Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#ifndef _MD_K_H
-#define _MD_K_H
-
-#ifdef CONFIG_BLOCK
+#ifndef _MD_MD_H
+#define _MD_MD_H
+
+#include <linux/blkdev.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>
#define MaxSector (~(sector_t)0)
typedef struct mdk_rdev_s mdk_rdev_t;
/*
- * options passed in raidrun:
- */
-
-/* Currently this must fit in an 'int' */
-#define MAX_CHUNK_SIZE (1<<30)
-
-/*
* MD's 'extended' device
*/
struct mdk_rdev_s
{
struct list_head same_set; /* RAID devices within the same set */
- sector_t size; /* Device size (in blocks) */
+ sector_t sectors; /* Device size (in 512bytes sectors) */
mddev_t *mddev; /* RAID array if running */
int last_events; /* IO event timestamp */
atomic_t read_errors; /* number of consecutive read errors that
* we have tried to ignore.
*/
+ struct timespec 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.
#define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */
#define MD_CHANGE_PENDING 2 /* superblock update in progress */
+ int suspended;
+ atomic_t active_io;
int ro;
struct gendisk *gendisk;
int external; /* metadata is
* managed externally */
char metadata_type[17]; /* externally set*/
- int chunk_size;
+ int chunk_sectors;
time_t ctime, utime;
int level, layout;
char clevel[16];
int raid_disks;
int max_disks;
- sector_t size; /* used size of component devices */
+ sector_t dev_sectors; /* used size of
+ * component devices */
sector_t array_sectors; /* exported array size */
+ int external_size; /* size managed
+ * externally */
__u64 events;
char uuid[16];
* If reshape_position is MaxSector, then no reshape is happening (yet).
*/
sector_t reshape_position;
- int delta_disks, new_level, new_layout, new_chunk;
+ int delta_disks, new_level, new_layout;
+ int new_chunk_sectors;
struct mdk_thread_s *thread; /* management thread */
struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */
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 */
* INTR: resync needs to be aborted for some reason
* 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
+ * CHECK: user-space request for check-only, no repair
* RESHAPE: A reshape is happening
*
* If neither SYNC or RESHAPE are set, then it is a recovery.
* so we don't loop trying */
int in_sync; /* know to not need resync */
+ /* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so
+ * that we are never stopping an array while it is open.
+ * 'reconfig_mutex' protects all other reconfiguration.
+ * These locks are separate due to conflicting interactions
+ * with bdev->bd_mutex.
+ * Lock ordering is:
+ * reconfig_mutex -> bd_mutex : e.g. do_md_run -> revalidate_disk
+ * bd_mutex -> open_mutex: e.g. __blkdev_get -> md_open
+ */
+ struct mutex open_mutex;
struct mutex reconfig_mutex;
atomic_t active; /* general refcount */
atomic_t openers; /* number of active opens */
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 {
+ struct file *file; /* the bitmap file */
+ loff_t offset; /* offset from superblock of
+ * start of bitmap. May be
+ * negative, but not '0'
+ * For external metadata, offset
+ * from start of device.
+ */
+ loff_t default_offset; /* this is the offset to use when
+ * hot-adding a bitmap. It should
+ * eventually be settable by sysfs.
+ */
+ struct mutex mutex;
+ unsigned long chunksize;
+ unsigned long daemon_sleep; /* how many seconds between updates? */
+ unsigned long max_write_behind; /* write-behind mode */
+ int external;
+ } bitmap_info;
+
+ atomic_t max_corr_read_errors; /* max read retries */
struct list_head all_mddevs;
+
+ /* Generic barrier handling.
+ * If there is a pending barrier request, all other
+ * writes are blocked while the devices are flushed.
+ * The last to finish a flush schedules a worker to
+ * submit the barrier request (without the barrier flag),
+ * then submit more flush requests.
+ */
+ struct bio *barrier;
+ atomic_t flush_pending;
+ struct work_struct barrier_work;
};
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);
- int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
+ void (*finish_reshape) (mddev_t *mddev);
/* quiesce moves between quiescence states
* 0 - fully active
* 1 - no new requests allowed
* others - reserved
*/
void (*quiesce) (mddev_t *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.
+ * e.g. 2drive raid1 -> 2drive raid5
+ * ndrive raid5 -> degraded n+1drive raid6 with special layout
+ * If the takeover succeeds, a new 'private' structure is returned.
+ * This needs to be installed and then ->run used to activate the
+ * array.
+ */
+ void *(*takeover) (mddev_t *mddev);
};
ssize_t (*show)(mddev_t *, char *);
ssize_t (*store)(mddev_t *, const char *, size_t);
};
-
+extern struct attribute_group md_bitmap_group;
static inline char * mdname (mddev_t * mddev)
{
if (p) put_page(p);
}
-#endif /* CONFIG_BLOCK */
-#endif
-
-
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),
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_barrier_request(mddev_t *mddev, struct bio *bio);
extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
sector_t sector, int size, struct page *page);
extern void md_super_wait(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 int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
+extern void restore_bitmap_write_access(struct file *file);
+
+#endif /* _MD_MD_H */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff