Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (45 commits)
  md: don't insist on valid event count for spare devices.
  md: simplify updating of event count to sometimes avoid updating spares.
  md/raid6: Fix raid-6 read-error correction in degraded state
  md: restore ability of spare drives to spin down.
  md: Fix read balancing in RAID1 and RAID10 on drives > 2TB
  md/linear: standardise all printk messages
  md/raid0: tidy up printk messages.
  md/raid10: tidy up printk messages.
  md/raid1: improve printk messages
  md/raid5: improve consistency of error messages.
  md: remove EXPERIMENTAL designation from RAID10
  md: allow integers to be passed to md/level
  md: notify mdstat waiters of level change
  md/raid4: permit raid0 takeover
  md/raid1: delay reads that could overtake behind-writes.
  md/raid1: fix confusing 'redirect sector' message.
  md: don't unregister the thread in mddev_suspend
  md: factor out init code for an mddev
  md: pass mddev to make_request functions rather than request_queue
  md: call md_stop_writes from md_stop
  ...

drivers/md/Kconfig

@@ -100,8 +100,8 @@ config MD_RAID1
 	  If unsure, say Y.
 
 config MD_RAID10
-	tristate "RAID-10 (mirrored striping) mode (EXPERIMENTAL)"
-	depends on BLK_DEV_MD && EXPERIMENTAL
+	tristate "RAID-10 (mirrored striping) mode"
+	depends on BLK_DEV_MD
 	---help---
 	  RAID-10 provides a combination of striping (RAID-0) and
 	  mirroring (RAID-1) with easier configuration and more flexible

drivers/md/bitmap.c

@@ -505,7 +505,7 @@ void bitmap_update_sb(struct bitmap *bitmap)
 		return;
 	}
 	spin_unlock_irqrestore(&bitmap->lock, flags);
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
 	if (bitmap->mddev->events < bitmap->events_cleared) {
 		/* rocking back to read-only */
@@ -526,7 +526,7 @@ void bitmap_print_sb(struct bitmap *bitmap)
 
 	if (!bitmap || !bitmap->sb_page)
 		return;
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));
 	printk(KERN_DEBUG "         magic: %08x\n", le32_to_cpu(sb->magic));
 	printk(KERN_DEBUG "       version: %d\n", le32_to_cpu(sb->version));
@@ -575,7 +575,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 		return err;
 	}
 
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 
 	chunksize = le32_to_cpu(sb->chunksize);
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
@@ -661,7 +661,7 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
 		return 0;
 	}
 	spin_unlock_irqrestore(&bitmap->lock, flags);
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	old = le32_to_cpu(sb->state) & bits;
 	switch (op) {
 		case MASK_SET: sb->state |= cpu_to_le32(bits);
@@ -1292,9 +1292,14 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 	if (!bitmap) return 0;
 
 	if (behind) {
+		int bw;
 		atomic_inc(&bitmap->behind_writes);
+		bw = atomic_read(&bitmap->behind_writes);
+		if (bw > bitmap->behind_writes_used)
+			bitmap->behind_writes_used = bw;
+
 		PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n",
-		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
+		       bw, bitmap->max_write_behind);
 	}
 
 	while (sectors) {
@@ -1351,7 +1356,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 {
 	if (!bitmap) return;
 	if (behind) {
-		atomic_dec(&bitmap->behind_writes);
+		if (atomic_dec_and_test(&bitmap->behind_writes))
+			wake_up(&bitmap->behind_wait);
 		PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
 		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
 	}
@@ -1675,6 +1681,7 @@ int bitmap_create(mddev_t *mddev)
 	atomic_set(&bitmap->pending_writes, 0);
 	init_waitqueue_head(&bitmap->write_wait);
 	init_waitqueue_head(&bitmap->overflow_wait);
+	init_waitqueue_head(&bitmap->behind_wait);
 
 	bitmap->mddev = mddev;
 
@@ -2006,6 +2013,27 @@ static ssize_t can_clear_store(mddev_t *mddev, const char *buf, size_t len)
 static struct md_sysfs_entry bitmap_can_clear =
 __ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store);
 
