#ifndef _MD_K_H
#define _MD_K_H
-#define MD_RESERVED 0UL
-#define LINEAR 1UL
-#define RAID0 2UL
-#define RAID1 3UL
-#define RAID5 4UL
-#define TRANSLUCENT 5UL
-#define HSM 6UL
-#define MULTIPATH 7UL
-#define RAID6 8UL
-#define RAID10 9UL
-#define FAULTY 10UL
-#define MAX_PERSONALITY 11UL
+/* and dm-bio-list.h is not under include/linux because.... ??? */
+#include "../../../drivers/md/dm-bio-list.h"
+
+#ifdef CONFIG_BLOCK
#define LEVEL_MULTIPATH (-4)
#define LEVEL_LINEAR (-1)
#define LEVEL_FAULTY (-5)
-#define MaxSector (~(sector_t)0)
-#define MD_THREAD_NAME_MAX 14
-
-static inline int pers_to_level (int pers)
-{
- switch (pers) {
- case FAULTY: return LEVEL_FAULTY;
- case MULTIPATH: return LEVEL_MULTIPATH;
- case HSM: return -3;
- case TRANSLUCENT: return -2;
- case LINEAR: return LEVEL_LINEAR;
- case RAID0: return 0;
- case RAID1: return 1;
- case RAID5: return 5;
- case RAID6: return 6;
- case RAID10: return 10;
- }
- BUG();
- return MD_RESERVED;
-}
+/* we need a value for 'no level specified' and 0
+ * means 'raid0', so we need something else. This is
+ * for internal use only
+ */
+#define LEVEL_NONE (-1000000)
-static inline int level_to_pers (int level)
-{
- switch (level) {
- case LEVEL_FAULTY: return FAULTY;
- case LEVEL_MULTIPATH: return MULTIPATH;
- case -3: return HSM;
- case -2: return TRANSLUCENT;
- case LEVEL_LINEAR: return LINEAR;
- case 0: return RAID0;
- case 1: return RAID1;
- case 4:
- case 5: return RAID5;
- case 6: return RAID6;
- case 10: return RAID10;
- }
- return MD_RESERVED;
-}
+#define MaxSector (~(sector_t)0)
typedef struct mddev_s mddev_t;
typedef struct mdk_rdev_s mdk_rdev_t;
-#define MAX_MD_DEVS 256 /* Max number of md dev */
-
/*
* options passed in raidrun:
*/
-#define MAX_CHUNK_SIZE (4096*1024)
-
-/*
- * default readahead
- */
-
-static inline int disk_faulty(mdp_disk_t * d)
-{
- return d->state & (1 << MD_DISK_FAULTY);
-}
-
-static inline int disk_active(mdp_disk_t * d)
-{
- return d->state & (1 << MD_DISK_ACTIVE);
-}
-
-static inline int disk_sync(mdp_disk_t * d)
-{
- return d->state & (1 << MD_DISK_SYNC);
-}
-
-static inline int disk_spare(mdp_disk_t * d)
-{
- return !disk_sync(d) && !disk_active(d) && !disk_faulty(d);
-}
-
-static inline int disk_removed(mdp_disk_t * d)
-{
- return d->state & (1 << MD_DISK_REMOVED);
-}
-
-static inline void mark_disk_faulty(mdp_disk_t * d)
-{
- d->state |= (1 << MD_DISK_FAULTY);
-}
-
-static inline void mark_disk_active(mdp_disk_t * d)
-{
- d->state |= (1 << MD_DISK_ACTIVE);
-}
-
-static inline void mark_disk_sync(mdp_disk_t * d)
-{
- d->state |= (1 << MD_DISK_SYNC);
-}
-
-static inline void mark_disk_spare(mdp_disk_t * d)
-{
- d->state = 0;
-}
-
-static inline void mark_disk_removed(mdp_disk_t * d)
-{
- d->state = (1 << MD_DISK_FAULTY) | (1 << MD_DISK_REMOVED);
-}
-
-static inline void mark_disk_inactive(mdp_disk_t * d)
-{
- d->state &= ~(1 << MD_DISK_ACTIVE);
-}
-
-static inline void mark_disk_nonsync(mdp_disk_t * d)
-{
- d->state &= ~(1 << MD_DISK_SYNC);
-}
+/* Currently this must fit in an 'int' */
+#define MAX_CHUNK_SIZE (1<<30)
/*
* MD's 'extended' device
struct page *sb_page;
int sb_loaded;
+ __u64 sb_events;
sector_t data_offset; /* start of data in array */
sector_t sb_offset;
+ 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
* It can never have faulty==1, in_sync==1
* This reduces the burden of testing multiple flags in many cases
*/
- int faulty; /* if faulty do not issue IO requests */
- int in_sync; /* device is a full member of the array */
+
+ 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 BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */
int desc_nr; /* descriptor index in the superblock */
int raid_disk; /* role of device in array */
+ 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
+ */
+ sector_t recovery_offset;/* If this device has been partially
+ * recovered, this is where we were
+ * up to.
+ */
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.
+ */
+ atomic_t corrected_errors; /* number of corrected read errors,
+ * for reporting to userspace and storing
+ * in superblock.
