/* SPDX-License-Identifier: GPL-2.0-or-later *//* md.h : kernel internal structure of the Linux MD driver Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman */ #ifndef _MD_MD_H#define _MD_MD_H #include <linux/blkdev.h>#include <linux/backing-dev.h>#include <linux/badblocks.h>#include <linux/kobject.h>#include <linux/list.h>#include <linux/mm.h>#include <linux/mutex.h>#include <linux/timer.h>#include <linux/wait.h>#include <linux/workqueue.h>#include <linux/raid/md_u.h>#include <trace/events/block.h> #define MaxSector (~(sector_t)0)/* * Number of guaranteed raid bios in case of extreme VM load: */#define NR_RAID_BIOS 256 enum md_submodule_type { MD_PERSONALITY = 0, MD_CLUSTER, MD_BITMAP,}; enum md_submodule_id { ID_LINEAR = LEVEL_LINEAR, ID_RAID0 = 0, ID_RAID1 = 1, ID_RAID4 = 4, ID_RAID5 = 5, ID_RAID6 = 6, ID_RAID10 = 10, ID_CLUSTER, ID_BITMAP, ID_LLBITMAP, ID_BITMAP_NONE,}; struct md_submodule_head { enum md_submodule_type type; enum md_submodule_id id; const char *name; struct module *owner;}; /* * These flags should really be called "NO_RETRY" rather than * "FAILFAST" because they don't make any promise about time lapse, * only about the number of retries, which will be zero. * REQ_FAILFAST_DRIVER is not included because * Commit: 4a27446f3e39 ("[SCSI] modify scsi to handle new fail fast flags.") * seems to suggest that the errors it avoids retrying should usually * be retried. */#define MD_FAILFAST (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT) /* Status of sync thread. */enum sync_action { /* * Represent by MD_RECOVERY_SYNC, start when: * 1) after assemble, sync data from first rdev to other copies, this * must be done first before other sync actions and will only execute * once; * 2) resize the array(notice that this is not reshape), sync data for * the new range; */ ACTION_RESYNC, /* * Represent by MD_RECOVERY_RECOVER, start when: * 1) for new replacement, sync data based on the replace rdev or * available copies from other rdev; * 2) for new member disk while the array is degraded, sync data from * other rdev; * 3) reassemble after power failure or re-add a hot removed rdev, sync * data from first rdev to other copies based on bitmap; */ ACTION_RECOVER, /* * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED | * MD_RECOVERY_CHECK, start when user echo "check" to sysfs api * sync_action, used to check if data copies from differenct rdev are * the same. The number of mismatch sectors will be exported to user * by sysfs api mismatch_cnt; */ ACTION_CHECK, /* * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED, start when * user echo "repair" to sysfs api sync_action, usually paired with * ACTION_CHECK, used to force syncing data once user found that there * are inconsistent data, */ ACTION_REPAIR, /* * Represent by MD_RECOVERY_RESHAPE, start when new member disk is added * to the conf, notice that this is different from spares or * replacement; */ ACTION_RESHAPE, /* * Represent by MD_RECOVERY_FROZEN, can be set by sysfs api sync_action * or internal usage like setting the array read-only, will forbid above * actions. */ ACTION_FROZEN, /* * All above actions don't match. */ ACTION_IDLE, NR_SYNC_ACTIONS,}; /* * The struct embedded in rdev is used to serialize IO. */struct serial_in_rdev { struct rb_root_cached serial_rb; spinlock_t serial_lock;}; /* * MD's 'extended' device */struct md_rdev { struct list_head same_set; /* RAID devices within the same set */ sector_t sectors; /* Device size (in 512bytes sectors) */ struct mddev *mddev; /* RAID array if running */ unsigned long last_events; /* IO event timestamp */ /* * If meta_bdev is non-NULL, it means that a separate device is * being used to store the metadata (superblock/bitmap) which * would otherwise be contained on the same device as the data (bdev). */ struct block_device *meta_bdev; struct block_device *bdev; /* block device handle */ struct file *bdev_file; /* Handle from open for bdev */ struct page *sb_page, *bb_page; 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 */ struct kobject kobj; /* A device can be in one of three states based on two flags: * Not working: faulty==1 in_sync==0 * Fully working: faulty==0 in_sync==1 * Working, but not * in sync with array * faulty==0 