+static ssize_t
+behind_writes_used_show(mddev_t *mddev, char *page)
+{
+	if (mddev->bitmap == NULL)
+		return sprintf(page, "0\n");
+	return sprintf(page, "%lu\n",
+		       mddev->bitmap->behind_writes_used);
+}
+
+static ssize_t
+behind_writes_used_reset(mddev_t *mddev, const char *buf, size_t len)
+{
+	if (mddev->bitmap)
+		mddev->bitmap->behind_writes_used = 0;
+	return len;
+}
+
+static struct md_sysfs_entry max_backlog_used =
+__ATTR(max_backlog_used, S_IRUGO | S_IWUSR,
+       behind_writes_used_show, behind_writes_used_reset);
+
 static struct attribute *md_bitmap_attrs[] = {
 	&bitmap_location.attr,
 	&bitmap_timeout.attr,
@@ -2013,6 +2041,7 @@ static struct attribute *md_bitmap_attrs[] = {
 	&bitmap_chunksize.attr,
 	&bitmap_metadata.attr,
 	&bitmap_can_clear.attr,
+	&max_backlog_used.attr,
 	NULL
 };
 struct attribute_group md_bitmap_group = {

drivers/md/bitmap.h

@@ -227,6 +227,7 @@ struct bitmap {
 	int allclean;
 
 	atomic_t behind_writes;
+	unsigned long behind_writes_used; /* highest actual value at runtime */
 
 	/*
 	 * the bitmap daemon - periodically wakes up and sweeps the bitmap
@@ -239,6 +240,7 @@ struct bitmap {
 	atomic_t pending_writes; /* pending writes to the bitmap file */
 	wait_queue_head_t write_wait;
 	wait_queue_head_t overflow_wait;
+	wait_queue_head_t behind_wait;
 
 	struct sysfs_dirent *sysfs_can_clear;
 };

drivers/md/faulty.c

@@ -169,10 +169,9 @@ static void add_sector(conf_t *conf, sector_t start, int mode)
 		conf->nfaults = n+1;
 }
 
-static int make_request(struct request_queue *q, struct bio *bio)
+static int make_request(mddev_t *mddev, struct bio *bio)
 {
-	mddev_t *mddev = q->queuedata;
-	conf_t *conf = (conf_t*)mddev->private;
+	conf_t *conf = mddev->private;
 	int failit = 0;
 
 	if (bio_data_dir(bio) == WRITE) {
@@ -225,7 +224,7 @@ static int make_request(struct request_queue *q, struct bio *bio)
 
 static void status(struct seq_file *seq, mddev_t *mddev)
 {
-	conf_t *conf = (conf_t*)mddev->private;
+	conf_t *conf = mddev->private;
 	int n;
 
 	if ((n=atomic_read(&conf->counters[WriteTransient])) != 0)
@@ -328,7 +327,7 @@ static int run(mddev_t *mddev)
 
 static int stop(mddev_t *mddev)
 {
-	conf_t *conf = (conf_t *)mddev->private;
+	conf_t *conf = mddev->private;
 
 	kfree(conf);
 	mddev->private = NULL;

drivers/md/linear.c

@@ -159,7 +159,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		sector_t sectors;
 
 		if (j < 0 || j >= raid_disks || disk->rdev) {
-			printk("linear: disk numbering problem. Aborting!\n");
+			printk(KERN_ERR "md/linear:%s: disk numbering problem. Aborting!\n",
+			       mdname(mddev));
 			goto out;
 		}
 
@@ -187,7 +188,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 
 	}
 	if (cnt != raid_disks) {
-		printk("linear: not enough drives present. Aborting!\n");
+		printk(KERN_ERR "md/linear:%s: not enough drives present. Aborting!\n",
+		       mdname(mddev));
 		goto out;
 	}
 
@@ -282,29 +284,21 @@ static int linear_stop (mddev_t *mddev)
 	rcu_barrier();
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	kfree(conf);
+	mddev->private = NULL;
 
 	return 0;
 }
 
-static int linear_make_request (struct request_queue *q, struct bio *bio)
+static int linear_make_request (mddev_t *mddev, struct bio *bio)
 {
-	const int rw = bio_data_dir(bio);
-	mddev_t *mddev = q->queuedata;
 	dev_info_t *tmp_dev;
 	sector_t start_sector;
-	int cpu;
 
 	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		md_barrier_request(mddev, bio);
 		return 0;
 	}
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	rcu_read_lock();
 	tmp_dev = which_dev(mddev, bio->bi_sector);
 	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
@@ -314,12 +308,14 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
 		     || (bio->bi_sector < start_sector))) {
 		char b[BDEVNAME_SIZE];
 
