drivers/md/md.c

/*
   md.c : Multiple Devices driver for Linux
	  Copyright (C) 1998, 1999, 2000 Ingo Molnar

     completely rewritten, based on the MD driver code from Marc Zyngier

   Changes:

   - RAID-1/RAID-5 extensions by Miguel de Icaza, Gadi Oxman, Ingo Molnar
   - RAID-6 extensions by H. Peter Anvin <hpa@zytor.com>
   - boot support for linear and striped mode by Harald Hoyer <HarryH@Royal.Net>
   - kerneld support by Boris Tobotras <boris@xtalk.msk.su>
   - kmod support by: Cyrus Durgin
   - RAID0 bugfixes: Mark Anthony Lisher <markal@iname.com>
   - Devfs support by Richard Gooch <rgooch@atnf.csiro.au>

   - lots of fixes and improvements to the RAID1/RAID5 and generic
     RAID code (such as request based resynchronization):

     Neil Brown <neilb@cse.unsw.edu.au>.

   - persistent bitmap code
     Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.

   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.
*/

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/linkage.h>
#include <linux/raid/md.h>
#include <linux/raid/bitmap.h>
#include <linux/sysctl.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
#include <linux/poll.h>
#include <linux/mutex.h>
#include <linux/ctype.h>
#include <linux/freezer.h>

#include <linux/init.h>

#include <linux/file.h>

#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif

#include <asm/unaligned.h>

#define MAJOR_NR MD_MAJOR
#define MD_DRIVER

/* 63 partitions with the alternate major number (mdp) */
#define MdpMinorShift 6

#define DEBUG 0
#define dprintk(x...) ((void)(DEBUG && printk(x)))


#ifndef MODULE
static void autostart_arrays (int part);
#endif

static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);

static void md_print_devices(void);

#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }

/*
 * Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
 * is 1000 KB/sec, so the extra system load does not show up that much.
 * Increase it if you want to have more _guaranteed_ speed. Note that
 * the RAID driver will use the maximum available bandwidth if the IO
 * subsystem is idle. There is also an 'absolute maximum' reconstruction
 * speed limit - in case reconstruction slows down your system despite
 * idle IO detection.
 *
 * you can change it via /proc/sys/dev/raid/speed_limit_min and _max.
 * or /sys/block/mdX/md/sync_speed_{min,max}
 */

static int sysctl_speed_limit_min = 1000;
static int sysctl_speed_limit_max = 200000;
static inline int speed_min(mddev_t *mddev)
{
	return mddev->sync_speed_min ?
		mddev->sync_speed_min : sysctl_speed_limit_min;
}

static inline int speed_max(mddev_t *mddev)
{
	return mddev->sync_speed_max ?
		mddev->sync_speed_max : sysctl_speed_limit_max;
}

static struct ctl_table_header *raid_table_header;

static ctl_table raid_table[] = {
	{
		.ctl_name	= DEV_RAID_SPEED_LIMIT_MIN,
		.procname	= "speed_limit_min",
		.data		= &sysctl_speed_limit_min,
		.maxlen		= sizeof(int),
		.mode		= S_IRUGO|S_IWUSR,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= DEV_RAID_SPEED_LIMIT_MAX,
		.procname	= "speed_limit_max",
		.data		= &sysctl_speed_limit_max,
		.maxlen		= sizeof(int),
		.mode		= S_IRUGO|S_IWUSR,
		.proc_handler	= &proc_dointvec,
	},
	{ .ctl_name = 0 }
};

static ctl_table raid_dir_table[] = {
	{
		.ctl_name	= DEV_RAID,
		.procname	= "raid",
		.maxlen		= 0,
		.mode		= S_IRUGO|S_IXUGO,
		.child		= raid_table,
	},
	{ .ctl_name = 0 }
};

static ctl_table raid_root_table[] = {
	{
		.ctl_name	= CTL_DEV,
		.procname	= "dev",
		.maxlen		= 0,
		.mode		= 0555,
		.child		= raid_dir_table,
	},
	{ .ctl_name = 0 }
};

static struct block_device_operations md_fops;

static int start_readonly;

/*
 * We have a system wide 'event count' that is incremented
 * on any 'interesting' event, and readers of /proc/mdstat
 * can use 'poll' or 'select' to find out when the event
 * count increases.
 *
 * Events are:
 *  start array, stop array, error, add device, remove device,
 *  start build, activate spare
 */
static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
static atomic_t md_event_count;
void md_new_event(mddev_t *mddev)
{
	atomic_inc(&md_event_count);
	wake_up(&md_event_waiters);
	sysfs_notify(&mddev->kobj, NULL, "sync_action");
}
EXPORT_SYMBOL_GPL(md_new_event);

/* Alternate version that can be called from interrupts
 * when calling sysfs_notify isn't needed.
 */
static void md_new_event_inintr(mddev_t *mddev)
{
	atomic_inc(&md_event_count);
	wake_up(&md_event_waiters);
}

/*
 * Enables to iterate over all existing md arrays
 * all_mddevs_lock protects this list.
 */
static LIST_HEAD(all_mddevs);
static DEFINE_SPINLOCK(all_mddevs_lock);


/*
 * iterates through all used mddevs in the system.
 * We take care to grab the all_mddevs_lock whenever navigating
 * the list, and to always hold a refcount when unlocked.
 * Any code which breaks out of this loop while own
 * a reference to the current mddev and must mddev_put it.
 */
#define ITERATE_MDDEV(mddev,tmp)					\
									\
	for (({ spin_lock(&all_mddevs_lock); 				\
		tmp = all_mddevs.next;					\
		mddev = NULL;});					\
	     ({ if (tmp != &all_mddevs)					\
			mddev_get(list_entry(tmp, mddev_t, all_mddevs));\
		spin_unlock(&all_mddevs_lock);				\
		if (mddev) mddev_put(mddev);				\
		mddev = list_entry(tmp, mddev_t, all_mddevs);		\
		tmp != &all_mddevs;});					\
	     ({ spin_lock(&all_mddevs_lock);				\
		tmp = tmp->next;})					\
		)


static int md_fail_request (struct request_queue *q, struct bio *bio)
{
	bio_io_error(bio);
	return 0;
}

static inline mddev_t *mddev_get(mddev_t *mddev)
{
	atomic_inc(&mddev->active);
	return mddev;
}

static void mddev_put(mddev_t *mddev)
{
	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
		return;
	if (!mddev->raid_disks && list_empty(&mddev->disks)) {
		list_del(&mddev->all_mddevs);
		spin_unlock(&all_mddevs_lock);
		blk_cleanup_queue(mddev->queue);
		kobject_unregister(&mddev->kobj);
	} else
		spin_unlock(&all_mddevs_lock);
}

static mddev_t * mddev_find(dev_t unit)
{
	mddev_t *mddev, *new = NULL;

 retry:
	spin_lock(&all_mddevs_lock);
	list_for_each_entry(mddev, &all_mddevs, all_mddevs)
		if (mddev->unit == unit) {
			mddev_get(mddev);
			spin_unlock(&all_mddevs_lock);
			kfree(new);
			return mddev;
		}

	if (new) {
		list_add(&new->all_mddevs, &all_mddevs);
		spin_unlock(&all_mddevs_lock);
		return new;
	}
	spin_unlock(&all_mddevs_lock);

	new = kzalloc(sizeof(*new), GFP_KERNEL);
	if (!new)
		return NULL;

	new->unit = unit;
	if (MAJOR(unit) == MD_MAJOR)
		new->md_minor = MINOR(unit);
	else
		new->md_minor = MINOR(unit) >> MdpMinorShift;

	mutex_init(&new->reconfig_mutex);
	INIT_LIST_HEAD(&new->disks);
	INIT_LIST_HEAD(&new->all_mddevs);
	init_timer(&new->safemode_timer);
	atomic_set(&new->active, 1);
	spin_lock_init(&new->write_lock);
	init_waitqueue_head(&new->sb_wait);
	new->reshape_position = MaxSector;

	new->queue = blk_alloc_queue(GFP_KERNEL);
	if (!new->queue) {
		kfree(new);
		return NULL;
	}
	set_bit(QUEUE_FLAG_CLUSTER, &new->queue->queue_flags);

	blk_queue_make_request(new->queue, md_fail_request);

	goto retry;
}

static inline int mddev_lock(mddev_t * mddev)
{
	return mutex_lock_interruptible(&mddev->reconfig_mutex);
}

static inline int mddev_trylock(mddev_t * mddev)
{
	return mutex_trylock(&mddev->reconfig_mutex);
}

static inline void mddev_unlock(mddev_t * mddev)
{
	mutex_unlock(&mddev->reconfig_mutex);

	md_wakeup_thread(mddev->thread);
}

static mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr)
{
	mdk_rdev_t * rdev;
	struct list_head *tmp;

	ITERATE_RDEV(mddev,rdev,tmp) {
		if (rdev->desc_nr == nr)
			return rdev;
	}
	return NULL;
}

static mdk_rdev_t * find_rdev(mddev_t * mddev, dev_t dev)
{
	struct list_head *tmp;
	mdk_rdev_t *rdev;

	ITERATE_RDEV(mddev,rdev,tmp) {
		if (rdev->bdev->bd_dev == dev)
			return rdev;
	}
	return NULL;
}

static struct mdk_personality *find_pers(int level, char *clevel)
{
	struct mdk_personality *pers;
	list_for_each_entry(pers, &pers_list, list) {
		if (level != LEVEL_NONE && pers->level == level)
			return pers;
		if (strcmp(pers->name, clevel)==0)
			return pers;
	}
	return NULL;
}

static inline sector_t calc_dev_sboffset(struct block_device *bdev)
{
	sector_t size = bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
	return MD_NEW_SIZE_BLOCKS(size);
}

static sector_t calc_dev_size(mdk_rdev_t *rdev, unsigned chunk_size)
{
	sector_t size;

	size = rdev->sb_offset;

	if (chunk_size)
		size &= ~((sector_t)chunk_size/1024 - 1);
	return size;
}

static int alloc_disk_sb(mdk_rdev_t * rdev)
{
	if (rdev->sb_page)
		MD_BUG();

	rdev->sb_page = alloc_page(GFP_KERNEL);
	if (!rdev->sb_page) {
		printk(KERN_ALERT "md: out of memory.\n");
		return -EINVAL;
	}

	return 0;
}

static void free_disk_sb(mdk_rdev_t * rdev)
{
	if (rdev->sb_page) {
		put_page(rdev->sb_page);
		rdev->sb_loaded = 0;
		rdev->sb_page = NULL;
		rdev->sb_offset = 0;
		rdev->size = 0;
	}
}


static void super_written(struct bio *bio, int error)
{
	mdk_rdev_t *rdev = bio->bi_private;
	mddev_t *mddev = rdev->mddev;

