// SPDX-License-Identifier: GPL-2.0-or-later
/*
   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.


   Errors, Warnings, etc.
   Please use:
     pr_crit() for error conditions that risk data loss
     pr_err() for error conditions that are unexpected, like an IO error
         or internal inconsistency
     pr_warn() for error conditions that could have been predicated, like
         adding a device to an array when it has incompatible metadata
     pr_info() for every interesting, very rare events, like an array starting
         or stopping, or resync starting or stopping
     pr_debug() for everything else.

*/

#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/kthread.h>
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
#include <linux/badblocks.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/hdreg.h>
#include <linux/proc_fs.h>
#include <linux/random.h>
#include <linux/major.h>
#include <linux/module.h>
#include <linux/reboot.h>
#include <linux/file.h>
#include <linux/compat.h>
#include <linux/delay.h>
#include <linux/raid/md_p.h>
#include <linux/raid/md_u.h>
#include <linux/raid/detect.h>
#include <linux/slab.h>
#include <linux/percpu-refcount.h>
#include <linux/part_stat.h>

#include <trace/events/block.h>
#include "md.h"
#include "md-bitmap.h"
#include "md-cluster.h"

/* pers_list is a list of registered personalities protected by pers_lock. */
static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);

static const struct kobj_type md_ktype;

struct md_cluster_operations *md_cluster_ops;
EXPORT_SYMBOL(md_cluster_ops);
static struct module *md_cluster_mod;

static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
static struct workqueue_struct *md_wq;
static struct workqueue_struct *md_misc_wq;
struct workqueue_struct *md_bitmap_wq;

static int remove_and_add_spares(struct mddev *mddev,
				 struct md_rdev *this);
static void mddev_detach(struct mddev *mddev);
static void export_rdev(struct md_rdev *rdev, struct mddev *mddev);
static void md_wakeup_thread_directly(struct md_thread __rcu *thread);

/*
 * Default number of read corrections we'll attempt on an rdev
 * before ejecting it from the array. We divide the read error
 * count by 2 for every hour elapsed between read errors.
 */
#define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 20
/* Default safemode delay: 200 msec */
#define DEFAULT_SAFEMODE_DELAY ((200 * HZ)/1000 +1)
/*
 * 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(struct mddev *mddev)
{
	return mddev->sync_speed_min ?
		mddev->sync_speed_min : sysctl_speed_limit_min;
}

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

static void rdev_uninit_serial(struct md_rdev *rdev)
{
	if (!test_and_clear_bit(CollisionCheck, &rdev->flags))
		return;

	kvfree(rdev->serial);
	rdev->serial = NULL;
}

static void rdevs_uninit_serial(struct mddev *mddev)
{
	struct md_rdev *rdev;

	rdev_for_each(rdev, mddev)
		rdev_uninit_serial(rdev);
}

static int rdev_init_serial(struct md_rdev *rdev)
{
	/* serial_nums equals with BARRIER_BUCKETS_NR */
	int i, serial_nums = 1 << ((PAGE_SHIFT - ilog2(sizeof(atomic_t))));
	struct serial_in_rdev *serial = NULL;

	if (test_bit(CollisionCheck, &rdev->flags))
		return 0;

	serial = kvmalloc(sizeof(struct serial_in_rdev) * serial_nums,
			  GFP_KERNEL);
	if (!serial)
		return -ENOMEM;

	for (i = 0; i < serial_nums; i++) {
		struct serial_in_rdev *serial_tmp = &serial[i];

		spin_lock_init(&serial_tmp->serial_lock);
		serial_tmp->serial_rb = RB_ROOT_CACHED;
		init_waitqueue_head(&serial_tmp->serial_io_wait);
	}

	rdev->serial = serial;
	set_bit(CollisionCheck, &rdev->flags);

	return 0;
}

static int rdevs_init_serial(struct mddev *mddev)
{
	struct md_rdev *rdev;
	int ret = 0;

	rdev_for_each(rdev, mddev) {
		ret = rdev_init_serial(rdev);
		if (ret)
			break;
	}

	/* Free all resources if pool is not existed */
	if (ret && !mddev->serial_info_pool)
		rdevs_uninit_serial(mddev);

	return ret;
}

/*
 * rdev needs to enable serial stuffs if it meets the conditions:
 * 1. it is multi-queue device flaged with writemostly.
 * 2. the write-behind mode is enabled.
 */
static int rdev_need_serial(struct md_rdev *rdev)
{
	return (rdev && rdev->mddev->bitmap_info.max_write_behind > 0 &&
		rdev->bdev->bd_disk->queue->nr_hw_queues != 1 &&
		test_bit(WriteMostly, &rdev->flags));
}

/*
 * Init resource for rdev(s), then create serial_info_pool if:
 * 1. rdev is the first device which return true from rdev_enable_serial.
 * 2. rdev is NULL, means we want to enable serialization for all rdevs.
 */
void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
			      bool is_suspend)
{
	int ret = 0;

	if (rdev && !rdev_need_serial(rdev) &&
	    !test_bit(CollisionCheck, &rdev->flags))
		return;

	if (!is_suspend)
		mddev_suspend(mddev);

	if (!rdev)
		ret = rdevs_init_serial(mddev);
	else
		ret = rdev_init_serial(rdev);
	if (ret)
		goto abort;

	if (mddev->serial_info_pool == NULL) {
		/*
		 * already in memalloc noio context by
		 * mddev_suspend()
		 */
		mddev->serial_info_pool =
			mempool_create_kmalloc_pool(NR_SERIAL_INFOS,
						sizeof(struct serial_info));
		if (!mddev->serial_info_pool) {
			rdevs_uninit_serial(mddev);
			pr_err("can't alloc memory pool for serialization\n");
		}
	}

abort:
	if (!is_suspend)
		mddev_resume(mddev);
}

/*
 * Free resource from rdev(s), and destroy serial_info_pool under conditions:
 * 1. rdev is the last device flaged with CollisionCheck.
 * 2. when bitmap is destroyed while policy is not enabled.
 * 3. for disable policy, the pool is destroyed only when no rdev needs it.
 */
void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
			       bool is_suspend)
{
	if (rdev && !test_bit(CollisionCheck, &rdev->flags))
		return;

	if (mddev->serial_info_pool) {
		struct md_rdev *temp;
		int num = 0; /* used to track if other rdevs need the pool */

		if (!is_suspend)
			mddev_suspend(mddev);
		rdev_for_each(temp, mddev) {
			if (!rdev) {
				if (!mddev->serialize_policy ||
				    !rdev_need_serial(temp))
					rdev_uninit_serial(temp);
				else
					num++;
			} else if (temp != rdev &&
				   test_bit(CollisionCheck, &temp->flags))
				num++;
		}

		if (rdev)
			rdev_uninit_serial(rdev);

		if (num)
			pr_info("The mempool could be used by other devices\n");
		else {
			mempool_destroy(mddev->serial_info_pool);
			mddev->serial_info_pool = NULL;
		}
		if (!is_suspend)
			mddev_resume(mddev);
	}
}

static struct ctl_table_header *raid_table_header;

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

static int start_readonly;

/*
 * The original mechanism for creating an md device is to create
 * a device node in /dev and to open it.  This causes races with device-close.
 * The preferred method is to write to the "new_array" module parameter.
 * This can avoid races.
 * Setting create_on_open to false disables the original mechanism
 * so all the races disappear.
 */
static bool create_on_open = true;

/*
 * 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(void)
{
	atomic_inc(&md_event_count);
	wake_up(&md_event_waiters);
}
EXPORT_SYMBOL_GPL(md_new_event);

/*
 * 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);

/* Rather than calling directly into the personality make_request function,
 * IO requests come here first so that we can check if the device is
 * being suspended pending a reconfiguration.
 * We hold a refcount over the call to ->make_request.  By the time that
 * call has finished, the bio has been linked into some internal structure
 * and so is visible to ->quiesce(), so we don't need the refcount any more.
 */
static bool is_suspended(struct mddev *mddev, struct bio *bio)
{
	if (is_md_suspended(mddev))
		return true;
	if (bio_data_dir(bio) != WRITE)
		return false;
	if (mddev->suspend_lo >= mddev->suspend_hi)
		return false;
	if (bio->bi_iter.bi_sector >= mddev->suspend_hi)
		return false;
	if (bio_end_sector(bio) < mddev->suspend_lo)
		return false;
	return true;
}

void md_handle_request(struct mddev *mddev, struct bio *bio)
{
check_suspended:
	if (is_suspended(mddev, bio)) {
		DEFINE_WAIT(__wait);
		/* Bail out if REQ_NOWAIT is set for the bio */
		if (bio->bi_opf & REQ_NOWAIT) {
			bio_wouldblock_error(bio);
			return;
		}
		for (;;) {
			prepare_to_wait(&mddev->sb_wait, &__wait,
					TASK_UNINTERRUPTIBLE);
			if (!is_suspended(mddev, bio))
				break;
			schedule();
		}
		finish_wait(&mddev->sb_wait, &__wait);
	}
	if (!percpu_ref_tryget_live(&mddev->active_io))
		goto check_suspended;

	if (!mddev->pers->make_request(mddev, bio)) {
		percpu_ref_put(&mddev->active_io);
		goto check_suspended;
	}

	percpu_ref_put(&mddev->active_io);
}
EXPORT_SYMBOL(md_handle_request);

static void md_submit_bio(struct bio *bio)
{
	const int rw = bio_data_dir(bio);
	struct mddev *mddev = bio->bi_bdev->bd_disk->private_data;

	if (mddev == NULL || mddev->pers == NULL) {
		bio_io_error(bio);
		return;
	}

	if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
		bio_io_error(bio);
		return;
	}

	bio = bio_split_to_limits(bio);
	if (!bio)
		return;

	if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) {
		if (bio_sectors(bio) != 0)
			bio->bi_status = BLK_STS_IOERR;
		bio_endio(bio);
		return;
	}

	/* bio could be mergeable after passing to underlayer */
	bio->bi_opf &= ~REQ_NOMERGE;

	md_handle_request(mddev, bio);
}

/* mddev_suspend makes sure no new requests are submitted
 * to the device, and that any requests that have been submitted
 * are completely handled.
 * Once mddev_detach() is called and completes, the module will be
 * completely unused.
 */
void mddev_suspend(struct mddev *mddev)
{
	struct md_thread *thread = rcu_dereference_protected(mddev->thread,
			lockdep_is_held(&mddev->reconfig_mutex));

	WARN_ON_ONCE(thread && current == thread->tsk);
	if (mddev->suspended++)
		return;
	wake_up(&mddev->sb_wait);
	set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags);
	percpu_ref_kill(&mddev->active_io);

	if (mddev->pers->prepare_suspend)
		mddev->pers->prepare_suspend(mddev);

	wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io));
	clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags);
	wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags));

	del_timer_sync(&mddev->safemode_timer);
	/* restrict memory reclaim I/O during raid array is suspend */
	mddev->noio_flag = memalloc_noio_save();
}
EXPORT_SYMBOL_GPL(mddev_suspend);

void mddev_resume(struct mddev *mddev)
{
	lockdep_assert_held(&mddev->reconfig_mutex);
	if (--mddev->suspended)
		return;

	/* entred the memalloc scope from mddev_suspend() */
	memalloc_noio_restore(mddev->noio_flag);

	percpu_ref_resurrect(&mddev->active_io);
	wake_up(&mddev->sb_wait);

	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	md_wakeup_thread(mddev->thread);
	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
}
EXPORT_SYMBOL_GPL(mddev_resume);

/*
 * Generic flush handling for md
 */

static void md_end_flush(struct bio *bio)
{
	struct md_rdev *rdev = bio->bi_private;
	struct mddev *mddev = rdev->mddev;

	bio_put(bio);

	rdev_dec_pending(rdev, mddev);

	if (atomic_dec_and_test(&mddev->flush_pending)) {
		/* The pre-request flush has finished */
		queue_work(md_wq, &mddev->flush_work);
	}
}

static void md_submit_flush_data(struct work_struct *ws);

static void submit_flushes(struct work_struct *ws)
{
	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
	struct md_rdev *rdev;

	mddev->start_flush = ktime_get_boottime();
	INIT_WORK(&mddev->flush_work, md_submit_flush_data);
	atomic_set(&mddev->flush_pending, 1);
	rcu_read_lock();
	rdev_for_each_rcu(rdev, mddev)
		if (rdev->raid_disk >= 0 &&
		    !test_bit(Faulty, &rdev->flags)) {
			/* Take two references, one is dropped
			 * when request finishes, one after
			 * we reclaim rcu_read_lock
			 */
			struct bio *bi;
			atomic_inc(&rdev->nr_pending);
			atomic_inc(&rdev->nr_pending);
			rcu_read_unlock();
			bi = bio_alloc_bioset(rdev->bdev, 0,
					      REQ_OP_WRITE | REQ_PREFLUSH,
					      GFP_NOIO, &mddev->bio_set);
			bi->bi_end_io = md_end_flush;
			bi->bi_private = rdev;
			atomic_inc(&mddev->flush_pending);
			submit_bio(bi);
			rcu_read_lock();
			rdev_dec_pending(rdev, mddev);
		}
	rcu_read_unlock();
	if (atomic_dec_and_test(&mddev->flush_pending))
		queue_work(md_wq, &mddev->flush_work);
}

static void md_submit_flush_data(struct work_struct *ws)
{
	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
	struct bio *bio = mddev->flush_bio;

	/*
	 * must reset flush_bio before calling into md_handle_request to avoid a
	 * deadlock, because other bios passed md_handle_request suspend check
	 * could wait for this and below md_handle_request could wait for those
	 * bios because of suspend check
	 */
	spin_lock_irq(&mddev->lock);
	mddev->prev_flush_start = mddev->start_flush;
	mddev->flush_bio = NULL;
	spin_unlock_irq(&mddev->lock);
	wake_up(&mddev->sb_wait);

	if (bio->bi_iter.bi_size == 0) {
		/* an empty barrier - all done */
		bio_endio(bio);
	} else {
		bio->bi_opf &= ~REQ_PREFLUSH;
		md_handle_request(mddev, bio);
	}
}

/*
 * Manages consolidation of flushes and submitting any flushes needed for
 * a bio with REQ_PREFLUSH.  Returns true if the bio is finished or is
 * being finished in another context.  Returns false if the flushing is
 * complete but still needs the I/O portion of the bio to be processed.
 */
bool md_flush_request(struct mddev *mddev, struct bio *bio)
{
	ktime_t req_start = ktime_get_boottime();
	spin_lock_irq(&mddev->lock);
	/* flush requests wait until ongoing flush completes,
	 * hence coalescing all the pending requests.
	 */
	wait_event_lock_irq(mddev->sb_wait,
			    !mddev->flush_bio ||
			    ktime_before(req_start, mddev->prev_flush_start),
			    mddev->lock);
	/* new request after previous flush is completed */
	if (ktime_after(req_start, mddev->prev_flush_start)) {
		WARN_ON(mddev->flush_bio);
		mddev->flush_bio = bio;
		bio = NULL;
	}
	spin_unlock_irq(&mddev->lock);

	if (!bio) {
		INIT_WORK(&mddev->flush_work, submit_flushes);
		queue_work(md_wq, &mddev->flush_work);
	} else {
		/* flush was performed for some other bio while we waited. */
		if (bio->bi_iter.bi_size == 0)
			/* an empty barrier - all done */
			bio_endio(bio);
		else {
			bio->bi_opf &= ~REQ_PREFLUSH;
			return false;
		}
	}
	return true;
}
EXPORT_SYMBOL(md_flush_request);

static inline struct mddev *mddev_get(struct mddev *mddev)
{
	lockdep_assert_held(&all_mddevs_lock);

	if (test_bit(MD_DELETED, &mddev->flags))
		return NULL;
	atomic_inc(&mddev->active);
	return mddev;
}

static void mddev_delayed_delete(struct work_struct *ws);

void mddev_put(struct mddev *mddev)
{
	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
		return;
	if (!mddev->raid_disks && list_empty(&mddev->disks) &&
	    mddev->ctime == 0 && !mddev->hold_active) {
		/* Array is not configured at all, and not held active,
		 * so destroy it */
		set_bit(MD_DELETED, &mddev->flags);

		/*
		 * Call queue_work inside the spinlock so that
		 * flush_workqueue() after mddev_find will succeed in waiting
		 * for the work to be done.
		 */
		INIT_WORK(&mddev->del_work, mddev_delayed_delete);
		queue_work(md_misc_wq, &mddev->del_work);
	}
	spin_unlock(&all_mddevs_lock);
}

static void md_safemode_timeout(struct timer_list *t);

void mddev_init(struct mddev *mddev)
{
	mutex_init(&mddev->open_mutex);
	mutex_init(&mddev->reconfig_mutex);
	mutex_init(&mddev->sync_mutex);
	mutex_init(&mddev->bitmap_info.mutex);
	INIT_LIST_HEAD(&mddev->disks);
	INIT_LIST_HEAD(&mddev->all_mddevs);
	INIT_LIST_HEAD(&mddev->deleting);
	timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0);
	atomic_set(&mddev->active, 1);
	atomic_set(&mddev->openers, 0);
	atomic_set(&mddev->sync_seq, 0);
	spin_lock_init(&mddev->lock);
	atomic_set(&mddev->flush_pending, 0);
	init_waitqueue_head(&mddev->sb_wait);
	init_waitqueue_head(&mddev->recovery_wait);
	mddev->reshape_position = MaxSector;
	mddev->reshape_backwards = 0;
	mddev->last_sync_action = "none";
	mddev->resync_min = 0;
	mddev->resync_max = MaxSector;
	mddev->level = LEVEL_NONE;
}
EXPORT_SYMBOL_GPL(mddev_init);

static struct mddev *mddev_find_locked(dev_t unit)
{
	struct mddev *mddev;

	list_for_each_entry(mddev, &all_mddevs, all_mddevs)
		if (mddev->unit == unit)
			return mddev;

	return NULL;
}

/* find an unused unit number */
static dev_t mddev_alloc_unit(void)
{
	static int next_minor = 512;
	int start = next_minor;
	bool is_free = 0;
	dev_t dev = 0;

	while (!is_free) {
		dev = MKDEV(MD_MAJOR, next_minor);
		next_minor++;
		if (next_minor > MINORMASK)
			next_minor = 0;
		if (next_minor == start)
			return 0;		/* Oh dear, all in use. */
		is_free = !mddev_find_locked(dev);
	}

	return dev;
}

static struct mddev *mddev_alloc(dev_t unit)
{
	struct mddev *new;
	int error;

	if (unit && MAJOR(unit) != MD_MAJOR)
		unit &= ~((1 << MdpMinorShift) - 1);

	new = kzalloc(sizeof(*new), GFP_KERNEL);
	if (!new)
		return ERR_PTR(-ENOMEM);
	mddev_init(new);

	spin_lock(&all_mddevs_lock);
	if (unit) {
		error = -EEXIST;
		if (mddev_find_locked(unit))
			goto out_free_new;
		new->unit = unit;
		if (MAJOR(unit) == MD_MAJOR)
			new->md_minor = MINOR(unit);
		else
			new->md_minor = MINOR(unit) >> MdpMinorShift;
		new->hold_active = UNTIL_IOCTL;
	} else {
		error = -ENODEV;
		new->unit = mddev_alloc_unit();
		if (!new->unit)
			goto out_free_new;
		new->md_minor = MINOR(new->unit);
		new->hold_active = UNTIL_STOP;
	}

	list_add(&new->all_mddevs, &all_mddevs);
	spin_unlock(&all_mddevs_lock);
	return new;
out_free_new:
	spin_unlock(&all_mddevs_lock);
	kfree(new);
	return ERR_PTR(error);
}

