raid5.h 23.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4
#ifndef _RAID5_H
#define _RAID5_H

#include <linux/raid/xor.h>
D
Dan Williams 已提交
5
#include <linux/dmaengine.h>
L
Linus Torvalds 已提交
6 7 8

/*
 *
9
 * Each stripe contains one buffer per device.  Each buffer can be in
L
Linus Torvalds 已提交
10
 * one of a number of states stored in "flags".  Changes between
11 12 13
 * these states happen *almost* exclusively under the protection of the
 * STRIPE_ACTIVE flag.  Some very specific changes can happen in bi_end_io, and
 * these are not protected by STRIPE_ACTIVE.
L
Linus Torvalds 已提交
14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
 *
 * 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
N
NeilBrown 已提交
30
 *  Empty -> Dirty  - on compute_parity to satisfy write/sync request.
L
Linus Torvalds 已提交
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51
 *  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).
52
 * To distinguish these states we have a stripe bit STRIPE_INSYNC that
L
Linus Torvalds 已提交
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
 * 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.
 *
79 80 81 82
 * The write list and read list both act as fifos.  The read list,
 * write list and written list are protected by the device_lock.
 * The device_lock is only for list manipulations and will only be
 * held for a very short time.  It can be claimed from interrupts.
L
Linus Torvalds 已提交
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
 *
 *
 * 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 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())
116
 *     setSTRIPE_ACTIVE,  clrSTRIPE_HANDLE ...
117 118
 *		(lockdev check-buffers unlockdev) ..
 *		change-state ..
119
 *		record io/ops needed clearSTRIPE_ACTIVE schedule io/ops
L
Linus Torvalds 已提交
120 121 122 123 124
 *  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
125 126 127
 * on a cached buffer, and plus one if the stripe is undergoing stripe
 * operations.
 *
128
 * The stripe operations are:
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
 * -copying data between the stripe cache and user application buffers
 * -computing blocks to save a disk access, or to recover a missing block
 * -updating the parity on a write operation (reconstruct write and
 *  read-modify-write)
 * -checking parity correctness
 * -running i/o to disk
 * These operations are carried out by raid5_run_ops which uses the async_tx
 * api to (optionally) offload operations to dedicated hardware engines.
 * When requesting an operation handle_stripe sets the pending bit for the
 * operation and increments the count.  raid5_run_ops is then run whenever
 * the count is non-zero.
 * There are some critical dependencies between the operations that prevent some
 * from being requested while another is in flight.
 * 1/ Parity check operations destroy the in cache version of the parity block,
 *    so we prevent parity dependent operations like writes and compute_blocks
 *    from starting while a check is in progress.  Some dma engines can perform
 *    the check without damaging the parity block, in these cases the parity
 *    block is re-marked up to date (assuming the check was successful) and is
 *    not re-read from disk.
 * 2/ When a write operation is requested we immediately lock the affected
 *    blocks, and mark them as not up to date.  This causes new read requests
 *    to be held off, as well as parity checks and compute block operations.
 * 3/ Once a compute block operation has been requested handle_stripe treats
 *    that block as if it is up to date.  raid5_run_ops guaruntees that any
 *    operation that is dependent on the compute block result is initiated after
 *    the compute block completes.
L
Linus Torvalds 已提交
155 156
 */

157
/*
158
 * Operations state - intermediate states that are visible outside of
159
 *   STRIPE_ACTIVE.
160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175
 * In general _idle indicates nothing is running, _run indicates a data
 * processing operation is active, and _result means the data processing result
 * is stable and can be acted upon.  For simple operations like biofill and
 * compute that only have an _idle and _run state they are indicated with
 * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN)
 */
/**
 * enum check_states - handles syncing / repairing a stripe
 * @check_state_idle - check operations are quiesced
 * @check_state_run - check operation is running
 * @check_state_result - set outside lock when check result is valid
 * @check_state_compute_run - check failed and we are repairing
 * @check_state_compute_result - set outside lock when compute result is valid
 */
enum check_states {
	check_state_idle = 0,
176 177 178
	check_state_run, /* xor parity check */
	check_state_run_q, /* q-parity check */
	check_state_run_pq, /* pq dual parity check */
179 180 181 182 183 184 185 186 187 188
	check_state_check_result,
	check_state_compute_run, /* parity repair */
	check_state_compute_result,
};