	if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
		printk("md: super_written gets error=%d, uptodate=%d\n",
		       error, test_bit(BIO_UPTODATE, &bio->bi_flags));
		WARN_ON(test_bit(BIO_UPTODATE, &bio->bi_flags));
		md_error(mddev, rdev);
	}

	if (atomic_dec_and_test(&mddev->pending_writes))
		wake_up(&mddev->sb_wait);
	bio_put(bio);
}

static void super_written_barrier(struct bio *bio, int error)
{
	struct bio *bio2 = bio->bi_private;
	mdk_rdev_t *rdev = bio2->bi_private;
	mddev_t *mddev = rdev->mddev;

	if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
	    error == -EOPNOTSUPP) {
		unsigned long flags;
		/* barriers don't appear to be supported :-( */
		set_bit(BarriersNotsupp, &rdev->flags);
		mddev->barriers_work = 0;
		spin_lock_irqsave(&mddev->write_lock, flags);
		bio2->bi_next = mddev->biolist;
		mddev->biolist = bio2;
		spin_unlock_irqrestore(&mddev->write_lock, flags);
		wake_up(&mddev->sb_wait);
		bio_put(bio);
	} else {
		bio_put(bio2);
		bio->bi_private = rdev;
		super_written(bio, error);
	}
}

void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
		   sector_t sector, int size, struct page *page)
{
	/* write first size bytes of page to sector of rdev
	 * Increment mddev->pending_writes before returning
	 * and decrement it on completion, waking up sb_wait
	 * if zero is reached.
	 * If an error occurred, call md_error
	 *
	 * As we might need to resubmit the request if BIO_RW_BARRIER
	 * causes ENOTSUPP, we allocate a spare bio...
	 */
	struct bio *bio = bio_alloc(GFP_NOIO, 1);
	int rw = (1<<BIO_RW) | (1<<BIO_RW_SYNC);

	bio->bi_bdev = rdev->bdev;
	bio->bi_sector = sector;
	bio_add_page(bio, page, size, 0);
	bio->bi_private = rdev;
	bio->bi_end_io = super_written;
	bio->bi_rw = rw;

	atomic_inc(&mddev->pending_writes);
	if (!test_bit(BarriersNotsupp, &rdev->flags)) {
		struct bio *rbio;
		rw |= (1<<BIO_RW_BARRIER);
		rbio = bio_clone(bio, GFP_NOIO);
		rbio->bi_private = bio;
		rbio->bi_end_io = super_written_barrier;
		submit_bio(rw, rbio);
	} else
		submit_bio(rw, bio);
}

void md_super_wait(mddev_t *mddev)
{
	/* wait for all superblock writes that were scheduled to complete.
	 * if any had to be retried (due to BARRIER problems), retry them
	 */
	DEFINE_WAIT(wq);
	for(;;) {
		prepare_to_wait(&mddev->sb_wait, &wq, TASK_UNINTERRUPTIBLE);
		if (atomic_read(&mddev->pending_writes)==0)
			break;
		while (mddev->biolist) {
			struct bio *bio;
			spin_lock_irq(&mddev->write_lock);
			bio = mddev->biolist;
			mddev->biolist = bio->bi_next ;
			bio->bi_next = NULL;
			spin_unlock_irq(&mddev->write_lock);
			submit_bio(bio->bi_rw, bio);
		}
		schedule();
	}
	finish_wait(&mddev->sb_wait, &wq);
}

static void bi_complete(struct bio *bio, int error)
{
	complete((struct completion*)bio->bi_private);
}

int sync_page_io(struct block_device *bdev, sector_t sector, int size,
		   struct page *page, int rw)
{
	struct bio *bio = bio_alloc(GFP_NOIO, 1);
	struct completion event;
	int ret;

	rw |= (1 << BIO_RW_SYNC);

	bio->bi_bdev = bdev;
	bio->bi_sector = sector;
	bio_add_page(bio, page, size, 0);
	init_completion(&event);
	bio->bi_private = &event;
	bio->bi_end_io = bi_complete;
	submit_bio(rw, bio);
	wait_for_completion(&event);

	ret = test_bit(BIO_UPTODATE, &bio->bi_flags);
	bio_put(bio);
	return ret;
}
EXPORT_SYMBOL_GPL(sync_page_io);

static int read_disk_sb(mdk_rdev_t * rdev, int size)
{
	char b[BDEVNAME_SIZE];
	if (!rdev->sb_page) {
		MD_BUG();
		return -EINVAL;
	}
	if (rdev->sb_loaded)
		return 0;


	if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, size, rdev->sb_page, READ))
		goto fail;
	rdev->sb_loaded = 1;
	return 0;

fail:
	printk(KERN_WARNING "md: disabled device %s, could not read superblock.\n",
		bdevname(rdev->bdev,b));
	return -EINVAL;
}

static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
{
	if (	(sb1->set_uuid0 == sb2->set_uuid0) &&
		(sb1->set_uuid1 == sb2->set_uuid1) &&
		(sb1->set_uuid2 == sb2->set_uuid2) &&
		(sb1->set_uuid3 == sb2->set_uuid3))

		return 1;

	return 0;
}


static int sb_equal(mdp_super_t *sb1, mdp_super_t *sb2)
{
	int ret;
	mdp_super_t *tmp1, *tmp2;

	tmp1 = kmalloc(sizeof(*tmp1),GFP_KERNEL);
	tmp2 = kmalloc(sizeof(*tmp2),GFP_KERNEL);

	if (!tmp1 || !tmp2) {
		ret = 0;
		printk(KERN_INFO "md.c: sb1 is not equal to sb2!\n");
		goto abort;
	}

	*tmp1 = *sb1;
	*tmp2 = *sb2;

	/*
	 * nr_disks is not constant
	 */
	tmp1->nr_disks = 0;
	tmp2->nr_disks = 0;

	if (memcmp(tmp1, tmp2, MD_SB_GENERIC_CONSTANT_WORDS * 4))
		ret = 0;
	else
		ret = 1;

abort:
	kfree(tmp1);
	kfree(tmp2);
	return ret;
}


static u32 md_csum_fold(u32 csum)
{
	csum = (csum & 0xffff) + (csum >> 16);
	return (csum & 0xffff) + (csum >> 16);
}

static unsigned int calc_sb_csum(mdp_super_t * sb)
{
	u64 newcsum = 0;
	u32 *sb32 = (u32*)sb;
	int i;
	unsigned int disk_csum, csum;

	disk_csum = sb->sb_csum;
	sb->sb_csum = 0;

	for (i = 0; i < MD_SB_BYTES/4 ; i++)
		newcsum += sb32[i];
	csum = (newcsum & 0xffffffff) + (newcsum>>32);


#ifdef CONFIG_ALPHA
	/* This used to use csum_partial, which was wrong for several
	 * reasons including that different results are returned on
	 * different architectures.  It isn't critical that we get exactly
	 * the same return value as before (we always csum_fold before
	 * testing, and that removes any differences).  However as we
	 * know that csum_partial always returned a 16bit value on
	 * alphas, do a fold to maximise conformity to previous behaviour.
	 */
	sb->sb_csum = md_csum_fold(disk_csum);
#else
	sb->sb_csum = disk_csum;
#endif
	return csum;
}


/*
 * Handle superblock details.
 * We want to be able to handle multiple superblock formats
 * so we have a common interface to them all, and an array of
 * different handlers.
 * We rely on user-space to write the initial superblock, and support
 * reading and updating of superblocks.
 * Interface methods are:
 *   int load_super(mdk_rdev_t *dev, mdk_rdev_t *refdev, int minor_version)
 *      loads and validates a superblock on dev.
 *      if refdev != NULL, compare superblocks on both devices
 *    Return:
 *      0 - dev has a superblock that is compatible with refdev
 *      1 - dev has a superblock that is compatible and newer than refdev
 *          so dev should be used as the refdev in future
 *     -EINVAL superblock incompatible or invalid
 *     -othererror e.g. -EIO
 *
 *   int validate_super(mddev_t *mddev, mdk_rdev_t *dev)
 *      Verify that dev is acceptable into mddev.
 *       The first time, mddev->raid_disks will be 0, and data from
 *       dev should be merged in.  Subsequent calls check that dev
 *       is new enough.  Return 0 or -EINVAL
 *
 *   void sync_super(mddev_t *mddev, mdk_rdev_t *dev)
 *     Update the superblock for rdev with data in mddev
 *     This does not write to disc.
 *
 */

struct super_type  {
	char 		*name;
	struct module	*owner;
	int		(*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version);
	int		(*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev);
	void		(*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev);
};

/*
 * load_super for 0.90.0 
 */
static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
{
	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
	mdp_super_t *sb;
	int ret;
	sector_t sb_offset;

	/*
	 * Calculate the position of the superblock,
	 * it's at the end of the disk.
	 *
	 * It also happens to be a multiple of 4Kb.
	 */
	sb_offset = calc_dev_sboffset(rdev->bdev);
	rdev->sb_offset = sb_offset;

	ret = read_disk_sb(rdev, MD_SB_BYTES);
	if (ret) return ret;

	ret = -EINVAL;

	bdevname(rdev->bdev, b);
	sb = (mdp_super_t*)page_address(rdev->sb_page);

	if (sb->md_magic != MD_SB_MAGIC) {
		printk(KERN_ERR "md: invalid raid superblock magic on %s\n",
		       b);
		goto abort;
	}

	if (sb->major_version != 0 ||
	    sb->minor_version < 90 ||
	    sb->minor_version > 91) {
		printk(KERN_WARNING "Bad version number %d.%d on %s\n",
			sb->major_version, sb->minor_version,
			b);
		goto abort;
	}

	if (sb->raid_disks <= 0)
		goto abort;

	if (md_csum_fold(calc_sb_csum(sb)) != md_csum_fold(sb->sb_csum)) {
		printk(KERN_WARNING "md: invalid superblock checksum on %s\n",
			b);
		goto abort;
	}

	rdev->preferred_minor = sb->md_minor;
	rdev->data_offset = 0;
	rdev->sb_size = MD_SB_BYTES;

	if (sb->state & (1<<MD_SB_BITMAP_PRESENT)) {
		if (sb->level != 1 && sb->level != 4
		    && sb->level != 5 && sb->level != 6
		    && sb->level != 10) {
			/* FIXME use a better test */
			printk(KERN_WARNING
			       "md: bitmaps not supported for this level.\n");
			goto abort;
		}
	}

	if (sb->level == LEVEL_MULTIPATH)
		rdev->desc_nr = -1;
	else
		rdev->desc_nr = sb->this_disk.number;