static void mddev_free(struct mddev *mddev)
{
	spin_lock(&all_mddevs_lock);
	list_del(&mddev->all_mddevs);
	spin_unlock(&all_mddevs_lock);

	kfree(mddev);
}

static const struct attribute_group md_redundancy_group;

void mddev_unlock(struct mddev *mddev)
{
	struct md_rdev *rdev;
	struct md_rdev *tmp;
	LIST_HEAD(delete);

	if (!list_empty(&mddev->deleting))
		list_splice_init(&mddev->deleting, &delete);

	if (mddev->to_remove) {
		/* These cannot be removed under reconfig_mutex as
		 * an access to the files will try to take reconfig_mutex
		 * while holding the file unremovable, which leads to
		 * a deadlock.
		 * So hold set sysfs_active while the remove in happeing,
		 * and anything else which might set ->to_remove or my
		 * otherwise change the sysfs namespace will fail with
		 * -EBUSY if sysfs_active is still set.
		 * We set sysfs_active under reconfig_mutex and elsewhere
		 * test it under the same mutex to ensure its correct value
		 * is seen.
		 */
		const struct attribute_group *to_remove = mddev->to_remove;
		mddev->to_remove = NULL;
		mddev->sysfs_active = 1;
		mutex_unlock(&mddev->reconfig_mutex);

		if (mddev->kobj.sd) {
			if (to_remove != &md_redundancy_group)
				sysfs_remove_group(&mddev->kobj, to_remove);
			if (mddev->pers == NULL ||
			    mddev->pers->sync_request == NULL) {
				sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
				if (mddev->sysfs_action)
					sysfs_put(mddev->sysfs_action);
				if (mddev->sysfs_completed)
					sysfs_put(mddev->sysfs_completed);
				if (mddev->sysfs_degraded)
					sysfs_put(mddev->sysfs_degraded);
				mddev->sysfs_action = NULL;
				mddev->sysfs_completed = NULL;
				mddev->sysfs_degraded = NULL;
			}
		}
		mddev->sysfs_active = 0;
	} else
		mutex_unlock(&mddev->reconfig_mutex);

	md_wakeup_thread(mddev->thread);
	wake_up(&mddev->sb_wait);

	list_for_each_entry_safe(rdev, tmp, &delete, same_set) {
		list_del_init(&rdev->same_set);
		kobject_del(&rdev->kobj);
		export_rdev(rdev, mddev);
	}
}
EXPORT_SYMBOL_GPL(mddev_unlock);

struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr)
{
	struct md_rdev *rdev;

	rdev_for_each_rcu(rdev, mddev)
		if (rdev->desc_nr == nr)
			return rdev;

	return NULL;
}
EXPORT_SYMBOL_GPL(md_find_rdev_nr_rcu);

static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev)
{
	struct md_rdev *rdev;

	rdev_for_each(rdev, mddev)
		if (rdev->bdev->bd_dev == dev)
			return rdev;

	return NULL;
}

struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev)
{
	struct md_rdev *rdev;

	rdev_for_each_rcu(rdev, mddev)
		if (rdev->bdev->bd_dev == dev)
			return rdev;

	return NULL;
}
EXPORT_SYMBOL_GPL(md_find_rdev_rcu);

static struct md_personality *find_pers(int level, char *clevel)
{
	struct md_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;
}

/* return the offset of the super block in 512byte sectors */
static inline sector_t calc_dev_sboffset(struct md_rdev *rdev)
{
	return MD_NEW_SIZE_SECTORS(bdev_nr_sectors(rdev->bdev));
}

static int alloc_disk_sb(struct md_rdev *rdev)
{
	rdev->sb_page = alloc_page(GFP_KERNEL);
	if (!rdev->sb_page)
		return -ENOMEM;
	return 0;
}

void md_rdev_clear(struct md_rdev *rdev)
{
	if (rdev->sb_page) {
		put_page(rdev->sb_page);
		rdev->sb_loaded = 0;
		rdev->sb_page = NULL;
		rdev->sb_start = 0;
		rdev->sectors = 0;
	}
	if (rdev->bb_page) {
		put_page(rdev->bb_page);
		rdev->bb_page = NULL;
	}
	badblocks_exit(&rdev->badblocks);
}
EXPORT_SYMBOL_GPL(md_rdev_clear);

static void super_written(struct bio *bio)
{
	struct md_rdev *rdev = bio->bi_private;
	struct mddev *mddev = rdev->mddev;

	if (bio->bi_status) {
		pr_err("md: %s gets error=%d\n", __func__,
		       blk_status_to_errno(bio->bi_status));
		md_error(mddev, rdev);
		if (!test_bit(Faulty, &rdev->flags)
		    && (bio->bi_opf & MD_FAILFAST)) {
			set_bit(MD_SB_NEED_REWRITE, &mddev->sb_flags);
			set_bit(LastDev, &rdev->flags);
		}
	} else
		clear_bit(LastDev, &rdev->flags);

	bio_put(bio);

	rdev_dec_pending(rdev, mddev);

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

void md_super_write(struct mddev *mddev, struct md_rdev *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
	 */
	struct bio *bio;

	if (!page)
		return;

	if (test_bit(Faulty, &rdev->flags))
		return;

	bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev,
			       1,
			       REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA,
			       GFP_NOIO, &mddev->sync_set);

	atomic_inc(&rdev->nr_pending);

	bio->bi_iter.bi_sector = sector;
	__bio_add_page(bio, page, size, 0);
	bio->bi_private = rdev;
	bio->bi_end_io = super_written;

	if (test_bit(MD_FAILFAST_SUPPORTED, &mddev->flags) &&
	    test_bit(FailFast, &rdev->flags) &&
	    !test_bit(LastDev, &rdev->flags))
		bio->bi_opf |= MD_FAILFAST;

	atomic_inc(&mddev->pending_writes);
	submit_bio(bio);
}

int md_super_wait(struct mddev *mddev)
{
	/* wait for all superblock writes that were scheduled to complete */
	wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0);
	if (test_and_clear_bit(MD_SB_NEED_REWRITE, &mddev->sb_flags))
		return -EAGAIN;
	return 0;
}

int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
		 struct page *page, blk_opf_t opf, bool metadata_op)
{
	struct bio bio;
	struct bio_vec bvec;

	if (metadata_op && rdev->meta_bdev)
		bio_init(&bio, rdev->meta_bdev, &bvec, 1, opf);
	else
		bio_init(&bio, rdev->bdev, &bvec, 1, opf);

	if (metadata_op)
		bio.bi_iter.bi_sector = sector + rdev->sb_start;
	else if (rdev->mddev->reshape_position != MaxSector &&
		 (rdev->mddev->reshape_backwards ==
		  (sector >= rdev->mddev->reshape_position)))
		bio.bi_iter.bi_sector = sector + rdev->new_data_offset;
	else
		bio.bi_iter.bi_sector = sector + rdev->data_offset;
	__bio_add_page(&bio, page, size, 0);

	submit_bio_wait(&bio);

	return !bio.bi_status;
}
EXPORT_SYMBOL_GPL(sync_page_io);

static int read_disk_sb(struct md_rdev *rdev, int size)
{
	if (rdev->sb_loaded)
		return 0;

	if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, true))
		goto fail;
	rdev->sb_loaded = 1;
	return 0;

fail:
	pr_err("md: disabled device %pg, could not read superblock.\n",
	       rdev->bdev);
	return -EINVAL;
}

static int md_uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
{
	return	sb1->set_uuid0 == sb2->set_uuid0 &&
		sb1->set_uuid1 == sb2->set_uuid1 &&
		sb1->set_uuid2 == sb2->set_uuid2 &&
		sb1->set_uuid3 == sb2->set_uuid3;
}

static int md_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;
		goto abort;
	}

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

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

	ret = (memcmp(tmp1, tmp2, MD_SB_GENERIC_CONSTANT_WORDS * 4) == 0);
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(struct md_rdev *dev, struct md_rdev *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(struct mddev *mddev, struct md_rdev *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(struct mddev *mddev, struct md_rdev *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)(struct md_rdev *rdev,
					  struct md_rdev *refdev,
					  int minor_version);
	int		    (*validate_super)(struct mddev *mddev,
					      struct md_rdev *rdev);
	void		    (*sync_super)(struct mddev *mddev,
					  struct md_rdev *rdev);
	unsigned long long  (*rdev_size_change)(struct md_rdev *rdev,
						sector_t num_sectors);
	int		    (*allow_new_offset)(struct md_rdev *rdev,
						unsigned long long new_offset);
};

/*
 * Check that the given mddev has no bitmap.
 *
 * This function is called from the run method of all personalities that do not
 * support bitmaps. It prints an error message and returns non-zero if mddev
 * has a bitmap. Otherwise, it returns 0.
 *
 */
int md_check_no_bitmap(struct mddev *mddev)
{
	if (!mddev->bitmap_info.file && !mddev->bitmap_info.offset)
		return 0;
	pr_warn("%s: bitmaps are not supported for %s\n",
		mdname(mddev), mddev->pers->name);
	return 1;
}
EXPORT_SYMBOL(md_check_no_bitmap);

/*
 * load_super for 0.90.0
 */
static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version)
{
	mdp_super_t *sb;
	int ret;
	bool spare_disk = true;

	/*
	 * Calculate the position of the superblock (512byte sectors),
	 * it's at the end of the disk.
	 *
	 * It also happens to be a multiple of 4Kb.
	 */
	rdev->sb_start = calc_dev_sboffset(rdev);

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

	ret = -EINVAL;

	sb = page_address(rdev->sb_page);

	if (sb->md_magic != MD_SB_MAGIC) {
		pr_warn("md: invalid raid superblock magic on %pg\n",
			rdev->bdev);
		goto abort;
	}

	if (sb->major_version != 0 ||
	    sb->minor_version < 90 ||
	    sb->minor_version > 91) {
		pr_warn("Bad version number %d.%d on %pg\n",
			sb->major_version, sb->minor_version, rdev->bdev);
		goto abort;
	}

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

	if (md_csum_fold(calc_sb_csum(sb)) != md_csum_fold(sb->sb_csum)) {
		pr_warn("md: invalid superblock checksum on %pg\n", rdev->bdev);
		goto abort;
	}

	rdev->preferred_minor = sb->md_minor;
	rdev->data_offset = 0;
	rdev->new_data_offset = 0;
	rdev->sb_size = MD_SB_BYTES;
	rdev->badblocks.shift = -1;

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

	/* not spare disk, or LEVEL_MULTIPATH */
	if (sb->level == LEVEL_MULTIPATH ||
		(rdev->desc_nr >= 0 &&
		 rdev->desc_nr < MD_SB_DISKS &&
		 sb->disks[rdev->desc_nr].state &
		 ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))))
		spare_disk = false;

	if (!refdev) {
		if (!spare_disk)
			ret = 1;
		else
			ret = 0;
	} else {
		__u64 ev1, ev2;
		mdp_super_t *refsb = page_address(refdev->sb_page);
		if (!md_uuid_equal(refsb, sb)) {
			pr_warn("md: %pg has different UUID to %pg\n",
				rdev->bdev, refdev->bdev);
			goto abort;
		}
		if (!md_sb_equal(refsb, sb)) {
			pr_warn("md: %pg has same UUID but different superblock to %pg\n",
				rdev->bdev, refdev->bdev);
			goto abort;
		}
		ev1 = md_event(sb);
		ev2 = md_event(refsb);

		if (!spare_disk && ev1 > ev2)
			ret = 1;
		else
			ret = 0;
	}
	rdev->sectors = rdev->sb_start;
	/* Limit to 4TB as metadata cannot record more than that.
	 * (not needed for Linear and RAID0 as metadata doesn't
	 * record this size)
	 */
	if ((u64)rdev->sectors >= (2ULL << 32) && sb->level >= 1)
		rdev->sectors = (sector_t)(2ULL << 32) - 2;

	if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
		/* "this cannot possibly happen" ... */
		ret = -EINVAL;

 abort:
	return ret;
}

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

	rdev->raid_disk = -1;
	clear_bit(Faulty, &rdev->flags);
	clear_bit(In_sync, &rdev->flags);
	clear_bit(Bitmap_sync, &rdev->flags);
	clear_bit(WriteMostly, &rdev->flags);

	if (mddev->raid_disks == 0) {
		mddev->major_version = 0;
		mddev->minor_version = sb->minor_version;
		mddev->patch_version = sb->patch_version;
		mddev->external = 0;
		mddev->chunk_sectors = sb->chunk_size >> 9;
		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->dev_sectors = ((sector_t)sb->size) * 2;
		mddev->events = ev1;
		mddev->bitmap_info.offset = 0;
		mddev->bitmap_info.space = 0;
		/* bitmap can use 60 K after the 4K superblocks */
		mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
		mddev->bitmap_info.default_space = 64*2 - (MD_SB_BYTES >> 9);
		mddev->reshape_backwards = 0;

		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_sectors = sb->new_chunk >> 9;
			if (mddev->delta_disks < 0)
				mddev->reshape_backwards = 1;
		} else {
			mddev->reshape_position = MaxSector;
			mddev->delta_disks = 0;
			mddev->new_level = mddev->level;
			mddev->new_layout = mddev->layout;
			mddev->new_chunk_sectors = mddev->chunk_sectors;
		}
		if (mddev->level == 0)
			mddev->layout = -1;

		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_info.file == NULL) {
			mddev->bitmap_info.offset =
				mddev->bitmap_info.default_offset;
			mddev->bitmap_info.space =
				mddev->bitmap_info.default_space;
		}

	} else if (mddev->pers == NULL) {
		/* Insist on good event counter while assembling, except
		 * for spares (which don't need an event count) */
		++ev1;
		if (sb->disks[rdev->desc_nr].state & (
			    (1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))
			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;
		if (ev1 < mddev->events)
			set_bit(Bitmap_sync, &rdev->flags);
	} 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;
			rdev->saved_raid_disk = desc->raid_disk;
		} else if (desc->state & (1<<MD_DISK_ACTIVE)) {
			/* active but not in sync implies recovery up to
			 * reshape position.  We don't know exactly where
			 * that is, so set to zero for now */
			if (mddev->minor_version >= 91) {
				rdev->recovery_offset = 0;
				rdev->raid_disk = desc->raid_disk;
			}
		}
		if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
			set_bit(WriteMostly, &rdev->flags);
		if (desc->state & (1<<MD_DISK_FAILFAST))
			set_bit(FailFast, &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(struct mddev *mddev, struct md_rdev *rdev)
{
	mdp_super_t *sb;
	struct md_rdev *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 = 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 = clamp_t(time64_t, mddev->ctime, 0, U32_MAX);
	sb->level = mddev->level;
	sb->size = mddev->dev_sectors / 2;
	sb->raid_disks = mddev->raid_disks;
	sb->md_minor = mddev->md_minor;
	sb->not_persistent = 0;
	sb->utime = clamp_t(time64_t, mddev->utime, 0, U32_MAX);
	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_sectors << 9;
	}
	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_sectors << 9;

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

	sb->disks[0].state = (1<<MD_DISK_REMOVED);
	rdev_for_each(rdev2, mddev) {
		mdp_disk_t *d;
		int desc_nr;
		int is_active = test_bit(In_sync, &rdev2->flags);

		if (rdev2->raid_disk >= 0 &&
		    sb->minor_version >= 91)
			/* we have nowhere to store the recovery_offset,
			 * but if it is not below the reshape_position,
			 * we can piggy-back on that.
			 */
			is_active = 1;
		if (rdev2->raid_disk < 0 ||
		    test_bit(Faulty, &rdev2->flags))
			is_active = 0;
		if (is_active)
			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 (is_active)
			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 (is_active) {
			d->state = (1<<MD_DISK_ACTIVE);
			if (test_bit(In_sync, &rdev2->flags))
				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);
		if (test_bit(FailFast, &rdev2->flags))
			d->state |= (1<<MD_DISK_FAILFAST);
	}
	/* 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);
}

/*
 * rdev_size_change for 0.90.0
 */
static unsigned long long
super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
{
	if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
		return 0; /* component must fit device */
	if (rdev->mddev->bitmap_info.offset)
		return 0; /* can't move bitmap */
	rdev->sb_start = calc_dev_sboffset(rdev);
	if (!num_sectors || num_sectors > rdev->sb_start)
		num_sectors = rdev->sb_start;
	/* Limit to 4TB as metadata cannot record more than that.
	 * 4TB == 2^32 KB, or 2*2^32 sectors.
	 */
	if ((u64)num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
		num_sectors = (sector_t)(2ULL << 32) - 2;
	do {
		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
		       rdev->sb_page);
	} while (md_super_wait(rdev->mddev) < 0);
	return num_sectors;
}

static int
super_90_allow_new_offset(struct md_rdev *rdev, unsigned long long new_offset)
{
	/* non-zero offset changes not possible with v0.90 */
	return new_offset == 0;
}

/*
 * 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;

	disk_csum = sb->sb_csum;
	sb->sb_csum = 0;
	newcsum = 0;
	for (; 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(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version)
{
	struct mdp_superblock_1 *sb;
	int ret;
	sector_t sb_start;
	sector_t sectors;
	int bmask;
	bool spare_disk = true;

	/*
	 * Calculate the position of the superblock in 512byte sectors.
	 * 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_start = bdev_nr_sectors(rdev->bdev) - 8 * 2;
		sb_start &= ~(sector_t)(4*2-1);
		break;
	case 1:
		sb_start = 0;
		break;
	case 2:
		sb_start = 8;
		break;
	default:
		return -EINVAL;
	}
	rdev->sb_start = sb_start;

	/* 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 = 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_start ||
	    (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
		return -EINVAL;

	if (calc_sb_1_csum(sb) != sb->sb_csum) {
		pr_warn("md: invalid superblock checksum on %pg\n",
			rdev->bdev);
		return -EINVAL;
	}
	if (le64_to_cpu(sb->data_size) < 10) {
		pr_warn("md: data_size too small on %pg\n",
			rdev->bdev);
		return -EINVAL;
	}
	if (sb->pad0 ||
	    sb->pad3[0] ||
	    memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1])))
		/* Some padding is non-zero, might be a new feature */
		return -EINVAL;

	rdev->preferred_minor = 0xffff;
	rdev->data_offset = le64_to_cpu(sb->data_offset);
	rdev->new_data_offset = rdev->data_offset;
	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE) &&
	    (le32_to_cpu(sb->feature_map) & MD_FEATURE_NEW_OFFSET))
		rdev->new_data_offset += (s32)le32_to_cpu(sb->new_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_logical_block_size(rdev->bdev->bd_disk->queue)-1;
	if (rdev->sb_size & bmask)
		rdev->sb_size = (rdev->sb_size | bmask) + 1;

	if (minor_version
	    && rdev->data_offset < sb_start + (rdev->sb_size/512))
		return -EINVAL;
	if (minor_version
	    && rdev->new_data_offset < sb_start + (rdev->sb_size/512))
		return -EINVAL;

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

	if (!rdev->bb_page) {
		rdev->bb_page = alloc_page(GFP_KERNEL);
		if (!rdev->bb_page)
			return -ENOMEM;
	}
	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BAD_BLOCKS) &&
	    rdev->badblocks.count == 0) {
		/* need to load the bad block list.
		 * Currently we limit it to one page.
		 */
		s32 offset;
		sector_t bb_sector;
		__le64 *bbp;
		int i;
		int sectors = le16_to_cpu(sb->bblog_size);
		if (sectors > (PAGE_SIZE / 512))
			return -EINVAL;
		offset = le32_to_cpu(sb->bblog_offset);
		if (offset == 0)
			return -EINVAL;
		bb_sector = (long long)offset;
		if (!sync_page_io(rdev, bb_sector, sectors << 9,
				  rdev->bb_page, REQ_OP_READ, true))
			return -EIO;
		bbp = (__le64 *)page_address(rdev->bb_page);
		rdev->badblocks.shift = sb->bblog_shift;
		for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) {
			u64 bb = le64_to_cpu(*bbp);
			int count = bb & (0x3ff);
			u64 sector = bb >> 10;
			sector <<= sb->bblog_shift;
			count <<= sb->bblog_shift;
			if (bb + 1 == 0)
				break;
			if (badblocks_set(&rdev->badblocks, sector, count, 1))
				return -EINVAL;
		}
	} else if (sb->bblog_offset != 0)
		rdev->badblocks.shift = 0;

	if ((le32_to_cpu(sb->feature_map) &
	    (MD_FEATURE_PPL | MD_FEATURE_MULTIPLE_PPLS))) {
		rdev->ppl.offset = (__s16)le16_to_cpu(sb->ppl.offset);
		rdev->ppl.size = le16_to_cpu(sb->ppl.size);
		rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset;
	}