/**
 * enum reconstruct_states - handles writing or expanding a stripe
 */
enum reconstruct_states {
	reconstruct_state_idle = 0,
189
	reconstruct_state_prexor_drain_run,	/* prexor-write */
190 191
	reconstruct_state_drain_run,		/* write */
	reconstruct_state_run,			/* expand */
192
	reconstruct_state_prexor_drain_result,
193 194 195 196
	reconstruct_state_drain_result,
	reconstruct_state_result,
};

L
Linus Torvalds 已提交
197
struct stripe_head {
198
	struct hlist_node	hash;
199
	struct list_head	lru;	      /* inactive_list or handle_list */
S
Shaohua Li 已提交
200
	struct llist_node	release_list;
201
	struct r5conf		*raid_conf;
202 203
	short			generation;	/* increments with every
						 * reshape */
204 205 206
	sector_t		sector;		/* sector of this row */
	short			pd_idx;		/* parity disk index */
	short			qd_idx;		/* 'Q' disk index for raid6 */
207
	short			ddf_layout;/* use DDF ordering to calculate Q */
208
	short			hash_lock_index;
209 210
	unsigned long		state;		/* state flags */
	atomic_t		count;	      /* nr of active thread/requests */
211
	int			bm_seq;	/* sequence number for bitmap flushes */
212
	int			disks;		/* disks in stripe */
213 214 215 216
	int			overwrite_disks; /* total overwrite disks in stripe,
						  * this is only checked when stripe
						  * has STRIPE_BATCH_READY
						  */
217
	enum check_states	check_state;
218
	enum reconstruct_states reconstruct_state;
S
Shaohua Li 已提交
219
	spinlock_t		stripe_lock;
220
	int			cpu;
221
	struct r5worker_group	*group;
222 223 224 225

	struct stripe_head	*batch_head; /* protected by stripe lock */
	spinlock_t		batch_lock; /* only header's lock is useful */
	struct list_head	batch_list; /* protected by head's batch lock*/
S
Shaohua Li 已提交
226 227 228

	struct r5l_io_unit	*log_io;
	struct list_head	log_list;
229 230
	/**
	 * struct stripe_operations
231
	 * @target - STRIPE_OP_COMPUTE_BLK target
232 233 234
	 * @target2 - 2nd compute target in the raid6 case
	 * @zero_sum_result - P and Q verification flags
	 * @request - async service request flags for raid_run_ops
235 236
	 */
	struct stripe_operations {
237
		int 		     target, target2;
D
Dan Williams 已提交
238
		enum sum_check_flags zero_sum_result;
239
	} ops;
L
Linus Torvalds 已提交
240
	struct r5dev {
241 242 243 244 245
		/* rreq and rvec are used for the replacement device when
		 * writing data to both devices.
		 */
		struct bio	req, rreq;
		struct bio_vec	vec, rvec;
246
		struct page	*page, *orig_page;
247
		struct bio	*toread, *read, *towrite, *written;
L
Linus Torvalds 已提交
248 249
		sector_t	sector;			/* sector of this page */
		unsigned long	flags;
S
Shaohua Li 已提交
250
		u32		log_checksum;
L
Linus Torvalds 已提交
251 252
	} dev[1]; /* allocated with extra space depending of RAID geometry */
};
253 254

/* stripe_head_state - collects and tracks the dynamic state of a stripe_head
255
 *     for handle_stripe.
256 257
 */
struct stripe_head_state {
258 259 260 261 262 263 264
	/* 'syncing' means that we need to read all devices, either
	 * to check/correct parity, or to reconstruct a missing device.
	 * 'replacing' means we are replacing one or more drives and
	 * the source is valid at this point so we don't need to
	 * read all devices, just the replacement targets.
	 */
	int syncing, expanding, expanded, replacing;
265
	int locked, uptodate, to_read, to_write, failed, written;
266
	int to_fill, compute, req_compute, non_overwrite;
267 268
	int failed_num[2];
	int p_failed, q_failed;
269 270 271
	int dec_preread_active;
	unsigned long ops_request;