	if (refdev == 0)
		ret = 1;
	else {
		__u64 ev1, ev2;
		mdp_super_t *refsb = (mdp_super_t*)page_address(refdev->sb_page);
		if (!uuid_equal(refsb, sb)) {
			printk(KERN_WARNING "md: %s has different UUID to %s\n",
				b, bdevname(refdev->bdev,b2));
			goto abort;
		}
		if (!sb_equal(refsb, sb)) {
			printk(KERN_WARNING "md: %s has same UUID"
			       " but different superblock to %s\n",
			       b, bdevname(refdev->bdev, b2));
			goto abort;
		}
		ev1 = md_event(sb);
		ev2 = md_event(refsb);
		if (ev1 > ev2)
			ret = 1;
		else 
			ret = 0;
	}
	rdev->size = calc_dev_size(rdev, sb->chunk_size);

	if (rdev->size < sb->size && sb->level > 1)
		/* "this cannot possibly happen" ... */
		ret = -EINVAL;

 abort:
	return ret;
}

/*
 * validate_super for 0.90.0
 */
static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
{
	mdp_disk_t *desc;
	mdp_super_t *sb = (mdp_super_t *)page_address(rdev->sb_page);
	__u64 ev1 = md_event(sb);

	rdev->raid_disk = -1;
	rdev->flags = 0;
	if (mddev->raid_disks == 0) {
		mddev->major_version = 0;
		mddev->minor_version = sb->minor_version;
		mddev->patch_version = sb->patch_version;
		mddev->persistent = ! sb->not_persistent;
		mddev->chunk_size = sb->chunk_size;
		mddev->ctime = sb->ctime;
		mddev->utime = sb->utime;
		mddev->level = sb->level;
		mddev->clevel[0] = 0;
		mddev->layout = sb->layout;
		mddev->raid_disks = sb->raid_disks;
		mddev->size = sb->size;
		mddev->events = ev1;
		mddev->bitmap_offset = 0;
		mddev->default_bitmap_offset = MD_SB_BYTES >> 9;

		if (mddev->minor_version >= 91) {
			mddev->reshape_position = sb->reshape_position;
			mddev->delta_disks = sb->delta_disks;
			mddev->new_level = sb->new_level;
			mddev->new_layout = sb->new_layout;
			mddev->new_chunk = sb->new_chunk;
		} else {
			mddev->reshape_position = MaxSector;
			mddev->delta_disks = 0;
			mddev->new_level = mddev->level;
			mddev->new_layout = mddev->layout;
			mddev->new_chunk = mddev->chunk_size;
		}

		if (sb->state & (1<<MD_SB_CLEAN))
			mddev->recovery_cp = MaxSector;
		else {
			if (sb->events_hi == sb->cp_events_hi && 
				sb->events_lo == sb->cp_events_lo) {
				mddev->recovery_cp = sb->recovery_cp;
			} else
				mddev->recovery_cp = 0;
		}

		memcpy(mddev->uuid+0, &sb->set_uuid0, 4);
		memcpy(mddev->uuid+4, &sb->set_uuid1, 4);
		memcpy(mddev->uuid+8, &sb->set_uuid2, 4);
		memcpy(mddev->uuid+12,&sb->set_uuid3, 4);

		mddev->max_disks = MD_SB_DISKS;

		if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
		    mddev->bitmap_file == NULL)
			mddev->bitmap_offset = mddev->default_bitmap_offset;

	} else if (mddev->pers == NULL) {
		/* Insist on good event counter while assembling */
		++ev1;
		if (ev1 < mddev->events) 
			return -EINVAL;
	} else if (mddev->bitmap) {
		/* if adding to array with a bitmap, then we can accept an
		 * older device ... but not too old.
		 */
		if (ev1 < mddev->bitmap->events_cleared)
			return 0;
	} else {
		if (ev1 < mddev->events)
			/* just a hot-add of a new device, leave raid_disk at -1 */
			return 0;
	}

	if (mddev->level != LEVEL_MULTIPATH) {
		desc = sb->disks + rdev->desc_nr;

		if (desc->state & (1<<MD_DISK_FAULTY))
			set_bit(Faulty, &rdev->flags);
		else if (desc->state & (1<<MD_DISK_SYNC) /* &&
			    desc->raid_disk < mddev->raid_disks */) {
			set_bit(In_sync, &rdev->flags);
			rdev->raid_disk = desc->raid_disk;
		}
		if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
			set_bit(WriteMostly, &rdev->flags);
	} else /* MULTIPATH are always insync */
		set_bit(In_sync, &rdev->flags);
	return 0;
}

/*
 * sync_super for 0.90.0
 */
static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
{
	mdp_super_t *sb;
	struct list_head *tmp;
	mdk_rdev_t *rdev2;
	int next_spare = mddev->raid_disks;


	/* make rdev->sb match mddev data..
	 *
	 * 1/ zero out disks
	 * 2/ Add info for each disk, keeping track of highest desc_nr (next_spare);
	 * 3/ any empty disks < next_spare become removed
	 *
	 * disks[0] gets initialised to REMOVED because
	 * we cannot be sure from other fields if it has
	 * been initialised or not.
	 */
	int i;
	int active=0, working=0,failed=0,spare=0,nr_disks=0;

	rdev->sb_size = MD_SB_BYTES;

	sb = (mdp_super_t*)page_address(rdev->sb_page);

	memset(sb, 0, sizeof(*sb));

	sb->md_magic = MD_SB_MAGIC;
	sb->major_version = mddev->major_version;
	sb->patch_version = mddev->patch_version;
	sb->gvalid_words  = 0; /* ignored */
	memcpy(&sb->set_uuid0, mddev->uuid+0, 4);
	memcpy(&sb->set_uuid1, mddev->uuid+4, 4);
	memcpy(&sb->set_uuid2, mddev->uuid+8, 4);
	memcpy(&sb->set_uuid3, mddev->uuid+12,4);

	sb->ctime = mddev->ctime;
	sb->level = mddev->level;
	sb->size  = mddev->size;
	sb->raid_disks = mddev->raid_disks;
	sb->md_minor = mddev->md_minor;
	sb->not_persistent = !mddev->persistent;
	sb->utime = mddev->utime;
	sb->state = 0;
	sb->events_hi = (mddev->events>>32);
	sb->events_lo = (u32)mddev->events;

	if (mddev->reshape_position == MaxSector)
		sb->minor_version = 90;
	else {
		sb->minor_version = 91;
		sb->reshape_position = mddev->reshape_position;
		sb->new_level = mddev->new_level;
		sb->delta_disks = mddev->delta_disks;
		sb->new_layout = mddev->new_layout;
		sb->new_chunk = mddev->new_chunk;
	}
	mddev->minor_version = sb->minor_version;
	if (mddev->in_sync)
	{
		sb->recovery_cp = mddev->recovery_cp;
		sb->cp_events_hi = (mddev->events>>32);
		sb->cp_events_lo = (u32)mddev->events;
		if (mddev->recovery_cp == MaxSector)
			sb->state = (1<< MD_SB_CLEAN);
	} else
		sb->recovery_cp = 0;

	sb->layout = mddev->layout;
	sb->chunk_size = mddev->chunk_size;

	if (mddev->bitmap && mddev->bitmap_file == NULL)
		sb->state |= (1<<MD_SB_BITMAP_PRESENT);

	sb->disks[0].state = (1<<MD_DISK_REMOVED);
	ITERATE_RDEV(mddev,rdev2,tmp) {
		mdp_disk_t *d;
		int desc_nr;
		if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
		    && !test_bit(Faulty, &rdev2->flags))
			desc_nr = rdev2->raid_disk;
		else
			desc_nr = next_spare++;
		rdev2->desc_nr = desc_nr;
		d = &sb->disks[rdev2->desc_nr];
		nr_disks++;
		d->number = rdev2->desc_nr;
		d->major = MAJOR(rdev2->bdev->bd_dev);
		d->minor = MINOR(rdev2->bdev->bd_dev);
		if (rdev2->raid_disk >= 0 && test_bit(In_sync, &rdev2->flags)
		    && !test_bit(Faulty, &rdev2->flags))
			d->raid_disk = rdev2->raid_disk;
		else
			d->raid_disk = rdev2->desc_nr; /* compatibility */
		if (test_bit(Faulty, &rdev2->flags))
			d->state = (1<<MD_DISK_FAULTY);
		else if (test_bit(In_sync, &rdev2->flags)) {
			d->state = (1<<MD_DISK_ACTIVE);
			d->state |= (1<<MD_DISK_SYNC);
			active++;
			working++;
		} else {
			d->state = 0;
			spare++;
			working++;
		}
		if (test_bit(WriteMostly, &rdev2->flags))
			d->state |= (1<<MD_DISK_WRITEMOSTLY);
	}
	/* now set the "removed" and "faulty" bits on any missing devices */
	for (i=0 ; i < mddev->raid_disks ; i++) {
		mdp_disk_t *d = &sb->disks[i];
		if (d->state == 0 && d->number == 0) {
			d->number = i;
			d->raid_disk = i;
			d->state = (1<<MD_DISK_REMOVED);
			d->state |= (1<<MD_DISK_FAULTY);
			failed++;
		}
	}
	sb->nr_disks = nr_disks;
	sb->active_disks = active;
	sb->working_disks = working;
	sb->failed_disks = failed;
	sb->spare_disks = spare;

	sb->this_disk = sb->disks[rdev->desc_nr];
	sb->sb_csum = calc_sb_csum(sb);
}

/*
 * version 1 superblock
 */

static __le32 calc_sb_1_csum(struct mdp_superblock_1 * sb)
{
	__le32 disk_csum;
	u32 csum;
	unsigned long long newcsum;
	int size = 256 + le32_to_cpu(sb->max_dev)*2;
	__le32 *isuper = (__le32*)sb;
	int i;

	disk_csum = sb->sb_csum;
	sb->sb_csum = 0;
	newcsum = 0;
	for (i=0; size>=4; size -= 4 )
		newcsum += le32_to_cpu(*isuper++);

	if (size == 2)
		newcsum += le16_to_cpu(*(__le16*) isuper);

	csum = (newcsum & 0xffffffff) + (newcsum >> 32);
	sb->sb_csum = disk_csum;
	return cpu_to_le32(csum);
}

static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
{
	struct mdp_superblock_1 *sb;
	int ret;
	sector_t sb_offset;
	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
	int bmask;

	/*
	 * Calculate the position of the superblock.
	 * It is always aligned to a 4K boundary and
	 * depeding on minor_version, it can be:
	 * 0: At least 8K, but less than 12K, from end of device
	 * 1: At start of device
	 * 2: 4K from start of device.
	 */
	switch(minor_version) {
	case 0:
		sb_offset = rdev->bdev->bd_inode->i_size >> 9;
		sb_offset -= 8*2;
		sb_offset &= ~(sector_t)(4*2-1);
		/* convert from sectors to K */
		sb_offset /= 2;
		break;
	case 1:
		sb_offset = 0;
		break;
	case 2:
		sb_offset = 4;
		break;
	default:
		return -EINVAL;
	}
	rdev->sb_offset = sb_offset;