	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) &&
	    sb->level != 0)
		return -EINVAL;

	/* not spare disk, or LEVEL_MULTIPATH */
	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) ||
		(rdev->desc_nr >= 0 &&
		rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
		(le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
		 le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)))
		spare_disk = false;

	if (!refdev) {
		if (!spare_disk)
			ret = 1;
		else
			ret = 0;
	} else {
		__u64 ev1, ev2;
		struct mdp_superblock_1 *refsb = 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) {
			pr_warn("md: %pg has strangely different superblock to %pg\n",
				rdev->bdev,
				refdev->bdev);
			return -EINVAL;
		}
		ev1 = le64_to_cpu(sb->events);
		ev2 = le64_to_cpu(refsb->events);

		if (!spare_disk && ev1 > ev2)
			ret = 1;
		else
			ret = 0;
	}
	if (minor_version)
		sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset;
	else
		sectors = rdev->sb_start;
	if (sectors < le64_to_cpu(sb->data_size))
		return -EINVAL;
	rdev->sectors = le64_to_cpu(sb->data_size);
	return ret;
}

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

	rdev->raid_disk = -1;
	clear_bit(Faulty, &rdev->flags);
	clear_bit(In_sync, &rdev->flags);
	clear_bit(Bitmap_sync, &rdev->flags);
	clear_bit(WriteMostly, &rdev->flags);

	if (mddev->raid_disks == 0) {
		mddev->major_version = 1;
		mddev->patch_version = 0;
		mddev->external = 0;
		mddev->chunk_sectors = le32_to_cpu(sb->chunksize);
		mddev->ctime = le64_to_cpu(sb->ctime);
		mddev->utime = le64_to_cpu(sb->utime);
		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->dev_sectors = le64_to_cpu(sb->size);
		mddev->events = ev1;
		mddev->bitmap_info.offset = 0;
		mddev->bitmap_info.space = 0;
		/* Default location for bitmap is 1K after superblock
		 * using 3K - total of 4K
		 */
		mddev->bitmap_info.default_offset = 1024 >> 9;
		mddev->bitmap_info.default_space = (4096-1024) >> 9;
		mddev->reshape_backwards = 0;

		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_info.file == NULL) {
			mddev->bitmap_info.offset =
				(__s32)le32_to_cpu(sb->bitmap_offset);
			/* Metadata doesn't record how much space is available.
			 * For 1.0, we assume we can use up to the superblock
			 * if before, else to 4K beyond superblock.
			 * For others, assume no change is possible.
			 */
			if (mddev->minor_version > 0)
				mddev->bitmap_info.space = 0;
			else if (mddev->bitmap_info.offset > 0)
				mddev->bitmap_info.space =
					8 - mddev->bitmap_info.offset;
			else
				mddev->bitmap_info.space =
					-mddev->bitmap_info.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_sectors = le32_to_cpu(sb->new_chunk);
			if (mddev->delta_disks < 0 ||
			    (mddev->delta_disks == 0 &&
			     (le32_to_cpu(sb->feature_map)
			      & MD_FEATURE_RESHAPE_BACKWARDS)))
				mddev->reshape_backwards = 1;
		} else {
			mddev->reshape_position = MaxSector;
			mddev->delta_disks = 0;
			mddev->new_level = mddev->level;
			mddev->new_layout = mddev->layout;
			mddev->new_chunk_sectors = mddev->chunk_sectors;
		}

		if (mddev->level == 0 &&
		    !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT))
			mddev->layout = -1;

		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
			set_bit(MD_HAS_JOURNAL, &mddev->flags);

		if (le32_to_cpu(sb->feature_map) &
		    (MD_FEATURE_PPL | MD_FEATURE_MULTIPLE_PPLS)) {
			if (le32_to_cpu(sb->feature_map) &
			    (MD_FEATURE_BITMAP_OFFSET | MD_FEATURE_JOURNAL))
				return -EINVAL;
			if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL) &&
			    (le32_to_cpu(sb->feature_map) &
					    MD_FEATURE_MULTIPLE_PPLS))
				return -EINVAL;
			set_bit(MD_HAS_PPL, &mddev->flags);
		}
	} else if (mddev->pers == NULL) {
		/* Insist of good event counter while assembling, except for
		 * spares (which don't need an event count) */
		++ev1;
		if (rdev->desc_nr >= 0 &&
		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
		    (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
		     le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))
			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;
		if (ev1 < mddev->events)
			set_bit(Bitmap_sync, &rdev->flags);
	} 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;
		if (rdev->desc_nr < 0 ||
		    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
			role = MD_DISK_ROLE_SPARE;
			rdev->desc_nr = -1;
		} else
			role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
		switch(role) {
		case MD_DISK_ROLE_SPARE: /* spare */
			break;
		case MD_DISK_ROLE_FAULTY: /* faulty */
			set_bit(Faulty, &rdev->flags);
			break;
		case MD_DISK_ROLE_JOURNAL: /* journal device */
			if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) {
				/* journal device without journal feature */
				pr_warn("md: journal device provided without journal feature, ignoring the device\n");
				return -EINVAL;
			}
			set_bit(Journal, &rdev->flags);
			rdev->journal_tail = le64_to_cpu(sb->journal_tail);
			rdev->raid_disk = 0;
			break;
		default:
			rdev->saved_raid_disk = role;
			if ((le32_to_cpu(sb->feature_map) &
			     MD_FEATURE_RECOVERY_OFFSET)) {
				rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
				if (!(le32_to_cpu(sb->feature_map) &
				      MD_FEATURE_RECOVERY_BITMAP))
					rdev->saved_raid_disk = -1;
			} else {
				/*
				 * If the array is FROZEN, then the device can't
				 * be in_sync with rest of array.
				 */
				if (!test_bit(MD_RECOVERY_FROZEN,
					      &mddev->recovery))
					set_bit(In_sync, &rdev->flags);
			}
			rdev->raid_disk = role;
			break;
		}
		if (sb->devflags & WriteMostly1)
			set_bit(WriteMostly, &rdev->flags);
		if (sb->devflags & FailFast1)
			set_bit(FailFast, &rdev->flags);
		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
			set_bit(Replacement, &rdev->flags);
	} else /* MULTIPATH are always insync */
		set_bit(In_sync, &rdev->flags);

	return 0;
}

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

	sb = page_address(rdev->sb_page);

	sb->feature_map = 0;
	sb->pad0 = 0;
	sb->recovery_offset = cpu_to_le64(0);
	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 if (test_bit(MD_JOURNAL_CLEAN, &mddev->flags))
		sb->resync_offset = cpu_to_le64(MaxSector);
	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->dev_sectors);
	sb->chunksize = cpu_to_le32(mddev->chunk_sectors);
	sb->level = cpu_to_le32(mddev->level);
	sb->layout = cpu_to_le32(mddev->layout);
	if (test_bit(FailFast, &rdev->flags))
		sb->devflags |= FailFast1;
	else
		sb->devflags &= ~FailFast1;

	if (test_bit(WriteMostly, &rdev->flags))
		sb->devflags |= WriteMostly1;
	else
		sb->devflags &= ~WriteMostly1;
	sb->data_offset = cpu_to_le64(rdev->data_offset);
	sb->data_size = cpu_to_le64(rdev->sectors);

	if (mddev->bitmap && mddev->bitmap_info.file == NULL) {
		sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_info.offset);
		sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
	}

	if (rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags) &&
	    !test_bit(In_sync, &rdev->flags)) {
		sb->feature_map |=
			cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
		sb->recovery_offset =
			cpu_to_le64(rdev->recovery_offset);
		if (rdev->saved_raid_disk >= 0 && mddev->bitmap)
			sb->feature_map |=
				cpu_to_le32(MD_FEATURE_RECOVERY_BITMAP);
	}
	/* Note: recovery_offset and journal_tail share space  */
	if (test_bit(Journal, &rdev->flags))
		sb->journal_tail = cpu_to_le64(rdev->journal_tail);
	if (test_bit(Replacement, &rdev->flags))
		sb->feature_map |=
			cpu_to_le32(MD_FEATURE_REPLACEMENT);

	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_sectors);
		if (mddev->delta_disks == 0 &&
		    mddev->reshape_backwards)
			sb->feature_map
				|= cpu_to_le32(MD_FEATURE_RESHAPE_BACKWARDS);
		if (rdev->new_data_offset != rdev->data_offset) {
			sb->feature_map
				|= cpu_to_le32(MD_FEATURE_NEW_OFFSET);
			sb->new_offset = cpu_to_le32((__u32)(rdev->new_data_offset
							     - rdev->data_offset));
		}
	}

	if (mddev_is_clustered(mddev))
		sb->feature_map |= cpu_to_le32(MD_FEATURE_CLUSTERED);

	if (rdev->badblocks.count == 0)
		/* Nothing to do for bad blocks*/ ;
	else if (sb->bblog_offset == 0)
		/* Cannot record bad blocks on this device */
		md_error(mddev, rdev);
	else {
		struct badblocks *bb = &rdev->badblocks;
		__le64 *bbp = (__le64 *)page_address(rdev->bb_page);
		u64 *p = bb->page;
		sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS);
		if (bb->changed) {
			unsigned seq;

retry:
			seq = read_seqbegin(&bb->lock);

			memset(bbp, 0xff, PAGE_SIZE);

			for (i = 0 ; i < bb->count ; i++) {
				u64 internal_bb = p[i];
				u64 store_bb = ((BB_OFFSET(internal_bb) << 10)
						| BB_LEN(internal_bb));
				bbp[i] = cpu_to_le64(store_bb);
			}
			bb->changed = 0;
			if (read_seqretry(&bb->lock, seq))
				goto retry;

			bb->sector = (rdev->sb_start +
				      (int)le32_to_cpu(sb->bblog_offset));
			bb->size = le16_to_cpu(sb->bblog_size);
		}
	}

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

	if (max_dev > le32_to_cpu(sb->max_dev)) {
		int bmask;
		sb->max_dev = cpu_to_le32(max_dev);
		rdev->sb_size = max_dev * 2 + 256;
		bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
		if (rdev->sb_size & bmask)
			rdev->sb_size = (rdev->sb_size | bmask) + 1;
	} else
		max_dev = le32_to_cpu(sb->max_dev);

	for (i=0; i<max_dev;i++)
		sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE);

	if (test_bit(MD_HAS_JOURNAL, &mddev->flags))
		sb->feature_map |= cpu_to_le32(MD_FEATURE_JOURNAL);

	if (test_bit(MD_HAS_PPL, &mddev->flags)) {
		if (test_bit(MD_HAS_MULTIPLE_PPLS, &mddev->flags))
			sb->feature_map |=
			    cpu_to_le32(MD_FEATURE_MULTIPLE_PPLS);
		else
			sb->feature_map |= cpu_to_le32(MD_FEATURE_PPL);
		sb->ppl.offset = cpu_to_le16(rdev->ppl.offset);
		sb->ppl.size = cpu_to_le16(rdev->ppl.size);
	}

	rdev_for_each(rdev2, mddev) {
		i = rdev2->desc_nr;
		if (test_bit(Faulty, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY);
		else if (test_bit(In_sync, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else if (test_bit(Journal, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_JOURNAL);
		else if (rdev2->raid_disk >= 0)
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else
			sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE);
	}

	sb->sb_csum = calc_sb_1_csum(sb);
}

static sector_t super_1_choose_bm_space(sector_t dev_size)
{
	sector_t bm_space;

	/* if the device is bigger than 8Gig, save 64k for bitmap
	 * usage, if bigger than 200Gig, save 128k
	 */
	if (dev_size < 64*2)
		bm_space = 0;
	else if (dev_size - 64*2 >= 200*1024*1024*2)
		bm_space = 128*2;
	else if (dev_size - 4*2 > 8*1024*1024*2)
		bm_space = 64*2;
	else
		bm_space = 4*2;
	return bm_space;
}

static unsigned long long
super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
{
	struct mdp_superblock_1 *sb;
	sector_t max_sectors;
	if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
		return 0; /* component must fit device */
	if (rdev->data_offset != rdev->new_data_offset)
		return 0; /* too confusing */
	if (rdev->sb_start < rdev->data_offset) {
		/* minor versions 1 and 2; superblock before data */
		max_sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset;
		if (!num_sectors || num_sectors > max_sectors)
			num_sectors = max_sectors;
	} else if (rdev->mddev->bitmap_info.offset) {
		/* minor version 0 with bitmap we can't move */
		return 0;
	} else {
		/* minor version 0; superblock after data */
		sector_t sb_start, bm_space;
		sector_t dev_size = bdev_nr_sectors(rdev->bdev);

		/* 8K is for superblock */
		sb_start = dev_size - 8*2;
		sb_start &= ~(sector_t)(4*2 - 1);

		bm_space = super_1_choose_bm_space(dev_size);

		/* Space that can be used to store date needs to decrease
		 * superblock bitmap space and bad block space(4K)
		 */
		max_sectors = sb_start - bm_space - 4*2;

		if (!num_sectors || num_sectors > max_sectors)
			num_sectors = max_sectors;
		rdev->sb_start = sb_start;
	}
	sb = page_address(rdev->sb_page);
	sb->data_size = cpu_to_le64(num_sectors);
	sb->super_offset = cpu_to_le64(rdev->sb_start);
	sb->sb_csum = calc_sb_1_csum(sb);
	do {
		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
			       rdev->sb_page);
	} while (md_super_wait(rdev->mddev) < 0);
	return num_sectors;

}

static int
super_1_allow_new_offset(struct md_rdev *rdev,
			 unsigned long long new_offset)
{
	/* All necessary checks on new >= old have been done */
	struct bitmap *bitmap;
	if (new_offset >= rdev->data_offset)
		return 1;

	/* with 1.0 metadata, there is no metadata to tread on
	 * so we can always move back */
	if (rdev->mddev->minor_version == 0)
		return 1;

	/* otherwise we must be sure not to step on
	 * any metadata, so stay:
	 * 36K beyond start of superblock
	 * beyond end of badblocks
	 * beyond write-intent bitmap
	 */
	if (rdev->sb_start + (32+4)*2 > new_offset)
		return 0;
	bitmap = rdev->mddev->bitmap;
	if (bitmap && !rdev->mddev->bitmap_info.file &&
	    rdev->sb_start + rdev->mddev->bitmap_info.offset +
	    bitmap->storage.file_pages * (PAGE_SIZE>>9) > new_offset)
		return 0;
	if (rdev->badblocks.sector + rdev->badblocks.size > new_offset)
		return 0;

	return 1;
}

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,
		.rdev_size_change   = super_90_rdev_size_change,
		.allow_new_offset   = super_90_allow_new_offset,
	},
	[1] = {
		.name	= "md-1",
		.owner	= THIS_MODULE,
		.load_super	    = super_1_load,
		.validate_super	    = super_1_validate,
		.sync_super	    = super_1_sync,
		.rdev_size_change   = super_1_rdev_size_change,
		.allow_new_offset   = super_1_allow_new_offset,
	},
};

static void sync_super(struct mddev *mddev, struct md_rdev *rdev)
{
	if (mddev->sync_super) {
		mddev->sync_super(mddev, rdev);
		return;
	}

	BUG_ON(mddev->major_version >= ARRAY_SIZE(super_types));

	super_types[mddev->major_version].sync_super(mddev, rdev);
}

static int match_mddev_units(struct mddev *mddev1, struct mddev *mddev2)
{
	struct md_rdev *rdev, *rdev2;

	rcu_read_lock();
	rdev_for_each_rcu(rdev, mddev1) {
		if (test_bit(Faulty, &rdev->flags) ||
		    test_bit(Journal, &rdev->flags) ||
		    rdev->raid_disk == -1)
			continue;
		rdev_for_each_rcu(rdev2, mddev2) {
			if (test_bit(Faulty, &rdev2->flags) ||
			    test_bit(Journal, &rdev2->flags) ||
			    rdev2->raid_disk == -1)
				continue;
			if (rdev->bdev->bd_disk == rdev2->bdev->bd_disk) {
				rcu_read_unlock();
				return 1;
			}
		}
	}
	rcu_read_unlock();
	return 0;
}

static LIST_HEAD(pending_raid_disks);

/*
 * Try to register data integrity profile for an mddev
 *
 * This is called when an array is started and after a disk has been kicked
 * from the array. It only succeeds if all working and active component devices
 * are integrity capable with matching profiles.
 */
int md_integrity_register(struct mddev *mddev)
{
	struct md_rdev *rdev, *reference = NULL;

	if (list_empty(&mddev->disks))
		return 0; /* nothing to do */
	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
		return 0; /* shouldn't register, or already is */
	rdev_for_each(rdev, mddev) {
		/* skip spares and non-functional disks */
		if (test_bit(Faulty, &rdev->flags))
			continue;
		if (rdev->raid_disk < 0)
			continue;
		if (!reference) {
			/* Use the first rdev as the reference */
			reference = rdev;
			continue;
		}
		/* does this rdev's profile match the reference profile? */
		if (blk_integrity_compare(reference->bdev->bd_disk,
				rdev->bdev->bd_disk) < 0)
			return -EINVAL;
	}
	if (!reference || !bdev_get_integrity(reference->bdev))
		return 0;
	/*
	 * All component devices are integrity capable and have matching
	 * profiles, register the common profile for the md device.
	 */
	blk_integrity_register(mddev->gendisk,
			       bdev_get_integrity(reference->bdev));

	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
	    (mddev->level != 1 && mddev->level != 10 &&
	     bioset_integrity_create(&mddev->io_clone_set, BIO_POOL_SIZE))) {
		/*
		 * No need to handle the failure of bioset_integrity_create,
		 * because the function is called by md_run() -> pers->run(),
		 * md_run calls bioset_exit -> bioset_integrity_free in case
		 * of failure case.
		 */
		pr_err("md: failed to create integrity pool for %s\n",
		       mdname(mddev));
		return -EINVAL;
	}
	return 0;
}
EXPORT_SYMBOL(md_integrity_register);

/*
 * Attempt to add an rdev, but only if it is consistent with the current
 * integrity profile
 */
int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
{
	struct blk_integrity *bi_mddev;

	if (!mddev->gendisk)
		return 0;

	bi_mddev = blk_get_integrity(mddev->gendisk);

	if (!bi_mddev) /* nothing to do */
		return 0;

	if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) {
		pr_err("%s: incompatible integrity profile for %pg\n",
		       mdname(mddev), rdev->bdev);
		return -ENXIO;
	}

	return 0;
}
EXPORT_SYMBOL(md_integrity_add_rdev);

static bool rdev_read_only(struct md_rdev *rdev)
{
	return bdev_read_only(rdev->bdev) ||
		(rdev->meta_bdev && bdev_read_only(rdev->meta_bdev));
}

static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
{
	char b[BDEVNAME_SIZE];
	int err;

	/* prevent duplicates */
	if (find_rdev(mddev, rdev->bdev->bd_dev))
		return -EEXIST;

	if (rdev_read_only(rdev) && mddev->pers)
		return -EROFS;