in_sync==0 * * It can never have faulty==1, in_sync==1 * This reduces the burden of testing multiple flags in many cases */ unsigned long flags; /* bit set of 'enum flag_bits' bits. */ wait_queue_head_t blocked_wait; int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ int new_raid_disk; /* role that the device will have in * the array after a level-change completes. */ int saved_raid_disk; /* role that device used to have in the * array and could again if we did a partial * resync from the bitmap */ union { sector_t recovery_offset;/* If this device has been partially * recovered, this is where we were * up to. */ sector_t journal_tail; /* If this device is a journal device, * this is the journal tail (journal * recovery start point) */ }; atomic_t nr_pending; /* number of pending requests. * only maintained for arrays that * support hot removal */ atomic_t read_errors; /* number of consecutive read errors that * we have tried to ignore. */ time64_t last_read_error; /* monotonic time since our * last read error */ atomic_t corrected_errors; /* number of corrected read errors, * for reporting to userspace and storing * in superblock. */ struct serial_in_rdev *serial; /* used for raid1 io serialization */ struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ /* handle for 'unacknowledged_bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_unack_badblocks; /* handle for 'bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_badblocks; struct badblocks badblocks; struct { short offset; /* Offset from superblock to start of PPL. * Not used by external metadata. */ unsigned int size; /* Size in sectors of the PPL space */ sector_t sector; /* First sector of the PPL space */ } ppl;};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. * The bit is only meaningful before device * has been passed to pers->hot_add_disk. */ 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. */ Candidate, /* For clustered environments only: * This device is seen locally but not * by the whole cluster */ Journal, /* This device is used as journal for * raid-5/6. * Usually, this device should be faster * than other devices in the array */ ClusterRemove, ExternalBbl, /* External metadata provides bad * block management for a disk */ FailFast, /* Minimal retries should be attempted on * this device, so use REQ_FAILFAST_DEV. * Also don't try to repair failed reads. * It is expects that no bad block log * is present. */ LastDev, /* Seems to be the last working dev as * it didn't fail, so don't use FailFast * any more for metadata */ CollisionCheck, /* * check if there is collision between raid1 * serial bios. */ Nonrot, /* non-rotational device (SSD) */}; static inline int is_badblock(struct md_rdev *rdev, sector_t s, sector_t sectors, sector_t *first_bad, sector_t *bad_sectors){ if (unlikely(rdev->badblocks.count)) { int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s, sectors, first_bad, bad_sectors); if (rv) *first_bad -= rdev->data_offset; return rv; } return 0;} static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s, sector_t sectors){ sector_t first_bad; sector_t bad_sectors; return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors);} extern bool rdev_set_badblocks(struct md_rdev *rdev, sector_t s, sector_t sectors, int is_new);extern void rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, sector_t sectors, int is_new);struct md_cluster_info;struct md_cluster_operations; /** * enum mddev_flags - md device flags. * @MD_ARRAY_FIRST_USE: First use of array, needs initialization. * @MD_CLOSING: If set, we are closing the array, do not open it then. * @MD_JOURNAL_CLEAN: A raid with journal is already clean. * @MD_HAS_JOURNAL: The raid array has journal feature set. * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took * resync lock, need to release the lock. * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as * calls to md_error() will never cause the array to * become failed. * @MD_HAS_PPL: The raid array has PPL feature set. * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set. * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that * array is ready yet. * @MD_BROKEN: This is used to stop writes and mark array as failed. * @MD_DELETED: This