	/* superblock is rarely larger than 1K, but it can be larger,
	 * and it is safe to read 4k, so we do that
	 */
	ret = read_disk_sb(rdev, 4096);
	if (ret) return ret;


	sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);

	if (sb->magic != cpu_to_le32(MD_SB_MAGIC) ||
	    sb->major_version != cpu_to_le32(1) ||
	    le32_to_cpu(sb->max_dev) > (4096-256)/2 ||
	    le64_to_cpu(sb->super_offset) != (rdev->sb_offset<<1) ||
	    (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
		return -EINVAL;

	if (calc_sb_1_csum(sb) != sb->sb_csum) {
		printk("md: invalid superblock checksum on %s\n",
			bdevname(rdev->bdev,b));
		return -EINVAL;
	}
	if (le64_to_cpu(sb->data_size) < 10) {
		printk("md: data_size too small on %s\n",
		       bdevname(rdev->bdev,b));
		return -EINVAL;
	}
	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)) {
		if (sb->level != cpu_to_le32(1) &&
		    sb->level != cpu_to_le32(4) &&
		    sb->level != cpu_to_le32(5) &&
		    sb->level != cpu_to_le32(6) &&
		    sb->level != cpu_to_le32(10)) {
			printk(KERN_WARNING
			       "md: bitmaps not supported for this level.\n");
			return -EINVAL;
		}
	}

	rdev->preferred_minor = 0xffff;
	rdev->data_offset = le64_to_cpu(sb->data_offset);
	atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));

	rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
	bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
	if (rdev->sb_size & bmask)
		rdev-> sb_size = (rdev->sb_size | bmask)+1;

	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
		rdev->desc_nr = -1;
	else
		rdev->desc_nr = le32_to_cpu(sb->dev_number);

	if (refdev == 0)
		ret = 1;
	else {
		__u64 ev1, ev2;
		struct mdp_superblock_1 *refsb = 
			(struct mdp_superblock_1*)page_address(refdev->sb_page);

		if (memcmp(sb->set_uuid, refsb->set_uuid, 16) != 0 ||
		    sb->level != refsb->level ||
		    sb->layout != refsb->layout ||
		    sb->chunksize != refsb->chunksize) {
			printk(KERN_WARNING "md: %s has strangely different"
				" superblock to %s\n",
				bdevname(rdev->bdev,b),
				bdevname(refdev->bdev,b2));
			return -EINVAL;
		}
		ev1 = le64_to_cpu(sb->events);
		ev2 = le64_to_cpu(refsb->events);

		if (ev1 > ev2)
			ret = 1;
		else
			ret = 0;
	}
	if (minor_version) 
		rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
	else
		rdev->size = rdev->sb_offset;
	if (rdev->size < le64_to_cpu(sb->data_size)/2)
		return -EINVAL;
	rdev->size = le64_to_cpu(sb->data_size)/2;
	if (le32_to_cpu(sb->chunksize))
		rdev->size &= ~((sector_t)le32_to_cpu(sb->chunksize)/2 - 1);

	if (le64_to_cpu(sb->size) > rdev->size*2)
		return -EINVAL;
	return ret;
}

static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
{
	struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
	__u64 ev1 = le64_to_cpu(sb->events);

	rdev->raid_disk = -1;
	rdev->flags = 0;
	if (mddev->raid_disks == 0) {
		mddev->major_version = 1;
		mddev->patch_version = 0;
		mddev->persistent = 1;
		mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9;
		mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1);
		mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1);
		mddev->level = le32_to_cpu(sb->level);
		mddev->clevel[0] = 0;
		mddev->layout = le32_to_cpu(sb->layout);
		mddev->raid_disks = le32_to_cpu(sb->raid_disks);
		mddev->size = le64_to_cpu(sb->size)/2;
		mddev->events = ev1;
		mddev->bitmap_offset = 0;
		mddev->default_bitmap_offset = 1024 >> 9;
		
		mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
		memcpy(mddev->uuid, sb->set_uuid, 16);

		mddev->max_disks =  (4096-256)/2;

		if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
		    mddev->bitmap_file == NULL )
			mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);

		if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
			mddev->reshape_position = le64_to_cpu(sb->reshape_position);
			mddev->delta_disks = le32_to_cpu(sb->delta_disks);
			mddev->new_level = le32_to_cpu(sb->new_level);
			mddev->new_layout = le32_to_cpu(sb->new_layout);
			mddev->new_chunk = le32_to_cpu(sb->new_chunk)<<9;
		} else {
			mddev->reshape_position = MaxSector;
			mddev->delta_disks = 0;
			mddev->new_level = mddev->level;
			mddev->new_layout = mddev->layout;
			mddev->new_chunk = mddev->chunk_size;
		}

	} else if (mddev->pers == NULL) {
		/* Insist of good event counter while assembling */
		++ev1;
		if (ev1 < mddev->events)
			return -EINVAL;
	} else if (mddev->bitmap) {
		/* If adding to array with a bitmap, then we can accept an
		 * older device, but not too old.
		 */
		if (ev1 < mddev->bitmap->events_cleared)
			return 0;
	} else {
		if (ev1 < mddev->events)
			/* just a hot-add of a new device, leave raid_disk at -1 */
			return 0;
	}
	if (mddev->level != LEVEL_MULTIPATH) {
		int role;
		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
		switch(role) {
		case 0xffff: /* spare */
			break;
		case 0xfffe: /* faulty */
			set_bit(Faulty, &rdev->flags);
			break;
		default:
			if ((le32_to_cpu(sb->feature_map) &
			     MD_FEATURE_RECOVERY_OFFSET))
				rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
			else
				set_bit(In_sync, &rdev->flags);
			rdev->raid_disk = role;
			break;
		}
		if (sb->devflags & WriteMostly1)
			set_bit(WriteMostly, &rdev->flags);
	} else /* MULTIPATH are always insync */
		set_bit(In_sync, &rdev->flags);

	return 0;
}

static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
{
	struct mdp_superblock_1 *sb;
	struct list_head *tmp;
	mdk_rdev_t *rdev2;
	int max_dev, i;
	/* make rdev->sb match mddev and rdev data. */

	sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);

	sb->feature_map = 0;
	sb->pad0 = 0;
	sb->recovery_offset = cpu_to_le64(0);
	memset(sb->pad1, 0, sizeof(sb->pad1));
	memset(sb->pad2, 0, sizeof(sb->pad2));
	memset(sb->pad3, 0, sizeof(sb->pad3));

	sb->utime = cpu_to_le64((__u64)mddev->utime);
	sb->events = cpu_to_le64(mddev->events);
	if (mddev->in_sync)
		sb->resync_offset = cpu_to_le64(mddev->recovery_cp);
	else
		sb->resync_offset = cpu_to_le64(0);

	sb->cnt_corrected_read = cpu_to_le32(atomic_read(&rdev->corrected_errors));

	sb->raid_disks = cpu_to_le32(mddev->raid_disks);
	sb->size = cpu_to_le64(mddev->size<<1);

	if (mddev->bitmap && mddev->bitmap_file == NULL) {
		sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
		sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
	}

	if (rdev->raid_disk >= 0 &&
	    !test_bit(In_sync, &rdev->flags) &&
	    rdev->recovery_offset > 0) {
		sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
		sb->recovery_offset = cpu_to_le64(rdev->recovery_offset);
	}

	if (mddev->reshape_position != MaxSector) {
		sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
		sb->reshape_position = cpu_to_le64(mddev->reshape_position);
		sb->new_layout = cpu_to_le32(mddev->new_layout);
		sb->delta_disks = cpu_to_le32(mddev->delta_disks);
		sb->new_level = cpu_to_le32(mddev->new_level);
		sb->new_chunk = cpu_to_le32(mddev->new_chunk>>9);
	}

	max_dev = 0;
	ITERATE_RDEV(mddev,rdev2,tmp)
		if (rdev2->desc_nr+1 > max_dev)
			max_dev = rdev2->desc_nr+1;

	if (max_dev > le32_to_cpu(sb->max_dev))
		sb->max_dev = cpu_to_le32(max_dev);
	for (i=0; i<max_dev;i++)
		sb->dev_roles[i] = cpu_to_le16(0xfffe);
	
	ITERATE_RDEV(mddev,rdev2,tmp) {
		i = rdev2->desc_nr;
		if (test_bit(Faulty, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(0xfffe);
		else if (test_bit(In_sync, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else if (rdev2->raid_disk >= 0 && rdev2->recovery_offset > 0)
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else
			sb->dev_roles[i] = cpu_to_le16(0xffff);
	}

	sb->sb_csum = calc_sb_1_csum(sb);
}


static struct super_type super_types[] = {
	[0] = {
		.name	= "0.90.0",
		.owner	= THIS_MODULE,
		.load_super	= super_90_load,
		.validate_super	= super_90_validate,
		.sync_super	= super_90_sync,
	},
	[1] = {
		.name	= "md-1",
		.owner	= THIS_MODULE,
		.load_super	= super_1_load,
		.validate_super	= super_1_validate,
		.sync_super	= super_1_sync,
	},
};

static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
{
	struct list_head *tmp, *tmp2;
	mdk_rdev_t *rdev, *rdev2;

	ITERATE_RDEV(mddev1,rdev,tmp)
		ITERATE_RDEV(mddev2, rdev2, tmp2)
			if (rdev->bdev->bd_contains ==
			    rdev2->bdev->bd_contains)
				return 1;

	return 0;
}

static LIST_HEAD(pending_raid_disks);

static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
{
	char b[BDEVNAME_SIZE];
	struct kobject *ko;
	char *s;
	int err;

	if (rdev->mddev) {
		MD_BUG();
		return -EINVAL;
	}
	/* make sure rdev->size exceeds mddev->size */
	if (rdev->size && (mddev->size == 0 || rdev->size < mddev->size)) {
		if (mddev->pers) {
			/* Cannot change size, so fail
			 * If mddev->level <= 0, then we don't care
			 * about aligning sizes (e.g. linear)
			 */
			if (mddev->level > 0)
				return -ENOSPC;
		} else
			mddev->size = rdev->size;
	}

