[linux-block.git] / drivers / md / raid1.h

#ifndef _RAID1_H
#define _RAID1_H

/*
 * each barrier unit size is 64MB fow now
 * note: it must be larger than RESYNC_DEPTH
 */
#define BARRIER_UNIT_SECTOR_BITS	17
#define BARRIER_UNIT_SECTOR_SIZE	(1<<17)
/*
 * In struct r1conf, the following members are related to I/O barrier
 * buckets,
 *	atomic_t	*nr_pending;
 *	atomic_t	*nr_waiting;
 *	atomic_t	*nr_queued;
 *	atomic_t	*barrier;
 * Each of them points to array of atomic_t variables, each array is
 * designed to have BARRIER_BUCKETS_NR elements and occupy a single
 * memory page. The data width of atomic_t variables is 4 bytes, equal
 * to 1<<(ilog2(sizeof(atomic_t))), BARRIER_BUCKETS_NR_BITS is defined
 * as (PAGE_SHIFT - ilog2(sizeof(int))) to make sure an array of
 * atomic_t variables with BARRIER_BUCKETS_NR elements just exactly
 * occupies a single memory page.
 */
#define BARRIER_BUCKETS_NR_BITS		(PAGE_SHIFT - ilog2(sizeof(atomic_t)))
#define BARRIER_BUCKETS_NR		(1<<BARRIER_BUCKETS_NR_BITS)

struct raid1_info {
	struct md_rdev	*rdev;
	sector_t	head_position;

	/* When choose the best device for a read (read_balance())
	 * we try to keep sequential reads one the same device
	 */
	sector_t	next_seq_sect;
	sector_t	seq_start;
};

/*
 * 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.
 * The 'raid_disks' here is twice the raid_disks in r1conf.
 * This allows space for each 'real' device can have a replacement in the
 * second half of the array.
 */

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

struct r1conf {
	struct mddev		*mddev;
	struct raid1_info	*mirrors;	/* twice 'raid_disks' to
						 * allow for replacements.
						 */
	int			raid_disks;

	spinlock_t		device_lock;

	/* list of 'struct r1bio' that need to be processed by raid1d,
	 * whether to retry a read, writeout a resync or recovery
	 * block, or anything else.
	 */
	struct list_head	retry_list;
	/* A separate list of r1bio which just need raid_end_bio_io called.
	 * This mustn't happen for writes which had any errors if the superblock
	 * needs to be written.
	 */
	struct list_head	bio_end_io_list;

	/* queue pending writes to be submitted on unplug */
	struct bio_list		pending_bio_list;
	int			pending_count;

	/* for use when syncing mirrors:
	 * We don't allow both normal IO and resync/recovery IO at
	 * the same time - resync/recovery can only happen when there
	 * is no other IO.  So when either is active, the other has to wait.
	 * See more details description in raid1.c near raise_barrier().
	 */
	wait_queue_head_t	wait_barrier;
	spinlock_t		resync_lock;
	atomic_t		nr_sync_pending;
	atomic_t		*nr_pending;
	atomic_t		*nr_waiting;
	atomic_t		*nr_queued;
	atomic_t		*barrier;
	int			array_frozen;

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

	/* When the same as mddev->recovery_disabled we don't allow
	 * recovery to be attempted as we expect a read error.
	 */
	int			recovery_disabled;

	/* poolinfo contains information about the content of the
	 * mempools - it changes when the array grows or shrinks
	 */
	struct pool_info	*poolinfo;
	mempool_t		*r1bio_pool;
	mempool_t		*r1buf_pool;

	struct bio_set		*bio_split;

	/* temporary buffer to synchronous IO when attempting to repair
	 * a read error.
	 */
	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;

	/* Keep track of cluster resync window to send to other
	 * nodes.
	 */
	sector_t		cluster_sync_low;
	sector_t		cluster_sync_high;

};

/*
 * 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 {
	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;
	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_disk;

	struct list_head	retry_list;

	/*
	 * When R1BIO_BehindIO is set, we store pages for write behind
	 * in behind_master_bio.
	 */
	struct bio		*behind_master_bio;

	/*
	 * 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*/
};

