path: root/drivers/md/md.h

/* 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 "md-cluster.h"

#define MaxSector (~(sector_t)0)

/*
 * 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)
/*
 * 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.
					   */

	/*
	 * The members for check collision of write behind IOs.
	 */
	struct list_head wb_list;
	spinlock_t wb_list_lock;
	wait_queue_head_t wb_io_wait;

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

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

	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,
	RemoveSynchronized,	/* synchronize_rcu() was called after
				 * this device was known to be faulty,
				 * so it is safe to remove without
				 * another synchronize_rcu() call.
				 */
	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
				 */
	WBCollisionCheck,	/*
				 * multiqueue device should check if there
				 * is collision between write behind bios.
				 */
};

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;

/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
enum mddev_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_ALLOW_SB_UPDATE,	/* md_check_recovery is allowed to update
				 * the metadata without taking reconfig_mutex.
				 */
	MD_UPDATING_SB,		/* md_check_recovery is updating the metadata
				 * without explicitly holding reconfig_mutex.
				 */
	MD_NOT_READY,		/* do_md_run() is active, so 'array_state'
				 * must not report that array is ready yet
				 */
	MD_BROKEN,              /* This is used in RAID-0/LINEAR only, to stop
				 * I/O in case an array member is gone/failed.
				 */
};

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_WB_INFOS	8
/* record current range of write behind IOs */
struct wb_info {
	sector_t lo;
	sector_t hi;
	struct list_head list;
};

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