	/* Verify rdev->desc_nr is unique.
	 * If it is -1, assign a free number, else
	 * check number is not in use
	 */
	if (rdev->desc_nr < 0) {
		int choice = 0;
		if (mddev->pers) choice = mddev->raid_disks;
		while (find_rdev_nr(mddev, choice))
			choice++;
		rdev->desc_nr = choice;
	} else {
		if (find_rdev_nr(mddev, rdev->desc_nr))
			return -EBUSY;
	}
	bdevname(rdev->bdev,b);
	if (kobject_set_name(&rdev->kobj, "dev-%s", b) < 0)
		return -ENOMEM;
	while ( (s=strchr(rdev->kobj.k_name, '/')) != NULL)
		*s = '!';
			
	rdev->mddev = mddev;
	printk(KERN_INFO "md: bind<%s>\n", b);

	rdev->kobj.parent = &mddev->kobj;
	if ((err = kobject_add(&rdev->kobj)))
		goto fail;

	if (rdev->bdev->bd_part)
		ko = &rdev->bdev->bd_part->kobj;
	else
		ko = &rdev->bdev->bd_disk->kobj;
	if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
		kobject_del(&rdev->kobj);
		goto fail;
	}
	list_add(&rdev->same_set, &mddev->disks);
	bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk);
	return 0;

 fail:
	printk(KERN_WARNING "md: failed to register dev-%s for %s\n",
	       b, mdname(mddev));
	return err;
}

static void delayed_delete(struct work_struct *ws)
{
	mdk_rdev_t *rdev = container_of(ws, mdk_rdev_t, del_work);
	kobject_del(&rdev->kobj);
}

static void unbind_rdev_from_array(mdk_rdev_t * rdev)
{
	char b[BDEVNAME_SIZE];
	if (!rdev->mddev) {
		MD_BUG();
		return;
	}
	bd_release_from_disk(rdev->bdev, rdev->mddev->gendisk);
	list_del_init(&rdev->same_set);
	printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
	rdev->mddev = NULL;
	sysfs_remove_link(&rdev->kobj, "block");

	/* We need to delay this, otherwise we can deadlock when
	 * writing to 'remove' to "dev/state"
	 */
	INIT_WORK(&rdev->del_work, delayed_delete);
	schedule_work(&rdev->del_work);
}

/*
 * prevent the device from being mounted, repartitioned or
 * otherwise reused by a RAID array (or any other kernel
 * subsystem), by bd_claiming the device.
 */
static int lock_rdev(mdk_rdev_t *rdev, dev_t dev)
{
	int err = 0;
	struct block_device *bdev;
	char b[BDEVNAME_SIZE];

	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
	if (IS_ERR(bdev)) {
		printk(KERN_ERR "md: could not open %s.\n",
			__bdevname(dev, b));
		return PTR_ERR(bdev);
	}
	err = bd_claim(bdev, rdev);
	if (err) {
		printk(KERN_ERR "md: could not bd_claim %s.\n",
			bdevname(bdev, b));
		blkdev_put(bdev);
		return err;
	}
	rdev->bdev = bdev;
	return err;
}

static void unlock_rdev(mdk_rdev_t *rdev)
{
	struct block_device *bdev = rdev->bdev;
	rdev->bdev = NULL;
	if (!bdev)
		MD_BUG();
	bd_release(bdev);
	blkdev_put(bdev);
}

void md_autodetect_dev(dev_t dev);

static void export_rdev(mdk_rdev_t * rdev)
{
	char b[BDEVNAME_SIZE];
	printk(KERN_INFO "md: export_rdev(%s)\n",
		bdevname(rdev->bdev,b));
	if (rdev->mddev)
		MD_BUG();
	free_disk_sb(rdev);
	list_del_init(&rdev->same_set);
#ifndef MODULE
	md_autodetect_dev(rdev->bdev->bd_dev);
#endif
	unlock_rdev(rdev);
	kobject_put(&rdev->kobj);
}

static void kick_rdev_from_array(mdk_rdev_t * rdev)
{
	unbind_rdev_from_array(rdev);
	export_rdev(rdev);
}

static void export_array(mddev_t *mddev)
{
	struct list_head *tmp;
	mdk_rdev_t *rdev;

	ITERATE_RDEV(mddev,rdev,tmp) {
		if (!rdev->mddev) {
			MD_BUG();
			continue;
		}
		kick_rdev_from_array(rdev);
	}
	if (!list_empty(&mddev->disks))
		MD_BUG();
	mddev->raid_disks = 0;
	mddev->major_version = 0;
}

static void print_desc(mdp_disk_t *desc)
{
	printk(" DISK<N:%d,(%d,%d),R:%d,S:%d>\n", desc->number,
		desc->major,desc->minor,desc->raid_disk,desc->state);
}

static void print_sb(mdp_super_t *sb)
{
	int i;

	printk(KERN_INFO 
		"md:  SB: (V:%d.%d.%d) ID:<%08x.%08x.%08x.%08x> CT:%08x\n",
		sb->major_version, sb->minor_version, sb->patch_version,
		sb->set_uuid0, sb->set_uuid1, sb->set_uuid2, sb->set_uuid3,
		sb->ctime);
	printk(KERN_INFO "md:     L%d S%08d ND:%d RD:%d md%d LO:%d CS:%d\n",
		sb->level, sb->size, sb->nr_disks, sb->raid_disks,
		sb->md_minor, sb->layout, sb->chunk_size);
	printk(KERN_INFO "md:     UT:%08x ST:%d AD:%d WD:%d"
		" FD:%d SD:%d CSUM:%08x E:%08lx\n",
		sb->utime, sb->state, sb->active_disks, sb->working_disks,
		sb->failed_disks, sb->spare_disks,
		sb->sb_csum, (unsigned long)sb->events_lo);

	printk(KERN_INFO);
	for (i = 0; i < MD_SB_DISKS; i++) {
		mdp_disk_t *desc;

		desc = sb->disks + i;
		if (desc->number || desc->major || desc->minor ||
		    desc->raid_disk || (desc->state && (desc->state != 4))) {
			printk("     D %2d: ", i);
			print_desc(desc);
		}
	}
	printk(KERN_INFO "md:     THIS: ");
	print_desc(&sb->this_disk);

}

static void print_rdev(mdk_rdev_t *rdev)
{
	char b[BDEVNAME_SIZE];
	printk(KERN_INFO "md: rdev %s, SZ:%08llu F:%d S:%d DN:%u\n",
		bdevname(rdev->bdev,b), (unsigned long long)rdev->size,
	        test_bit(Faulty, &rdev->flags), test_bit(In_sync, &rdev->flags),
	        rdev->desc_nr);
	if (rdev->sb_loaded) {
		printk(KERN_INFO "md: rdev superblock:\n");
		print_sb((mdp_super_t*)page_address(rdev->sb_page));
	} else
		printk(KERN_INFO "md: no rdev superblock!\n");
}

static void md_print_devices(void)
{
	struct list_head *tmp, *tmp2;
	mdk_rdev_t *rdev;
	mddev_t *mddev;
	char b[BDEVNAME_SIZE];

	printk("\n");
	printk("md:	**********************************\n");
	printk("md:	* <COMPLETE RAID STATE PRINTOUT> *\n");
	printk("md:	**********************************\n");
	ITERATE_MDDEV(mddev,tmp) {

		if (mddev->bitmap)
			bitmap_print_sb(mddev->bitmap);
		else
			printk("%s: ", mdname(mddev));
		ITERATE_RDEV(mddev,rdev,tmp2)
			printk("<%s>", bdevname(rdev->bdev,b));
		printk("\n");

		ITERATE_RDEV(mddev,rdev,tmp2)
			print_rdev(rdev);
	}
	printk("md:	**********************************\n");
	printk("\n");
}


static void sync_sbs(mddev_t * mddev, int nospares)
{
	/* Update each superblock (in-memory image), but
	 * if we are allowed to, skip spares which already
	 * have the right event counter, or have one earlier
	 * (which would mean they aren't being marked as dirty
	 * with the rest of the array)
	 */
	mdk_rdev_t *rdev;
	struct list_head *tmp;

	ITERATE_RDEV(mddev,rdev,tmp) {
		if (rdev->sb_events == mddev->events ||
		    (nospares &&
		     rdev->raid_disk < 0 &&
		     (rdev->sb_events&1)==0 &&
		     rdev->sb_events+1 == mddev->events)) {
			/* Don't update this superblock */
			rdev->sb_loaded = 2;
		} else {
			super_types[mddev->major_version].
				sync_super(mddev, rdev);
			rdev->sb_loaded = 1;
		}
	}
}

static void md_update_sb(mddev_t * mddev, int force_change)
{
	struct list_head *tmp;
	mdk_rdev_t *rdev;
	int sync_req;
	int nospares = 0;

repeat:
	spin_lock_irq(&mddev->write_lock);

	set_bit(MD_CHANGE_PENDING, &mddev->flags);
	if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
		force_change = 1;
	if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags))
		/* just a clean<-> dirty transition, possibly leave spares alone,
		 * though if events isn't the right even/odd, we will have to do
		 * spares after all
		 */
		nospares = 1;
	if (force_change)
		nospares = 0;
	if (mddev->degraded)
		/* If the array is degraded, then skipping spares is both
		 * dangerous and fairly pointless.
		 * Dangerous because a device that was removed from the array
		 * might have a event_count that still looks up-to-date,
		 * so it can be re-added without a resync.
		 * Pointless because if there are any spares to skip,
		 * then a recovery will happen and soon that array won't
		 * be degraded any more and the spare can go back to sleep then.
		 */
		nospares = 0;

	sync_req = mddev->in_sync;
	mddev->utime = get_seconds();

	/* If this is just a dirty<->clean transition, and the array is clean
	 * and 'events' is odd, we can roll back to the previous clean state */
	if (nospares
	    && (mddev->in_sync && mddev->recovery_cp == MaxSector)
	    && (mddev->events & 1)
	    && mddev->events != 1)
		mddev->events--;
	else {
		/* otherwise we have to go forward and ... */
		mddev->events ++;
		if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
			/* .. if the array isn't clean, insist on an odd 'events' */
			if ((mddev->events&1)==0) {
				mddev->events++;
				nospares = 0;
			}
		} else {
			/* otherwise insist on an even 'events' (for clean states) */
			if ((mddev->events&1)) {
				mddev->events++;
				nospares = 0;
			}
		}
	}

	if (!mddev->events) {
		/*
		 * oops, this 64-bit counter should never wrap.
		 * Either we are in around ~1 trillion A.C., assuming
		 * 1 reboot per second, or we have a bug:
		 */
		MD_BUG();
		mddev->events --;
	}
	sync_sbs(mddev, nospares);