272
	struct bio_list return_bi;
273
	struct md_rdev *blocked_rdev;
274
	int handle_bad_blocks;
S
Shaohua Li 已提交
275
	int log_failed;
276 277
};

278 279 280 281
/* Flags for struct r5dev.flags */
enum r5dev_flags {
	R5_UPTODATE,	/* page contains current data */
	R5_LOCKED,	/* IO has been submitted on "req" */
282
	R5_DOUBLE_LOCKED,/* Cannot clear R5_LOCKED until 2 writes complete */
283
	R5_OVERWRITE,	/* towrite covers whole page */
L
Linus Torvalds 已提交
284
/* and some that are internal to handle_stripe */
285 286 287 288 289
	R5_Insync,	/* rdev && rdev->in_sync at start */
	R5_Wantread,	/* want to schedule a read */
	R5_Wantwrite,
	R5_Overlap,	/* There is a pending overlapping request
			 * on this block */
290
	R5_ReadNoMerge, /* prevent bio from merging in block-layer */
291 292
	R5_ReadError,	/* seen a read error here recently */
	R5_ReWrite,	/* have tried to over-write the readerror */
L
Linus Torvalds 已提交
293

294 295 296 297 298 299 300 301 302
	R5_Expanded,	/* This block now has post-expand data */
	R5_Wantcompute,	/* compute_block in progress treat as
			 * uptodate
			 */
	R5_Wantfill,	/* dev->toread contains a bio that needs
			 * filling
			 */
	R5_Wantdrain,	/* dev->towrite needs to be drained */
	R5_WantFUA,	/* Write should be FUA */
S
Shaohua Li 已提交
303
	R5_SyncIO,	/* The IO is sync */
304 305 306 307 308
	R5_WriteError,	/* got a write error - need to record it */
	R5_MadeGood,	/* A bad block has been fixed by writing to it */
	R5_ReadRepl,	/* Will/did read from replacement rather than orig */
	R5_MadeGoodRepl,/* A bad block on the replacement device has been
			 * fixed by writing to it */
309 310 311 312 313
	R5_NeedReplace,	/* This device has a replacement which is not
			 * up-to-date at this stripe. */
	R5_WantReplace, /* We need to update the replacement, we have read
			 * data in, and now is a good time to write it out.
			 */
S
Shaohua Li 已提交
314
	R5_Discard,	/* Discard the stripe */
315
	R5_SkipCopy,	/* Don't copy data from bio to stripe cache */
316
};
L
Linus Torvalds 已提交
317 318 319 320

/*
 * Stripe state
 */
321
enum {
322
	STRIPE_ACTIVE,
323 324 325 326
	STRIPE_HANDLE,
	STRIPE_SYNC_REQUESTED,
	STRIPE_SYNCING,
	STRIPE_INSYNC,
327
	STRIPE_REPLACED,
328 329 330 331 332 333 334 335 336 337 338 339
	STRIPE_PREREAD_ACTIVE,
	STRIPE_DELAYED,
	STRIPE_DEGRADED,
	STRIPE_BIT_DELAY,
	STRIPE_EXPANDING,
	STRIPE_EXPAND_SOURCE,
	STRIPE_EXPAND_READY,
	STRIPE_IO_STARTED,	/* do not count towards 'bypass_count' */
	STRIPE_FULL_WRITE,	/* all blocks are set to be overwritten */
	STRIPE_BIOFILL_RUN,
	STRIPE_COMPUTE_RUN,
	STRIPE_OPS_REQ_PENDING,
340
	STRIPE_ON_UNPLUG_LIST,
341
	STRIPE_DISCARD,
S
Shaohua Li 已提交
342
	STRIPE_ON_RELEASE_LIST,
343
	STRIPE_BATCH_READY,
344
	STRIPE_BATCH_ERR,
345 346 347
	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
				 * to batch yet.
				 */
348
	STRIPE_LOG_TRAPPED, /* trapped into log */
349
};
350

