diff options
Diffstat (limited to 'drivers/md/raid5.h')
| -rw-r--r-- | drivers/md/raid5.h | 169 |
1 files changed, 118 insertions, 51 deletions
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index f6536399677a..eafc6e9ed6ee 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -1,8 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _RAID5_H #define _RAID5_H #include <linux/raid/xor.h> #include <linux/dmaengine.h> +#include <linux/local_lock.h> /* * @@ -194,6 +196,7 @@ enum reconstruct_states { reconstruct_state_result, }; +#define DEFAULT_STRIPE_SIZE 4096 struct stripe_head { struct hlist_node hash; struct list_head lru; /* inactive_list or handle_list */ @@ -245,6 +248,13 @@ struct stripe_head { int target, target2; enum sum_check_flags zero_sum_result; } ops; + +#if PAGE_SIZE != DEFAULT_STRIPE_SIZE + /* These pages will be used by bios in dev[i] */ + struct page **pages; + int nr_pages; /* page array size */ + int stripes_per_page; +#endif struct r5dev { /* rreq and rvec are used for the replacement device when * writing data to both devices. @@ -252,11 +262,13 @@ struct stripe_head { struct bio req, rreq; struct bio_vec vec, rvec; struct page *page, *orig_page; + unsigned int offset; /* offset of the page */ struct bio *toread, *read, *towrite, *written; sector_t sector; /* sector of this page */ unsigned long flags; u32 log_checksum; - } dev[1]; /* allocated with extra space depending of RAID geometry */ + unsigned short write_hint; + } dev[]; /* allocated depending of RAID geometry ("disks" member) */ }; /* stripe_head_state - collects and tracks the dynamic state of a stripe_head @@ -346,7 +358,6 @@ enum { STRIPE_REPLACED, STRIPE_PREREAD_ACTIVE, STRIPE_DELAYED, - STRIPE_DEGRADED, STRIPE_BIT_DELAY, STRIPE_EXPANDING, STRIPE_EXPAND_SOURCE, @@ -355,15 +366,11 @@ enum { STRIPE_FULL_WRITE, /* all blocks are set to be overwritten */ STRIPE_BIOFILL_RUN, STRIPE_COMPUTE_RUN, - STRIPE_OPS_REQ_PENDING, STRIPE_ON_UNPLUG_LIST, STRIPE_DISCARD, STRIPE_ON_RELEASE_LIST, STRIPE_BATCH_READY, STRIPE_BATCH_ERR, - STRIPE_BITMAP_PENDING, /* Being added to bitmap, don't add - * to batch yet. - */ STRIPE_LOG_TRAPPED, /* trapped into log (see raid5-cache.c) * this bit is used in two scenarios: * @@ -449,8 +456,21 @@ enum { * HANDLE gets cleared if stripe_handle leaves nothing locked. */ +/* Note: disk_info.rdev can be set to NULL asynchronously by raid5_remove_disk. + * There are three safe ways to access disk_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery/reshape is known to be happening - i.e. in code that + * is called as part of performing resync/recovery/reshape. + * 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 disk_info { - struct md_rdev *rdev, *replacement; + struct md_rdev *rdev; + struct md_rdev *replacement; struct page *extra_page; /* extra page to use in prexor */ }; @@ -459,34 +479,19 @@ struct disk_info { */ #define NR_STRIPES 256 + +#if PAGE_SIZE == DEFAULT_STRIPE_SIZE #define STRIPE_SIZE PAGE_SIZE #define STRIPE_SHIFT (PAGE_SHIFT - 9) #define STRIPE_SECTORS (STRIPE_SIZE>>9) +#endif + #define IO_THRESHOLD 1 #define BYPASS_THRESHOLD 1 #define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head)) #define HASH_MASK (NR_HASH - 1) #define MAX_STRIPE_BATCH 8 -/* bio's attached to a stripe+device for I/O are linked together in bi_sector - * order without overlap. There may be several bio's per stripe+device, and - * a bio could span several devices. - * When walking this list for a particular stripe+device, we must never proceed - * beyond a bio that extends past this device, as the next bio might no longer - * be valid. - * This function is used to determine the 'next' bio in the list, given the - * sector of the current stripe+device - */ -static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector) -{ - int sectors = bio_sectors(bio); - - if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS) - return bio->bi_next; - else - return NULL; -} - /* 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 @@ -552,6 +557,16 @@ struct r5pending_data { struct bio_list bios; }; +struct raid5_percpu { + struct page *spare_page; /* Used when checking P/Q in raid6 */ + void *scribble; /* space for constructing buffer + * lists and performing address + * conversions + */ + int scribble_obj_size; + local_lock_t lock; +}; + struct r5conf { struct hlist_head *stripe_hashtbl; /* only protect corresponding hash list and inactive_list */ @@ -563,6 +578,11 @@ struct r5conf { int raid_disks; int max_nr_stripes; int min_nr_stripes; +#if PAGE_SIZE != DEFAULT_STRIPE_SIZE + unsigned long stripe_size; + unsigned int stripe_shift; + unsigned long stripe_sectors; +#endif /* reshape_progress is the leading edge of a 'reshape' * It