-		printk("linear_make_request: Sector %llu out of bounds on "
-			"dev %s: %llu sectors, offset %llu\n",
-			(unsigned long long)bio->bi_sector,
-			bdevname(tmp_dev->rdev->bdev, b),
-			(unsigned long long)tmp_dev->rdev->sectors,
-			(unsigned long long)start_sector);
+		printk(KERN_ERR
+		       "md/linear:%s: make_request: Sector %llu out of bounds on "
+		       "dev %s: %llu sectors, offset %llu\n",
+		       mdname(mddev),
+		       (unsigned long long)bio->bi_sector,
+		       bdevname(tmp_dev->rdev->bdev, b),
+		       (unsigned long long)tmp_dev->rdev->sectors,
+		       (unsigned long long)start_sector);
 		rcu_read_unlock();
 		bio_io_error(bio);
 		return 0;
@@ -336,9 +332,9 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
 
 		bp = bio_split(bio, end_sector - bio->bi_sector);
 
-		if (linear_make_request(q, &bp->bio1))
+		if (linear_make_request(mddev, &bp->bio1))
 			generic_make_request(&bp->bio1);
-		if (linear_make_request(q, &bp->bio2))
+		if (linear_make_request(mddev, &bp->bio2))
 			generic_make_request(&bp->bio2);
 		bio_pair_release(bp);
 		return 0;

drivers/md/md.c

@@ -215,8 +215,11 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
  */
 static int md_make_request(struct request_queue *q, struct bio *bio)
 {
+	const int rw = bio_data_dir(bio);
 	mddev_t *mddev = q->queuedata;
 	int rv;
+	int cpu;
+
 	if (mddev == NULL || mddev->pers == NULL) {
 		bio_io_error(bio);
 		return 0;
@@ -237,13 +240,27 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
 	}
 	atomic_inc(&mddev->active_io);
 	rcu_read_unlock();
-	rv = mddev->pers->make_request(q, bio);
+
+	rv = mddev->pers->make_request(mddev, bio);
+
+	cpu = part_stat_lock();
+	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
+	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
+		      bio_sectors(bio));
+	part_stat_unlock();
+
 	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
 		wake_up(&mddev->sb_wait);
 
 	return rv;
 }
 
+/* mddev_suspend makes sure no new requests are submitted
+ * to the device, and that any requests that have been submitted
+ * are completely handled.
+ * Once ->stop is called and completes, the module will be completely
+ * unused.
+ */
 static void mddev_suspend(mddev_t *mddev)
 {
 	BUG_ON(mddev->suspended);
@@ -251,13 +268,6 @@ static void mddev_suspend(mddev_t *mddev)
 	synchronize_rcu();
 	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
 	mddev->pers->quiesce(mddev, 1);
-	md_unregister_thread(mddev->thread);
-	mddev->thread = NULL;
-	/* we now know that no code is executing in the personality module,
-	 * except possibly the tail end of a ->bi_end_io function, but that
-	 * is certain to complete before the module has a chance to get
-	 * unloaded
-	 */
 }
 
 static void mddev_resume(mddev_t *mddev)
@@ -344,7 +354,7 @@ static void md_submit_barrier(struct work_struct *ws)
 		bio_endio(bio, 0);
 	else {
 		bio->bi_rw &= ~(1<<BIO_RW_BARRIER);
-		if (mddev->pers->make_request(mddev->queue, bio))
+		if (mddev->pers->make_request(mddev, bio))
 			generic_make_request(bio);
 		mddev->barrier = POST_REQUEST_BARRIER;
 		submit_barriers(mddev);
@@ -406,6 +416,27 @@ static void mddev_put(mddev_t *mddev)
 	spin_unlock(&all_mddevs_lock);
 }
 
+static void mddev_init(mddev_t *mddev)
+{
+	mutex_init(&mddev->open_mutex);
+	mutex_init(&mddev->reconfig_mutex);
+	mutex_init(&mddev->bitmap_info.mutex);
+	INIT_LIST_HEAD(&mddev->disks);
+	INIT_LIST_HEAD(&mddev->all_mddevs);
+	init_timer(&mddev->safemode_timer);
+	atomic_set(&mddev->active, 1);
+	atomic_set(&mddev->openers, 0);
+	atomic_set(&mddev->active_io, 0);
+	spin_lock_init(&mddev->write_lock);
+	atomic_set(&mddev->flush_pending, 0);
+	init_waitqueue_head(&mddev->sb_wait);
+	init_waitqueue_head(&mddev->recovery_wait);
+	mddev->reshape_position = MaxSector;
+	mddev->resync_min = 0;
+	mddev->resync_max = MaxSector;
+	mddev->level = LEVEL_NONE;
+}
+
 static mddev_t * mddev_find(dev_t unit)
 {
 	mddev_t *mddev, *new = NULL;
@@ -472,23 +503,7 @@ static mddev_t * mddev_find(dev_t unit)
 	else
 		new->md_minor = MINOR(unit) >> MdpMinorShift;
 