/* bits for r1bio.state */
enum r1bio_state {
	R1BIO_Uptodate,
	R1BIO_IsSync,
	R1BIO_Degraded,
	R1BIO_BehindIO,
/* Set ReadError on bios that experience a readerror so that
 * raid1d knows what to do with them.
 */
	R1BIO_ReadError,
/* 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...
 */
	R1BIO_Returned,
/* If a write for this request means we can clear some
 * known-bad-block records, we set this flag
 */
	R1BIO_MadeGood,
	R1BIO_WriteError,
	R1BIO_FailFast,
};

static inline int sector_to_idx(sector_t sector)
{
	return hash_long(sector >> BARRIER_UNIT_SECTOR_BITS,
			 BARRIER_BUCKETS_NR_BITS);
}
#endif
Commit	Line	Data
1da177e4 LT	1	#ifndef _RAID1_H
	2	#define _RAID1_H
	3
fd76863e	4	/*
	5	* each barrier unit size is 64MB fow now
	6	* note: it must be larger than RESYNC_DEPTH
	7	*/
	8	#define BARRIER_UNIT_SECTOR_BITS 17
	9	#define BARRIER_UNIT_SECTOR_SIZE (1<<17)
	10	/*
	11	* In struct r1conf, the following members are related to I/O barrier
	12	* buckets,
824e47da	13	* atomic_t *nr_pending;
	14	* atomic_t *nr_waiting;
	15	* atomic_t *nr_queued;
	16	* atomic_t *barrier;
	17	* Each of them points to array of atomic_t variables, each array is
	18	* designed to have BARRIER_BUCKETS_NR elements and occupy a single
	19	* memory page. The data width of atomic_t variables is 4 bytes, equal
	20	* to 1<<(ilog2(sizeof(atomic_t))), BARRIER_BUCKETS_NR_BITS is defined
	21	* as (PAGE_SHIFT - ilog2(sizeof(int))) to make sure an array of
	22	* atomic_t variables with BARRIER_BUCKETS_NR elements just exactly
	23	* occupies a single memory page.
fd76863e	24	*/
824e47da	25	#define BARRIER_BUCKETS_NR_BITS (PAGE_SHIFT - ilog2(sizeof(atomic_t)))
fd76863e	26	#define BARRIER_BUCKETS_NR (1<<BARRIER_BUCKETS_NR_BITS)
fd76863e	27
0eaf822c	28	struct raid1_info {
3cb03002	29	struct md_rdev *rdev;
1da177e4	30	sector_t head_position;
be4d3280 SL	31
	32	/* When choose the best device for a read (read_balance())
	33	* we try to keep sequential reads one the same device
	34	*/
	35	sector_t next_seq_sect;
12cee5a8	36	sector_t seq_start;
1da177e4 LT	37	};
	38
	39	/*
	40	* memory pools need a pointer to the mddev, so they can force an unplug
	41	* when memory is tight, and a count of the number of drives that the
	42	* pool was allocated for, so they know how much to allocate and free.
	43	* mddev->raid_disks cannot be used, as it can change while a pool is active
	44	* These two datums are stored in a kmalloced struct.
8f19ccb2 N	45	* The 'raid_disks' here is twice the raid_disks in r1conf.
	46	* This allows space for each 'real' device can have a replacement in the
	47	* second half of the array.
1da177e4 LT	48	*/
	49
	50	struct pool_info {
fd01b88c	51	struct mddev *mddev;
1da177e4 LT	52	int raid_disks;
	53	};
	54
e8096360	55	struct r1conf {
fd01b88c	56	struct mddev *mddev;
0eaf822c	57	struct raid1_info mirrors; / twice 'raid_disks' to
8f19ccb2 N	58	* allow for replacements.
8f19ccb2 N	59	*/
1da177e4	60	int raid_disks;
ce550c20	61
1da177e4 LT	62	spinlock_t device_lock;
1da177e4 LT	63
9f2c9d12 N	64	/* list of 'struct r1bio' that need to be processed by raid1d,
	65	* whether to retry a read, writeout a resync or recovery
	66	* block, or anything else.
ce550c20	67	*/
1da177e4	68	struct list_head retry_list;
55ce74d4 N	69	/* A separate list of r1bio which just need raid_end_bio_io called.
	70	* This mustn't happen for writes which had any errors if the superblock
	71	* needs to be written.
	72	*/
	73	struct list_head bio_end_io_list;
191ea9b2	74
ce550c20 N	75	/* queue pending writes to be submitted on unplug */
ce550c20 N	76	struct bio_list pending_bio_list;
34db0cd6	77	int pending_count;
1da177e4	78
ce550c20 N	79	/* for use when syncing mirrors:
	80	* We don't allow both normal IO and resync/recovery IO at
	81	* the same time - resync/recovery can only happen when there
	82	* is no other IO. So when either is active, the other has to wait.