+ */
};
-typedef struct mdk_personality_s mdk_personality_t;
-
struct mddev_s
{
void *private;
- mdk_personality_t *pers;
+ struct mdk_personality *pers;
dev_t unit;
int md_minor;
struct list_head disks;
- int sb_dirty;
+ 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 /* superblock update in progress */
+
int ro;
struct gendisk *gendisk;
+ struct kobject kobj;
+
/* Superblock information */
int major_version,
minor_version,
int chunk_size;
time_t ctime, utime;
int level, layout;
+ char clevel[16];
int raid_disks;
int max_disks;
sector_t size; /* used size of component devices */
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, new_chunk;
+
struct mdk_thread_s *thread; /* management thread */
struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */
- sector_t curr_resync; /* blocks scheduled */
+ sector_t curr_resync; /* last block scheduled */
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 */
+
+ sector_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;
+ sector_t suspend_hi;
+ /* if zero, use the system-wide default */
+ int sync_speed_min;
+ int sync_speed_max;
+
+ int ok_start_degraded;
/* recovery/resync flags
* NEEDED: we might need to start a resync/recover
* RUNNING: a thread is running, or about to be started
* ERR: and IO error was detected - abort the resync/recovery
* INTR: someone requested a (clean) early abort.
* DONE: thread is done and is waiting to be reaped
+ * REQUEST: user-space has requested a sync (used with SYNC)
+ * CHECK: user-space request for for check-only, no repair
+ * RESHAPE: A reshape is happening
+ *
+ * If neither SYNC or RESHAPE are set, then it is a recovery.
*/
#define MD_RECOVERY_RUNNING 0
#define MD_RECOVERY_SYNC 1
#define MD_RECOVERY_INTR 3
#define MD_RECOVERY_DONE 4
#define MD_RECOVERY_NEEDED 5
+#define MD_RECOVERY_REQUESTED 6
+#define MD_RECOVERY_CHECK 7
+#define MD_RECOVERY_RESHAPE 8
+#define MD_RECOVERY_FROZEN 9
+
unsigned long recovery;
int in_sync; /* know to not need resync */
- struct semaphore reconfig_sem;
+ struct mutex reconfig_mutex;
atomic_t active;
int changed; /* true if we might need to reread partition info */
int degraded; /* whether md should consider
* adding a spare
*/
+ int barriers_work; /* initialised to true, cleared as soon
+ * as a barrier request to slave
+ * fails. Only supported
+ */
+ struct bio *biolist; /* bios that need to be retried
+ * because BIO_RW_BARRIER is not supported
+ */
atomic_t recovery_active; /* blocks scheduled, but not written */
wait_queue_head_t recovery_wait;
sector_t recovery_cp;
+
+ spinlock_t write_lock;
+ wait_queue_head_t sb_wait; /* for waiting on superblock updates */
+ atomic_t pending_writes; /* number of active superblock writes */
+
unsigned int safemode; /* if set, update "clean" superblock
* when no writes pending.
*/
atomic_t writes_pending;
request_queue_t *queue; /* for plugging ... */
+ atomic_t write_behind; /* outstanding async IO */
+ unsigned int max_write_behind; /* 0 = sync */
+
+ struct bitmap *bitmap; /* the bitmap for the device */
+ struct file *bitmap_file; /* the bitmap file */
+ long bitmap_offset; /* offset from superblock of
+ * start of bitmap. May be
+ * negative, but not '0'
+ */
+ long default_bitmap_offset; /* this is the offset to use when
+ * hot-adding a bitmap. It should
+ * eventually be settable by sysfs.
+ */
+
struct list_head all_mddevs;
};
static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev)
{
- int faulty = rdev->faulty;
+ int faulty = test_bit(Faulty, &rdev->flags);
if (atomic_dec_and_test(&rdev->nr_pending) && faulty)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}
atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
}
-struct mdk_personality_s
+struct mdk_personality
{
char *name;
+ int level;
+ struct list_head list;
struct module *owner;
int (*make_request)(request_queue_t *q, struct bio *bio);
int (*run)(mddev_t *mddev);
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);
- int (*sync_request)(mddev_t *mddev, sector_t sector_nr, int go_faster);
+ sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
int (*resize) (mddev_t *mddev, sector_t sectors);
- int (*reshape) (mddev_t *mddev, int raid_disks);
+ int (*check_reshape) (mddev_t *mddev);
+ int (*start_reshape) (mddev_t *mddev);
int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
+ /* quiesce moves between quiescence states
+ * 0 - fully active
+ * 1 - no new requests allowed
+ * others - reserved
+ */
+ void (*quiesce) (mddev_t *mddev, int state);
+};
+
+
+struct md_sysfs_entry {
+ struct attribute attr;
+ ssize_t (*show)(mddev_t *, char *);
+ ssize_t (*store)(mddev_t *, const char *, size_t);
};
return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
}
-extern mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr);
-
/*
* iterates through some rdev ringlist. It's safe to remove the
* current 'rdev'. Dont touch 'tmp' though.
mddev_t *mddev;
wait_queue_head_t wqueue;
unsigned long flags;
- struct completion *event;
struct task_struct *tsk;
- const char *name;
+ unsigned long timeout;
} mdk_thread_t;
#define THREAD_WAKEUP 0
__wait_event_lock_irq(wq, condition, lock, cmd); \
} while (0)
+static inline void safe_put_page(struct page *p)
+{
+ if (p) put_page(p);
+}
+
+#endif /* CONFIG_BLOCK */
#endif