device is being deleted * @MD_HAS_SUPERBLOCK: There is persistence sb in member disks. * @MD_FAILLAST_DEV: Allow last rdev to be removed. * @MD_SERIALIZE_POLICY: Enforce write IO is not reordered, just used by raid1. * @MD_DM_SUSPENDING: This DM raid device is suspending. * * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */enum mddev_flags { MD_ARRAY_FIRST_USE, MD_CLOSING, MD_JOURNAL_CLEAN, MD_HAS_JOURNAL, MD_CLUSTER_RESYNC_LOCKED, MD_FAILFAST_SUPPORTED, MD_HAS_PPL, MD_HAS_MULTIPLE_PPLS, MD_NOT_READY, MD_BROKEN, MD_DO_DELETE, MD_DELETED, MD_HAS_SUPERBLOCK, MD_FAILLAST_DEV, MD_SERIALIZE_POLICY, MD_DM_SUSPENDING,}; enum mddev_sb_flags { MD_SB_CHANGE_DEVS, /* Some device status has changed */ MD_SB_CHANGE_CLEAN, /* transition to or from 'clean' */ MD_SB_CHANGE_PENDING, /* switch from 'clean' to 'active' in progress */ MD_SB_NEED_REWRITE, /* metadata write needs to be repeated */}; #define NR_SERIAL_INFOS 8/* record current range of serialize IOs */struct serial_info { struct rb_node node; sector_t start; /* start sector of rb node */ sector_t last; /* end sector of rb node */ sector_t wnode_start; /* address of waiting nodes on the same list */ sector_t _subtree_last; /* highest sector in subtree of rb node */ struct list_head list_node; struct list_head waiters; struct completion ready;}; /* * mddev->curr_resync stores the current sector of the resync but * also has some overloaded values. */enum { /* No resync in progress */ MD_RESYNC_NONE = 0, /* Yielded to allow another conflicting resync to commence */ MD_RESYNC_YIELDED = 1, /* Delayed to check that there is no conflict with another sync */ MD_RESYNC_DELAYED = 2, /* Any value greater than or equal to this is in an active resync */ MD_RESYNC_ACTIVE = 3,}; struct mddev { void *private; struct md_personality *pers; dev_t unit; int md_minor; struct list_head disks; unsigned long flags; unsigned long sb_flags; int suspended; struct mutex suspend_mutex; struct percpu_ref active_io; int ro; int sysfs_active; /* set when sysfs deletes * are happening, so run/ * takeover/stop are not safe */ struct gendisk *gendisk; /* mdraid gendisk */ struct gendisk *dm_gendisk; /* dm-raid gendisk */ struct kobject kobj; int hold_active;#define UNTIL_IOCTL 1#define UNTIL_STOP 2 /* Superblock information */ int major_version, minor_version, patch_version; int persistent; int external; /* metadata is * managed externally */ char metadata_type[17]; /* externally set*/ int chunk_sectors; time64_t ctime, utime; int level, layout; char clevel[16]; int raid_disks; int max_disks; sector_t dev_sectors; /* used size of * component devices */ sector_t array_sectors; /* exported array size */ int external_size; /* size managed * externally */ unsigned int logical_block_size; __u64 events; /* If the last 'event' was simply a clean->dirty transition, and * we didn't write it to the spares, then it is safe and simple * to just decrement the event count on a dirty->clean transition. * So we record that possibility here. */ int can_decrease_events; char uuid[16]; /* If the array is being reshaped, we need to record the * new shape and an indication of where we are up to. * This is written to the superblock. * If reshape_position is MaxSector, then no reshape is happening (yet). */ sector_t reshape_position; int delta_disks, new_level, new_layout; int new_chunk_sectors; int reshape_backwards; struct md_thread __rcu *thread; /* management thread */ struct md_thread __rcu *sync_thread; /* doing resync or reconstruct */ /* * Set when a sync operation 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. */ enum sync_action 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 * everything completes, then set curr_resync_completed to curr_resync. * As such it may be well behind the real resync mark, but it is a value * we are certain of. */ sector_t curr_resync_completed; unsigned long resync_mark; /* a recent timestamp */ sector_t resync_mark_cnt;/* blocks written at resync_mark */ sector_t curr_mark_cnt; /* blocks scheduled now */ sector_t resync_max_sectors; /* may be set by personality */ atomic64_t resync_mismatches; /* count of sectors where * parity/replica mismatch found */ /* allow user-space to request suspension of IO to regions of the array */ sector_t suspend_lo;Lines 1–500 of 1110. Load more