	/* make sure rdev->sectors exceeds mddev->dev_sectors */
	if (!test_bit(Journal, &rdev->flags) &&
	    rdev->sectors &&
	    (mddev->dev_sectors == 0 || rdev->sectors < mddev->dev_sectors)) {
		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->dev_sectors = rdev->sectors;
	}

	/* Verify rdev->desc_nr is unique.
	 * If it is -1, assign a free number, else
	 * check number is not in use
	 */
	rcu_read_lock();
	if (rdev->desc_nr < 0) {
		int choice = 0;
		if (mddev->pers)
			choice = mddev->raid_disks;
		while (md_find_rdev_nr_rcu(mddev, choice))
			choice++;
		rdev->desc_nr = choice;
	} else {
		if (md_find_rdev_nr_rcu(mddev, rdev->desc_nr)) {
			rcu_read_unlock();
			return -EBUSY;
		}
	}
	rcu_read_unlock();
	if (!test_bit(Journal, &rdev->flags) &&
	    mddev->max_disks && rdev->desc_nr >= mddev->max_disks) {
		pr_warn("md: %s: array is limited to %d devices\n",
			mdname(mddev), mddev->max_disks);
		return -EBUSY;
	}
	snprintf(b, sizeof(b), "%pg", rdev->bdev);
	strreplace(b, '/', '!');

	rdev->mddev = mddev;
	pr_debug("md: bind<%s>\n", b);

	if (mddev->raid_disks)
		mddev_create_serial_pool(mddev, rdev, false);

	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
		goto fail;

	/* failure here is OK */
	err = sysfs_create_link(&rdev->kobj, bdev_kobj(rdev->bdev), "block");
	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
	rdev->sysfs_unack_badblocks =
		sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks");
	rdev->sysfs_badblocks =
		sysfs_get_dirent_safe(rdev->kobj.sd, "bad_blocks");

	list_add_rcu(&rdev->same_set, &mddev->disks);
	bd_link_disk_holder(rdev->bdev, mddev->gendisk);

	/* May as well allow recovery to be retried once */
	mddev->recovery_disabled++;

	return 0;

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

void md_autodetect_dev(dev_t dev);

/* just for claiming the bdev */
static struct md_rdev claim_rdev;

static void export_rdev(struct md_rdev *rdev, struct mddev *mddev)
{
	pr_debug("md: export_rdev(%pg)\n", rdev->bdev);
	md_rdev_clear(rdev);
#ifndef MODULE
	if (test_bit(AutoDetected, &rdev->flags))
		md_autodetect_dev(rdev->bdev->bd_dev);
#endif
	blkdev_put(rdev->bdev,
		   test_bit(Holder, &rdev->flags) ? rdev : &claim_rdev);
	rdev->bdev = NULL;
	kobject_put(&rdev->kobj);
}

static void md_kick_rdev_from_array(struct md_rdev *rdev)
{
	struct mddev *mddev = rdev->mddev;

	bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk);
	list_del_rcu(&rdev->same_set);
	pr_debug("md: unbind<%pg>\n", rdev->bdev);
	mddev_destroy_serial_pool(rdev->mddev, rdev, false);
	rdev->mddev = NULL;
	sysfs_remove_link(&rdev->kobj, "block");
	sysfs_put(rdev->sysfs_state);
	sysfs_put(rdev->sysfs_unack_badblocks);
	sysfs_put(rdev->sysfs_badblocks);
	rdev->sysfs_state = NULL;
	rdev->sysfs_unack_badblocks = NULL;
	rdev->sysfs_badblocks = NULL;
	rdev->badblocks.count = 0;

	synchronize_rcu();

	/*
	 * kobject_del() will wait for all in progress writers to be done, where
	 * reconfig_mutex is held, hence it can't be called under
	 * reconfig_mutex and it's delayed to mddev_unlock().
	 */
	list_add(&rdev->same_set, &mddev->deleting);
}

static void export_array(struct mddev *mddev)
{
	struct md_rdev *rdev;

	while (!list_empty(&mddev->disks)) {
		rdev = list_first_entry(&mddev->disks, struct md_rdev,
					same_set);
		md_kick_rdev_from_array(rdev);
	}
	mddev->raid_disks = 0;
	mddev->major_version = 0;
}

static bool set_in_sync(struct mddev *mddev)
{
	lockdep_assert_held(&mddev->lock);
	if (!mddev->in_sync) {
		mddev->sync_checkers++;
		spin_unlock(&mddev->lock);
		percpu_ref_switch_to_atomic_sync(&mddev->writes_pending);
		spin_lock(&mddev->lock);
		if (!mddev->in_sync &&
		    percpu_ref_is_zero(&mddev->writes_pending)) {
			mddev->in_sync = 1;
			/*
			 * Ensure ->in_sync is visible before we clear
			 * ->sync_checkers.
			 */
			smp_mb();
			set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
			sysfs_notify_dirent_safe(mddev->sysfs_state);
		}
		if (--mddev->sync_checkers == 0)
			percpu_ref_switch_to_percpu(&mddev->writes_pending);
	}
	if (mddev->safemode == 1)
		mddev->safemode = 0;
	return mddev->in_sync;
}

static void sync_sbs(struct mddev *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)
	 */
	struct md_rdev *rdev;
	rdev_for_each(rdev, mddev) {
		if (rdev->sb_events == mddev->events ||
		    (nospares &&
		     rdev->raid_disk < 0 &&
		     rdev->sb_events+1 == mddev->events)) {
			/* Don't update this superblock */
			rdev->sb_loaded = 2;
		} else {
			sync_super(mddev, rdev);
			rdev->sb_loaded = 1;
		}
	}
}

static bool does_sb_need_changing(struct mddev *mddev)
{
	struct md_rdev *rdev = NULL, *iter;
	struct mdp_superblock_1 *sb;
	int role;

	/* Find a good rdev */
	rdev_for_each(iter, mddev)
		if ((iter->raid_disk >= 0) && !test_bit(Faulty, &iter->flags)) {
			rdev = iter;
			break;
		}

	/* No good device found. */
	if (!rdev)
		return false;

	sb = page_address(rdev->sb_page);
	/* Check if a device has become faulty or a spare become active */
	rdev_for_each(rdev, mddev) {
		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
		/* Device activated? */
		if (role == MD_DISK_ROLE_SPARE && rdev->raid_disk >= 0 &&
		    !test_bit(Faulty, &rdev->flags))
			return true;
		/* Device turned faulty? */
		if (test_bit(Faulty, &rdev->flags) && (role < MD_DISK_ROLE_MAX))
			return true;
	}

	/* Check if any mddev parameters have changed */
	if ((mddev->dev_sectors != le64_to_cpu(sb->size)) ||
	    (mddev->reshape_position != le64_to_cpu(sb->reshape_position)) ||
	    (mddev->layout != le32_to_cpu(sb->layout)) ||
	    (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) ||
	    (mddev->chunk_sectors != le32_to_cpu(sb->chunksize)))
		return true;

	return false;
}

void md_update_sb(struct mddev *mddev, int force_change)
{
	struct md_rdev *rdev;
	int sync_req;
	int nospares = 0;
	int any_badblocks_changed = 0;
	int ret = -1;

	if (!md_is_rdwr(mddev)) {
		if (force_change)
			set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
		return;
	}

repeat:
	if (mddev_is_clustered(mddev)) {
		if (test_and_clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags))
			force_change = 1;
		if (test_and_clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags))
			nospares = 1;
		ret = md_cluster_ops->metadata_update_start(mddev);
		/* Has someone else has updated the sb */
		if (!does_sb_need_changing(mddev)) {
			if (ret == 0)
				md_cluster_ops->metadata_update_cancel(mddev);
			bit_clear_unless(&mddev->sb_flags, BIT(MD_SB_CHANGE_PENDING),
							 BIT(MD_SB_CHANGE_DEVS) |
							 BIT(MD_SB_CHANGE_CLEAN));
			return;
		}
	}

	/*
	 * First make sure individual recovery_offsets are correct
	 * curr_resync_completed can only be used during recovery.
	 * During reshape/resync it might use array-addresses rather
	 * that device addresses.
	 */
	rdev_for_each(rdev, mddev) {
		if (rdev->raid_disk >= 0 &&
		    mddev->delta_disks >= 0 &&
		    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
		    test_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
		    !test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
		    !test_bit(Journal, &rdev->flags) &&
		    !test_bit(In_sync, &rdev->flags) &&
		    mddev->curr_resync_completed > rdev->recovery_offset)
				rdev->recovery_offset = mddev->curr_resync_completed;

	}
	if (!mddev->persistent) {
		clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
		clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
		if (!mddev->external) {
			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
			rdev_for_each(rdev, mddev) {
				if (rdev->badblocks.changed) {
					rdev->badblocks.changed = 0;
					ack_all_badblocks(&rdev->badblocks);
					md_error(mddev, rdev);
				}
				clear_bit(Blocked, &rdev->flags);
				clear_bit(BlockedBadBlocks, &rdev->flags);
				wake_up(&rdev->blocked_wait);
			}
		}
		wake_up(&mddev->sb_wait);
		return;
	}

	spin_lock(&mddev->lock);

	mddev->utime = ktime_get_real_seconds();

	if (test_and_clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags))
		force_change = 1;
	if (test_and_clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_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;

	/* 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->can_decrease_events
	    && mddev->events != 1) {
		mddev->events--;
		mddev->can_decrease_events = 0;
	} else {
		/* otherwise we have to go forward and ... */
		mddev->events ++;
		mddev->can_decrease_events = nospares;
	}

	/*
	 * 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...
	 */
	WARN_ON(mddev->events == 0);

	rdev_for_each(rdev, mddev) {
		if (rdev->badblocks.changed)
			any_badblocks_changed++;
		if (test_bit(Faulty, &rdev->flags))
			set_bit(FaultRecorded, &rdev->flags);
	}

	sync_sbs(mddev, nospares);
	spin_unlock(&mddev->lock);

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

	if (mddev->queue)
		blk_add_trace_msg(mddev->queue, "md md_update_sb");
rewrite:
	md_bitmap_update_sb(mddev->bitmap);
	rdev_for_each(rdev, mddev) {
		if (rdev->sb_loaded != 1)
			continue; /* no noise on spare devices */

		if (!test_bit(Faulty, &rdev->flags)) {
			md_super_write(mddev,rdev,
				       rdev->sb_start, rdev->sb_size,
				       rdev->sb_page);
			pr_debug("md: (write) %pg's sb offset: %llu\n",
				 rdev->bdev,
				 (unsigned long long)rdev->sb_start);
			rdev->sb_events = mddev->events;
			if (rdev->badblocks.size) {
				md_super_write(mddev, rdev,
					       rdev->badblocks.sector,
					       rdev->badblocks.size << 9,
					       rdev->bb_page);
				rdev->badblocks.size = 0;
			}

		} else
			pr_debug("md: %pg (skipping faulty)\n",
				 rdev->bdev);

		if (mddev->level == LEVEL_MULTIPATH)
			/* only need to write one superblock... */
			break;
	}
	if (md_super_wait(mddev) < 0)
		goto rewrite;
	/* if there was a failure, MD_SB_CHANGE_DEVS was set, and we re-write super */

	if (mddev_is_clustered(mddev) && ret == 0)
		md_cluster_ops->metadata_update_finish(mddev);

	if (mddev->in_sync != sync_req ||
	    !bit_clear_unless(&mddev->sb_flags, BIT(MD_SB_CHANGE_PENDING),
			       BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_CLEAN)))
		/* have to write it out again */
		goto repeat;
	wake_up(&mddev->sb_wait);
	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
		sysfs_notify_dirent_safe(mddev->sysfs_completed);

	rdev_for_each(rdev, mddev) {
		if (test_and_clear_bit(FaultRecorded, &rdev->flags))
			clear_bit(Blocked, &rdev->flags);

		if (any_badblocks_changed)
			ack_all_badblocks(&rdev->badblocks);
		clear_bit(BlockedBadBlocks, &rdev->flags);
		wake_up(&rdev->blocked_wait);
	}
}
EXPORT_SYMBOL(md_update_sb);

static int add_bound_rdev(struct md_rdev *rdev)
{
	struct mddev *mddev = rdev->mddev;
	int err = 0;
	bool add_journal = test_bit(Journal, &rdev->flags);

	if (!mddev->pers->hot_remove_disk || add_journal) {
		/* If there is hot_add_disk but no hot_remove_disk
		 * then added disks for geometry changes,
		 * and should be added immediately.
		 */
		super_types[mddev->major_version].
			validate_super(mddev, rdev);
		if (add_journal)
			mddev_suspend(mddev);
		err = mddev->pers->hot_add_disk(mddev, rdev);
		if (add_journal)
			mddev_resume(mddev);
		if (err) {
			md_kick_rdev_from_array(rdev);
			return err;
		}
	}
	sysfs_notify_dirent_safe(rdev->sysfs_state);

	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
	if (mddev->degraded)
		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	md_new_event();
	md_wakeup_thread(mddev->thread);
	return 0;
}

/* words written to sysfs files may, or may 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)(struct md_rdev *, char *);
	ssize_t (*store)(struct md_rdev *, const char *, size_t);
};

static ssize_t
state_show(struct md_rdev *rdev, char *page)
{
	char *sep = ",";
	size_t len = 0;
	unsigned long flags = READ_ONCE(rdev->flags);

	if (test_bit(Faulty, &flags) ||
	    (!test_bit(ExternalBbl, &flags) &&
	    rdev->badblocks.unacked_exist))
		len += sprintf(page+len, "faulty%s", sep);
	if (test_bit(In_sync, &flags))
		len += sprintf(page+len, "in_sync%s", sep);
	if (test_bit(Journal, &flags))
		len += sprintf(page+len, "journal%s", sep);
	if (test_bit(WriteMostly, &flags))
		len += sprintf(page+len, "write_mostly%s", sep);
	if (test_bit(Blocked, &flags) ||
	    (rdev->badblocks.unacked_exist
	     && !test_bit(Faulty, &flags)))
		len += sprintf(page+len, "blocked%s", sep);
	if (!test_bit(Faulty, &flags) &&
	    !test_bit(Journal, &flags) &&
	    !test_bit(In_sync, &flags))
		len += sprintf(page+len, "spare%s", sep);
	if (test_bit(WriteErrorSeen, &flags))
		len += sprintf(page+len, "write_error%s", sep);
	if (test_bit(WantReplacement, &flags))
		len += sprintf(page+len, "want_replacement%s", sep);
	if (test_bit(Replacement, &flags))
		len += sprintf(page+len, "replacement%s", sep);
	if (test_bit(ExternalBbl, &flags))
		len += sprintf(page+len, "external_bbl%s", sep);
	if (test_bit(FailFast, &flags))
		len += sprintf(page+len, "failfast%s", sep);

	if (len)
		len -= strlen(sep);

	return len+sprintf(page+len, "\n");
}

static ssize_t
state_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	/* can write
	 *  faulty  - simulates an error
	 *  remove  - disconnects the device
	 *  writemostly - sets write_mostly
	 *  -writemostly - clears write_mostly
	 *  blocked - sets the Blocked flags
	 *  -blocked - clears the Blocked and possibly simulates an error
	 *  insync - sets Insync providing device isn't active
	 *  -insync - clear Insync for a device with a slot assigned,
	 *            so that it gets rebuilt based on bitmap
	 *  write_error - sets WriteErrorSeen
	 *  -write_error - clears WriteErrorSeen
	 *  {,-}failfast - set/clear FailFast
	 */

	struct mddev *mddev = rdev->mddev;
	int err = -EINVAL;
	bool need_update_sb = false;

	if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
		md_error(rdev->mddev, rdev);

		if (test_bit(MD_BROKEN, &rdev->mddev->flags))
			err = -EBUSY;
		else
			err = 0;
	} else if (cmd_match(buf, "remove")) {
		if (rdev->mddev->pers) {
			clear_bit(Blocked, &rdev->flags);
			remove_and_add_spares(rdev->mddev, rdev);
		}
		if (rdev->raid_disk >= 0)
			err = -EBUSY;
		else {
			err = 0;
			if (mddev_is_clustered(mddev))
				err = md_cluster_ops->remove_disk(mddev, rdev);

			if (err == 0) {
				md_kick_rdev_from_array(rdev);
				if (mddev->pers) {
					set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
					md_wakeup_thread(mddev->thread);
				}
				md_new_event();
			}
		}
	} else if (cmd_match(buf, "writemostly")) {
		set_bit(WriteMostly, &rdev->flags);
		mddev_create_serial_pool(rdev->mddev, rdev, false);
		need_update_sb = true;
		err = 0;
	} else if (cmd_match(buf, "-writemostly")) {
		mddev_destroy_serial_pool(rdev->mddev, rdev, false);
		clear_bit(WriteMostly, &rdev->flags);
		need_update_sb = true;
		err = 0;
	} else if (cmd_match(buf, "blocked")) {
		set_bit(Blocked, &rdev->flags);
		err = 0;
	} else if (cmd_match(buf, "-blocked")) {
		if (!test_bit(Faulty, &rdev->flags) &&
		    !test_bit(ExternalBbl, &rdev->flags) &&
		    rdev->badblocks.unacked_exist) {
			/* metadata handler doesn't understand badblocks,
			 * so we need to fail the device
			 */
			md_error(rdev->mddev, rdev);
		}
		clear_bit(Blocked, &rdev->flags);
		clear_bit(BlockedBadBlocks, &rdev->flags);
		wake_up(&rdev->blocked_wait);
		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
		md_wakeup_thread(rdev->mddev->thread);

		err = 0;
	} else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) {
		set_bit(In_sync, &rdev->flags);
		err = 0;
	} else if (cmd_match(buf, "failfast")) {
		set_bit(FailFast, &rdev->flags);
		need_update_sb = true;
		err = 0;
	} else if (cmd_match(buf, "-failfast")) {
		clear_bit(FailFast, &rdev->flags);
		need_update_sb = true;
		err = 0;
	} else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0 &&
		   !test_bit(Journal, &rdev->flags)) {
		if (rdev->mddev->pers == NULL) {
			clear_bit(In_sync, &rdev->flags);
			rdev->saved_raid_disk = rdev->raid_disk;
			rdev->raid_disk = -1;
			err = 0;
		}
	} else if (cmd_match(buf, "write_error")) {
		set_bit(WriteErrorSeen, &rdev->flags);
		err = 0;
	} else if (cmd_match(buf, "-write_error")) {
		clear_bit(WriteErrorSeen, &rdev->flags);
		err = 0;
	} else if (cmd_match(buf, "want_replacement")) {
		/* Any non-spare device that is not a replacement can
		 * become want_replacement at any time, but we then need to
		 * check if recovery is needed.
		 */
		if (rdev->raid_disk >= 0 &&
		    !test_bit(Journal, &rdev->flags) &&
		    !test_bit(Replacement, &rdev->flags))
			set_bit(WantReplacement, &rdev->flags);
		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
		md_wakeup_thread(rdev->mddev->thread);
		err = 0;
	} else if (cmd_match(buf, "-want_replacement")) {
		/* Clearing 'want_replacement' is always allowed.
		 * Once replacements starts it is too late though.
		 */
		err = 0;
		clear_bit(WantReplacement, &rdev->flags);
	} else if (cmd_match(buf, "replacement")) {
		/* Can only set a device as a replacement when array has not
		 * yet been started.  Once running, replacement is automatic
		 * from spares, or by assigning 'slot'.
		 */
		if (rdev->mddev->pers)
			err = -EBUSY;
		else {
			set_bit(Replacement, &rdev->flags);
			err = 0;
		}
	} else if (cmd_match(buf, "-replacement")) {
		/* Similarly, can only clear Replacement before start */
		if (rdev->mddev->pers)
			err = -EBUSY;
		else {
			clear_bit(Replacement, &rdev->flags);
			err = 0;
		}
	} else if (cmd_match(buf, "re-add")) {
		if (!rdev->mddev->pers)
			err = -EINVAL;
		else if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) &&
				rdev->saved_raid_disk >= 0) {
			/* clear_bit is performed _after_ all the devices
			 * have their local Faulty bit cleared. If any writes
			 * happen in the meantime in the local node, they
			 * will land in the local bitmap, which will be synced
			 * by this node eventually
			 */
			if (!mddev_is_clustered(rdev->mddev) ||
			    (err = md_cluster_ops->gather_bitmaps(rdev)) == 0) {
				clear_bit(Faulty, &rdev->flags);
				err = add_bound_rdev(rdev);
			}
		} else
			err = -EBUSY;
	} else if (cmd_match(buf, "external_bbl") && (rdev->mddev->external)) {
		set_bit(ExternalBbl, &rdev->flags);
		rdev->badblocks.shift = 0;
		err = 0;
	} else if (cmd_match(buf, "-external_bbl") && (rdev->mddev->external)) {
		clear_bit(ExternalBbl, &rdev->flags);
		err = 0;
	}
	if (need_update_sb)
		md_update_sb(mddev, 1);
	if (!err)
		sysfs_notify_dirent_safe(rdev->sysfs_state);
	return err ? err : len;
}
static struct rdev_sysfs_entry rdev_state =
__ATTR_PREALLOC(state, S_IRUGO|S_IWUSR, state_show, state_store);