351
#define STRIPE_EXPAND_SYNC_FLAGS \
352 353 354 355
	((1 << STRIPE_EXPAND_SOURCE) |\
	(1 << STRIPE_EXPAND_READY) |\
	(1 << STRIPE_EXPANDING) |\
	(1 << STRIPE_SYNC_REQUESTED))
356
/*
357
 * Operation request flags
358
 */
N
NeilBrown 已提交
359 360 361 362 363 364 365 366
enum {
	STRIPE_OP_BIOFILL,
	STRIPE_OP_COMPUTE_BLK,
	STRIPE_OP_PREXOR,
	STRIPE_OP_BIODRAIN,
	STRIPE_OP_RECONSTRUCT,
	STRIPE_OP_CHECK,
};
367 368 369 370 371 372 373

/*
 * RAID parity calculation preferences
 */
enum {
	PARITY_DISABLE_RMW = 0,
	PARITY_ENABLE_RMW,
374
	PARITY_PREFER_RMW,
375 376 377 378 379 380 381 382 383 384
};

/*
 * Pages requested from set_syndrome_sources()
 */
enum {
	SYNDROME_SRC_ALL,
	SYNDROME_SRC_WANT_DRAIN,
	SYNDROME_SRC_WRITTEN,
};
L
Linus Torvalds 已提交
385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400
/*
 * 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
401 402 403
 * Whenever the 'handle' 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.
L
Linus Torvalds 已提交
404 405
 * 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.
406
 * HANDLE gets cleared if stripe_handle leaves nothing locked.
L
Linus Torvalds 已提交
407
 */
408

L
Linus Torvalds 已提交
409
struct disk_info {
410
	struct md_rdev	*rdev, *replacement;
L
Linus Torvalds 已提交
411 412
};

413 414 415 416 417 418 419 420
/* NOTE NR_STRIPE_HASH_LOCKS must remain below 64.
 * This is because we sometimes take all the spinlocks
 * and creating that much locking depth can cause
 * problems.
 */
#define NR_STRIPE_HASH_LOCKS 8
#define STRIPE_HASH_LOCKS_MASK (NR_STRIPE_HASH_LOCKS - 1)

421 422 423
struct r5worker {
	struct work_struct work;
	struct r5worker_group *group;
424
	struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS];
425
	bool working;
426 427 428 429 430 431
};

struct r5worker_group {
	struct list_head handle_list;
	struct r5conf *conf;
	struct r5worker *workers;
432
	int stripes_cnt;
433 434
};

435
struct r5conf {
436
	struct hlist_head	*stripe_hashtbl;
437 438
	/* only protect corresponding hash list and inactive_list */
	spinlock_t		hash_locks[NR_STRIPE_HASH_LOCKS];
439
	struct mddev		*mddev;
440
	int			chunk_sectors;
441
	int			level, algorithm, rmw_level;
442
	int			max_degraded;
443
	int			raid_disks;
L
Linus Torvalds 已提交
444
	int			max_nr_stripes;
445
	int			min_nr_stripes;
L
Linus Torvalds 已提交
446

447 448 449 450 451 452 453 454 455 456
	/* reshape_progress is the leading edge of a 'reshape'
	 * It has value MaxSector when no reshape is happening
	 * If delta_disks < 0, it is the last sector we started work on,
	 * else is it the next sector to work on.
	 */
	sector_t		reshape_progress;
	/* reshape_safe is the trailing edge of a reshape.  We know that
	 * before (or after) this address, all reshape has completed.
	 */
	sector_t		reshape_safe;
457
	int			previous_raid_disks;
458 459
	int			prev_chunk_sectors;
	int			prev_algo;
460
	short			generation; /* increments with every reshape */
461
	seqcount_t		gen_lock;	/* lock against generation changes */
462 463
	unsigned long		reshape_checkpoint; /* Time we last updated
						     * metadata */
464 465 466 467 468 469
	long long		min_offset_diff; /* minimum difference between
						  * data_offset and
						  * new_data_offset across all
						  * devices.  May be negative,
						  * but is closest to zero.
						  */
470