-	mutex_init(&new->open_mutex);
-	mutex_init(&new->reconfig_mutex);
-	mutex_init(&new->bitmap_info.mutex);
-	INIT_LIST_HEAD(&new->disks);
-	INIT_LIST_HEAD(&new->all_mddevs);
-	init_timer(&new->safemode_timer);
-	atomic_set(&new->active, 1);
-	atomic_set(&new->openers, 0);
-	atomic_set(&new->active_io, 0);
-	spin_lock_init(&new->write_lock);
-	atomic_set(&new->flush_pending, 0);
-	init_waitqueue_head(&new->sb_wait);
-	init_waitqueue_head(&new->recovery_wait);
-	new->reshape_position = MaxSector;
-	new->resync_min = 0;
-	new->resync_max = MaxSector;
-	new->level = LEVEL_NONE;
+	mddev_init(new);
 
 	goto retry;
 }
@@ -508,9 +523,36 @@ static inline int mddev_trylock(mddev_t * mddev)
 	return mutex_trylock(&mddev->reconfig_mutex);
 }
 
-static inline void mddev_unlock(mddev_t * mddev)
+static struct attribute_group md_redundancy_group;
+
+static void mddev_unlock(mddev_t * mddev)
 {
-	mutex_unlock(&mddev->reconfig_mutex);
+	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 open_mutex instead - we are allowed to take
+		 * it while holding reconfig_mutex, and md_run can
+		 * use it to wait for the remove to complete.
+		 */
+		struct attribute_group *to_remove = mddev->to_remove;
+		mddev->to_remove = NULL;
+		mutex_lock(&mddev->open_mutex);
+		mutex_unlock(&mddev->reconfig_mutex);
+
+		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);
+			mddev->sysfs_action = NULL;
+		}
+		mutex_unlock(&mddev->open_mutex);
+	} else
+		mutex_unlock(&mddev->reconfig_mutex);
 
 	md_wakeup_thread(mddev->thread);
 }
@@ -1029,10 +1071,13 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 				mddev->bitmap_info.default_offset;
 
 	} else if (mddev->pers == NULL) {
-		/* Insist on good event counter while assembling */
+		/* Insist on good event counter while assembling, except
+		 * for spares (which don't need an event count) */
 		++ev1;
-		if (ev1 < mddev->events) 
-			return -EINVAL;
+		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.
@@ -1428,10 +1473,14 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 		}
 
 	} else if (mddev->pers == NULL) {
-		/* Insist of good event counter while assembling */
+		/* Insist of good event counter while assembling, except for
+		 * spares (which don't need an event count) */
 		++ev1;
-		if (ev1 < mddev->events)
-			return -EINVAL;
+		if (rdev->desc_nr >= 0 &&
+		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+		    le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < 0xfffe)
+			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.
@@ -2047,7 +2096,6 @@ static void sync_sbs(mddev_t * mddev, int nospares)
 		if (rdev->sb_events == mddev->events ||
 		    (nospares &&
 		     rdev->raid_disk < 0 &&
-		     (rdev->sb_events&1)==0 &&
 		     rdev->sb_events+1 == mddev->events)) {
 			/* Don't update this superblock */
 			rdev->sb_loaded = 2;
@@ -2100,28 +2148,14 @@ repeat:
 	 * and 'events' is odd, we can roll back to the previous clean state */
 	if (nospares
 	    && (mddev->in_sync && mddev->recovery_cp == MaxSector)
-	    && (mddev->events & 1)
-	    && mddev->events != 1)
+	    && mddev->can_decrease_events
+	    && mddev->events != 1) {
 		mddev->events--;
-	else {
+		mddev->can_decrease_events = 0;
+	} else {
 		/* otherwise we have to go forward and ... */
 		mddev->events ++;
-		if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
-			/* .. if the array isn't clean, an 'even' event must also go
-			 * to spares. */
-			if ((mddev->events&1)==0) {
-				nospares = 0;
-				sync_req = 2; /* force a second update to get the
-					       * even/odd in sync */
-			}
-		} else {
-			/* otherwise an 'odd' event must go to spares */
-			if ((mddev->events&1)) {
-				nospares = 0;
-				sync_req = 2; /* force a second update to get the
-					       * even/odd in sync */
-			}
-		}
+		mddev->can_decrease_events = nospares;
 	}
 