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

static ssize_t
errors_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	unsigned int n;
	int rv;

	rv = kstrtouint(buf, 10, &n);
	if (rv < 0)
		return rv;
	atomic_set(&rdev->corrected_errors, n);
	return len;
}
static struct rdev_sysfs_entry rdev_errors =
__ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store);

static ssize_t
slot_show(struct md_rdev *rdev, char *page)
{
	if (test_bit(Journal, &rdev->flags))
		return sprintf(page, "journal\n");
	else if (rdev->raid_disk < 0)
		return sprintf(page, "none\n");
	else
		return sprintf(page, "%d\n", rdev->raid_disk);
}

static ssize_t
slot_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	int slot;
	int err;

	if (test_bit(Journal, &rdev->flags))
		return -EBUSY;
	if (strncmp(buf, "none", 4)==0)
		slot = -1;
	else {
		err = kstrtouint(buf, 10, (unsigned int *)&slot);
		if (err < 0)
			return err;
		if (slot < 0)
			/* overflow */
			return -ENOSPC;
	}
	if (rdev->mddev->pers && slot == -1) {
		/* Setting 'slot' on an active array requires also
		 * updating the 'rd%d' link, and communicating
		 * with the personality with ->hot_*_disk.
		 * For now we only support removing
		 * failed/spare devices.  This normally happens automatically,
		 * but not when the metadata is externally managed.
		 */
		if (rdev->raid_disk == -1)
			return -EEXIST;
		/* personality does all needed checks */
		if (rdev->mddev->pers->hot_remove_disk == NULL)
			return -EINVAL;
		clear_bit(Blocked, &rdev->flags);
		remove_and_add_spares(rdev->mddev, rdev);
		if (rdev->raid_disk >= 0)
			return -EBUSY;
		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
		md_wakeup_thread(rdev->mddev->thread);
	} else if (rdev->mddev->pers) {
		/* Activating a spare .. or possibly reactivating
		 * if we ever get bitmaps working here.
		 */
		int err;

		if (rdev->raid_disk != -1)
			return -EBUSY;

		if (test_bit(MD_RECOVERY_RUNNING, &rdev->mddev->recovery))
			return -EBUSY;

		if (rdev->mddev->pers->hot_add_disk == NULL)
			return -EINVAL;

		if (slot >= rdev->mddev->raid_disks &&
		    slot >= rdev->mddev->raid_disks + rdev->mddev->delta_disks)
			return -ENOSPC;

		rdev->raid_disk = slot;
		if (test_bit(In_sync, &rdev->flags))
			rdev->saved_raid_disk = slot;
		else
			rdev->saved_raid_disk = -1;
		clear_bit(In_sync, &rdev->flags);
		clear_bit(Bitmap_sync, &rdev->flags);
		err = rdev->mddev->pers->hot_add_disk(rdev->mddev, rdev);
		if (err) {
			rdev->raid_disk = -1;
			return err;
		} else
			sysfs_notify_dirent_safe(rdev->sysfs_state);
		/* failure here is OK */;
		sysfs_link_rdev(rdev->mddev, rdev);
		/* don't wakeup anyone, leave that to userspace. */
	} else {
		if (slot >= rdev->mddev->raid_disks &&
		    slot >= rdev->mddev->raid_disks + rdev->mddev->delta_disks)
			return -ENOSPC;
		rdev->raid_disk = slot;
		/* assume it is working */
		clear_bit(Faulty, &rdev->flags);
		clear_bit(WriteMostly, &rdev->flags);
		set_bit(In_sync, &rdev->flags);
		sysfs_notify_dirent_safe(rdev->sysfs_state);
	}
	return len;
}

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

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

static ssize_t
offset_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	unsigned long long offset;
	if (kstrtoull(buf, 10, &offset) < 0)
		return -EINVAL;
	if (rdev->mddev->pers && rdev->raid_disk >= 0)
		return -EBUSY;
	if (rdev->sectors && rdev->mddev->external)
		/* Must set offset before size, so overlap checks
		 * can be sane */
		return -EBUSY;
	rdev->data_offset = offset;
	rdev->new_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 new_offset_show(struct md_rdev *rdev, char *page)
{
	return sprintf(page, "%llu\n",
		       (unsigned long long)rdev->new_data_offset);
}

static ssize_t new_offset_store(struct md_rdev *rdev,
				const char *buf, size_t len)
{
	unsigned long long new_offset;
	struct mddev *mddev = rdev->mddev;

	if (kstrtoull(buf, 10, &new_offset) < 0)
		return -EINVAL;

	if (mddev->sync_thread ||
	    test_bit(MD_RECOVERY_RUNNING,&mddev->recovery))
		return -EBUSY;
	if (new_offset == rdev->data_offset)
		/* reset is always permitted */
		;
	else if (new_offset > rdev->data_offset) {
		/* must not push array size beyond rdev_sectors */
		if (new_offset - rdev->data_offset
		    + mddev->dev_sectors > rdev->sectors)
				return -E2BIG;
	}
	/* Metadata worries about other space details. */

	/* decreasing the offset is inconsistent with a backwards
	 * reshape.
	 */
	if (new_offset < rdev->data_offset &&
	    mddev->reshape_backwards)
		return -EINVAL;
	/* Increasing offset is inconsistent with forwards
	 * reshape.  reshape_direction should be set to
	 * 'backwards' first.
	 */
	if (new_offset > rdev->data_offset &&
	    !mddev->reshape_backwards)
		return -EINVAL;

	if (mddev->pers && mddev->persistent &&
	    !super_types[mddev->major_version]
	    .allow_new_offset(rdev, new_offset))
		return -E2BIG;
	rdev->new_data_offset = new_offset;
	if (new_offset > rdev->data_offset)
		mddev->reshape_backwards = 1;
	else if (new_offset < rdev->data_offset)
		mddev->reshape_backwards = 0;

	return len;
}
static struct rdev_sysfs_entry rdev_new_offset =
__ATTR(new_offset, S_IRUGO|S_IWUSR, new_offset_show, new_offset_store);

static ssize_t
rdev_size_show(struct md_rdev *rdev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)rdev->sectors / 2);
}

static int md_rdevs_overlap(struct md_rdev *a, struct md_rdev *b)
{
	/* check if two start/length pairs overlap */
	if (a->data_offset + a->sectors <= b->data_offset)
		return false;
	if (b->data_offset + b->sectors <= a->data_offset)
		return false;
	return true;
}

static bool md_rdev_overlaps(struct md_rdev *rdev)
{
	struct mddev *mddev;
	struct md_rdev *rdev2;

	spin_lock(&all_mddevs_lock);
	list_for_each_entry(mddev, &all_mddevs, all_mddevs) {
		if (test_bit(MD_DELETED, &mddev->flags))
			continue;
		rdev_for_each(rdev2, mddev) {
			if (rdev != rdev2 && rdev->bdev == rdev2->bdev &&
			    md_rdevs_overlap(rdev, rdev2)) {
				spin_unlock(&all_mddevs_lock);
				return true;
			}
		}
	}
	spin_unlock(&all_mddevs_lock);
	return false;
}

static int strict_blocks_to_sectors(const char *buf, sector_t *sectors)
{
	unsigned long long blocks;
	sector_t new;

	if (kstrtoull(buf, 10, &blocks) < 0)
		return -EINVAL;

	if (blocks & 1ULL << (8 * sizeof(blocks) - 1))
		return -EINVAL; /* sector conversion overflow */

	new = blocks * 2;
	if (new != blocks * 2)
		return -EINVAL; /* unsigned long long to sector_t overflow */

	*sectors = new;
	return 0;
}

static ssize_t
rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	struct mddev *my_mddev = rdev->mddev;
	sector_t oldsectors = rdev->sectors;
	sector_t sectors;

	if (test_bit(Journal, &rdev->flags))
		return -EBUSY;
	if (strict_blocks_to_sectors(buf, &sectors) < 0)
		return -EINVAL;
	if (rdev->data_offset != rdev->new_data_offset)
		return -EINVAL; /* too confusing */
	if (my_mddev->pers && rdev->raid_disk >= 0) {
		if (my_mddev->persistent) {
			sectors = super_types[my_mddev->major_version].
				rdev_size_change(rdev, sectors);
			if (!sectors)
				return -EBUSY;
		} else if (!sectors)
			sectors = bdev_nr_sectors(rdev->bdev) -
				rdev->data_offset;
		if (!my_mddev->pers->resize)
			/* Cannot change size for RAID0 or Linear etc */
			return -EINVAL;
	}
	if (sectors < my_mddev->dev_sectors)
		return -EINVAL; /* component must fit device */

	rdev->sectors = sectors;

	/*
	 * Check that all other rdevs with the same bdev do not overlap.  This
	 * check does not provide a hard guarantee, it just helps avoid
	 * dangerous mistakes.
	 */
	if (sectors > oldsectors && my_mddev->external &&
	    md_rdev_overlaps(rdev)) {
		/*
		 * Someone else could have slipped in a size change here, but
		 * doing so is just silly.  We put oldsectors back because we
		 * know it is safe, and trust userspace not to race with itself.
		 */
		rdev->sectors = oldsectors;
		return -EBUSY;
	}
	return len;
}

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

static ssize_t recovery_start_show(struct md_rdev *rdev, char *page)
{
	unsigned long long recovery_start = rdev->recovery_offset;

	if (test_bit(In_sync, &rdev->flags) ||
	    recovery_start == MaxSector)
		return sprintf(page, "none\n");

	return sprintf(page, "%llu\n", recovery_start);
}

static ssize_t recovery_start_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	unsigned long long recovery_start;

	if (cmd_match(buf, "none"))
		recovery_start = MaxSector;
	else if (kstrtoull(buf, 10, &recovery_start))
		return -EINVAL;

	if (rdev->mddev->pers &&
	    rdev->raid_disk >= 0)
		return -EBUSY;

	rdev->recovery_offset = recovery_start;
	if (recovery_start == MaxSector)
		set_bit(In_sync, &rdev->flags);
	else
		clear_bit(In_sync, &rdev->flags);
	return len;
}

static struct rdev_sysfs_entry rdev_recovery_start =
__ATTR(recovery_start, S_IRUGO|S_IWUSR, recovery_start_show, recovery_start_store);

/* sysfs access to bad-blocks list.
 * We present two files.
 * 'bad-blocks' lists sector numbers and lengths of ranges that
 *    are recorded as bad.  The list is truncated to fit within
 *    the one-page limit of sysfs.
 *    Writing "sector length" to this file adds an acknowledged
 *    bad block list.
 * 'unacknowledged-bad-blocks' lists bad blocks that have not yet
 *    been acknowledged.  Writing to this file adds bad blocks
 *    without acknowledging them.  This is largely for testing.
 */
static ssize_t bb_show(struct md_rdev *rdev, char *page)
{
	return badblocks_show(&rdev->badblocks, page, 0);
}
static ssize_t bb_store(struct md_rdev *rdev, const char *page, size_t len)
{
	int rv = badblocks_store(&rdev->badblocks, page, len, 0);
	/* Maybe that ack was all we needed */
	if (test_and_clear_bit(BlockedBadBlocks, &rdev->flags))
		wake_up(&rdev->blocked_wait);
	return rv;
}
static struct rdev_sysfs_entry rdev_bad_blocks =
__ATTR(bad_blocks, S_IRUGO|S_IWUSR, bb_show, bb_store);

static ssize_t ubb_show(struct md_rdev *rdev, char *page)
{
	return badblocks_show(&rdev->badblocks, page, 1);
}
static ssize_t ubb_store(struct md_rdev *rdev, const char *page, size_t len)
{
	return badblocks_store(&rdev->badblocks, page, len, 1);
}
static struct rdev_sysfs_entry rdev_unack_bad_blocks =
__ATTR(unacknowledged_bad_blocks, S_IRUGO|S_IWUSR, ubb_show, ubb_store);

static ssize_t
ppl_sector_show(struct md_rdev *rdev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)rdev->ppl.sector);
}

static ssize_t
ppl_sector_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	unsigned long long sector;

	if (kstrtoull(buf, 10, &sector) < 0)
		return -EINVAL;
	if (sector != (sector_t)sector)
		return -EINVAL;

	if (rdev->mddev->pers && test_bit(MD_HAS_PPL, &rdev->mddev->flags) &&
	    rdev->raid_disk >= 0)
		return -EBUSY;

	if (rdev->mddev->persistent) {
		if (rdev->mddev->major_version == 0)
			return -EINVAL;
		if ((sector > rdev->sb_start &&
		     sector - rdev->sb_start > S16_MAX) ||
		    (sector < rdev->sb_start &&
		     rdev->sb_start - sector > -S16_MIN))
			return -EINVAL;
		rdev->ppl.offset = sector - rdev->sb_start;
	} else if (!rdev->mddev->external) {
		return -EBUSY;
	}
	rdev->ppl.sector = sector;
	return len;
}

static struct rdev_sysfs_entry rdev_ppl_sector =
__ATTR(ppl_sector, S_IRUGO|S_IWUSR, ppl_sector_show, ppl_sector_store);

static ssize_t
ppl_size_show(struct md_rdev *rdev, char *page)
{
	return sprintf(page, "%u\n", rdev->ppl.size);
}

static ssize_t
ppl_size_store(struct md_rdev *rdev, const char *buf, size_t len)
{
	unsigned int size;

	if (kstrtouint(buf, 10, &size) < 0)
		return -EINVAL;

	if (rdev->mddev->pers && test_bit(MD_HAS_PPL, &rdev->mddev->flags) &&
	    rdev->raid_disk >= 0)
		return -EBUSY;

	if (rdev->mddev->persistent) {
		if (rdev->mddev->major_version == 0)
			return -EINVAL;
		if (size > U16_MAX)
			return -EINVAL;
	} else if (!rdev->mddev->external) {
		return -EBUSY;
	}
	rdev->ppl.size = size;
	return len;
}

static struct rdev_sysfs_entry rdev_ppl_size =
__ATTR(ppl_size, S_IRUGO|S_IWUSR, ppl_size_show, ppl_size_store);

static struct attribute *rdev_default_attrs[] = {
	&rdev_state.attr,
	&rdev_errors.attr,
	&rdev_slot.attr,
	&rdev_offset.attr,
	&rdev_new_offset.attr,
	&rdev_size.attr,
	&rdev_recovery_start.attr,
	&rdev_bad_blocks.attr,
	&rdev_unack_bad_blocks.attr,
	&rdev_ppl_sector.attr,
	&rdev_ppl_size.attr,
	NULL,
};
ATTRIBUTE_GROUPS(rdev_default);
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);
	struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj);

	if (!entry->show)
		return -EIO;
	if (!rdev->mddev)
		return -ENODEV;
	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);
	struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj);
	struct kernfs_node *kn = NULL;
	ssize_t rv;
	struct mddev *mddev = rdev->mddev;

	if (!entry->store)
		return -EIO;
	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

	if (entry->store == state_store && cmd_match(page, "remove"))
		kn = sysfs_break_active_protection(kobj, attr);

	rv = mddev ? mddev_lock(mddev) : -ENODEV;
	if (!rv) {
		if (rdev->mddev == NULL)
			rv = -ENODEV;
		else
			rv = entry->store(rdev, page, length);
		mddev_unlock(mddev);
	}

	if (kn)
		sysfs_unbreak_active_protection(kn);

	return rv;
}

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

int md_rdev_init(struct md_rdev *rdev)
{
	rdev->desc_nr = -1;
	rdev->saved_raid_disk = -1;
	rdev->raid_disk = -1;
	rdev->flags = 0;
	rdev->data_offset = 0;
	rdev->new_data_offset = 0;
	rdev->sb_events = 0;
	rdev->last_read_error = 0;
	rdev->sb_loaded = 0;
	rdev->bb_page = NULL;
	atomic_set(&rdev->nr_pending, 0);
	atomic_set(&rdev->read_errors, 0);
	atomic_set(&rdev->corrected_errors, 0);

	INIT_LIST_HEAD(&rdev->same_set);
	init_waitqueue_head(&rdev->blocked_wait);

	/* Add space to store bad block list.
	 * This reserves the space even on arrays where it cannot
	 * be used - I wonder if that matters
	 */
	return badblocks_init(&rdev->badblocks, 0);
}
EXPORT_SYMBOL_GPL(md_rdev_init);

/*
 * 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 struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
{
	struct md_rdev *rdev;
	struct md_rdev *holder;
	sector_t size;
	int err;

	rdev = kzalloc(sizeof(*rdev), GFP_KERNEL);
	if (!rdev)
		return ERR_PTR(-ENOMEM);

	err = md_rdev_init(rdev);
	if (err)
		goto out_free_rdev;
	err = alloc_disk_sb(rdev);
	if (err)
		goto out_clear_rdev;

	if (super_format == -2) {
		holder = &claim_rdev;
	} else {
		holder = rdev;
		set_bit(Holder, &rdev->flags);
	}

	rdev->bdev = blkdev_get_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE,
				       holder, NULL);
	if (IS_ERR(rdev->bdev)) {
		pr_warn("md: could not open device unknown-block(%u,%u).\n",
			MAJOR(newdev), MINOR(newdev));
		err = PTR_ERR(rdev->bdev);
		goto out_clear_rdev;
	}

	kobject_init(&rdev->kobj, &rdev_ktype);

	size = bdev_nr_bytes(rdev->bdev) >> BLOCK_SIZE_BITS;
	if (!size) {
		pr_warn("md: %pg has zero or unknown size, marking faulty!\n",
			rdev->bdev);
		err = -EINVAL;
		goto out_blkdev_put;
	}

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

	return rdev;

out_blkdev_put:
	blkdev_put(rdev->bdev, holder);
out_clear_rdev:
	md_rdev_clear(rdev);
out_free_rdev:
	kfree(rdev);
	return ERR_PTR(err);
}

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

static int analyze_sbs(struct mddev *mddev)
{
	int i;
	struct md_rdev *rdev, *freshest, *tmp;

	freshest = NULL;
	rdev_for_each_safe(rdev, tmp, mddev)
		switch (super_types[mddev->major_version].
			load_super(rdev, freshest, mddev->minor_version)) {
		case 1:
			freshest = rdev;
			break;
		case 0:
			break;
		default:
			pr_warn("md: fatal superblock inconsistency in %pg -- removing from array\n",
				rdev->bdev);
			md_kick_rdev_from_array(rdev);
		}