L
Linus Torvalds 已提交
471
	struct list_head	handle_list; /* stripes needing handling */
472
	struct list_head	hold_list; /* preread ready stripes */
L
Linus Torvalds 已提交
473
	struct list_head	delayed_list; /* stripes that have plugged requests */
474
	struct list_head	bitmap_list; /* stripes delaying awaiting bitmap update */
475 476
	struct bio		*retry_read_aligned; /* currently retrying aligned bios   */
	struct bio		*retry_read_aligned_list; /* aligned bios retry list  */
L
Linus Torvalds 已提交
477
	atomic_t		preread_active_stripes; /* stripes with scheduled io */
478
	atomic_t		active_aligned_reads;
479 480 481
	atomic_t		pending_full_writes; /* full write backlog */
	int			bypass_count; /* bypassed prereads */
	int			bypass_threshold; /* preread nice */
482
	int			skip_copy; /* Don't copy data from bio to stripe cache */
483
	struct list_head	*last_hold; /* detect hold_list promotions */
L
Linus Torvalds 已提交
484

485 486 487
	/* bios to have bi_end_io called after metadata is synced */
	struct bio_list		return_bi;

488
	atomic_t		reshape_stripes; /* stripes with pending writes for reshape */
489 490 491 492
	/* unfortunately we need two cache names as we temporarily have
	 * two caches.
	 */
	int			active_name;
493
	char			cache_name[2][32];
494 495
	struct kmem_cache	*slab_cache; /* for allocating stripes */
	struct mutex		cache_size_mutex; /* Protect changes to cache size */
496 497 498 499 500 501 502 503

	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.
					    */
504
	int			recovery_disabled;
505 506 507
	/* per cpu variables */
	struct raid5_percpu {
		struct page	*spare_page; /* Used when checking P/Q in raid6 */
508
		struct flex_array *scribble;   /* space for constructing buffer
509 510 511
					      * lists and performing address
					      * conversions
					      */
512
	} __percpu *percpu;
513 514
	int scribble_disks;
	int scribble_sectors;
515 516 517
#ifdef CONFIG_HOTPLUG_CPU
	struct notifier_block	cpu_notify;
#endif
518

L
Linus Torvalds 已提交
519 520 521 522
	/*
	 * Free stripes pool
	 */
	atomic_t		active_stripes;
523
	struct list_head	inactive_list[NR_STRIPE_HASH_LOCKS];
524
	atomic_t		empty_inactive_list_nr;
S
Shaohua Li 已提交
525
	struct llist_head	released_stripes;
526
	wait_queue_head_t	wait_for_quiescent;
527
	wait_queue_head_t	wait_for_stripe[NR_STRIPE_HASH_LOCKS];
L
Linus Torvalds 已提交
528
	wait_queue_head_t	wait_for_overlap;
529 530 531 532
	unsigned long		cache_state;
#define R5_INACTIVE_BLOCKED	1	/* release of inactive stripes blocked,
					 * waiting for 25% to be free
					 */
533 534 535 536 537 538 539 540 541
#define R5_ALLOC_MORE		2	/* It might help to allocate another
					 * stripe.
					 */
#define R5_DID_ALLOC		4	/* A stripe was allocated, don't allocate
					 * more until at least one has been
					 * released.  This avoids flooding
					 * the cache.
					 */
	struct shrinker		shrinker;
542
	int			pool_size; /* number of disks in stripeheads in pool */
L
Linus Torvalds 已提交
543
	spinlock_t		device_lock;
544
	struct disk_info	*disks;
N
NeilBrown 已提交
545 546 547 548

	/* When taking over an array from a different personality, we store
	 * the new thread here until we fully activate the array.
	 */
549
	struct md_thread	*thread;
550
	struct list_head	temp_inactive_list[NR_STRIPE_HASH_LOCKS];
551 552 553
	struct r5worker_group	*worker_groups;
	int			group_cnt;
	int			worker_cnt_per_group;
S
Shaohua Li 已提交
554
	struct r5l_log		*log;
L
Linus Torvalds 已提交
555 556
};

