path: root/drivers/md/md.h

/*
   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
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2, or (at your option)
   any later version.

   You should have received a copy of the GNU General Public License
   (for example /usr/src/linux/COPYING); if not, write to the Free
   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/

#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 "md-cluster.h"

#define MaxSector (~(sector_t)0)

/*
 * 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 */
	int 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 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 work_struct del_work;	/* used for delayed sysfs removal */

	struct kernfs_node *sysfs_state; /* handle for 'state'
					   * sysfs entry */

	struct badblocks 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
				 */
	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,
	RemoveSynchronized,	/* synchronize_rcu() was called after
				 * this device was known to be faulty,
				 * so it is safe to remove without
				 * another synchronize_rcu() call.
				 */
};

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)) {
		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;
}
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);
struct md_cluster_info;

struct mddev {
	void				*private;
	struct md_personality		*pers;
	dev_t				unit;
	int				md_minor;
	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.
				 */
#define MD_JOURNAL_CLEAN 5	/* A raid with journal is already clean */
#define MD_HAS_JOURNAL	6	/* The raid array has journal feature set */
#define MD_RELOAD_SB	7	/* Reload the superblock because another node
				 * updated it.
				 */
#define MD_CLUSTER_RESYNC_LOCKED 8 /* cluster raid only, which means node
				    * already took resync lock, need to
				    * release the lock */

	int				suspended;
	atomic_t			active_io;
	int				ro;
	int				sysfs_active; /* set when sysfs deletes
						       * are happening, so run/
						       * takeover/stop are not safe
						       */
	struct gendisk			*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 */
	__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		*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
	 * 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;
	sector_t			suspend_hi;
	/* if zero, use the system-wide default */
	int				sync_speed_min;
	int				sync_speed_max;

	/* resync even though the same disks are shared among md-devices */
	int				parallel_resync;

	int				ok_start_degraded;
<