 	if (!mddev->events) {
@@ -2365,6 +2399,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 			return err;
 		sprintf(nm, "rd%d", rdev->raid_disk);
 		sysfs_remove_link(&rdev->mddev->kobj, nm);
+		rdev->raid_disk = -1;
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
 		md_wakeup_thread(rdev->mddev->thread);
 	} else if (rdev->mddev->pers) {
@@ -2780,8 +2815,9 @@ static void analyze_sbs(mddev_t * mddev)
 
 	i = 0;
 	rdev_for_each(rdev, tmp, mddev) {
-		if (rdev->desc_nr >= mddev->max_disks ||
-		    i > mddev->max_disks) {
+		if (mddev->max_disks &&
+		    (rdev->desc_nr >= mddev->max_disks ||
+		     i > mddev->max_disks)) {
 			printk(KERN_WARNING
 			       "md: %s: %s: only %d devices permitted\n",
 			       mdname(mddev), bdevname(rdev->bdev, b),
@@ -2897,9 +2933,10 @@ level_show(mddev_t *mddev, char *page)
 static ssize_t
 level_store(mddev_t *mddev, const char *buf, size_t len)
 {
-	char level[16];
+	char clevel[16];
 	ssize_t rv = len;
 	struct mdk_personality *pers;
+	long level;
 	void *priv;
 	mdk_rdev_t *rdev;
 
@@ -2932,19 +2969,22 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 	}
 
 	/* Now find the new personality */
-	if (len == 0 || len >= sizeof(level))
+	if (len == 0 || len >= sizeof(clevel))
 		return -EINVAL;
-	strncpy(level, buf, len);
-	if (level[len-1] == '\n')
+	strncpy(clevel, buf, len);
+	if (clevel[len-1] == '\n')
 		len--;
-	level[len] = 0;
+	clevel[len] = 0;
+	if (strict_strtol(clevel, 10, &level))
+		level = LEVEL_NONE;
 
-	request_module("md-%s", level);
+	if (request_module("md-%s", clevel) != 0)
+		request_module("md-level-%s", clevel);
 	spin_lock(&pers_lock);
-	pers = find_pers(LEVEL_NONE, level);
+	pers = find_pers(level, clevel);
 	if (!pers || !try_module_get(pers->owner)) {
 		spin_unlock(&pers_lock);
-		printk(KERN_WARNING "md: personality %s not loaded\n", level);
+		printk(KERN_WARNING "md: personality %s not loaded\n", clevel);
 		return -EINVAL;
 	}
 	spin_unlock(&pers_lock);
@@ -2957,7 +2997,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 	if (!pers->takeover) {
 		module_put(pers->owner);
 		printk(KERN_WARNING "md: %s: %s does not support personality takeover\n",
-		       mdname(mddev), level);
+		       mdname(mddev), clevel);
 		return -EINVAL;
 	}
 
@@ -2973,13 +3013,44 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 		mddev->delta_disks = 0;
 		module_put(pers->owner);
 		printk(KERN_WARNING "md: %s: %s would not accept array\n",
-		       mdname(mddev), level);
+		       mdname(mddev), clevel);
 		return PTR_ERR(priv);
 	}
 
 	/* Looks like we have a winner */
 	mddev_suspend(mddev);
 	mddev->pers->stop(mddev);
+	
+	if (mddev->pers->sync_request == NULL &&
+	    pers->sync_request != NULL) {
+		/* need to add the md_redundancy_group */
+		if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+			printk(KERN_WARNING
+			       "md: cannot register extra attributes for %s\n",
+			       mdname(mddev));
+		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action");
+	}		
+	if (mddev->pers->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;
+	}
+
+	if (mddev->pers->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;
+	}
+
 	module_put(mddev->pers->owner);
 	/* Invalidate devices that are now superfluous */
 	list_for_each_entry(rdev, &mddev->disks, same_set)
@@ -2994,11 +3065,20 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 	mddev->layout = mddev->new_layout;
 	mddev->chunk_sectors = mddev->new_chunk_sectors;
 	mddev->delta_disks = 0;
+	if (mddev->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);
+	}
 	pers->run(mddev);
 	mddev_resume(mddev);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
+	sysfs_notify(&mddev->kobj, NULL, "level");
+	md_new_event(mddev);
 	return rv;
 }
 
