diff options
Diffstat (limited to 'drivers/md/md.h')
| -rw-r--r-- | drivers/md/md.h | 330 |
1 files changed, 178 insertions, 152 deletions
diff --git a/drivers/md/md.h b/drivers/md/md.h index 1e586bb4452..a49d991f3fe 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -1,5 +1,5 @@ /* - md_k.h : kernel internal structure of the Linux MD driver + md.h : kernel internal structure of the Linux MD driver Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman This program is free software; you can redistribute it and/or modify @@ -26,9 +26,6 @@ #define MaxSector (~(sector_t)0) -typedef struct mddev_s mddev_t; -typedef struct mdk_rdev_s mdk_rdev_t; - /* Bad block numbers are stored sorted in a single page. * 64bits is used for each block or extent. * 54 bits are sector number, 9 bits are extent size, @@ -39,12 +36,11 @@ typedef struct mdk_rdev_s mdk_rdev_t; /* * MD's 'extended' device */ -struct mdk_rdev_s -{ +struct md_rdev { struct list_head same_set; /* RAID devices within the same set */ sector_t sectors; /* Device size (in 512bytes sectors) */ - mddev_t *mddev; /* RAID array if running */ + struct mddev *mddev; /* RAID array if running */ int last_events; /* IO event timestamp */ /* @@ -59,6 +55,7 @@ struct mdk_rdev_s int sb_loaded; __u64 sb_events; sector_t data_offset; /* start of data in array */ + sector_t new_data_offset;/* only relevant while reshaping */ sector_t sb_start; /* offset of the super block (in 512byte sectors) */ int sb_size; /* bytes in the superblock */ int preferred_minor; /* autorun support */ @@ -76,34 +73,7 @@ struct mdk_rdev_s * This reduces the burden of testing multiple flags in many cases */ - unsigned long flags; -#define Faulty 1 /* device is known to have a fault */ -#define In_sync 2 /* device is in_sync with rest of array */ -#define WriteMostly 4 /* Avoid reading if at all possible */ -#define AutoDetected 7 /* added by auto-detect */ -#define Blocked 8 /* An error occurred but has not yet - * been acknowledged by the metadata - * handler, so don't allow writes - * until it is cleared */ -#define WriteErrorSeen 9 /* A write error has been seen on this - * device - */ -#define FaultRecorded 10 /* Intermediate state for clearing - * Blocked. The Fault is/will-be - * recorded in the metadata, but that - * metadata hasn't been stored safely - * on disk yet. - */ -#define BlockedBadBlocks 11 /* A writer is blocked because they - * found an unacknowledged bad-block. - * This can safely be cleared at any - * time, and the writer will re-check. - * It may be set at any time, and at - * worst the writer will timeout and - * re-check. So setting it as - * accurately as possible is good, but - * not absolutely critical. - */ + unsigned long flags; /* bit set of 'enum flag_bits' bits. */ wait_queue_head_t blocked_wait; int desc_nr; /* descriptor index in the superblock */ @@ -136,7 +106,7 @@ struct mdk_rdev_s */ struct work_struct del_work; /* used for delayed sysfs removal */ - struct sysfs_dirent *sysfs_state; /* handle for 'state' + struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ struct badblocks { @@ -156,6 +126,51 @@ struct mdk_rdev_s sector_t size; /* in sectors */ } badblocks; }; +enum flag_bits { + Faulty, /* device is known to have a fault */ + In_sync, /* device is in_sync with rest of array */ + Bitmap_sync, /* ..actually, not quite In_sync. Need a + * bitmap-based recovery to get fully in sync + */ + Unmerged, /* device is being added to array and should + * be considerred for bvec_merge_fn but not + * yet for actual IO + */ + WriteMostly, /* Avoid reading if at all possible */ + AutoDetected, /* added by auto-detect */ + Blocked, /* An error occurred but has not yet + * been acknowledged by the metadata + * handler, so don't allow writes + * until it is cleared */ + WriteErrorSeen, /* A write error has been seen on this + * device + */ + FaultRecorded, /* Intermediate state for clearing + * Blocked. The Fault is/will-be + * recorded in the metadata, but that + * metadata hasn't been stored safely + * on disk yet. + */ + BlockedBadBlocks, /* A writer is blocked because they + * found an unacknowledged bad-block. + * This can safely be cleared at any + * time, and the writer will re-check. + * It may be set at any time, and at + * worst the writer will timeout and + * re-check. So setting it as + * accurately as possible is good, but + * not absolutely critical. + */ + WantReplacement, /* This device is a candidate to be + * hot-replaced, either because it has + * reported some faults, or because + * of explicit request. + */ + Replacement, /* This device is a replacement for + * a want_replacement device with same + * raid_disk number. + */ +}; #define BB_LEN_MASK (0x00000000000001FFULL) #define BB_OFFSET_MASK (0x7FFFFFFFFFFFFE00ULL) @@ -168,7 +183,7 @@ struct mdk_rdev_s extern int md_is_badblock(struct badblocks *bb, sector_t s, int sectors, sector_t *first_bad, int *bad_sectors); -static