557

L
Linus Torvalds 已提交
558 559 560
/*
 * Our supported algorithms
 */
561 562 563 564
#define ALGORITHM_LEFT_ASYMMETRIC	0 /* Rotating Parity N with Data Restart */
#define ALGORITHM_RIGHT_ASYMMETRIC	1 /* Rotating Parity 0 with Data Restart */
#define ALGORITHM_LEFT_SYMMETRIC	2 /* Rotating Parity N with Data Continuation */
#define ALGORITHM_RIGHT_SYMMETRIC	3 /* Rotating Parity 0 with Data Continuation */
L
Linus Torvalds 已提交
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
/* Define non-rotating (raid4) algorithms.  These allow
 * conversion of raid4 to raid5.
 */
#define ALGORITHM_PARITY_0		4 /* P or P,Q are initial devices */
#define ALGORITHM_PARITY_N		5 /* P or P,Q are final devices. */

/* DDF RAID6 layouts differ from md/raid6 layouts in two ways.
 * Firstly, the exact positioning of the parity block is slightly
 * different between the 'LEFT_*' modes of md and the "_N_*" modes
 * of DDF.
 * Secondly, or order of datablocks over which the Q syndrome is computed
 * is different.
 * Consequently we have different layouts for DDF/raid6 than md/raid6.
 * These layouts are from the DDFv1.2 spec.
 * Interestingly DDFv1.2-Errata-A does not specify N_CONTINUE but
 * leaves RLQ=3 as 'Vendor Specific'
 */

#define ALGORITHM_ROTATING_ZERO_RESTART	8 /* DDF PRL=6 RLQ=1 */
#define ALGORITHM_ROTATING_N_RESTART	9 /* DDF PRL=6 RLQ=2 */
#define ALGORITHM_ROTATING_N_CONTINUE	10 /*DDF PRL=6 RLQ=3 */

/* For every RAID5 algorithm we define a RAID6 algorithm
 * with exactly the same layout for data and parity, and
 * with the Q block always on the last device (N-1).
 * This allows trivial conversion from RAID5 to RAID6
 */
#define ALGORITHM_LEFT_ASYMMETRIC_6	16
#define ALGORITHM_RIGHT_ASYMMETRIC_6	17
#define ALGORITHM_LEFT_SYMMETRIC_6	18
#define ALGORITHM_RIGHT_SYMMETRIC_6	19
#define ALGORITHM_PARITY_0_6		20
#define ALGORITHM_PARITY_N_6		ALGORITHM_PARITY_N

static inline int algorithm_valid_raid5(int layout)
{
	return (layout >= 0) &&
		(layout <= 5);
}
static inline int algorithm_valid_raid6(int layout)
{
	return (layout >= 0 && layout <= 5)
		||
609
		(layout >= 8 && layout <= 10)
610 611 612 613 614 615 616 617
		||
		(layout >= 16 && layout <= 20);
}

static inline int algorithm_is_DDF(int layout)
{
	return layout >= 8 && layout <= 10;
}
N
NeilBrown 已提交
618

619
extern void md_raid5_kick_device(struct r5conf *conf);
620
extern int raid5_set_cache_size(struct mddev *mddev, int size);
S
Shaohua Li 已提交
621 622 623 624 625 626 627 628
extern sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous);
extern void raid5_release_stripe(struct stripe_head *sh);
extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
				     int previous, int *dd_idx,
				     struct stripe_head *sh);
extern struct stripe_head *
raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
			int previous, int noblock, int noquiesce);
S
Shaohua Li 已提交
629 630 631 632
extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev);
extern void r5l_exit_log(struct r5l_log *log);
extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh);
extern void r5l_write_stripe_run(struct r5l_log *log);
S
Shaohua Li 已提交
633 634
extern void r5l_flush_stripe_to_raid(struct r5l_log *log);
extern void r5l_stripe_write_finished(struct stripe_head *sh);
635
extern int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio);
636
extern void r5l_quiesce(struct r5l_log *log, int state);
S
Shaohua Li 已提交
637
extern bool r5l_log_disk_error(struct r5conf *conf);
L
Linus Torvalds 已提交
638
#endif