@@ -3237,6 +3317,7 @@ array_state_show(mddev_t *mddev, char *page)
 }
 
 static int do_md_stop(mddev_t * mddev, int ro, int is_open);
+static int md_set_readonly(mddev_t * mddev, int is_open);
 static int do_md_run(mddev_t * mddev);
 static int restart_array(mddev_t *mddev);
 
@@ -3267,7 +3348,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
 		break; /* not supported yet */
 	case readonly:
 		if (mddev->pers)
-			err = do_md_stop(mddev, 1, 0);
+			err = md_set_readonly(mddev, 0);
 		else {
 			mddev->ro = 1;
 			set_disk_ro(mddev->gendisk, 1);
@@ -3277,7 +3358,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
 	case read_auto:
 		if (mddev->pers) {
 			if (mddev->ro == 0)
-				err = do_md_stop(mddev, 1, 0);
+				err = md_set_readonly(mddev, 0);
 			else if (mddev->ro == 1)
 				err = restart_array(mddev);
 			if (err == 0) {
@@ -4082,15 +4163,6 @@ static void mddev_delayed_delete(struct work_struct *ws)
 {
 	mddev_t *mddev = container_of(ws, mddev_t, del_work);
 
-	if (mddev->private) {
-		sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
-		if (mddev->private != (void*)1)
-			sysfs_remove_group(&mddev->kobj, mddev->private);
-		if (mddev->sysfs_action)
-			sysfs_put(mddev->sysfs_action);
-		mddev->sysfs_action = NULL;
-		mddev->private = NULL;
-	}
 	sysfs_remove_group(&mddev->kobj, &md_bitmap_group);
 	kobject_del(&mddev->kobj);
 	kobject_put(&mddev->kobj);
@@ -4234,11 +4306,10 @@ static void md_safemode_timeout(unsigned long data)
 
 static int start_dirty_degraded;
 
-static int do_md_run(mddev_t * mddev)
+static int md_run(mddev_t *mddev)
 {
 	int err;
 	mdk_rdev_t *rdev;
-	struct gendisk *disk;
 	struct mdk_personality *pers;
 
 	if (list_empty(&mddev->disks))
@@ -4248,6 +4319,13 @@ static int do_md_run(mddev_t * mddev)
 	if (mddev->pers)
 		return -EBUSY;
 
+	/* These two calls synchronise us with the
+	 * sysfs_remove_group calls in mddev_unlock,
+	 * so they must have completed.
+	 */
+	mutex_lock(&mddev->open_mutex);
+	mutex_unlock(&mddev->open_mutex);
+
 	/*
 	 * Analyze all RAID superblock(s)
 	 */
@@ -4296,8 +4374,6 @@ static int do_md_run(mddev_t * mddev)
 		sysfs_notify_dirent(rdev->sysfs_state);
 	}
 
-	disk = mddev->gendisk;
-
 	spin_lock(&pers_lock);
 	pers = find_pers(mddev->level, mddev->clevel);
 	if (!pers || !try_module_get(pers->owner)) {
@@ -4425,22 +4501,32 @@ static int do_md_run(mddev_t * mddev)
 	if (mddev->flags)
 		md_update_sb(mddev, 0);
 
-	set_capacity(disk, mddev->array_sectors);
-
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
-	revalidate_disk(mddev->gendisk);
-	mddev->changed = 1;
 	md_new_event(mddev);
 	sysfs_notify_dirent(mddev->sysfs_state);
 	if (mddev->sysfs_action)
 		sysfs_notify_dirent(mddev->sysfs_action);
 	sysfs_notify(&mddev->kobj, NULL, "degraded");
-	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 	return 0;
 }
 
+static int do_md_run(mddev_t *mddev)
+{
+	int err;
+
+	err = md_run(mddev);
+	if (err)
+		goto out;
+
+	set_capacity(mddev->gendisk, mddev->array_sectors);
+	revalidate_disk(mddev->gendisk);
+	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
+out:
+	return err;
+}
+
 static int restart_array(mddev_t *mddev)
 {
 	struct gendisk *disk = mddev->gendisk;
@@ -4491,9 +4577,110 @@ void restore_bitmap_write_access(struct file *file)
 	spin_unlock(&inode->i_lock);
 }
 