inline int is_badblock(mdk_rdev_t *rdev, sector_t s, int sectors, +static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, sector_t *first_bad, int *bad_sectors) { if (unlikely(rdev->badblocks.count)) { @@ -181,23 +196,27 @@ static inline int is_badblock(mdk_rdev_t *rdev, sector_t s, int sectors, } return 0; } -extern int rdev_set_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors, - int acknowledged); -extern int rdev_clear_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors); +extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, + int is_new); +extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, + int is_new); extern void md_ack_all_badblocks(struct badblocks *bb); -struct mddev_s -{ +struct mddev { void *private; - struct mdk_personality *pers; + struct md_personality *pers; dev_t unit; int md_minor; - struct list_head disks; + struct list_head disks; unsigned long flags; #define MD_CHANGE_DEVS 0 /* Some device status has changed */ #define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */ #define MD_CHANGE_PENDING 2 /* switch from 'clean' to 'active' in progress */ +#define MD_UPDATE_SB_FLAGS (1 | 2 | 4) /* If these are set, md_update_sb needed */ #define MD_ARRAY_FIRST_USE 3 /* First use of array, needs initialization */ +#define MD_STILL_CLOSED 4 /* If set, then array has not been opened since + * md_ioctl checked on it. + */ int suspended; atomic_t active_io; @@ -206,7 +225,7 @@ struct mddev_s * are happening, so run/ * takeover/stop are not safe */ - int ready; /* See when safe to pass + int ready; /* See when safe to pass * IO requests down */ struct gendisk *gendisk; @@ -252,12 +271,18 @@ struct mddev_s sector_t reshape_position; int delta_disks, new_level, new_layout; int new_chunk_sectors; + int reshape_backwards; - atomic_t plug_cnt; /* If device is expecting - * more bios soon. - */ - struct mdk_thread_s *thread; /* management thread */ - struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */ + struct md_thread *thread; /* management thread */ + struct md_thread *sync_thread; /* doing resync or reconstruct */ + + /* 'last_sync_action' is initialized to "none". It is set when a + * sync operation (i.e "data-check", "requested-resync", "resync", + * "recovery", or "reshape") is started. It holds this value even + * when the sync thread is "frozen" (interrupted) or "idle" (stopped + * or finished). It is overwritten when a new sync operation is begun. + */ + char *last_sync_action; sector_t curr_resync; /* last block scheduled */ /* As resync requests can complete out of order, we cannot easily track * how much resync has been completed. So we occasionally pause until @@ -272,7 +297,7 @@ struct mddev_s sector_t resync_max_sectors; /* may be set by personality */ - sector_t resync_mismatches; /* count of sectors where + atomic64_t resync_mismatches; /* count of sectors where * parity/replica mismatch found */ @@ -297,6 +322,7 @@ struct mddev_s * REQUEST: user-space has requested a sync (used with SYNC) * CHECK: user-space request for check-only, no repair * RESHAPE: A reshape is happening + * ERROR: sync-action interrupted because io-error * * If neither SYNC or RESHAPE are set, then it is a recovery. */ @@ -310,6 +336,7 @@ struct mddev_s #define MD_RECOVERY_CHECK 7 #define MD_RECOVERY_RESHAPE 8 #define MD_RECOVERY_FROZEN 9 +#define MD_RECOVERY_ERROR 10 unsigned long recovery; /* If a RAID personality determines that recovery (of a particular @@ -339,6 +366,10 @@ struct mddev_s int degraded; /* whether md should consider * adding a spare */ + int merge_check_needed; /* at least one + * member device + * has a + * merge_bvec_fn */ atomic_t recovery_active; /* blocks scheduled, but not written */ wait_queue_head_t recovery_wait; @@ -348,10 +379,10 @@ struct mddev_s sector_t resync_max; /* resync should pause * when it gets here */ - struct sysfs_dirent *sysfs_state; /* handle for 'array_state' + struct kernfs_node *sysfs_state; /* handle for 'array_state' * file in sysfs. */ - struct sysfs_dirent *sysfs_action; /* handle for 'sync_action' */ + struct kernfs_node *sysfs_action; /* handle for 'sync_action' */ struct work_struct del_work; /* used for delayed sysfs removal */ @@ -376,10 +407,13 @@ struct mddev_s * For external metadata, offset * from start of device. */ + unsigned long space; /* space available at this offset */ loff_t default_offset; /* this is the offset to use when * hot-adding a bitmap. It should * eventually be settable by sysfs. */ + unsigned long default_space; /* space available at + * default offset */ struct mutex mutex; unsigned long chunksize; unsigned long daemon_sleep; /* how many jiffies between updates? */ @@ -402,11 +436,11 @@ struct mddev_s atomic_t flush_pending; struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ - void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev); + void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); }; -static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev) +static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) { int faulty = test_bit(Faulty, &rdev->flags); if (atomic_dec_and_test(&rdev->nr_pending) && faulty) @@ -418,35 +452,35 @@ static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sect atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io); } -struct mdk_personality +struct md_personality { char *name; int level; struct list_head list; struct module *owner; - int (*make_request)(mddev_t *mddev, struct bio *bio); - int (*run)(mddev_t *mddev); - int (*stop)(mddev_t *mddev); - void (*status)(struct seq_file *seq, mddev_t *mddev); + void (*make_request)(struct mddev *mddev, struct bio *bio); + int (*run)(struct mddev *mddev); + int (*stop)(struct mddev *mddev); + void (*status)(struct seq_file *seq, struct mddev *mddev); /* error_handler must set ->faulty and clear ->in_sync * if appropriate, and should abort recovery if needed */ - void (*error_handler)(mddev_t *mddev, mdk_rdev_t *rdev); - int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev); - int (*hot_remove_disk) (mddev_t *mddev, int number); - int (*spare_active) (mddev_t *mddev); - sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster); - int (*resize) (mddev_t *mddev, sector_t sectors); - sector_t (*size) (mddev_t *mddev, sector_t sectors, int raid_disks); - int (*check_reshape) (mddev_t *mddev); - int (*start_reshape) (mddev_t *mddev); - void (*finish_reshape) (mddev_t *mddev); + void (*error_handler)(struct mddev *mddev, struct md_rdev *rdev); + int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev); + int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev); + int (*spare_active) (struct mddev *mddev); + sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster); + int (*resize) (struct mddev *mddev, sector_t sectors); + sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks); + int (*check_reshape) (struct mddev *mddev); + int (*start_reshape) (struct mddev *mddev); + void (*finish_reshape) (struct mddev *mddev); /* quiesce moves between quiescence states * 0 - fully active * 1 - no new requests allowed * others - reserved */ - void (*quiesce) (mddev_t *mddev, int state); + void (*quiesce) (struct mddev *mddev, int state); /* takeover is used to transition an array from one * personality to another. The new personality must be able * to handle the data in the current layout. @@ -456,46 +490,51 @@ struct mdk_personality * This needs to be installed and then ->run used to activate the * array. */ - void *(*takeover) (mddev_t *mddev); + void *(*takeover) (struct mddev *mddev); }; struct md_sysfs_entry { struct attribute attr; - ssize_t (*show)(mddev_t *, char *); - ssize_t (*store)(mddev_t *, const char *, size_t); + ssize_t (*show)(struct mddev *, char *); + ssize_t (*store)(struct mddev *, const char *, size_t); }; extern struct attribute_group md_bitmap_group; -static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name) +static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name) { if (sd) - return sysfs_get_dirent(sd, NULL, name); + return sysfs_get_dirent(sd, name); return sd; } -static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd) +static inline void sysfs_notify_dirent_safe(struct kernfs_node *sd) { if (sd) sysfs_notify_dirent(sd); } -static inline char * mdname (mddev_t * mddev) +static inline char * mdname (struct mddev * mddev) { return mddev->gendisk ? mddev->gendisk->disk_name : "mdX"; } -static inline int sysfs_link_rdev(mddev_t *mddev, mdk_rdev_t *rdev) +static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - sprintf(nm, "rd%d", rdev->raid_disk); - return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); + if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + sprintf(nm, "rd%d", rdev->raid_disk); + return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); + } else + return 0; } -static inline void sysfs_unlink_rdev(mddev_t *mddev, mdk_rdev_t *rdev) +static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - sprintf(nm, "rd%d", rdev->raid_disk); - sysfs_remove_link(&mddev->kobj, nm); + if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + sprintf(nm, "rd%d", rdev->raid_disk); + sysfs_remove_link(&mddev->kobj, nm); + } } /* @@ -508,96 +547,83 @@ static inline void sysfs_unlink_rdev(mddev_t *mddev, mdk_rdev_t *rdev) /* * iterates through the 'same array disks' ringlist */ -#define rdev_for_each(rdev, tmp, mddev) \ +#define rdev_for_each(rdev, mddev) \ + list_for_each_entry(rdev, &((mddev)->disks), same_set) + +#define rdev_for_each_safe(rdev, tmp, mddev) \ list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set) #define rdev_for_each_rcu(rdev, mddev) \ list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set) -typedef struct mdk_thread_s { - void (*run) (mddev_t *mddev); - mddev_t *mddev; +struct md_thread { + void (*run) (struct md_thread *thread); + struct mddev *mddev; wait_queue_head_t wqueue; unsigned long flags; struct task_struct *tsk; unsigned long timeout; -} mdk_thread_t; + void *private; +}; #define THREAD_WAKEUP 0 -#define __wait_event_lock_irq(wq, condition, lock, cmd) \ -do { \ - wait_queue_t __wait; \ - init_waitqueue_entry(&__wait, current); \ - \ - add_wait_queue(&wq, &__wait); \ - for (;;) { \ - set_current_state(TASK_UNINTERRUPTIBLE); \ - if (condition) \ - break; \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ - spin_lock_irq(&lock); \ - } \ - current->state = TASK_RUNNING; \ - remove_wait_queue(&wq, &__wait); \ -} while (0) - -#define wait_event_lock_irq(wq, condition, lock, cmd) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, cmd); \ -} while (0) - static inline void safe_put_page(struct page *p) { if (p) put_page(p); } -extern int register_md_personality(struct mdk_personality *p); -extern int unregister_md_personality(struct mdk_personality *p); -extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev), - mddev_t *mddev, const char *name); -extern void md_unregister_thread(mdk_thread_t *thread); -extern void md_wakeup_thread(mdk_thread_t *thread); -extern void md_check_recovery(mddev_t *mddev); -extern void md_write_start(mddev_t *mddev, struct bio *bi); -extern void md_write_end(mddev_t *mddev); -extern void md_done_sync(mddev_t *mddev, int blocks, int ok); -extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev); - -extern int mddev_congested(mddev_t *mddev, int bits); -extern void md_flush_request(mddev_t *mddev, struct bio *bio); -extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, +extern int register_md_personality(struct md_personality *p); +extern int unregister_md_personality(struct md_personality *p); +extern struct md_thread *md_register_thread( + void (*run)(struct md_thread *thread), + struct mddev *mddev, + const char *name); +extern void md_unregister_thread(struct md_thread **threadp); +extern void md_wakeup_thread(struct md_thread *thread); +extern void md_check_recovery(struct mddev *mddev); +extern void md_reap_sync_thread(struct mddev *mddev); +extern void md_write_start(struct mddev *mddev, struct bio *bi); +extern void md_write_end(struct mddev *mddev); +extern void md_done_sync(struct mddev *mddev, int blocks, int ok); +extern void md_error(struct mddev *mddev, struct md_rdev *rdev); +extern void md_finish_reshape(struct mddev *mddev); + +extern int mddev_congested(struct mddev *mddev, int bits); +extern void md_flush_request(struct mddev *mddev, struct bio *bio); +extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); -extern void md_super_wait(mddev_t *mddev); -extern int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size, +extern void md_super_wait(struct mddev *mddev); +extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, int rw, bool metadata_op); -extern void md_do_sync(mddev_t *mddev); -extern void md_new_event(mddev_t *mddev); -extern int md_allow_write(mddev_t *mddev); -extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev); -extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors); -extern int md_check_no_bitmap(mddev_t *mddev); -extern int md_integrity_register(mddev_t *mddev); -extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev); +extern void md_do_sync(struct md_thread *thread); +extern void md_new_event(struct mddev *mddev); +extern int md_allow_write(struct mddev *mddev); +extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); +extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); +extern int md_check_no_bitmap(struct mddev *mddev); +extern int md_integrity_register(struct mddev *mddev); +extern void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); -extern void restore_bitmap_write_access(struct file *file); -extern void mddev_init(mddev_t *mddev); -extern int md_run(mddev_t *mddev); -extern void md_stop(mddev_t *mddev); -extern void md_stop_writes(mddev_t *mddev); -extern int md_rdev_init(mdk_rdev_t *rdev); +extern void mddev_init(struct mddev *mddev); +extern int md_run(struct mddev *mddev); +extern void md_stop(struct mddev *mddev); +extern void md_stop_writes(struct mddev *mddev); +extern int md_rdev_init(struct md_rdev *rdev); +extern void md_rdev_clear(struct md_rdev *rdev); -extern void mddev_suspend(mddev_t *mddev); -extern void mddev_resume(mddev_t *mddev); +extern void mddev_suspend(struct mddev *mddev); +extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, - mddev_t *mddev); + struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, - mddev_t *mddev); -extern int mddev_check_plugged(mddev_t *mddev); -extern void md_trim_bio(struct bio *bio, int offset, int size); + struct mddev *mddev); + +extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule); +static inline int mddev_check_plugged(struct mddev *mddev) +{ + return !!blk_check_plugged(md_unplug, mddev, + sizeof(struct blk_plug_cb)); +} #endif /* _MD_MD_H */ |