diff options
Diffstat (limited to 'drivers/md/raid1.h')
| -rw-r--r-- | drivers/md/raid1.h | 136 |
1 files changed, 86 insertions, 50 deletions
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index 0ff3715fb7eb..2ebe35aaa534 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -1,6 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #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) + +/* Note: raid1_info.rdev can be set to NULL asynchronously by raid1_remove_disk. + * There are three safe ways to access raid1_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery is known to be happening - i.e. in code that is + * called as part of performing resync/recovery. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the + * RCU lock. + * When .rdev is set to NULL, the nr_pending count checked again and if it has + * been incremented, the pointer is put back in .rdev. + */ + struct raid1_info { struct md_rdev *rdev; sector_t head_position; @@ -12,34 +49,13 @@ struct raid1_info { 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; - - /* During resync, read_balancing is only allowed on the part - * of the array that has been resynced. 'next_resync' tells us - * where that is. - */ - sector_t next_resync; + int nonrot_disks; spinlock_t device_lock; @@ -48,10 +64,14 @@ struct r1conf { * 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 @@ -61,10 +81,12 @@ struct r1conf { */ wait_queue_head_t wait_barrier; spinlock_t resync_lock; - int nr_pending; - int nr_waiting; - int nr_queued; - int barrier; + 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. @@ -76,24 +98,27 @@ struct r1conf { */ 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; + 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; + struct md_thread __rcu *thread; + + /* Keep track of cluster resync window to send to other + * nodes. + */ + sector_t cluster_sync_low; + sector_t cluster_sync_high; + }; /* @@ -124,40 +149,51 @@ struct r1bio { 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; + + /* + * 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]; + struct bio *bios[]; /* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/ }; /* bits for r1bio.state */ -#define R1BIO_Uptodate 0 -#define R1BIO_IsSync 1 -#define R1BIO_Degraded 2 -#define R1BIO_BehindIO 3 +enum r1bio_state { + R1BIO_Uptodate, + R1BIO_IsSync, + R1BIO_BehindIO, /* Set ReadError on bios that experience a readerror so that * raid1d knows what to do with them. */ -#define R1BIO_ReadError 4 + 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... + * + * And for bio_split errors, record that bi_end_io was called + * with this flag... */ -#define R1BIO_Returned 6 + R1BIO_Returned, /* 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(struct mddev *mddev, int bits); + 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 |