+static void md_clean(mddev_t *mddev)
+{
+	mddev->array_sectors = 0;
+	mddev->external_size = 0;
+	mddev->dev_sectors = 0;
+	mddev->raid_disks = 0;
+	mddev->recovery_cp = 0;
+	mddev->resync_min = 0;
+	mddev->resync_max = MaxSector;
+	mddev->reshape_position = MaxSector;
+	mddev->external = 0;
+	mddev->persistent = 0;
+	mddev->level = LEVEL_NONE;
+	mddev->clevel[0] = 0;
+	mddev->flags = 0;
+	mddev->ro = 0;
+	mddev->metadata_type[0] = 0;
+	mddev->chunk_sectors = 0;
+	mddev->ctime = mddev->utime = 0;
+	mddev->layout = 0;
+	mddev->max_disks = 0;
+	mddev->events = 0;
+	mddev->can_decrease_events = 0;
+	mddev->delta_disks = 0;
+	mddev->new_level = LEVEL_NONE;
+	mddev->new_layout = 0;
+	mddev->new_chunk_sectors = 0;
+	mddev->curr_resync = 0;
+	mddev->resync_mismatches = 0;
+	mddev->suspend_lo = mddev->suspend_hi = 0;
+	mddev->sync_speed_min = mddev->sync_speed_max = 0;
+	mddev->recovery = 0;
+	mddev->in_sync = 0;
+	mddev->degraded = 0;
+	mddev->barriers_work = 0;
+	mddev->safemode = 0;
+	mddev->bitmap_info.offset = 0;
+	mddev->bitmap_info.default_offset = 0;
+	mddev->bitmap_info.chunksize = 0;
+	mddev->bitmap_info.daemon_sleep = 0;
+	mddev->bitmap_info.max_write_behind = 0;
+}
+
+static void md_stop_writes(mddev_t *mddev)
+{
+	if (mddev->sync_thread) {
+		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+		md_unregister_thread(mddev->sync_thread);
+		mddev->sync_thread = NULL;
+	}
+
+	del_timer_sync(&mddev->safemode_timer);
+
+	bitmap_flush(mddev);
+	md_super_wait(mddev);
+
+	if (!mddev->in_sync || mddev->flags) {
+		/* mark array as shutdown cleanly */
+		mddev->in_sync = 1;
+		md_update_sb(mddev, 1);
+	}
+}
+
+static void md_stop(mddev_t *mddev)
+{
+	md_stop_writes(mddev);
+
+	mddev->pers->stop(mddev);
+	if (mddev->pers->sync_request && mddev->to_remove == NULL)
+		mddev->to_remove = &md_redundancy_group;
+	module_put(mddev->pers->owner);
+	mddev->pers = NULL;
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+}
+
+static int md_set_readonly(mddev_t *mddev, int is_open)
+{
+	int err = 0;
+	mutex_lock(&mddev->open_mutex);
+	if (atomic_read(&mddev->openers) > is_open) {
+		printk("md: %s still in use.\n",mdname(mddev));
+		err = -EBUSY;
+		goto out;
+	}
+	if (mddev->pers) {
+		md_stop_writes(mddev);
+
+		err  = -ENXIO;
+		if (mddev->ro==1)
+			goto out;
+		mddev->ro = 1;
+		set_disk_ro(mddev->gendisk, 1);
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		sysfs_notify_dirent(mddev->sysfs_state);
+		err = 0;	
+	}
+out:
+	mutex_unlock(&mddev->open_mutex);
+	return err;
+}
+
 /* mode:
  *   0 - completely stop and dis-assemble array
- *   1 - switch to readonly
  *   2 - stop but do not disassemble array
  */
 static int do_md_stop(mddev_t * mddev, int mode, int is_open)
@@ -4508,64 +4695,32 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		err = -EBUSY;
 	} else if (mddev->pers) {
 
-		if (mddev->sync_thread) {
-			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_unregister_thread(mddev->sync_thread);
-			mddev->sync_thread = NULL;
-		}
-
-		del_timer_sync(&mddev->safemode_timer);
+		if (mddev->ro)
+			set_disk_ro(disk, 0);
 
-		switch(mode) {
-		case 1: /* readonly */
-			err  = -ENXIO;
-			if (mddev->ro==1)
-				goto out;
-			mddev->ro = 1;
-			break;
-		case 0: /* disassemble */
-		case 2: /* stop */
-			bitmap_flush(mddev);
-			md_super_wait(mddev);
-			if (mddev->ro)
-				set_disk_ro(disk, 0);
+		md_stop(mddev);
+		mddev->queue->merge_bvec_fn = NULL;
+		mddev->queue->unplug_fn = NULL;
+		mddev->queue->backing_dev_info.congested_fn = NULL;
 