	/*
	 * do not write anything to disk if using
	 * nonpersistent superblocks
	 */
	if (!mddev->persistent) {
		clear_bit(MD_CHANGE_PENDING, &mddev->flags);
		spin_unlock_irq(&mddev->write_lock);
		wake_up(&mddev->sb_wait);
		return;
	}
	spin_unlock_irq(&mddev->write_lock);

	dprintk(KERN_INFO 
		"md: updating %s RAID superblock on device (in sync %d)\n",
		mdname(mddev),mddev->in_sync);

	bitmap_update_sb(mddev->bitmap);
	ITERATE_RDEV(mddev,rdev,tmp) {
		char b[BDEVNAME_SIZE];
		dprintk(KERN_INFO "md: ");
		if (rdev->sb_loaded != 1)
			continue; /* no noise on spare devices */
		if (test_bit(Faulty, &rdev->flags))
			dprintk("(skipping faulty ");

		dprintk("%s ", bdevname(rdev->bdev,b));
		if (!test_bit(Faulty, &rdev->flags)) {
			md_super_write(mddev,rdev,
				       rdev->sb_offset<<1, rdev->sb_size,
				       rdev->sb_page);
			dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
				bdevname(rdev->bdev,b),
				(unsigned long long)rdev->sb_offset);
			rdev->sb_events = mddev->events;

		} else
			dprintk(")\n");
		if (mddev->level == LEVEL_MULTIPATH)
			/* only need to write one superblock... */
			break;
	}
	md_super_wait(mddev);
	/* if there was a failure, MD_CHANGE_DEVS was set, and we re-write super */

	spin_lock_irq(&mddev->write_lock);
	if (mddev->in_sync != sync_req ||
	    test_bit(MD_CHANGE_DEVS, &mddev->flags)) {
		/* have to write it out again */
		spin_unlock_irq(&mddev->write_lock);
		goto repeat;
	}
	clear_bit(MD_CHANGE_PENDING, &mddev->flags);
	spin_unlock_irq(&mddev->write_lock);
	wake_up(&mddev->sb_wait);

}

/* words written to sysfs files may, or my not, be \n terminated.
 * We want to accept with case. For this we use cmd_match.
 */
static int cmd_match(const char *cmd, const char *str)
{
	/* See if cmd, written into a sysfs file, matches
	 * str.  They must either be the same, or cmd can
	 * have a trailing newline
	 */
	while (*cmd && *str && *cmd == *str) {
		cmd++;
		str++;
	}
	if (*cmd == '\n')
		cmd++;
	if (*str || *cmd)
		return 0;
	return 1;
}

struct rdev_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(mdk_rdev_t *, char *);
	ssize_t (*store)(mdk_rdev_t *, const char *, size_t);
};

static ssize_t
state_show(mdk_rdev_t *rdev, char *page)
{
	char *sep = "";
	int len=0;

	if (test_bit(Faulty, &rdev->flags)) {
		len+= sprintf(page+len, "%sfaulty",sep);
		sep = ",";
	}
	if (test_bit(In_sync, &rdev->flags)) {
		len += sprintf(page+len, "%sin_sync",sep);
		sep = ",";
	}
	if (test_bit(WriteMostly, &rdev->flags)) {
		len += sprintf(page+len, "%swrite_mostly",sep);
		sep = ",";
	}
	if (!test_bit(Faulty, &rdev->flags) &&
	    !test_bit(In_sync, &rdev->flags)) {
		len += sprintf(page+len, "%sspare", sep);
		sep = ",";
	}
	return len+sprintf(page+len, "\n");
}

static ssize_t
state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
{
	/* can write
	 *  faulty  - simulates and error
	 *  remove  - disconnects the device
	 *  writemostly - sets write_mostly
	 *  -writemostly - clears write_mostly
	 */
	int err = -EINVAL;
	if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
		md_error(rdev->mddev, rdev);
		err = 0;
	} else if (cmd_match(buf, "remove")) {
		if (rdev->raid_disk >= 0)
			err = -EBUSY;
		else {
			mddev_t *mddev = rdev->mddev;
			kick_rdev_from_array(rdev);
			if (mddev->pers)
				md_update_sb(mddev, 1);
			md_new_event(mddev);
			err = 0;
		}
	} else if (cmd_match(buf, "writemostly")) {
		set_bit(WriteMostly, &rdev->flags);
		err = 0;
	} else if (cmd_match(buf, "-writemostly")) {
		clear_bit(WriteMostly, &rdev->flags);
		err = 0;
	}
	return err ? err : len;
}
static struct rdev_sysfs_entry rdev_state =
__ATTR(state, S_IRUGO|S_IWUSR, state_show, state_store);

static ssize_t
super_show(mdk_rdev_t *rdev, char *page)
{
	if (rdev->sb_loaded && rdev->sb_size) {
		memcpy(page, page_address(rdev->sb_page), rdev->sb_size);
		return rdev->sb_size;
	} else
		return 0;
}
static struct rdev_sysfs_entry rdev_super = __ATTR_RO(super);

static ssize_t
errors_show(mdk_rdev_t *rdev, char *page)
{
	return sprintf(page, "%d\n", atomic_read(&rdev->corrected_errors));
}

static ssize_t
errors_store(mdk_rdev_t *rdev, const char *buf, size_t len)
{
	char *e;
	unsigned long n = simple_strtoul(buf, &e, 10);
	if (*buf && (*e == 0 || *e == '\n')) {
		atomic_set(&rdev->corrected_errors, n);
		return len;
	}
	return -EINVAL;
}
static struct rdev_sysfs_entry rdev_errors =
__ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store);

static ssize_t
slot_show(mdk_rdev_t *rdev, char *page)
{
	if (rdev->raid_disk < 0)
		return sprintf(page, "none\n");
	else
		return sprintf(page, "%d\n", rdev->raid_disk);
}

static ssize_t
slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
{
	char *e;
	int slot = simple_strtoul(buf, &e, 10);
	if (strncmp(buf, "none", 4)==0)
		slot = -1;
	else if (e==buf || (*e && *e!= '\n'))
		return -EINVAL;
	if (rdev->mddev->pers)
		/* Cannot set slot in active array (yet) */
		return -EBUSY;
	if (slot >= rdev->mddev->raid_disks)
		return -ENOSPC;
	rdev->raid_disk = slot;
	/* assume it is working */
	rdev->flags = 0;
	set_bit(In_sync, &rdev->flags);
	return len;
}


static struct rdev_sysfs_entry rdev_slot =
__ATTR(slot, S_IRUGO|S_IWUSR, slot_show, slot_store);

static ssize_t
offset_show(mdk_rdev_t *rdev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)rdev->data_offset);
}

static ssize_t
offset_store(mdk_rdev_t *rdev, const char *buf, size_t len)
{
	char *e;
	unsigned long long offset = simple_strtoull(buf, &e, 10);
	if (e==buf || (*e && *e != '\n'))
		return -EINVAL;
	if (rdev->mddev->pers)
		return -EBUSY;
	rdev->data_offset = offset;
	return len;
}

static struct rdev_sysfs_entry rdev_offset =
__ATTR(offset, S_IRUGO|S_IWUSR, offset_show, offset_store);

static ssize_t
rdev_size_show(mdk_rdev_t *rdev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)rdev->size);
}

static ssize_t
rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
{
	char *e;
	unsigned long long size = simple_strtoull(buf, &e, 10);
	if (e==buf || (*e && *e != '\n'))
		return -EINVAL;
	if (rdev->mddev->pers)
		return -EBUSY;
	rdev->size = size;
	if (size < rdev->mddev->size || rdev->mddev->size == 0)
		rdev->mddev->size = size;
	return len;
}

static struct rdev_sysfs_entry rdev_size =
__ATTR(size, S_IRUGO|S_IWUSR, rdev_size_show, rdev_size_store);

static struct attribute *rdev_default_attrs[] = {
	&rdev_state.attr,
	&rdev_super.attr,
	&rdev_errors.attr,
	&rdev_slot.attr,
	&rdev_offset.attr,
	&rdev_size.attr,
	NULL,
};
static ssize_t
rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
	struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
	mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);

	if (!entry->show)
		return -EIO;
	return entry->show(rdev, page);
}

static ssize_t
rdev_attr_store(struct kobject *kobj, struct attribute *attr,
	      const char *page, size_t length)
{
	struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
	mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);

	if (!entry->store)
		return -EIO;
	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	return entry->store(rdev, page, length);
}

static void rdev_free(struct kobject *ko)
{
	mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj);
	kfree(rdev);
}
static struct sysfs_ops rdev_sysfs_ops = {
	.show		= rdev_attr_show,
	.store		= rdev_attr_store,
};
static struct kobj_type rdev_ktype = {
	.release	= rdev_free,
	.sysfs_ops	= &rdev_sysfs_ops,
	.default_attrs	= rdev_default_attrs,
};

/*
 * Import a device. If 'super_format' >= 0, then sanity check the superblock
 *
 * mark the device faulty if:
 *
 *   - the device is nonexistent (zero size)
 *   - the device has no valid superblock
 *
 * a faulty rdev _never_ has rdev->sb set.
 */
static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_minor)
{
	char b[BDEVNAME_SIZE];
	int err;
	mdk_rdev_t *rdev;
	sector_t size;

	rdev = kzalloc(sizeof(*rdev), GFP_KERNEL);
	if (!rdev) {
		printk(KERN_ERR "md: could not alloc mem for new device!\n");
		return ERR_PTR(-ENOMEM);
	}

	if ((err = alloc_disk_sb(rdev)))
		goto abort_free;

	err = lock_rdev(rdev, newdev);
	if (err)
		goto abort_free;

	rdev->kobj.parent = NULL;
	rdev->kobj.ktype = &rdev_ktype;
	kobject_init(&rdev->kobj);

	rdev->desc_nr = -1;
	rdev->saved_raid_disk = -1;
	rdev->raid_disk = -1;
	rdev->flags = 0;
	rdev->data_offset = 0;
	rdev->sb_events = 0;
	atomic_set(&rdev->nr_pending, 0);
	atomic_set(&rdev->read_errors, 0);
	atomic_set(&rdev->corrected_errors, 0);

	size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
	if (!size) {
		printk(KERN_WARNING 
			"md: %s has zero or unknown size, marking faulty!\n",
			bdevname(rdev->bdev,b));
		err = -EINVAL;
		goto abort_free;
	}

	if (super_format >= 0) {
		err = super_types[super_format].
			load_super(rdev, NULL, super_minor);
		if (err == -EINVAL) {
			printk(KERN_WARNING
				"md: %s does not have a valid v%d.%d "
			       "superblock, not importing!\n",
				bdevname(rdev->bdev,b),
			       super_format, super_minor);
			goto abort_free;
		}
		if (err < 0) {
			printk(KERN_WARNING 
				"md: could not read %s's sb, not importing!\n",
				bdevname(rdev->bdev,b));
			goto abort_free;
		}
	}
	INIT_LIST_HEAD(&rdev->same_set);

	return rdev;

abort_free:
	if (rdev->sb_page) {
		if (rdev->bdev)
			unlock_rdev(rdev);
		free_disk_sb(rdev);
	}
	kfree(rdev);
	return ERR_PTR(err);
}

