the stripe,
 * plus raid5d if it is handling it, plus one for each active request
 * on a cached buffer.
 */

struct stripe_head {
	struct hlist_node	hash;
	struct list_head	lru;			/* inactive_list or handle_list */
	struct raid5_private_data	*raid_conf;
	sector_t		sector;			/* sector of this row */
	int			pd_idx;			/* parity disk index */
	unsigned long		state;			/* state flags */
	atomic_t		count;			/* nr of active thread/requests */
	spinlock_t		lock;
	int			bm_seq;	/* sequence number for bitmap flushes */
	int			disks;			/* disks in stripe */
	struct r5dev {
		struct bio	req;
		struct bio_vec	vec;
		struct page	*page;
		struct bio	*toread, *towrite, *written;
		sector_t	sector;			/* sector of this page */
		unsigned long	flags;
	} dev[1]; /* allocated with extra space depending of RAID geometry */
};
/* Flags */
#define	R5_UPTODATE	0	/* page contains current data */
#define	R5_LOCKED	1	/* IO has been submitted on "req" */
#define	R5_OVERWRITE	2	/* towrite covers whole page */
/* and some that are internal to handle_stripe */
#define	R5_Insync	3	/* rdev && rdev->in_sync at start */
#define	R5_Wantread	4	/* want to schedule a read */
#define	R5_Wantwrite	5
#define	R5_Overlap	7	/* There is a pending overlapping request on this block */
#define	R5_ReadError	8	/* seen a read error here recently */
#define	R5_ReWrite	9	/* have tried to over-write the readerror */

#define	R5_Expanded	10	/* This block now has post-expand data */
/*
 * Write method
 */
#define RECONSTRUCT_WRITE	1
#define READ_MODIFY_WRITE	2
/* not a write method, but a compute_parity mode */
#define	CHECK_PARITY		3

/*
 * Stripe state
 */
#define STRIPE_HANDLE		2
#define	STRIPE_SYNCING		3
#define	STRIPE_INSYNC		4
#define	STRIPE_PREREAD_ACTIVE	5
#define	STRIPE_DELAYED		6
#define	STRIPE_DEGRADED		7
#define	STRIPE_BIT_DELAY	8
#define	STRIPE_EXPANDING	9
#define	STRIPE_EXPAND_SOURCE	10
#define	STRIPE_EXPAND_READY	11
/*
 * Plugging:
 *
 * To improve write throughput, we need to delay the handling of some
 * stripes until there has been a chance that several write requests
 * for the one stripe have all been collected.
 * In particular, any write request that would require pre-reading
 * is put on a "delayed" queue until there are no stripes currently
 * in a pre-read phase.  Further, if the "delayed" queue is empty when
 * a stripe is put on it then we "plug" the queue and do not process it
 * until an unplug call is made. (the unplug_io_fn() is called).
 *
 * When preread is initiated on a stripe, we set PREREAD_ACTIVE and add
 * it to the count of prereading stripes.
 * When write is initiated, or the stripe refcnt == 0 (just in case) we
 * clear the PREREAD_ACTIVE flag and decrement the count
 * Whenever the delayed queue is empty and the device is not plugged, we
 * move any strips from delayed to handle and clear the DELAYED flag and set PREREAD_ACTIVE.
 * In stripe_handle, if we find pre-reading is necessary, we do it if
 * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue.
 * HANDLE gets cleared if stripe_handle leave nothing locked.
 */
 

struct disk_info {
	mdk_rdev_t	*rdev;
};

struct raid5_private_data {
	struct hlist_head	*stripe_hashtbl;
	mddev_t			*mddev;
	struct disk_info	*spare;
	int			chunk_size, level, algorithm;
	int			raid_disks, working_disks, failed_disks;
	int			max_nr_stripes;

	/* used during an expand */
	sector_t		expand_progress;	/* MaxSector when no expand happening */
	int			previous_raid_disks;

	struct list_head	handle_list; /* stripes needing handling */
	struct list_head	delayed_list; /* stripes that have plugged requests */
	struct list_head	bitmap_list; /* stripes delaying awaiting bitmap update */
	atomic_t		preread_active_stripes; /* stripes with scheduled io */

	/* unfortunately we need two cache names as we temporarily have
	 * two caches.
	 */
	int			active_name;
	char			cache_name[2][20];
	kmem_cache_t		*slab_cache; /* for allocating stripes */

	int			seq_flush, seq_write;
	int			quiesce;

	int			fullsync;  /* set to 1 if a full sync is needed,
					    * (fresh device added).
					    * Cleared when a sync completes.
					    */

	struct page 		*spare_page; /* Used when checking P/Q in raid6 */

	/*
	 * Free stripes pool
	 */
	atomic_t		active_stripes;
	struct list_head	inactive_list;
	wait_queue_head_t	wait_for_stripe;
	wait_queue_head_t	wait_for_overlap;
	int			inactive_blocked;	/* release of inactive stripes blocked,
							 * waiting for 25% to be free
							 */
	int			pool_size; /* number of disks in stripeheads in pool */
	spinlock_t		device_lock;
	struct disk_info	*disks;
};

typedef struct raid5_private_data raid5_conf_t;

#define mddev_to_conf(mddev) ((raid5_conf_t *) mddev->private)

/*
 * Our supported algorithms
 */
#define ALGORITHM_LEFT_ASYMMETRIC	0
#define ALGORITHM_RIGHT_ASYMMETRIC	1
#define ALGORITHM_LEFT_SYMMETRIC	2
#define ALGORITHM_RIGHT_SYMMETRIC	3

#endif