	/* Cannot find a valid fresh disk */
	if (!freshest) {
		pr_warn("md: cannot find a valid disk\n");
		return -EINVAL;
	}

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

	i = 0;
	rdev_for_each_safe(rdev, tmp, mddev) {
		if (mddev->max_disks &&
		    (rdev->desc_nr >= mddev->max_disks ||
		     i > mddev->max_disks)) {
			pr_warn("md: %s: %pg: only %d devices permitted\n",
				mdname(mddev), rdev->bdev,
				mddev->max_disks);
			md_kick_rdev_from_array(rdev);
			continue;
		}
		if (rdev != freshest) {
			if (super_types[mddev->major_version].
			    validate_super(mddev, rdev)) {
				pr_warn("md: kicking non-fresh %pg from array!\n",
					rdev->bdev);
				md_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 - min(0, mddev->delta_disks)) &&
			   !test_bit(Journal, &rdev->flags)) {
			rdev->raid_disk = -1;
			clear_bit(In_sync, &rdev->flags);
		}
	}

	return 0;
}

/* Read a fixed-point number.
 * Numbers in sysfs attributes should be in "standard" units where
 * possible, so time should be in seconds.
 * However we internally use a a much smaller unit such as
 * milliseconds or jiffies.
 * This function takes a decimal number with a possible fractional
 * component, and produces an integer which is the result of
 * multiplying that number by 10^'scale'.
 * all without any floating-point arithmetic.
 */
int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
{
	unsigned long result = 0;
	long decimals = -1;
	while (isdigit(*cp) || (*cp == '.' && decimals < 0)) {
		if (*cp == '.')
			decimals = 0;
		else if (decimals < scale) {
			unsigned int value;
			value = *cp - '0';
			result = result * 10 + value;
			if (decimals >= 0)
				decimals++;
		}
		cp++;
	}
	if (*cp == '\n')
		cp++;
	if (*cp)
		return -EINVAL;
	if (decimals < 0)
		decimals = 0;
	*res = result * int_pow(10, scale - decimals);
	return 0;
}

static ssize_t
safe_delay_show(struct mddev *mddev, char *page)
{
	unsigned int msec = ((unsigned long)mddev->safemode_delay*1000)/HZ;

	return sprintf(page, "%u.%03u\n", msec/1000, msec%1000);
}
static ssize_t
safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len)
{
	unsigned long msec;

	if (mddev_is_clustered(mddev)) {
		pr_warn("md: Safemode is disabled for clustered mode\n");
		return -EINVAL;
	}

	if (strict_strtoul_scaled(cbuf, &msec, 3) < 0 || msec > UINT_MAX / HZ)
		return -EINVAL;
	if (msec == 0)
		mddev->safemode_delay = 0;
	else {
		unsigned long old_delay = mddev->safemode_delay;
		unsigned long new_delay = (msec*HZ)/1000;

		if (new_delay == 0)
			new_delay = 1;
		mddev->safemode_delay = new_delay;
		if (new_delay < old_delay || old_delay == 0)
			mod_timer(&mddev->safemode_timer, jiffies+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(struct mddev *mddev, char *page)
{
	struct md_personality *p;
	int ret;
	spin_lock(&mddev->lock);
	p = mddev->pers;
	if (p)
		ret = sprintf(page, "%s\n", p->name);
	else if (mddev->clevel[0])
		ret = sprintf(page, "%s\n", mddev->clevel);
	else if (mddev->level != LEVEL_NONE)
		ret = sprintf(page, "%d\n", mddev->level);
	else
		ret = 0;
	spin_unlock(&mddev->lock);
	return ret;
}

static ssize_t
level_store(struct mddev *mddev, const char *buf, size_t len)
{
	char clevel[16];
	ssize_t rv;
	size_t slen = len;
	struct md_personality *pers, *oldpers;
	long level;
	void *priv, *oldpriv;
	struct md_rdev *rdev;

	if (slen == 0 || slen >= sizeof(clevel))
		return -EINVAL;

	rv = mddev_lock(mddev);
	if (rv)
		return rv;

	if (mddev->pers == NULL) {
		strncpy(mddev->clevel, buf, slen);
		if (mddev->clevel[slen-1] == '\n')
			slen--;
		mddev->clevel[slen] = 0;
		mddev->level = LEVEL_NONE;
		rv = len;
		goto out_unlock;
	}
	rv = -EROFS;
	if (!md_is_rdwr(mddev))
		goto out_unlock;

	/* request to change the personality.  Need to ensure:
	 *  - array is not engaged in resync/recovery/reshape
	 *  - old personality can be suspended
	 *  - new personality will access other array.
	 */

	rv = -EBUSY;
	if (mddev->sync_thread ||
	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
	    mddev->reshape_position != MaxSector ||
	    mddev->sysfs_active)
		goto out_unlock;

	rv = -EINVAL;
	if (!mddev->pers->quiesce) {
		pr_warn("md: %s: %s does not support online personality change\n",
			mdname(mddev), mddev->pers->name);
		goto out_unlock;
	}

	/* Now find the new personality */
	strncpy(clevel, buf, slen);
	if (clevel[slen-1] == '\n')
		slen--;
	clevel[slen] = 0;
	if (kstrtol(clevel, 10, &level))
		level = LEVEL_NONE;

	if (request_module("md-%s", clevel) != 0)
		request_module("md-level-%s", clevel);
	spin_lock(&pers_lock);
	pers = find_pers(level, clevel);
	if (!pers || !try_module_get(pers->owner)) {
		spin_unlock(&pers_lock);
		pr_warn("md: personality %s not loaded\n", clevel);
		rv = -EINVAL;
		goto out_unlock;
	}
	spin_unlock(&pers_lock);

	if (pers == mddev->pers) {
		/* Nothing to do! */
		module_put(pers->owner);
		rv = len;
		goto out_unlock;
	}
	if (!pers->takeover) {
		module_put(pers->owner);
		pr_warn("md: %s: %s does not support personality takeover\n",
			mdname(mddev), clevel);
		rv = -EINVAL;
		goto out_unlock;
	}

	rdev_for_each(rdev, mddev)
		rdev->new_raid_disk = rdev->raid_disk;

	/* ->takeover must set new_* and/or delta_disks
	 * if it succeeds, and may set them when it fails.
	 */
	priv = pers->takeover(mddev);
	if (IS_ERR(priv)) {
		mddev->new_level = mddev->level;
		mddev->new_layout = mddev->layout;
		mddev->new_chunk_sectors = mddev->chunk_sectors;
		mddev->raid_disks -= mddev->delta_disks;
		mddev->delta_disks = 0;
		mddev->reshape_backwards = 0;
		module_put(pers->owner);
		pr_warn("md: %s: %s would not accept array\n",
			mdname(mddev), clevel);
		rv = PTR_ERR(priv);
		goto out_unlock;
	}

	/* Looks like we have a winner */
	mddev_suspend(mddev);
	mddev_detach(mddev);

	spin_lock(&mddev->lock);
	oldpers = mddev->pers;
	oldpriv = mddev->private;
	mddev->pers = pers;
	mddev->private = priv;
	strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
	mddev->level = mddev->new_level;
	mddev->layout = mddev->new_layout;
	mddev->chunk_sectors = mddev->new_chunk_sectors;
	mddev->delta_disks = 0;
	mddev->reshape_backwards = 0;
	mddev->degraded = 0;
	spin_unlock(&mddev->lock);

	if (oldpers->sync_request == NULL &&
	    mddev->external) {
		/* We are converting from a no-redundancy array
		 * to a redundancy array and metadata is managed
		 * externally so we need to be sure that writes
		 * won't block due to a need to transition
		 *      clean->dirty
		 * until external management is started.
		 */
		mddev->in_sync = 0;
		mddev->safemode_delay = 0;
		mddev->safemode = 0;
	}

	oldpers->free(mddev, oldpriv);

	if (oldpers->sync_request == NULL &&
	    pers->sync_request != NULL) {
		/* need to add the md_redundancy_group */
		if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
			pr_warn("md: cannot register extra attributes for %s\n",
				mdname(mddev));
		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
		mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed");
		mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded");
	}
	if (oldpers->sync_request != NULL &&
	    pers->sync_request == NULL) {
		/* need to remove the md_redundancy_group */
		if (mddev->to_remove == NULL)
			mddev->to_remove = &md_redundancy_group;
	}

	module_put(oldpers->owner);

	rdev_for_each(rdev, mddev) {
		if (rdev->raid_disk < 0)
			continue;
		if (rdev->new_raid_disk >= mddev->raid_disks)
			rdev->new_raid_disk = -1;
		if (rdev->new_raid_disk == rdev->raid_disk)
			continue;
		sysfs_unlink_rdev(mddev, rdev);
	}
	rdev_for_each(rdev, mddev) {
		if (rdev->raid_disk < 0)
			continue;
		if (rdev->new_raid_disk == rdev->raid_disk)
			continue;
		rdev->raid_disk = rdev->new_raid_disk;
		if (rdev->raid_disk < 0)
			clear_bit(In_sync, &rdev->flags);
		else {
			if (sysfs_link_rdev(mddev, rdev))
				pr_warn("md: cannot register rd%d for %s after level change\n",
					rdev->raid_disk, mdname(mddev));
		}
	}

	if (pers->sync_request == NULL) {
		/* this is now an array without redundancy, so
		 * it must always be in_sync
		 */
		mddev->in_sync = 1;
		del_timer_sync(&mddev->safemode_timer);
	}
	blk_set_stacking_limits(&mddev->queue->limits);
	pers->run(mddev);
	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
	mddev_resume(mddev);
	if (!mddev->thread)
		md_update_sb(mddev, 1);
	sysfs_notify_dirent_safe(mddev->sysfs_level);
	md_new_event();
	rv = len;
out_unlock:
	mddev_unlock(mddev);
	return rv;
}

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

static ssize_t
layout_show(struct mddev *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(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned int n;
	int err;

	err = kstrtouint(buf, 10, &n);
	if (err < 0)
		return err;
	err = mddev_lock(mddev);
	if (err)
		return err;

	if (mddev->pers) {
		if (mddev->pers->check_reshape == NULL)
			err = -EBUSY;
		else if (!md_is_rdwr(mddev))
			err = -EROFS;
		else {
			mddev->new_layout = n;
			err = mddev->pers->check_reshape(mddev);
			if (err)
				mddev->new_layout = mddev->layout;
		}
	} else {
		mddev->new_layout = n;
		if (mddev->reshape_position == MaxSector)
			mddev->layout = n;
	}
	mddev_unlock(mddev);
	return err ?: len;
}
static struct md_sysfs_entry md_layout =
__ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);

static ssize_t
raid_disks_show(struct mddev *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(struct mddev *mddev, int raid_disks);

static ssize_t
raid_disks_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned int n;
	int err;

	err = kstrtouint(buf, 10, &n);
	if (err < 0)
		return err;

	err = mddev_lock(mddev);
	if (err)
		return err;
	if (mddev->pers)
		err = update_raid_disks(mddev, n);
	else if (mddev->reshape_position != MaxSector) {
		struct md_rdev *rdev;
		int olddisks = mddev->raid_disks - mddev->delta_disks;

		err = -EINVAL;
		rdev_for_each(rdev, mddev) {
			if (olddisks < n &&
			    rdev->data_offset < rdev->new_data_offset)
				goto out_unlock;
			if (olddisks > n &&
			    rdev->data_offset > rdev->new_data_offset)
				goto out_unlock;
		}
		err = 0;
		mddev->delta_disks = n - olddisks;
		mddev->raid_disks = n;
		mddev->reshape_backwards = (mddev->delta_disks < 0);
	} else
		mddev->raid_disks = n;
out_unlock:
	mddev_unlock(mddev);
	return err ? err : 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
uuid_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%pU\n", mddev->uuid);
}
static struct md_sysfs_entry md_uuid =
__ATTR(uuid, S_IRUGO, uuid_show, NULL);

static ssize_t
chunk_size_show(struct mddev *mddev, char *page)
{
	if (mddev->reshape_position != MaxSector &&
	    mddev->chunk_sectors != mddev->new_chunk_sectors)
		return sprintf(page, "%d (%d)\n",
			       mddev->new_chunk_sectors << 9,
			       mddev->chunk_sectors << 9);
	return sprintf(page, "%d\n", mddev->chunk_sectors << 9);
}

static ssize_t
chunk_size_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned long n;
	int err;

	err = kstrtoul(buf, 10, &n);
	if (err < 0)
		return err;

	err = mddev_lock(mddev);
	if (err)
		return err;
	if (mddev->pers) {
		if (mddev->pers->check_reshape == NULL)
			err = -EBUSY;
		else if (!md_is_rdwr(mddev))
			err = -EROFS;
		else {
			mddev->new_chunk_sectors = n >> 9;
			err = mddev->pers->check_reshape(mddev);
			if (err)
				mddev->new_chunk_sectors = mddev->chunk_sectors;
		}
	} else {
		mddev->new_chunk_sectors = n >> 9;
		if (mddev->reshape_position == MaxSector)
			mddev->chunk_sectors = n >> 9;
	}
	mddev_unlock(mddev);
	return err ?: 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(struct mddev *mddev, char *page)
{
	if (mddev->recovery_cp == MaxSector)
		return sprintf(page, "none\n");
	return sprintf(page, "%llu\n", (unsigned long long)mddev->recovery_cp);
}

static ssize_t
resync_start_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned long long n;
	int err;

	if (cmd_match(buf, "none"))
		n = MaxSector;
	else {
		err = kstrtoull(buf, 10, &n);
		if (err < 0)
			return err;
		if (n != (sector_t)n)
			return -EINVAL;
	}

	err = mddev_lock(mddev);
	if (err)
		return err;
	if (mddev->pers && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
		err = -EBUSY;

	if (!err) {
		mddev->recovery_cp = n;
		if (mddev->pers)
			set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
	}
	mddev_unlock(mddev);
	return err ?: len;
}
static struct md_sysfs_entry md_resync_start =
__ATTR_PREALLOC(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 quiescent
 * 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).
 *
 * broken
*     Array is failed. It's useful because mounted-arrays aren't stopped
*     when array is failed, so this state will at least alert the user that
*     something is wrong.
 */
enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
		   write_pending, active_idle, broken, bad_word};
static char *array_states[] = {
	"clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
	"write-pending", "active-idle", "broken", 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(struct mddev *mddev, char *page)
{
	enum array_state st = inactive;

	if (mddev->pers && !test_bit(MD_NOT_READY, &mddev->flags)) {
		switch(mddev->ro) {
		case MD_RDONLY:
			st = readonly;
			break;
		case MD_AUTO_READ:
			st = read_auto;
			break;
		case MD_RDWR:
			spin_lock(&mddev->lock);
			if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
				st = write_pending;
			else if (mddev->in_sync)
				st = clean;
			else if (mddev->safemode)
				st = active_idle;
			else
				st = active;
			spin_unlock(&mddev->lock);
		}

		if (test_bit(MD_BROKEN, &mddev->flags) && st == clean)
			st = broken;
	} else {
		if (list_empty(&mddev->disks) &&
		    mddev->raid_disks == 0 &&
		    mddev->dev_sectors == 0)
			st = clear;
		else
			st = inactive;
	}
	return sprintf(page, "%s\n", array_states[st]);
}

static int do_md_stop(struct mddev *mddev, int ro, struct block_device *bdev);
static int md_set_readonly(struct mddev *mddev, struct block_device *bdev);
static int restart_array(struct mddev *mddev);

static ssize_t
array_state_store(struct mddev *mddev, const char *buf, size_t len)
{
	int err = 0;
	enum array_state st = match_word(buf, array_states);

	if (mddev->pers && (st == active || st == clean) &&
	    mddev->ro != MD_RDONLY) {
		/* don't take reconfig_mutex when toggling between
		 * clean and active
		 */
		spin_lock(&mddev->lock);
		if (st == active) {
			restart_array(mddev);
			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
			md_wakeup_thread(mddev->thread);
			wake_up(&mddev->sb_wait);
		} else /* st == clean */ {
			restart_array(mddev);
			if (!set_in_sync(mddev))
				err = -EBUSY;
		}
		if (!err)
			sysfs_notify_dirent_safe(mddev->sysfs_state);
		spin_unlock(&mddev->lock);
		return err ?: len;
	}
	err = mddev_lock(mddev);
	if (err)
		return err;
	err = -EINVAL;
	switch(st) {
	case bad_word:
		break;
	case clear:
		/* stopping an active array */
		err = do_md_stop(mddev, 0, NULL);
		break;
	case inactive:
		/* stopping an active array */
		if (mddev->pers)
			err = do_md_stop(mddev, 2, NULL);
		else
			err = 0; /* already inactive */
		break;
	case suspended:
		break; /* not supported yet */
	case readonly:
		if (mddev->pers)
			err = md_set_readonly(mddev, NULL);
		else {
			mddev->ro = MD_RDONLY;
			set_disk_ro(mddev->gendisk, 1);
			err = do_md_run(mddev);
		}
		break;
	case read_auto:
		if (mddev->pers) {
			if (md_is_rdwr(mddev))
				err = md_set_readonly(mddev, NULL);
			else if (mddev->ro == MD_RDONLY)
				err = restart_array(mddev);
			if (err == 0) {
				mddev->ro = MD_AUTO_READ;
				set_disk_ro(mddev->gendisk, 0);
			}
		} else {
			mddev->ro = MD_AUTO_READ;
			err = do_md_run(mddev);
		}
		break;
	case clean:
		if (mddev->pers) {
			err = restart_array(mddev);
			if (err)
				break;
			spin_lock(&mddev->lock);
			if (!set_in_sync(mddev))
				err = -EBUSY;
			spin_unlock(&mddev->lock);
		} else
			err = -EINVAL;
		break;
	case active:
		if (mddev->pers) {
			err = restart_array(mddev);
			if (err)
				break;
			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
			wake_up(&mddev->sb_wait);
			err = 0;
		} else {
			mddev->ro = MD_RDWR;
			set_disk_ro(mddev->gendisk, 0);
			err = do_md_run(mddev);
		}
		break;
	case write_pending:
	case active_idle:
	case broken:
		/* these cannot be set */
		break;
	}

	if (!err) {
		if (mddev->hold_active == UNTIL_IOCTL)
			mddev->hold_active = 0;
		sysfs_notify_dirent_safe(mddev->sysfs_state);
	}
	mddev_unlock(mddev);
	return err ?: len;
}
static struct md_sysfs_entry md_array_state =
__ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);

static ssize_t
max_corrected_read_errors_show(struct mddev *mddev, char *page) {
	return sprintf(page, "%d\n",
		       atomic_read(&mddev->max_corr_read_errors));
}

static ssize_t
max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned int n;
	int rv;

	rv = kstrtouint(buf, 10, &n);
	if (rv < 0)
		return rv;
	if (n > INT_MAX)
		return -EINVAL;
	atomic_set(&mddev->max_corr_read_errors, n);
	return len;
}

static struct md_sysfs_entry max_corr_read_errors =
__ATTR(max_read_errors, S_IRUGO|S_IWUSR, max_corrected_read_errors_show,
	max_corrected_read_errors_store);