/*
 * Check a full RAID array for plausibility
 */


static void analyze_sbs(mddev_t * mddev)
{
	int i;
	struct list_head *tmp;
	mdk_rdev_t *rdev, *freshest;
	char b[BDEVNAME_SIZE];

	freshest = NULL;
	ITERATE_RDEV(mddev,rdev,tmp)
		switch (super_types[mddev->major_version].
			load_super(rdev, freshest, mddev->minor_version)) {
		case 1:
			freshest = rdev;
			break;
		case 0:
			break;
		default:
			printk( KERN_ERR \
				"md: fatal superblock inconsistency in %s"
				" -- removing from array\n", 
				bdevname(rdev->bdev,b));
			kick_rdev_from_array(rdev);
		}


	super_types[mddev->major_version].
		validate_super(mddev, freshest);

	i = 0;
	ITERATE_RDEV(mddev,rdev,tmp) {
		if (rdev != freshest)
			if (super_types[mddev->major_version].
			    validate_super(mddev, rdev)) {
				printk(KERN_WARNING "md: kicking non-fresh %s"
					" from array!\n",
					bdevname(rdev->bdev,b));
				kick_rdev_from_array(rdev);
				continue;
			}
		if (mddev->level == LEVEL_MULTIPATH) {
			rdev->desc_nr = i++;
			rdev->raid_disk = rdev->desc_nr;
			set_bit(In_sync, &rdev->flags);
		} else if (rdev->raid_disk >= mddev->raid_disks) {
			rdev->raid_disk = -1;
			clear_bit(In_sync, &rdev->flags);
		}
	}



	if (mddev->recovery_cp != MaxSector &&
	    mddev->level >= 1)
		printk(KERN_ERR "md: %s: raid array is not clean"
		       " -- starting background reconstruction\n",
		       mdname(mddev));

}

static ssize_t
safe_delay_show(mddev_t *mddev, char *page)
{
	int msec = (mddev->safemode_delay*1000)/HZ;
	return sprintf(page, "%d.%03d\n", msec/1000, msec%1000);
}
static ssize_t
safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
{
	int scale=1;
	int dot=0;
	int i;
	unsigned long msec;
	char buf[30];
	char *e;
	/* remove a period, and count digits after it */
	if (len >= sizeof(buf))
		return -EINVAL;
	strlcpy(buf, cbuf, len);
	buf[len] = 0;
	for (i=0; i<len; i++) {
		if (dot) {
			if (isdigit(buf[i])) {
				buf[i-1] = buf[i];
				scale *= 10;
			}
			buf[i] = 0;
		} else if (buf[i] == '.') {
			dot=1;
			buf[i] = 0;
		}
	}
	msec = simple_strtoul(buf, &e, 10);
	if (e == buf || (*e && *e != '\n'))
		return -EINVAL;
	msec = (msec * 1000) / scale;
	if (msec == 0)
		mddev->safemode_delay = 0;
	else {
		mddev->safemode_delay = (msec*HZ)/1000;
		if (mddev->safemode_delay == 0)
			mddev->safemode_delay = 1;
	}
	return len;
}
static struct md_sysfs_entry md_safe_delay =
__ATTR(safe_mode_delay, S_IRUGO|S_IWUSR,safe_delay_show, safe_delay_store);

static ssize_t
level_show(mddev_t *mddev, char *page)
{
	struct mdk_personality *p = mddev->pers;
	if (p)
		return sprintf(page, "%s\n", p->name);
	else if (mddev->clevel[0])
		return sprintf(page, "%s\n", mddev->clevel);
	else if (mddev->level != LEVEL_NONE)
		return sprintf(page, "%d\n", mddev->level);
	else
		return 0;
}

static ssize_t
level_store(mddev_t *mddev, const char *buf, size_t len)
{
	int rv = len;
	if (mddev->pers)
		return -EBUSY;
	if (len == 0)
		return 0;
	if (len >= sizeof(mddev->clevel))
		return -ENOSPC;
	strncpy(mddev->clevel, buf, len);
	if (mddev->clevel[len-1] == '\n')
		len--;
	mddev->clevel[len] = 0;
	mddev->level = LEVEL_NONE;
	return rv;
}

static struct md_sysfs_entry md_level =
__ATTR(level, S_IRUGO|S_IWUSR, level_show, level_store);


static ssize_t
layout_show(mddev_t *mddev, char *page)
{
	/* just a number, not meaningful for all levels */
	if (mddev->reshape_position != MaxSector &&
	    mddev->layout != mddev->new_layout)
		return sprintf(page, "%d (%d)\n",
			       mddev->new_layout, mddev->layout);
	return sprintf(page, "%d\n", mddev->layout);
}

static ssize_t
layout_store(mddev_t *mddev, const char *buf, size_t len)
{
	char *e;
	unsigned long n = simple_strtoul(buf, &e, 10);

	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	if (mddev->pers)
		return -EBUSY;
	if (mddev->reshape_position != MaxSector)
		mddev->new_layout = n;
	else
		mddev->layout = n;
	return len;
}
static struct md_sysfs_entry md_layout =
__ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);


static ssize_t
raid_disks_show(mddev_t *mddev, char *page)
{
	if (mddev->raid_disks == 0)
		return 0;
	if (mddev->reshape_position != MaxSector &&
	    mddev->delta_disks != 0)
		return sprintf(page, "%d (%d)\n", mddev->raid_disks,
			       mddev->raid_disks - mddev->delta_disks);
	return sprintf(page, "%d\n", mddev->raid_disks);
}

static int update_raid_disks(mddev_t *mddev, int raid_disks);

static ssize_t
raid_disks_store(mddev_t *mddev, const char *buf, size_t len)
{
	char *e;
	int rv = 0;
	unsigned long n = simple_strtoul(buf, &e, 10);

	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	if (mddev->pers)
		rv = update_raid_disks(mddev, n);
	else if (mddev->reshape_position != MaxSector) {
		int olddisks = mddev->raid_disks - mddev->delta_disks;
		mddev->delta_disks = n - olddisks;
		mddev->raid_disks = n;
	} else
		mddev->raid_disks = n;
	return rv ? rv : len;
}
static struct md_sysfs_entry md_raid_disks =
__ATTR(raid_disks, S_IRUGO|S_IWUSR, raid_disks_show, raid_disks_store);

static ssize_t
chunk_size_show(mddev_t *mddev, char *page)
{
	if (mddev->reshape_position != MaxSector &&
	    mddev->chunk_size != mddev->new_chunk)
		return sprintf(page, "%d (%d)\n", mddev->new_chunk,
			       mddev->chunk_size);
	return sprintf(page, "%d\n", mddev->chunk_size);
}

static ssize_t
chunk_size_store(mddev_t *mddev, const char *buf, size_t len)
{
	/* can only set chunk_size if array is not yet active */
	char *e;
	unsigned long n = simple_strtoul(buf, &e, 10);

	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	if (mddev->pers)
		return -EBUSY;
	else if (mddev->reshape_position != MaxSector)
		mddev->new_chunk = n;
	else
		mddev->chunk_size = n;
	return len;
}
static struct md_sysfs_entry md_chunk_size =
__ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store);

static ssize_t
resync_start_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)mddev->recovery_cp);
}

static ssize_t
resync_start_store(mddev_t *mddev, const char *buf, size_t len)
{
	/* can only set chunk_size if array is not yet active */
	char *e;
	unsigned long long n = simple_strtoull(buf, &e, 10);

	if (mddev->pers)
		return -EBUSY;
	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	mddev->recovery_cp = n;
	return len;
}
static struct md_sysfs_entry md_resync_start =
__ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store);

/*
 * The array state can be:
 *
 * clear
 *     No devices, no size, no level
 *     Equivalent to STOP_ARRAY ioctl
 * inactive
 *     May have some settings, but array is not active
 *        all IO results in error
 *     When written, doesn't tear down array, but just stops it
 * suspended (not supported yet)
 *     All IO requests will block. The array can be reconfigured.
 *     Writing this, if accepted, will block until array is quiessent
 * readonly
 *     no resync can happen.  no superblocks get written.
 *     write requests fail
 * read-auto
 *     like readonly, but behaves like 'clean' on a write request.
 *
 * clean - no pending writes, but otherwise active.
 *     When written to inactive array, starts without resync
 *     If a write request arrives then
 *       if metadata is known, mark 'dirty' and switch to 'active'.
 *       if not known, block and switch to write-pending
 *     If written to an active array that has pending writes, then fails.
 * active
 *     fully active: IO and resync can be happening.
 *     When written to inactive array, starts with resync
 *
 * write-pending
 *     clean, but writes are blocked waiting for 'active' to be written.
 *
 * active-idle
 *     like active, but no writes have been seen for a while (100msec).
 *
 */
enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
		   write_pending, active_idle, bad_word};
static char *array_states[] = {
	"clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
	"write-pending", "active-idle", NULL };

static int match_word(const char *word, char **list)
{
	int n;
	for (n=0; list[n]; n++)
		if (cmd_match(word, list[n]))
			break;
	return n;
}

static ssize_t
array_state_show(mddev_t *mddev, char *page)
{
	enum array_state st = inactive;

	if (mddev->pers)
		switch(mddev->ro) {
		case 1:
			st = readonly;
			break;
		case 2:
			st = read_auto;
			break;
		case 0:
			if (mddev->in_sync)
				st = clean;
			else if (mddev->safemode)
				st = active_idle;
			else
				st = active;
		}
	else {
		if (list_empty(&mddev->disks) &&
		    mddev->raid_disks == 0 &&
		    mddev->size == 0)
			st = clear;
		else
			st = inactive;
	}
	return sprintf(page, "%s\n", array_states[st]);
}

static int do_md_stop(mddev_t * mddev, int ro);
static int do_md_run(mddev_t * mddev);
static int restart_array(mddev_t *mddev);