/* SPDX-License-Identifier: GPL-2.0-or-later */ /* md.h : kernel internal structure of the Linux MD driver Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman */ #ifndef _MD_MD_H #define _MD_MD_H #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/badblocks.h> #include <linux/kobject.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <linux/raid/md_u.h> #include <trace/events/block.h> #define MaxSector (~(sector_t)0) /* * Number of guaranteed raid bios in case of extreme VM load: */ #define NR_RAID_BIOS 256 enum md_submodule_type { MD_PERSONALITY = 0, MD_CLUSTER, MD_BITMAP, }; enum md_submodule_id { ID_LINEAR = LEVEL_LINEAR, ID_RAID0 = 0, ID_RAID1 = 1, ID_RAID4 = 4, ID_RAID5 = 5, ID_RAID6 = 6, ID_RAID10 = 10, ID_CLUSTER, ID_BITMAP, ID_LLBITMAP, ID_BITMAP_NONE, }; struct md_submodule_head { enum md_submodule_type type; enum md_submodule_id id; const char *name; struct module *owner; }; /* * These flags should really be called "NO_RETRY" rather than * "FAILFAST" because they don't make any promise about time lapse, * only about the number of retries, which will be zero. * REQ_FAILFAST_DRIVER is not included because * Commit: 4a27446f3e39 ("[SCSI] modify scsi to handle new fail fast flags.") * seems to suggest that the errors it avoids retrying should usually * be retried. */ #define MD_FAILFAST (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT) /* Status of sync thread. */ enum sync_action { /* * Represent by MD_RECOVERY_SYNC, start when: * 1) after assemble, sync data from first rdev to other copies, this * must be done first before other sync actions and will only execute * once; * 2) resize the array(notice that this is not reshape), sync data for * the new range; */ ACTION_RESYNC, /* * Represent by MD_RECOVERY_RECOVER, start when: * 1) for new replacement, sync data based on the replace rdev or * available copies from other rdev; * 2) for new member disk while the array is degraded, sync data from * other rdev; * 3) reassemble after power failure or re-add a hot removed rdev, sync * data from first rdev to other copies based on bitmap; */ ACTION_RECOVER, /* * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED | * MD_RECOVERY_CHECK, start when user echo "check" to sysfs api * sync_action, used to check if data copies from differenct rdev are * the same. The number of mismatch sectors will be exported to user * by sysfs api mismatch_cnt; */ ACTION_CHECK, /* * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED, start when * user echo "repair" to sysfs api sync_action, usually paired with * ACTION_CHECK, used to force syncing data once user found that there * are inconsistent data, */ ACTION_REPAIR, /* * Represent by MD_RECOVERY_RESHAPE, start when new member disk is added * to the conf, notice that this is different from spares or * replacement; */ ACTION_RESHAPE, /* * Represent by MD_RECOVERY_FROZEN, can be set by sysfs api sync_action * or internal usage like setting the array read-only, will forbid above * actions. */ ACTION_FROZEN, /* * All above actions don't match. */ ACTION_IDLE, NR_SYNC_ACTIONS, }; /* * The struct embedded in rdev is used to serialize IO. */ struct serial_in_rdev { struct rb_root_cached serial_rb; spinlock_t serial_lock; }; /* * MD's 'extended' device */ struct md_rdev { struct list_head same_set; /* RAID devices within the same set */ sector_t sectors; /* Device size (in 512bytes sectors) */ struct mddev *mddev; /* RAID array if running */ unsigned long last_events; /* IO event timestamp */ /* * If meta_bdev is non-NULL, it means that a separate device is * being used to store the metadata (superblock/bitmap) which * would otherwise be contained on the same device as the data (bdev). */ struct block_device *meta_bdev; struct block_device *bdev; /* block device handle */ struct file *bdev_file; /* Handle from open for bdev */ struct page *sb_page, *bb_page; 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 */ struct kobject kobj; /* A device can be in one of three states based on two flags: * Not working: faulty==1 in_sync==0 * Fully working: faulty==0 in_sync==1 * Working, but not * in sync with array * faulty==0 in_sync==0 * * It can never have faulty==1, in_sync==1 * This reduces the burden of testing multiple flags in many cases */ unsigned long flags; /* bit set of 'enum flag_bits' bits. */ wait_queue_head_t blocked_wait; int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ int new_raid_disk; /* role that the device will have in * the array after a level-change completes. */ int saved_raid_disk; /* role that device used to have in the * array and could again if we did a partial * resync from the bitmap */ union { sector_t recovery_offset;/* If this device has been partially * recovered, this is where we were * up to. */ sector_t journal_tail; /* If this device is a journal device, * this is the journal tail (journal * recovery start point) */ }; atomic_t nr_pending; /* number of pending requests. * only maintained for arrays that * support hot removal */ atomic_t read_errors; /* number of consecutive read errors that * we have tried to ignore. */ time64_t last_read_error; /* monotonic time since our * last read error */ atomic_t corrected_errors; /* number of corrected read errors, * for reporting to userspace and storing * in superblock. */ struct serial_in_rdev *serial; /* used for raid1 io serialization */ struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ /* handle for 'unacknowledged_bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_unack_badblocks; /* handle for 'bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_badblocks; struct badblocks badblocks; struct { short offset; /* Offset from superblock to start of PPL. * Not used by external metadata. */ unsigned int size; /* Size in sectors of the PPL space */ sector_t sector; /* First sector of the PPL space */ } ppl; }; 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. * The bit is only meaningful before device * has been passed to pers->hot_add_disk. */ 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. */ Candidate, /* For clustered environments only: * This device is seen locally but not * by the whole cluster */ Journal, /* This device is used as journal for * raid-5/6. * Usually, this device should be faster * than other devices in the array */ ClusterRemove, ExternalBbl, /* External metadata provides bad * block management for a disk */ FailFast, /* Minimal retries should be attempted on * this device, so use REQ_FAILFAST_DEV. * Also don't try to repair failed reads. * It is expects that no bad block log * is present. */ LastDev, /* Seems to be the last working dev as * it didn't fail, so don't use FailFast * any more for metadata */ CollisionCheck, /* * check if there is collision between raid1 * serial bios. */ Nonrot, /* non-rotational device (SSD) */ }; static inline int is_badblock(struct md_rdev *rdev, sector_t s, sector_t sectors, sector_t *first_bad, sector_t *bad_sectors) { if (unlikely(rdev->badblocks.count)) { int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s, sectors, first_bad, bad_sectors); if (rv) *first_bad -= rdev->data_offset; return rv; } return 0; } static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s, sector_t sectors) { sector_t first_bad; sector_t bad_sectors; return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors); } extern bool rdev_set_badblocks(struct md_rdev *rdev, sector_t s, sector_t sectors, int is_new); extern void rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, sector_t sectors, int is_new); struct md_cluster_info; struct md_cluster_operations; /** * enum mddev_flags - md device flags. * @MD_ARRAY_FIRST_USE: First use of array, needs initialization. * @MD_CLOSING: If set, we are closing the array, do not open it then. * @MD_JOURNAL_CLEAN: A raid with journal is already clean. * @MD_HAS_JOURNAL: The raid array has journal feature set. * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took * resync lock, need to release the lock. * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as * calls to md_error() will never cause the array to * become failed. * @MD_HAS_PPL: The raid array has PPL feature set. * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set. * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that * array is ready yet. * @MD_BROKEN: This is used to stop writes and mark array as failed. * @MD_DELETED: This device is being deleted * @MD_HAS_SUPERBLOCK: There is persistence sb in member disks. * @MD_FAILLAST_DEV: Allow last rdev to be removed. * @MD_SERIALIZE_POLICY: Enforce write IO is not reordered, just used by raid1. * @MD_DM_SUSPENDING: This DM raid device is suspending. * * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */ enum mddev_flags { MD_ARRAY_FIRST_USE, MD_CLOSING, MD_JOURNAL_CLEAN, MD_HAS_JOURNAL, MD_CLUSTER_RESYNC_LOCKED, MD_FAILFAST_SUPPORTED, MD_HAS_PPL, MD_HAS_MULTIPLE_PPLS, MD_NOT_READY, MD_BROKEN, MD_DO_DELETE, MD_DELETED, MD_HAS_SUPERBLOCK, MD_FAILLAST_DEV, MD_SERIALIZE_POLICY, MD_DM_SUSPENDING, }; enum mddev_sb_flags { MD_SB_CHANGE_DEVS, /* Some device status has changed */ MD_SB_CHANGE_CLEAN, /* transition to or from 'clean' */ MD_SB_CHANGE_PENDING, /* switch from 'clean' to 'active' in progress */ MD_SB_NEED_REWRITE, /* metadata write needs to be repeated */ }; #define NR_SERIAL_INFOS 8 /* record current range of serialize IOs */ struct serial_info { struct rb_node node; sector_t start; /* start sector of rb node */ sector_t last; /* end sector of rb node */ sector_t wnode_start; /* address of waiting nodes on the same list */ sector_t _subtree_last; /* highest sector in subtree of rb node */ struct list_head list_node; struct list_head waiters; struct completion ready; }; /* * mddev->curr_resync stores the current sector of the resync but * also has some overloaded values. */ enum { /* No resync in progress */ MD_RESYNC_NONE = 0, /* Yielded to allow another conflicting resync to commence */ MD_RESYNC_YIELDED = 1, /* Delayed to check that there is no conflict with another sync */ MD_RESYNC_DELAYED = 2, /* Any value greater than or equal to this is in an active resync */ MD_RESYNC_ACTIVE = 3, }; struct mddev { void *private; struct md_personality *pers; dev_t unit; int md_minor; struct list_head disks; unsigned long flags; unsigned long sb_flags; int suspended; struct mutex suspend_mutex; struct percpu_ref active_io; int ro; int sysfs_active; /* set when sysfs deletes * are happening, so run/ * takeover/stop are not safe */ struct gendisk *gendisk; /* mdraid gendisk */ struct gendisk *dm_gendisk; /* dm-raid gendisk */ struct kobject kobj; int hold_active; #define UNTIL_IOCTL 1 #define UNTIL_STOP 2 /* Superblock information */ int major_version, minor_version, patch_version; int persistent; int external; /* metadata is * managed externally */ char metadata_type[17]; /* externally set*/ int chunk_sectors; time64_t ctime, utime; int level, layout; char clevel[16]; int raid_disks; int max_disks; sector_t dev_sectors; /* used size of * component devices */ sector_t array_sectors; /* exported array size */ int external_size; /* size managed * externally */ unsigned int logical_block_size; __u64 events; /* If the last 'event' was simply a clean->dirty transition, and * we didn't write it to the spares, then it is safe and simple * to just decrement the event count on a dirty->clean transition. * So we record that possibility here. */ int can_decrease_events; char uuid[16]; /* If the array is being reshaped, we need to record the * new shape and an indication of where we are up to. * This is written to the superblock. * If reshape_position is MaxSector, then no reshape is happening (yet). */ sector_t reshape_position; int delta_disks, new_level, new_layout; int new_chunk_sectors; int reshape_backwards; struct md_thread __rcu *thread; /* management thread */ struct md_thread __rcu *sync_thread; /* doing resync or reconstruct */ /* * Set when a sync operation 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. */ enum sync_action 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 * everything completes, then set curr_resync_completed to curr_resync. * As such it may be well behind the real resync mark, but it is a value * we are certain of. */ sector_t curr_resync_completed; unsigned long resync_mark; /* a recent timestamp */ sector_t resync_mark_cnt;/* blocks written at resync_mark */ sector_t curr_mark_cnt; /* blocks scheduled now */ sector_t resync_max_sectors; /* may be set by personality */ atomic64_t resync_mismatches; /* count of sectors where * parity/replica mismatch found */ /* allow user-space to request suspension of IO to regions of the array */ sector_t suspend_lo;