	83	* See more details description in raid1.c near raise_barrier().
	84	*/
	85	wait_queue_head_t wait_barrier;
1da177e4	86	spinlock_t resync_lock;
43ac9b84	87	atomic_t nr_sync_pending;
824e47da	88	atomic_t *nr_pending;
	89	atomic_t *nr_waiting;
	90	atomic_t *nr_queued;
	91	atomic_t *barrier;
b364e3d0	92	int array_frozen;
1da177e4	93
ce550c20 N	94	/* Set to 1 if a full sync is needed, (fresh device added).
	95	* Cleared when a sync completes.
	96	*/
	97	int fullsync;
1da177e4	98
ce550c20 N	99	/* When the same as mddev->recovery_disabled we don't allow
	100	* recovery to be attempted as we expect a read error.
	101	*/
	102	int recovery_disabled;
1da177e4	103
ce550c20 N	104	/* poolinfo contains information about the content of the
	105	* mempools - it changes when the array grows or shrinks
	106	*/
	107	struct pool_info *poolinfo;
9f2c9d12 N	108	mempool_t *r1bio_pool;
9f2c9d12 N	109	mempool_t *r1buf_pool;
709ae487	110
c230e7e5 N	111	struct bio_set *bio_split;
c230e7e5 N	112
ce550c20 N	113	/* temporary buffer to synchronous IO when attempting to repair
	114	* a read error.
	115	*/
	116	struct page *tmppage;
	117
709ae487 N	118	/* When taking over an array from a different personality, we store
	119	* the new thread here until we fully activate the array.
	120	*/
2b8bf345	121	struct md_thread *thread;
c40f341f GR	122
	123	/* Keep track of cluster resync window to send to other
	124	* nodes.
	125	*/
	126	sector_t cluster_sync_low;
	127	sector_t cluster_sync_high;
	128
1da177e4 LT	129	};
1da177e4 LT	130
1da177e4 LT	131	/*
	132	* this is our 'private' RAID1 bio.
	133	*
	134	* it contains information about what kind of IO operations were started
	135	* for this RAID1 operation, and about their status:
	136	*/
	137
9f2c9d12	138	struct r1bio {
1da177e4 LT	139	atomic_t remaining; /* 'have we finished' count,
	140	* used from IRQ handlers
	141	*/
4b6d287f N	142	atomic_t behind_remaining; /* number of write-behind ios remaining
	143	* in this BehindIO request
	144	*/
1da177e4 LT	145	sector_t sector;
	146	int sectors;
	147	unsigned long state;
fd01b88c	148	struct mddev *mddev;
1da177e4 LT	149	/*
	150	* original bio going to /dev/mdx
	151	*/
	152	struct bio *master_bio;
	153	/*
	154	* if the IO is in READ direction, then this is where we read
	155	*/
	156	int read_disk;
	157
	158	struct list_head retry_list;
841c1316 ML	159
	160	/*
	161	* When R1BIO_BehindIO is set, we store pages for write behind
	162	* in behind_master_bio.
	163	*/
	164	struct bio *behind_master_bio;
	165
1da177e4 LT	166	/*
	167	* if the IO is in WRITE direction, then multiple bios are used.
	168	* We choose the number when they are allocated.
	169	*/
	170	struct bio *bios[0];
191ea9b2	171	/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
1da177e4 LT	172	};
	173
	174	/* bits for r1bio.state */
be306c29 N	175	enum r1bio_state {
	176	R1BIO_Uptodate,
	177	R1BIO_IsSync,
	178	R1BIO_Degraded,
	179	R1BIO_BehindIO,
d2eb35ac N	180	/* Set ReadError on bios that experience a readerror so that
	181	* raid1d knows what to do with them.
	182	*/
be306c29	183	R1BIO_ReadError,
4b6d287f N	184	/* For write-behind requests, we call bi_end_io when
	185	* the last non-write-behind device completes, providing
	186	* any write was successful. Otherwise we call when
	187	* any write-behind write succeeds, otherwise we call
	188	* with failure when last write completes (and all failed).
	189	* Record that bi_end_io was called with this flag...
	190	*/
be306c29	191	R1BIO_Returned,
4367af55 N	192	/* If a write for this request means we can clear some
	193	* known-bad-block records, we set this flag
	194	*/
be306c29 N	195	R1BIO_MadeGood,
be306c29 N	196	R1BIO_WriteError,
2e52d449	197	R1BIO_FailFast,
be306c29	198	};
fd76863e	199
	200	static inline int sector_to_idx(sector_t sector)
	201	{
	202	return hash_long(sector >> BARRIER_UNIT_SECTOR_BITS,
	203	BARRIER_BUCKETS_NR_BITS);
	204	}
1da177e4	205	#endif