has value MaxSector when no reshape is happening @@ -578,7 +598,7 @@ struct r5conf { int prev_chunk_sectors; int prev_algo; short generation; /* increments with every reshape */ - seqcount_t gen_lock; /* lock against generation changes */ + seqcount_spinlock_t gen_lock; /* lock against generation changes */ unsigned long reshape_checkpoint; /* Time we last updated * metadata */ long long min_offset_diff; /* minimum difference between @@ -609,7 +629,7 @@ struct r5conf { * two caches. */ int active_name; - char cache_name[2][32]; + char cache_name[2][48]; struct kmem_cache *slab_cache; /* for allocating stripes */ struct mutex cache_size_mutex; /* Protect changes to cache size */ @@ -622,13 +642,7 @@ struct r5conf { */ int recovery_disabled; /* per cpu variables */ - struct raid5_percpu { - struct page *spare_page; /* Used when checking P/Q in raid6 */ - struct flex_array *scribble; /* space for constructing buffer - * lists and performing address - * conversions - */ - } __percpu *percpu; + struct raid5_percpu __percpu *percpu; int scribble_disks; int scribble_sectors; struct hlist_node node; @@ -650,18 +664,18 @@ struct r5conf { struct llist_head released_stripes; wait_queue_head_t wait_for_quiescent; wait_queue_head_t wait_for_stripe; - wait_queue_head_t wait_for_overlap; + wait_queue_head_t wait_for_reshape; unsigned long cache_state; - struct shrinker shrinker; + struct shrinker *shrinker; int pool_size; /* number of disks in stripeheads in pool */ spinlock_t device_lock; struct disk_info *disks; - struct bio_set *bio_split; + struct bio_set bio_split; /* 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; struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS]; struct r5worker_group *worker_groups; int group_cnt; @@ -678,6 +692,32 @@ struct r5conf { struct r5pending_data *next_pending_data; }; +#if PAGE_SIZE == DEFAULT_STRIPE_SIZE +#define RAID5_STRIPE_SIZE(conf) STRIPE_SIZE +#define RAID5_STRIPE_SHIFT(conf) STRIPE_SHIFT +#define RAID5_STRIPE_SECTORS(conf) STRIPE_SECTORS +#else +#define RAID5_STRIPE_SIZE(conf) ((conf)->stripe_size) +#define RAID5_STRIPE_SHIFT(conf) ((conf)->stripe_shift) +#define RAID5_STRIPE_SECTORS(conf) ((conf)->stripe_sectors) +#endif + +/* bio's attached to a stripe+device for I/O are linked together in bi_sector + * order without overlap. There may be several bio's per stripe+device, and + * a bio could span several devices. + * When walking this list for a particular stripe+device, we must never proceed + * beyond a bio that extends past this device, as the next bio might no longer + * be valid. + * This function is used to determine the 'next' bio in the list, given the + * sector of the current stripe+device + */ +static inline struct bio *r5_next_bio(struct r5conf *conf, struct bio *bio, sector_t sector) +{ + if (bio_end_sector(bio) < sector + RAID5_STRIPE_SECTORS(conf)) + return bio->bi_next; + else + return NULL; +} /* * Our supported algorithms @@ -740,16 +780,43 @@ static inline int algorithm_is_DDF(int layout) return layout >= 8 && layout <= 10; } -extern void md_raid5_kick_device(struct r5conf *conf); -extern int raid5_set_cache_size(struct mddev *mddev, int size); -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); -extern int raid5_calc_degraded(struct r5conf *conf); -extern int r5c_journal_mode_set(struct mddev *mddev, int journal_mode); +#if PAGE_SIZE != DEFAULT_STRIPE_SIZE +/* + * Return offset of the corresponding page for r5dev. + */ +static inline int raid5_get_page_offset(struct stripe_head *sh, int disk_idx) +{ + return (disk_idx % sh->stripes_per_page) * RAID5_STRIPE_SIZE(sh->raid_conf); +} + +/* + * Return corresponding page address for r5dev. + */ +static inline struct page * +raid5_get_dev_page(struct stripe_head *sh, int disk_idx) +{ + return sh->pages[disk_idx / sh->stripes_per_page]; +} +#endif + +void md_raid5_kick_device(struct r5conf *conf); +int raid5_set_cache_size(struct mddev *mddev, int size); +sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous); +void raid5_release_stripe(struct stripe_head *sh); +sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, + int previous, int *dd_idx, struct stripe_head *sh); + +struct stripe_request_ctx; +/* get stripe from previous generation (when reshaping) */ +#define R5_GAS_PREVIOUS (1 << 0) +/* do not block waiting for a free stripe */ +#define R5_GAS_NOBLOCK (1 << 1) +/* do not block waiting for quiesce to be released */ +#define R5_GAS_NOQUIESCE (1 << 2) +struct stripe_head *raid5_get_active_stripe(struct r5conf *conf, + struct stripe_request_ctx *ctx, sector_t sector, + unsigned int flags); + +int raid5_calc_degraded(struct r5conf *conf); +int r5c_journal_mode_set(struct mddev *mddev, int journal_mode); #endif |