static ssize_t
array_state_store(mddev_t *mddev, const char *buf, size_t len)
{
	int err = -EINVAL;
	enum array_state st = match_word(buf, array_states);
	switch(st) {
	case bad_word:
		break;
	case clear:
		/* stopping an active array */
		if (mddev->pers) {
			if (atomic_read(&mddev->active) > 1)
				return -EBUSY;
			err = do_md_stop(mddev, 0);
		}
		break;
	case inactive:
		/* stopping an active array */
		if (mddev->pers) {
			if (atomic_read(&mddev->active) > 1)
				return -EBUSY;
			err = do_md_stop(mddev, 2);
		}
		break;
	case suspended:
		break; /* not supported yet */
	case readonly:
		if (mddev->pers)
			err = do_md_stop(mddev, 1);
		else {
			mddev->ro = 1;
			err = do_md_run(mddev);
		}
		break;
	case read_auto:
		/* stopping an active array */
		if (mddev->pers) {
			err = do_md_stop(mddev, 1);
			if (err == 0)
				mddev->ro = 2; /* FIXME mark devices writable */
		} else {
			mddev->ro = 2;
			err = do_md_run(mddev);
		}
		break;
	case clean:
		if (mddev->pers) {
			restart_array(mddev);
			spin_lock_irq(&mddev->write_lock);
			if (atomic_read(&mddev->writes_pending) == 0) {
				mddev->in_sync = 1;
				set_bit(MD_CHANGE_CLEAN, &mddev->flags);
			}
			spin_unlock_irq(&mddev->write_lock);
		} else {
			mddev->ro = 0;
			mddev->recovery_cp = MaxSector;
			err = do_md_run(mddev);
		}
		break;
	case active:
		if (mddev->pers) {
			restart_array(mddev);
			clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
			wake_up(&mddev->sb_wait);
			err = 0;
		} else {
			mddev->ro = 0;
			err = do_md_run(mddev);
		}
		break;
	case write_pending:
	case active_idle:
		/* these cannot be set */
		break;
	}
	if (err)
		return err;
	else
		return len;
}
static struct md_sysfs_entry md_array_state =
__ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);

static ssize_t
null_show(mddev_t *mddev, char *page)
{
	return -EINVAL;
}

static ssize_t
new_dev_store(mddev_t *mddev, const char *buf, size_t len)
{
	/* buf must be %d:%d\n? giving major and minor numbers */
	/* The new device is added to the array.
	 * If the array has a persistent superblock, we read the
	 * superblock to initialise info and check validity.
	 * Otherwise, only checking done is that in bind_rdev_to_array,
	 * which mainly checks size.
	 */
	char *e;
	int major = simple_strtoul(buf, &e, 10);
	int minor;
	dev_t dev;
	mdk_rdev_t *rdev;
	int err;

	if (!*buf || *e != ':' || !e[1] || e[1] == '\n')
		return -EINVAL;
	minor = simple_strtoul(e+1, &e, 10);
	if (*e && *e != '\n')
		return -EINVAL;
	dev = MKDEV(major, minor);
	if (major != MAJOR(dev) ||
	    minor != MINOR(dev))
		return -EOVERFLOW;


	if (mddev->persistent) {
		rdev = md_import_device(dev, mddev->major_version,
					mddev->minor_version);
		if (!IS_ERR(rdev) && !list_empty(&mddev->disks)) {
			mdk_rdev_t *rdev0 = list_entry(mddev->disks.next,
						       mdk_rdev_t, same_set);
			err = super_types[mddev->major_version]
				.load_super(rdev, rdev0, mddev->minor_version);
			if (err < 0)
				goto out;
		}
	} else
		rdev = md_import_device(dev, -1, -1);

	if (IS_ERR(rdev))
		return PTR_ERR(rdev);
	err = bind_rdev_to_array(rdev, mddev);
 out:
	if (err)
		export_rdev(rdev);
	return err ? err : len;
}

static struct md_sysfs_entry md_new_device =
__ATTR(new_dev, S_IWUSR, null_show, new_dev_store);

static ssize_t
bitmap_store(mddev_t *mddev, const char *buf, size_t len)
{
	char *end;
	unsigned long chunk, end_chunk;

	if (!mddev->bitmap)
		goto out;
	/* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */
	while (*buf) {
		chunk = end_chunk = simple_strtoul(buf, &end, 0);
		if (buf == end) break;
		if (*end == '-') { /* range */
			buf = end + 1;
			end_chunk = simple_strtoul(buf, &end, 0);
			if (buf == end) break;
		}
		if (*end && !isspace(*end)) break;
		bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
		buf = end;
		while (isspace(*buf)) buf++;
	}
	bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
out:
	return len;
}

static struct md_sysfs_entry md_bitmap =
__ATTR(bitmap_set_bits, S_IWUSR, null_show, bitmap_store);

static ssize_t
size_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)mddev->size);
}

static int update_size(mddev_t *mddev, unsigned long size);

static ssize_t
size_store(mddev_t *mddev, const char *buf, size_t len)
{
	/* If array is inactive, we can reduce the component size, but
	 * not increase it (except from 0).
	 * If array is active, we can try an on-line resize
	 */
	char *e;
	int err = 0;
	unsigned long long size = simple_strtoull(buf, &e, 10);
	if (!*buf || *buf == '\n' ||
	    (*e && *e != '\n'))
		return -EINVAL;

	if (mddev->pers) {
		err = update_size(mddev, size);
		md_update_sb(mddev, 1);
	} else {
		if (mddev->size == 0 ||
		    mddev->size > size)
			mddev->size = size;
		else
			err = -ENOSPC;
	}
	return err ? err : len;
}

static struct md_sysfs_entry md_size =
__ATTR(component_size, S_IRUGO|S_IWUSR, size_show, size_store);


/* Metdata version.
 * This is either 'none' for arrays with externally managed metadata,
 * or N.M for internally known formats
 */
static ssize_t
metadata_show(mddev_t *mddev, char *page)
{
	if (mddev->persistent)
		return sprintf(page, "%d.%d\n",
			       mddev->major_version, mddev->minor_version);
	else
		return sprintf(page, "none\n");
}

static ssize_t
metadata_store(mddev_t *mddev, const char *buf, size_t len)
{
	int major, minor;
	char *e;
	if (!list_empty(&mddev->disks))
		return -EBUSY;

	if (cmd_match(buf, "none")) {
		mddev->persistent = 0;
		mddev->major_version = 0;
		mddev->minor_version = 90;
		return len;
	}
	major = simple_strtoul(buf, &e, 10);
	if (e==buf || *e != '.')
		return -EINVAL;
	buf = e+1;
	minor = simple_strtoul(buf, &e, 10);
	if (e==buf || (*e && *e != '\n') )
		return -EINVAL;
	if (major >= ARRAY_SIZE(super_types) || super_types[major].name == NULL)
		return -ENOENT;
	mddev->major_version = major;
	mddev->minor_version = minor;
	mddev->persistent = 1;
	return len;
}

static struct md_sysfs_entry md_metadata =
__ATTR(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);

static ssize_t
action_show(mddev_t *mddev, char *page)
{
	char *type = "idle";
	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
	    (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
			type = "reshape";
		else if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
			if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
				type = "resync";
			else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
				type = "check";
			else
				type = "repair";
		} else
			type = "recover";
	}
	return sprintf(page, "%s\n", type);
}

static ssize_t
action_store(mddev_t *mddev, const char *page, size_t len)
{
	if (!mddev->pers || !mddev->pers->sync_request)
		return -EINVAL;

	if (cmd_match(page, "idle")) {
		if (mddev->sync_thread) {
			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
			md_unregister_thread(mddev->sync_thread);
			mddev->sync_thread = NULL;
			mddev->recovery = 0;
		}
	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
		return -EBUSY;
	else if (cmd_match(page, "resync") || cmd_match(page, "recover"))
		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	else if (cmd_match(page, "reshape")) {
		int err;
		if (mddev->pers->start_reshape == NULL)
			return -EINVAL;
		err = mddev->pers->start_reshape(mddev);
		if (err)
			return err;
	} else {
		if (cmd_match(page, "check"))
			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
		else if (!cmd_match(page, "repair"))
			return -EINVAL;
		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
	}
	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	md_wakeup_thread(mddev->thread);
	return len;
}

static ssize_t
mismatch_cnt_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%llu\n",
		       (unsigned long long) mddev->resync_mismatches);
}

static struct md_sysfs_entry md_scan_mode =
__ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store);


static struct md_sysfs_entry md_mismatches = __ATTR_RO(mismatch_cnt);

static ssize_t
sync_min_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%d (%s)\n", speed_min(mddev),
		       mddev->sync_speed_min ? "local": "system");
}

static ssize_t
sync_min_store(mddev_t *mddev, const char *buf, size_t len)
{
	int min;
	char *e;
	if (strncmp(buf, "system", 6)==0) {
		mddev->sync_speed_min = 0;
		return len;
	}
	min = simple_strtoul(buf, &e, 10);
	if (buf == e || (*e && *e != '\n') || min <= 0)
		return -EINVAL;
	mddev->sync_speed_min = min;
	return len;
}

static struct md_sysfs_entry md_sync_min =
__ATTR(sync_speed_min, S_IRUGO|S_IWUSR, sync_min_show, sync_min_store);

static ssize_t
sync_max_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%d (%s)\n", speed_max(mddev),
		       mddev->sync_speed_max ? "local": "system");
}

static ssize_t
sync_max_store(mddev_t *mddev, const char *buf, size_t len)
{
	int max;
	char *e;
	if (strncmp(buf, "system", 6)==0) {
		mddev->sync_speed_max = 0;
		return len;
	}
	max = simple_strtoul(buf, &e, 10);
	if (buf == e || (*e && *e != '\n') || max <= 0)
		return -EINVAL;
	mddev->sync_speed_max = max;
	return len;
}

static struct md_sysfs_entry md_sync_max =
__ATTR(sync_speed_max, S_IRUGO|S_IWUSR, sync_max_show, sync_max_store);

static ssize_t
degraded_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%d\n", mddev->degraded);
}
static struct md_sysfs_entry md_degraded = __ATTR_RO(degraded);

static ssize_t
sync_speed_show(mddev_t *mddev, char *page)
{
	unsigned long resync, dt, db;
	resync = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active));
	dt = ((jiffies - mddev->resync_mark) / HZ);
	if (!dt) dt++;
	db = resync - (mddev->resync_mark_cnt);
	return sprintf(page, "%ld\n", db/dt/2); /* K/sec */
}

static struct md_sysfs_entry md_sync_speed = __ATTR_RO(sync_speed);

static ssize_t
sync_completed_show(mddev_t *mddev, char *page)
{
	unsigned long max_blocks, resync;

	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
		max_blocks = mddev->resync_max_sectors;
	else
		max_blocks = mddev->size << 1;

	resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active));
	return sprintf(page, "%lu / %lu\n", resync, max_blocks);
}

static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed);

static ssize_t
suspend_lo_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_lo);
}

static ssize_t
suspend_lo_store(mddev_t *mddev, const char *buf, size_t len)
{
	char *e;
	unsigned long long new = simple_strtoull(buf, &e, 10);

	if (mddev->pers->quiesce == NULL)
		return -EINVAL;
	if (buf == e || (*e && *e != '\n'))
		return -EINVAL;
	if (new >= mddev->suspend_hi ||
	    (new > mddev->suspend_lo && new < mddev->suspend_hi)) {
		mddev->suspend_lo = new;
		mddev->pers->quiesce(mddev, 2);
		return len;
	} else
		return -EINVAL;
}
static struct md_sysfs_entry md_suspend_lo =
__ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);


static ssize_t
suspend_hi_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_hi);
}

static ssize_t
suspend_hi_store(mddev_t *mddev, const char *buf, size_t len)
{