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

static ssize_t
new_dev_store(struct mddev *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;
	struct md_rdev *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;

	err = mddev_lock(mddev);
	if (err)
		return err;
	if (mddev->persistent) {
		rdev = md_import_device(dev, mddev->major_version,
					mddev->minor_version);
		if (!IS_ERR(rdev) && !list_empty(&mddev->disks)) {
			struct md_rdev *rdev0
				= list_entry(mddev->disks.next,
					     struct md_rdev, same_set);
			err = super_types[mddev->major_version]
				.load_super(rdev, rdev0, mddev->minor_version);
			if (err < 0)
				goto out;
		}
	} else if (mddev->external)
		rdev = md_import_device(dev, -2, -1);
	else
		rdev = md_import_device(dev, -1, -1);

	if (IS_ERR(rdev)) {
		mddev_unlock(mddev);
		return PTR_ERR(rdev);
	}
	err = bind_rdev_to_array(rdev, mddev);
 out:
	if (err)
		export_rdev(rdev, mddev);
	mddev_unlock(mddev);
	if (!err)
		md_new_event();
	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(struct mddev *mddev, const char *buf, size_t len)
{
	char *end;
	unsigned long chunk, end_chunk;
	int err;

	err = mddev_lock(mddev);
	if (err)
		return err;
	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;
		md_bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
		buf = skip_spaces(end);
	}
	md_bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
out:
	mddev_unlock(mddev);
	return len;
}

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

static ssize_t
size_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%llu\n",
		(unsigned long long)mddev->dev_sectors / 2);
}

static int update_size(struct mddev *mddev, sector_t num_sectors);

static ssize_t
size_store(struct mddev *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
	 */
	sector_t sectors;
	int err = strict_blocks_to_sectors(buf, &sectors);

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

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

/* Metadata version.
 * This is one of
 *   'none' for arrays with no metadata (good luck...)
 *   'external' for arrays with externally managed metadata,
 * or N.M for internally known formats
 */
static ssize_t
metadata_show(struct mddev *mddev, char *page)
{
	if (mddev->persistent)
		return sprintf(page, "%d.%d\n",
			       mddev->major_version, mddev->minor_version);
	else if (mddev->external)
		return sprintf(page, "external:%s\n", mddev->metadata_type);
	else
		return sprintf(page, "none\n");
}

static ssize_t
metadata_store(struct mddev *mddev, const char *buf, size_t len)
{
	int major, minor;
	char *e;
	int err;
	/* Changing the details of 'external' metadata is
	 * always permitted.  Otherwise there must be
	 * no devices attached to the array.
	 */

	err = mddev_lock(mddev);
	if (err)
		return err;
	err = -EBUSY;
	if (mddev->external && strncmp(buf, "external:", 9) == 0)
		;
	else if (!list_empty(&mddev->disks))
		goto out_unlock;

	err = 0;
	if (cmd_match(buf, "none")) {
		mddev->persistent = 0;
		mddev->external = 0;
		mddev->major_version = 0;
		mddev->minor_version = 90;
		goto out_unlock;
	}
	if (strncmp(buf, "external:", 9) == 0) {
		size_t namelen = len-9;
		if (namelen >= sizeof(mddev->metadata_type))
			namelen = sizeof(mddev->metadata_type)-1;
		strncpy(mddev->metadata_type, buf+9, namelen);
		mddev->metadata_type[namelen] = 0;
		if (namelen && mddev->metadata_type[namelen-1] == '\n')
			mddev->metadata_type[--namelen] = 0;
		mddev->persistent = 0;
		mddev->external = 1;
		mddev->major_version = 0;
		mddev->minor_version = 90;
		goto out_unlock;
	}
	major = simple_strtoul(buf, &e, 10);
	err = -EINVAL;
	if (e==buf || *e != '.')
		goto out_unlock;
	buf = e+1;
	minor = simple_strtoul(buf, &e, 10);
	if (e==buf || (*e && *e != '\n') )
		goto out_unlock;
	err = -ENOENT;
	if (major >= ARRAY_SIZE(super_types) || super_types[major].name == NULL)
		goto out_unlock;
	mddev->major_version = major;
	mddev->minor_version = minor;
	mddev->persistent = 1;
	mddev->external = 0;
	err = 0;
out_unlock:
	mddev_unlock(mddev);
	return err ?: len;
}

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

static ssize_t
action_show(struct mddev *mddev, char *page)
{
	char *type = "idle";
	unsigned long recovery = mddev->recovery;
	if (test_bit(MD_RECOVERY_FROZEN, &recovery))
		type = "frozen";
	else if (test_bit(MD_RECOVERY_RUNNING, &recovery) ||
	    (md_is_rdwr(mddev) && test_bit(MD_RECOVERY_NEEDED, &recovery))) {
		if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
			type = "reshape";
		else if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
			if (!test_bit(MD_RECOVERY_REQUESTED, &recovery))
				type = "resync";
			else if (test_bit(MD_RECOVERY_CHECK, &recovery))
				type = "check";
			else
				type = "repair";
		} else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
			type = "recover";
		else if (mddev->reshape_position != MaxSector)
			type = "reshape";
	}
	return sprintf(page, "%s\n", type);
}

static void stop_sync_thread(struct mddev *mddev)
{
	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
		return;

	if (mddev_lock(mddev))
		return;

	/*
	 * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
	 * held.
	 */
	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
		mddev_unlock(mddev);
		return;
	}

	if (work_pending(&mddev->del_work))
		flush_workqueue(md_misc_wq);

	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
	/*
	 * Thread might be blocked waiting for metadata update which will now
	 * never happen
	 */
	md_wakeup_thread_directly(mddev->sync_thread);

	mddev_unlock(mddev);
}

static void idle_sync_thread(struct mddev *mddev)
{
	int sync_seq = atomic_read(&mddev->sync_seq);

	mutex_lock(&mddev->sync_mutex);
	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
	stop_sync_thread(mddev);

	wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) ||
			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));

	mutex_unlock(&mddev->sync_mutex);
}

static void frozen_sync_thread(struct mddev *mddev)
{
	mutex_lock(&mddev->sync_mutex);
	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
	stop_sync_thread(mddev);

	wait_event(resync_wait, mddev->sync_thread == NULL &&
			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));

	mutex_unlock(&mddev->sync_mutex);
}

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


	if (cmd_match(page, "idle"))
		idle_sync_thread(mddev);
	else if (cmd_match(page, "frozen"))
		frozen_sync_thread(mddev);
	else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
		return -EBUSY;
	else if (cmd_match(page, "resync"))
		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
	else if (cmd_match(page, "recover")) {
		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
	} else if (cmd_match(page, "reshape")) {
		int err;
		if (mddev->pers->start_reshape == NULL)
			return -EINVAL;
		err = mddev_lock(mddev);
		if (!err) {
			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
				err =  -EBUSY;
			} else if (mddev->reshape_position == MaxSector ||
				   mddev->pers->check_reshape == NULL ||
				   mddev->pers->check_reshape(mddev)) {
				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
				err = mddev->pers->start_reshape(mddev);
			} else {
				/*
				 * If reshape is still in progress, and
				 * md_check_recovery() can continue to reshape,
				 * don't restart reshape because data can be
				 * corrupted for raid456.
				 */
				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
			}
			mddev_unlock(mddev);
		}
		if (err)
			return err;
		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
	} else {
		if (cmd_match(page, "check"))
			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
		else if (!cmd_match(page, "repair"))
			return -EINVAL;
		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
	}
	if (mddev->ro == MD_AUTO_READ) {
		/* A write to sync_action is enough to justify
		 * canceling read-auto mode
		 */
		mddev->ro = MD_RDWR;
		md_wakeup_thread(mddev->sync_thread);
	}
	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	md_wakeup_thread(mddev->thread);
	sysfs_notify_dirent_safe(mddev->sysfs_action);
	return len;
}

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

static ssize_t
last_sync_action_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%s\n", mddev->last_sync_action);
}

static struct md_sysfs_entry md_last_scan_mode = __ATTR_RO(last_sync_action);

static ssize_t
mismatch_cnt_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%llu\n",
		       (unsigned long long)
		       atomic64_read(&mddev->resync_mismatches));
}

static struct md_sysfs_entry md_mismatches = __ATTR_RO(mismatch_cnt);

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

static ssize_t
sync_min_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned int min;
	int rv;

	if (strncmp(buf, "system", 6)==0) {
		min = 0;
	} else {
		rv = kstrtouint(buf, 10, &min);
		if (rv < 0)
			return rv;
		if (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(struct mddev *mddev, char *page)
{
	return sprintf(page, "%d (%s)\n", speed_max(mddev),
		       mddev->sync_speed_max ? "local": "system");
}

static ssize_t
sync_max_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned int max;
	int rv;

	if (strncmp(buf, "system", 6)==0) {
		max = 0;
	} else {
		rv = kstrtouint(buf, 10, &max);
		if (rv < 0)
			return rv;
		if (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(struct mddev *mddev, char *page)
{
	return sprintf(page, "%d\n", mddev->degraded);
}
static struct md_sysfs_entry md_degraded = __ATTR_RO(degraded);

static ssize_t
sync_force_parallel_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%d\n", mddev->parallel_resync);
}

static ssize_t
sync_force_parallel_store(struct mddev *mddev, const char *buf, size_t len)
{
	long n;

	if (kstrtol(buf, 10, &n))
		return -EINVAL;

	if (n != 0 && n != 1)
		return -EINVAL;

	mddev->parallel_resync = n;

	if (mddev->sync_thread)
		wake_up(&resync_wait);

	return len;
}

/* force parallel resync, even with shared block devices */
static struct md_sysfs_entry md_sync_force_parallel =
__ATTR(sync_force_parallel, S_IRUGO|S_IWUSR,
       sync_force_parallel_show, sync_force_parallel_store);

static ssize_t
sync_speed_show(struct mddev *mddev, char *page)
{
	unsigned long resync, dt, db;
	if (mddev->curr_resync == MD_RESYNC_NONE)
		return sprintf(page, "none\n");
	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, "%lu\n", db/dt/2); /* K/sec */
}

static struct md_sysfs_entry md_sync_speed = __ATTR_RO(sync_speed);

static ssize_t
sync_completed_show(struct mddev *mddev, char *page)
{
	unsigned long long max_sectors, resync;

	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
		return sprintf(page, "none\n");

	if (mddev->curr_resync == MD_RESYNC_YIELDED ||
	    mddev->curr_resync == MD_RESYNC_DELAYED)
		return sprintf(page, "delayed\n");

	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
	    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
		max_sectors = mddev->resync_max_sectors;
	else
		max_sectors = mddev->dev_sectors;

	resync = mddev->curr_resync_completed;
	return sprintf(page, "%llu / %llu\n", resync, max_sectors);
}

static struct md_sysfs_entry md_sync_completed =
	__ATTR_PREALLOC(sync_completed, S_IRUGO, sync_completed_show, NULL);

static ssize_t
min_sync_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%llu\n",
		       (unsigned long long)mddev->resync_min);
}
static ssize_t
min_sync_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned long long min;
	int err;

	if (kstrtoull(buf, 10, &min))
		return -EINVAL;

	spin_lock(&mddev->lock);
	err = -EINVAL;
	if (min > mddev->resync_max)
		goto out_unlock;

	err = -EBUSY;
	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
		goto out_unlock;

	/* Round down to multiple of 4K for safety */
	mddev->resync_min = round_down(min, 8);
	err = 0;

out_unlock:
	spin_unlock(&mddev->lock);
	return err ?: len;
}

static struct md_sysfs_entry md_min_sync =
__ATTR(sync_min, S_IRUGO|S_IWUSR, min_sync_show, min_sync_store);

static ssize_t
max_sync_show(struct mddev *mddev, char *page)
{
	if (mddev->resync_max == MaxSector)
		return sprintf(page, "max\n");
	else
		return sprintf(page, "%llu\n",
			       (unsigned long long)mddev->resync_max);
}
static ssize_t
max_sync_store(struct mddev *mddev, const char *buf, size_t len)
{
	int err;
	spin_lock(&mddev->lock);
	if (strncmp(buf, "max", 3) == 0)
		mddev->resync_max = MaxSector;
	else {
		unsigned long long max;
		int chunk;

		err = -EINVAL;
		if (kstrtoull(buf, 10, &max))
			goto out_unlock;
		if (max < mddev->resync_min)
			goto out_unlock;

		err = -EBUSY;
		if (max < mddev->resync_max && md_is_rdwr(mddev) &&
		    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
			goto out_unlock;

		/* Must be a multiple of chunk_size */
		chunk = mddev->chunk_sectors;
		if (chunk) {
			sector_t temp = max;

			err = -EINVAL;
			if (sector_div(temp, chunk))
				goto out_unlock;
		}
		mddev->resync_max = max;
	}
	wake_up(&mddev->recovery_wait);
	err = 0;
out_unlock:
	spin_unlock(&mddev->lock);
	return err ?: len;
}

static struct md_sysfs_entry md_max_sync =
__ATTR(sync_max, S_IRUGO|S_IWUSR, max_sync_show, max_sync_store);

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

static ssize_t
suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned long long new;
	int err;

	err = kstrtoull(buf, 10, &new);
	if (err < 0)
		return err;
	if (new != (sector_t)new)
		return -EINVAL;

	err = mddev_lock(mddev);
	if (err)
		return err;
	err = -EINVAL;
	if (mddev->pers == NULL ||
	    mddev->pers->quiesce == NULL)
		goto unlock;
	mddev_suspend(mddev);
	mddev->suspend_lo = new;
	mddev_resume(mddev);

	err = 0;
unlock:
	mddev_unlock(mddev);
	return err ?: len;
}
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(struct mddev *mddev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_hi);
}

static ssize_t
suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
{
	unsigned long long new;
	int err;

	err = kstrtoull(buf, 10, &new);
	if (err < 0)
		return err;
	if (new != (sector_t)new)
		return -EINVAL;

	err = mddev_lock(mddev);
	if (err)
		return err;
	err = -EINVAL;
	if (mddev->pers == NULL)
		goto unlock;

	mddev_suspend(mddev);
	mddev->suspend_hi = new;
	mddev_resume(mddev);

	err = 0;
unlock:
	mddev_unlock(mddev);
	return err ?: len;
}
static struct md_sysfs_entry md_suspend_hi =
__ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);

static ssize_t
reshape_position_show(struct mddev *mddev, char *page)
{
	if (mddev->reshape_position != MaxSector)
		return sprintf(page, "%llu\n",
			       (unsigned long long)mddev->reshape_position);
	strcpy(page, "none\n");
	return 5;
}

static ssize_t
reshape_position_store(struct mddev *mddev, const char *buf, size_t len)
{
	struct md_rdev *rdev;
	unsigned long long new;
	int err;

	err = kstrtoull(buf, 10, &new);
	if (err < 0)
		return err;
	if (new != (sector_t)new)
		return -EINVAL;
	err = mddev_lock(mddev);
	if (err)
		return err;
	err = -EBUSY;
	if (mddev->pers)
		goto unlock;
	mddev->reshape_position = new;
	mddev->delta_disks = 0;
	mddev->reshape_backwards = 0;
	mddev->new_level = mddev->level;
	mddev->new_layout = mddev->layout;
	mddev->new_chunk_sectors = mddev->chunk_sectors;
	rdev_for_each(rdev, mddev)
		rdev->new_data_offset = rdev->data_offset;
	err = 0;
unlock:
	mddev_unlock(mddev);
	return err ?: len;
}

static struct md_sysfs_entry md_reshape_position =
__ATTR(reshape_position, S_IRUGO|S_IWUSR, reshape_position_show,
       reshape_position_store);

static ssize_t
reshape_direction_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%s\n",
		       mddev->reshape_backwards ? "backwards" : "forwards");
}

static ssize_t
reshape_direction_store(struct mddev *mddev, const char *buf, size_t len)
{
	int backwards = 0;
	int err;

	if (cmd_match(buf, "forwards"))
		backwards = 0;
	else if (cmd_match(buf, "backwards"))
		backwards = 1;
	else
		return -EINVAL;
	if (mddev->reshape_backwards == backwards)
		return len;

	err = mddev_lock(mddev);
	if (err)
		return err;
	/* check if we are allowed to change */
	if (mddev->delta_disks)
		err = -EBUSY;
	else if (mddev->persistent &&
	    mddev->major_version == 0)
		err =  -EINVAL;
	else
		mddev->reshape_backwards = backwards;
	mddev_unlock(mddev);
	return err ?: len;
}

static struct md_sysfs_entry md_reshape_direction =
__ATTR(reshape_direction, S_IRUGO|S_IWUSR, reshape_direction_show,
       reshape_direction_store);

static ssize_t
array_size_show(struct mddev *mddev, char *page)
{
	if (mddev->external_size)
		return sprintf(page, "%llu\n",
			       (unsigned long long)mddev->array_sectors/2);
	else
		return sprintf(page, "default\n");
}

static ssize_t
array_size_store(struct mddev *mddev, const char *buf, size_t len)
{
	sector_t sectors;
	int err;

	err = mddev_lock(mddev);
	if (err)
		return err;

	/* cluster raid doesn't support change array_sectors */
	if (mddev_is_clustered(mddev)) {
		mddev_unlock(mddev);
		return -EINVAL;
	}

	if (strncmp(buf, "default", 7) == 0) {
		if (mddev->pers)
			sectors = mddev->pers->size(mddev, 0, 0);
		else
			sectors = mddev->array_sectors;

		mddev->external_size = 0;
	} else {
		if (strict_blocks_to_sectors(buf, &sectors) < 0)
			err = -EINVAL;
		else if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
			err = -E2BIG;
		else
			mddev->external_size = 1;
	}

	if (!err) {
		mddev->array_sectors = sectors;
		if (mddev->pers)
			set_capacity_and_notify(mddev->gendisk,
						mddev->array_sectors);
	}
	mddev_unlock(mddev);
	return err ?: len;
}

static struct md_sysfs_entry md_array_size =
__ATTR(array_size, S_IRUGO|S_IWUSR, array_size_show,
       array_size_store);

static ssize_t
consistency_policy_show(struct mddev *mddev, char *page)
{
	int ret;

	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
		ret = sprintf(page, "journal\n");
	} else if (test_bit(MD_HAS_PPL, &mddev->flags)) {
		ret = sprintf(page, "ppl\n");
	} else if (mddev->bitmap) {
		ret = sprintf(page, "bitmap\n");
	} else if (mddev->pers) {
		if (mddev->pers->sync_request)
			ret = sprintf(page, "resync\n");
		else
			ret = sprintf(page, "none\n");
	} else {
		ret = sprintf(page, "unknown\n");
	}

	return ret;
}

static ssize_t
consistency_policy_store(struct mddev *mddev, const char *buf, size_t len)
{
	int err = 0;

	if (mddev->pers) {
		if (mddev->pers->change_consistency_policy)
			err = mddev->pers->change_consistency_policy(mddev, buf);
		else
			err = -EBUSY;
	} else if (mddev->external && strncmp(buf, "ppl", 3) == 0) {
		set_bit(MD_HAS_PPL, &mddev->flags);
	} else {
		err = -EINVAL;
	}

	return err ? err : len;
}

static struct md_sysfs_entry md_consistency_policy =
__ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show,
       consistency_policy_store);

static ssize_t fail_last_dev_show(struct mddev *mddev, char *page)
{
	return sprintf(page, "%d\n", mddev->fail_last_dev);
}

/*
 * Setting fail_last_dev to true to allow last device to be forcibly removed
 * from RAID1/RAID10.
 */
static ssize_t
fail_last_dev_store(struct mddev *mddev, const char *buf, size_t len)
{
	int ret;
	bool value;

	ret = kstrtobool(buf, &value);
	if (ret)
		return ret;

	if (value != mddev->fail_last_dev)
		mddev->fail_last_dev = value;

	return len;
}
static struct md_sysfs_entry md_fail_last_dev =
__ATTR(fail_last_dev, S_IRUGO | S_IWUSR, fail_last_dev_show,
       fail_last_dev_store);

static ssize_t serialize_policy_show(struct mddev *mddev, char *page)
{
	if (mddev->pers == NULL || (mddev->pers->level != 1))
		return sprintf(page, "n/a\n");
	else
		return sprintf(page, "%d\n", mddev->serialize_policy);
}

/*
 * Setting serialize_policy to true to enforce write IO is not reordered
 * for raid1.
 */
static ssize_t
serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)
{
	int err;
	bool value;

	err = kstrtobool(buf, &value);
	if (err)
		return err;

	if (value == mddev->serialize_policy)
		return len;

	err = mddev_lock(mddev);
	if (err)
		return err;
	if (mddev->pers == NULL || (mddev->pers->level != 1)) {
		pr_err("md: serialize_policy is only effective for raid1\n");
		err = -EINVAL;
		goto unlock;
	}

	mddev_suspend(mddev);
	if (value)
		mddev_create_serial_pool(mddev, NULL, true);
	else
		mddev_destroy_serial_pool(mddev, NULL, true);
	mddev->serialize_policy = value;
	mddev_resume(mddev);
unlock:
	mddev_unlock(mddev);
	return err ?: len;
}

static struct md_sysfs_entry md_serialize_policy =
__ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show,
       serialize_policy_store);


static struct attribute *md_default_attrs[] = {
	&md_level.attr,
	&md_layout.attr,
	&md_raid_disks.attr,
	&md_uuid.attr,
	&md_chunk_size.attr,
	&md_size.attr,
	&md_resync_start.attr,
	&md_metadata.attr,
	&md_new_device.attr,
	&md_safe_delay.attr,
	&md_array_state.attr,
	&md_reshape_position.attr,
	&md_reshape_direction.attr,
	&md_array_size.attr,
	&max_corr_read_errors.attr,
	&md_consistency_policy.attr,
	&md_fail_last_dev.attr,
	&md_serialize_policy.attr,
	NULL,
};

static const struct attribute_group md_default_group = {
	.attrs = md_default_attrs,
};

static struct attribute *md_redundancy_attrs[] = {
	&md_scan_mode.attr,
	&md_last_scan_mode.attr,
	&md_mismatches.attr,
	&md_sync_min.attr,
	&md_sync_max.attr,
	&md_sync_speed.attr,
	&md_sync_force_parallel.attr,
	&md_sync_completed.attr,
	&md_min_sync.attr,
	&md_max_sync.attr,
	&md_suspend_lo.attr,
	&md_suspend_hi.attr,
	&md_bitmap.attr,
	&md_degraded.attr,
	NULL,
};
static const struct attribute_group md_redundancy_group = {
	.name = NULL,
	.attrs = md_redundancy_attrs,
};

static const struct attribute_group *md_attr_groups[] = {
	&md_default_group,
	&md_bitmap_group,
	NULL,
};

static ssize_t
md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
	struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
	struct mddev *mddev = container_of(kobj, struct mddev, kobj);
	ssize_t rv;

	if (!entry->show)
		return -EIO;
	spin_lock(&all_mddevs_lock);
	if (!mddev_get(mddev)) {
		spin_unlock(&all_mddevs_lock);
		return -EBUSY;
	}
	spin_unlock(&all_mddevs_lock);

	rv = entry->show(mddev, page);
	mddev_put(mddev);
	return rv;
}

static ssize_t
md_attr_store(struct kobject *kobj, struct attribute *attr,
	      const char *page, size_t length)
{
	struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
	struct mddev *mddev = container_of(kobj, struct mddev, kobj);
	ssize_t rv;

	if (!entry->store)
		return -EIO;
	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	spin_lock(&all_mddevs_lock);
	if (!mddev_get(mddev)) {
		spin_unlock(&all_mddevs_lock);
		return -EBUSY;
	}
	spin_unlock(&all_mddevs_lock);
	rv = entry->store(mddev, page, length);
	mddev_put(mddev);
	return rv;
}

static void md_kobj_release(struct kobject *ko)
{
	struct mddev *mddev = container_of(ko, struct mddev, kobj);

	if (mddev->sysfs_state)
		sysfs_put(mddev->sysfs_state);
	if (mddev->sysfs_level)
		sysfs_put(mddev->sysfs_level);

	del_gendisk(mddev->gendisk);
	put_disk(mddev->gendisk);
}

static const struct sysfs_ops md_sysfs_ops = {
	.show	= md_attr_show,
	.store	= md_attr_store,
};
static const struct kobj_type md_ktype = {
	.release	= md_kobj_release,
	.sysfs_ops	= &md_sysfs_ops,
	.default_groups	= md_attr_groups,
};

int mdp_major = 0;

static void mddev_delayed_delete(struct work_struct *ws)
{
	struct mddev *mddev = container_of(ws, struct mddev, del_work);

	kobject_put(&mddev->kobj);
}

static void no_op(struct percpu_ref *r) {}

int mddev_init_writes_pending(struct mddev *mddev)
{
	if (mddev->writes_pending.percpu_count_ptr)
		return 0;
	if (percpu_ref_init(&mddev->writes_pending, no_op,
			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL) < 0)
		return -ENOMEM;
	/* We want to start with the refcount at zero */
	percpu_ref_put(&mddev->writes_pending);
	return 0;
}
EXPORT_SYMBOL_GPL(mddev_init_writes_pending);

struct mddev *md_alloc(dev_t dev, char *name)
{
	/*
	 * If dev is zero, name is the name of a device to allocate with
	 * an arbitrary minor number.  It will be "md_???"
	 * If dev is non-zero it must be a device number with a MAJOR of
	 * MD_MAJOR or mdp_major.  In this case, if "name" is NULL, then
	 * the device is being created by opening a node in /dev.
	 * If "name" is not NULL, the device is being created by
	 * writing to /sys/module/md_mod/parameters/new_array.
	 */
	static DEFINE_MUTEX(disks_mutex);
	struct mddev *mddev;
	struct gendisk *disk;
	int partitioned;
	int shift;
	int unit;
	int error ;

	/*
	 * Wait for any previous instance of this device to be completely
	 * removed (mddev_delayed_delete).
	 */
	flush_workqueue(md_misc_wq);

	mutex_lock(&disks_mutex);
	mddev = mddev_alloc(dev);
	if (IS_ERR(mddev)) {
		error = PTR_ERR(mddev);
		goto out_unlock;
	}

	partitioned = (MAJOR(mddev->unit) != MD_MAJOR);
	shift = partitioned ? MdpMinorShift : 0;
	unit = MINOR(mddev->unit) >> shift;

	if (name && !dev) {
		/* Need to ensure that 'name' is not a duplicate.
		 */
		struct mddev *mddev2;
		spin_lock(&all_mddevs_lock);

		list_for_each_entry(mddev2, &all_mddevs, all_mddevs)
			if (mddev2->gendisk &&
			    strcmp(mddev2->gendisk->disk_name, name) == 0) {
				spin_unlock(&all_mddevs_lock);
				error = -EEXIST;
				goto out_free_mddev;
			}
		spin_unlock(&all_mddevs_lock);
	}
	if (name && dev)
		/*
		 * Creating /dev/mdNNN via "newarray", so adjust hold_active.
		 */
		mddev->hold_active = UNTIL_STOP;

	error = -ENOMEM;
	disk = blk_alloc_disk(NUMA_NO_NODE);
	if (!disk)
		goto out_free_mddev;

	disk->major = MAJOR(mddev->unit);
	disk->first_minor = unit << shift;
	disk->minors = 1 << shift;
	if (name)
		strcpy(disk->disk_name, name);
	else if (partitioned)
		sprintf(disk->disk_name, "md_d%d", unit);
	else
		sprintf(disk->disk_name, "md%d", unit);
	disk->fops = &md_fops;
	disk->private_data = mddev;

	mddev->queue = disk->queue;
	blk_set_stacking_limits(&mddev->queue->limits);
	blk_queue_write_cache(mddev->queue, true, true);
	disk->events |= DISK_EVENT_MEDIA_CHANGE;
	mddev->gendisk = disk;
	error = add_disk(disk);
	if (error)
		goto out_put_disk;

	kobject_init(&mddev->kobj, &md_ktype);
	error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md");
	if (error) {
		/*
		 * The disk is already live at this point.  Clear the hold flag
		 * and let mddev_put take care of the deletion, as it isn't any
		 * different from a normal close on last release now.
		 */
		mddev->hold_active = 0;
		mutex_unlock(&disks_mutex);
		mddev_put(mddev);
		return ERR_PTR(error);
	}

	kobject_uevent(&mddev->kobj, KOBJ_ADD);
	mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
	mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
	mutex_unlock(&disks_mutex);
	return mddev;

out_put_disk:
	put_disk(disk);
out_free_mddev:
	mddev_free(mddev);
out_unlock:
	mutex_unlock(&disks_mutex);
	return ERR_PTR(error);
}

static int md_alloc_and_put(dev_t dev, char *name)
{
	struct mddev *mddev = md_alloc(dev, name);

	if (IS_ERR(mddev))
		return PTR_ERR(mddev);
	mddev_put(mddev);
	return 0;
}

static void md_probe(dev_t dev)
{
	if (MAJOR(dev) == MD_MAJOR && MINOR(dev) >= 512)
		return;
	if (create_on_open)
		md_alloc_and_put(dev, NULL);
}

static int add_named_array(const char *val, const struct kernel_param *kp)
{
	/*
	 * val must be "md_*" or "mdNNN".
	 * For "md_*" we allocate an array with a large free minor number, and
	 * set the name to val.  val must not already be an active name.
	 * For "mdNNN" we allocate an array with the minor number NNN
	 * which must not already be in use.
	 */
	int len = strlen(val);
	char buf[DISK_NAME_LEN];
	unsigned long devnum;

	while (len && val[len-1] == '\n')
		len--;
	if (len >= DISK_NAME_LEN)
		return -E2BIG;
	strscpy(buf, val, len+1);
	if (strncmp(buf, "md_", 3) == 0)
		return md_alloc_and_put(0, buf);
	if (strncmp(buf, "md", 2) == 0 &&
	    isdigit(buf[2]) &&
	    kstrtoul(buf+2, 10, &devnum) == 0 &&
	    devnum <= MINORMASK)
		return md_alloc_and_put(MKDEV(MD_MAJOR, devnum), NULL);

	return -EINVAL;
}

static void md_safemode_timeout(struct timer_list *t)
{
	struct mddev *mddev = from_timer(mddev, t, safemode_timer);

	mddev->safemode = 1;
	if (mddev->external)
		sysfs_notify_dirent_safe(mddev->sysfs_state);

	md_wakeup_thread(mddev->thread);
}

static int start_dirty_degraded;
static void active_io_release(struct percpu_ref *ref)
{
	struct mddev *mddev = container_of(ref, struct mddev, active_io);

	wake_up(&mddev->sb_wait);
}

int md_run(struct mddev *mddev)
{
	int err;
	struct md_rdev *rdev;
	struct md_personality *pers;
	bool nowait = true;

	if (list_empty(&mddev->disks))
		/* cannot run an array with no devices.. */
		return -EINVAL;

	if (mddev->pers)
		return -EBUSY;
	/* Cannot run until previous stop completes properly */
	if (mddev->sysfs_active)
		return -EBUSY;

	/*
	 * Analyze all RAID superblock(s)
	 */
	if (!mddev->raid_disks) {
		if (!mddev->persistent)
			return -EINVAL;
		err = analyze_sbs(mddev);
		if (err)
			return -EINVAL;
	}

	if (mddev->level != LEVEL_NONE)
		request_module("md-level-%d", mddev->level);
	else if (mddev->clevel[0])
		request_module("md-%s", mddev->clevel);

	/*
	 * Drop all container device buffers, from now on
	 * the only valid external interface is through the md
	 * device.
	 */
	mddev->has_superblocks = false;
	rdev_for_each(rdev, mddev) {
		if (test_bit(Faulty, &rdev->flags))
			continue;
		sync_blockdev(rdev->bdev);
		invalidate_bdev(rdev->bdev);
		if (mddev->ro != MD_RDONLY && rdev_read_only(rdev)) {
			mddev->ro = MD_RDONLY;
			if (mddev->gendisk)
				set_disk_ro(mddev->gendisk, 1);
		}

		if (rdev->sb_page)
			mddev->has_superblocks = true;

		/* perform some consistency tests on the device.
		 * We don't want the data to overlap the metadata,
		 * Internal Bitmap issues have been handled elsewhere.
		 */
		if (rdev->meta_bdev) {
			/* Nothing to check */;
		} else if (rdev->data_offset < rdev->sb_start) {
			if (mddev->dev_sectors &&
			    rdev->data_offset + mddev->dev_sectors
			    > rdev->sb_start) {
				pr_warn("md: %s: data overlaps metadata\n",
					mdname(mddev));
				return -EINVAL;
			}
		} else {
			if (rdev->sb_start + rdev->sb_size/512
			    > rdev->data_offset) {
				pr_warn("md: %s: metadata overlaps data\n",
					mdname(mddev));
				return -EINVAL;
			}
		}
		sysfs_notify_dirent_safe(rdev->sysfs_state);
		nowait = nowait && bdev_nowait(rdev->bdev);
	}

	err = percpu_ref_init(&mddev->active_io, active_io_release,
				PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
	if (err)
		return err;

	if (!bioset_initialized(&mddev->bio_set)) {
		err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
		if (err)
			goto exit_active_io;
	}
	if (!bioset_initialized(&mddev->sync_set)) {
		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
		if (err)
			goto exit_bio_set;
	}

	if (!bioset_initialized(&mddev->io_clone_set)) {
		err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
				  offsetof(struct md_io_clone, bio_clone), 0);
		if (err)
			goto exit_sync_set;
	}

	spin_lock(&pers_lock);
	pers = find_pers(mddev->level, mddev->clevel);
	if (!pers || !try_module_get(pers->owner)) {
		spin_unlock(&pers_lock);
		if (mddev->level != LEVEL_NONE)
			pr_warn("md: personality for level %d is not loaded!\n",
				mddev->level);
		else
			pr_warn("md: personality for level %s is not loaded!\n",
				mddev->clevel);
		err = -EINVAL;
		goto abort;
	}
	spin_unlock(&pers_lock);
	if (mddev->level != pers->level) {
		mddev->level = pers->level;
		mddev->new_level = pers->level;
	}
	strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));

	if (mddev->reshape_position != MaxSector &&
	    pers->start_reshape == NULL) {
		/* This personality cannot handle reshaping... */
		module_put(pers->owner);
		err = -EINVAL;
		goto abort;
	}

	if (pers->sync_request) {
		/* Warn if this is a potentially silly
		 * configuration.
		 */
		struct md_rdev *rdev2;
		int warned = 0;

		rdev_for_each(rdev, mddev)
			rdev_for_each(rdev2, mddev) {
				if (rdev < rdev2 &&
				    rdev->bdev->bd_disk ==
				    rdev2->bdev->bd_disk) {
					pr_warn("%s: WARNING: %pg appears to be on the same physical disk as %pg.\n",
						mdname(mddev),
						rdev->bdev,
						rdev2->bdev);
					warned = 1;
				}
			}

		if (warned)
			pr_warn("True protection against single-disk failure might be compromised.\n");
	}

	mddev->recovery = 0;
	/* may be over-ridden by personality */
	mddev->resync_max_sectors = mddev->dev_sectors;

	mddev->ok_start_degraded = start_dirty_degraded;

	if (start_readonly && md_is_rdwr(mddev))
		mddev->ro = MD_AUTO_READ; /* read-only, but switch on first write */

	err = pers->run(mddev);
	if (err)
		pr_warn("md: pers->run() failed ...\n");
	else if (pers->size(mddev, 0, 0) < mddev->array_sectors) {
		WARN_ONCE(!mddev->external_size,
			  "%s: default size too small, but 'external_size' not in effect?\n",
			  __func__);
		pr_warn("md: invalid array_size %llu > default size %llu\n",
			(unsigned long long)mddev->array_sectors / 2,
			(unsigned long long)pers->size(mddev, 0, 0) / 2);
		err = -EINVAL;
	}
	if (err == 0 && pers->sync_request &&
	    (mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
		struct bitmap *bitmap;

		bitmap = md_bitmap_create(mddev, -1);
		if (IS_ERR(bitmap)) {
			err = PTR_ERR(bitmap);
			pr_warn("%s: failed to create bitmap (%d)\n",
				mdname(mddev), err);
		} else
			mddev->bitmap = bitmap;

	}
	if (err)
		goto bitmap_abort;

	if (mddev->bitmap_info.max_write_behind > 0) {
		bool create_pool = false;

		rdev_for_each(rdev, mddev) {
			if (test_bit(WriteMostly, &rdev->flags) &&
			    rdev_init_serial(rdev))
				create_pool = true;
		}
		if (create_pool && mddev->serial_info_pool == NULL) {
			mddev->serial_info_pool =
				mempool_create_kmalloc_pool(NR_SERIAL_INFOS,
						    sizeof(struct serial_info));
			if (!mddev->serial_info_pool) {
				err = -ENOMEM;
				goto bitmap_abort;
			}
		}
	}

	if (mddev->queue) {
		bool nonrot = true;

		rdev_for_each(rdev, mddev) {
			if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) {
				nonrot = false;
				break;
			}
		}
		if (mddev->degraded)
			nonrot = false;
		if (nonrot)
			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
		else
			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);

		/* Set the NOWAIT flags if all underlying devices support it */
		if (nowait)
			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue);
	}
	if (pers->sync_request) {
		if (mddev->kobj.sd &&
		    sysfs_create_group(&mddev->kobj, &md_redundancy_group))
			pr_warn("md: cannot register extra attributes for %s\n",
				mdname(mddev));
		mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action");
		mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed");
		mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded");
	} else if (mddev->ro == MD_AUTO_READ)
		mddev->ro = MD_RDWR;

	atomic_set(&mddev->max_corr_read_errors,
		   MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
	mddev->safemode = 0;
	if (mddev_is_clustered(mddev))
		mddev->safemode_delay = 0;
	else
		mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
	mddev->in_sync = 1;
	smp_wmb();
	spin_lock(&mddev->lock);
	mddev->pers = pers;
	spin_unlock(&mddev->lock);
	rdev_for_each(rdev, mddev)
		if (rdev->raid_disk >= 0)
			sysfs_link_rdev(mddev, rdev); /* failure here is OK */

	if (mddev->degraded && md_is_rdwr(mddev))
		/* This ensures that recovering status is reported immediately
		 * via sysfs - until a lack of spares is confirmed.
		 */
		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);

	if (mddev->sb_flags)
		md_update_sb(mddev, 0);

	md_new_event();
	return 0;

bitmap_abort:
	mddev_detach(mddev);
	if (mddev->private)
		pers->free(mddev, mddev->private);
	mddev->private = NULL;
	module_put(pers->owner);
	md_bitmap_destroy(mddev);
abort:
	bioset_exit(&mddev->io_clone_set);
exit_sync_set:
	bioset_exit(&mddev->sync_set);
exit_bio_set:
	bioset_exit(&mddev->bio_set);
exit_active_io:
	percpu_ref_exit(&mddev->active_io);
	return err;
}
EXPORT_SYMBOL_GPL(md_run);

int do_md_run(struct mddev *mddev)
{
	int err;

	set_bit(MD_NOT_READY, &mddev->flags);
	err = md_run(mddev);
	if (err)
		goto out;
	err = md_bitmap_load(mddev);
	if (err) {
		md_bitmap_destroy(mddev);
		goto out;
	}

	if (mddev_is_clustered(mddev))
		md_allow_write(mddev);

	/* run start up tasks that require md_thread */
	md_start(mddev);

	md_wakeup_thread(mddev->thread);
	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */

	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
	clear_bit(MD_NOT_READY, &mddev->flags);
	mddev->changed = 1;
	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
	sysfs_notify_dirent_safe(mddev->sysfs_state);
	sysfs_notify_dirent_safe(mddev->sysfs_action);
	sysfs_notify_dirent_safe(mddev->sysfs_degraded);
out:
	clear_bit(MD_NOT_READY, &mddev->flags);
	return err;
}

int md_start(struct mddev *mddev)
{
	int ret = 0;

	if (mddev->pers->start) {
		set_bit(MD_RECOVERY_WAIT, &