-			mddev->pers->stop(mddev);
-			mddev->queue->merge_bvec_fn = NULL;
-			mddev->queue->unplug_fn = NULL;
-			mddev->queue->backing_dev_info.congested_fn = NULL;
-			module_put(mddev->pers->owner);
-			if (mddev->pers->sync_request && mddev->private == NULL)
-				mddev->private = (void*)1;
-			mddev->pers = NULL;
-			/* tell userspace to handle 'inactive' */
-			sysfs_notify_dirent(mddev->sysfs_state);
+		/* tell userspace to handle 'inactive' */
+		sysfs_notify_dirent(mddev->sysfs_state);
 
-			list_for_each_entry(rdev, &mddev->disks, same_set)
-				if (rdev->raid_disk >= 0) {
-					char nm[20];
-					sprintf(nm, "rd%d", rdev->raid_disk);
-					sysfs_remove_link(&mddev->kobj, nm);
-				}
+		list_for_each_entry(rdev, &mddev->disks, same_set)
+			if (rdev->raid_disk >= 0) {
+				char nm[20];
+				sprintf(nm, "rd%d", rdev->raid_disk);
+				sysfs_remove_link(&mddev->kobj, nm);
+			}
 
-			set_capacity(disk, 0);
-			mddev->changed = 1;
+		set_capacity(disk, 0);
+		revalidate_disk(disk);
 
-			if (mddev->ro)
-				mddev->ro = 0;
-		}
-		if (!mddev->in_sync || mddev->flags) {
-			/* mark array as shutdown cleanly */
-			mddev->in_sync = 1;
-			md_update_sb(mddev, 1);
-		}
-		if (mode == 1)
-			set_disk_ro(disk, 1);
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		if (mddev->ro)
+			mddev->ro = 0;
+		
 		err = 0;
 	}
-out:
 	mutex_unlock(&mddev->open_mutex);
 	if (err)
 		return err;
@@ -4586,52 +4741,12 @@ out:
 
 		export_array(mddev);
 
-		mddev->array_sectors = 0;
-		mddev->external_size = 0;
-		mddev->dev_sectors = 0;
-		mddev->raid_disks = 0;
-		mddev->recovery_cp = 0;
-		mddev->resync_min = 0;
-		mddev->resync_max = MaxSector;
-		mddev->reshape_position = MaxSector;
-		mddev->external = 0;
-		mddev->persistent = 0;
-		mddev->level = LEVEL_NONE;
-		mddev->clevel[0] = 0;
-		mddev->flags = 0;
-		mddev->ro = 0;
-		mddev->metadata_type[0] = 0;
-		mddev->chunk_sectors = 0;
-		mddev->ctime = mddev->utime = 0;
-		mddev->layout = 0;
-		mddev->max_disks = 0;
-		mddev->events = 0;
-		mddev->delta_disks = 0;
-		mddev->new_level = LEVEL_NONE;
-		mddev->new_layout = 0;
-		mddev->new_chunk_sectors = 0;
-		mddev->curr_resync = 0;
-		mddev->resync_mismatches = 0;
-		mddev->suspend_lo = mddev->suspend_hi = 0;
-		mddev->sync_speed_min = mddev->sync_speed_max = 0;
-		mddev->recovery = 0;
-		mddev->in_sync = 0;
-		mddev->changed = 0;
-		mddev->degraded = 0;
-		mddev->barriers_work = 0;
-		mddev->safemode = 0;
-		mddev->bitmap_info.offset = 0;
-		mddev->bitmap_info.default_offset = 0;
-		mddev->bitmap_info.chunksize = 0;
-		mddev->bitmap_info.daemon_sleep = 0;
-		mddev->bitmap_info.max_write_behind = 0;
+		md_clean(mddev);
 		kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 		if (mddev->hold_active == UNTIL_STOP)
 			mddev->hold_active = 0;
 
-	} else if (mddev->pers)
-		printk(KERN_INFO "md: %s switched to read-only mode.\n",
-			mdname(mddev));
+	}
 	err = 0;
 	blk_integrity_unregister(disk);
 	md_new_event(mddev);
@@ -5349,7 +5464,7 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks)
 	if (mddev->pers->check_reshape == NULL)
 		return -EINVAL;
 	if (raid_disks <= 0 ||
-	    raid_disks >= mddev->max_disks)
+	    (mddev->max_disks && raid_disks >= mddev->max_disks))
 		return -EINVAL;
 	if (mddev->sync_thread || mddev->reshape_position != MaxSector)
 		return -EBUSY;
@@ -5486,7 +5601,7 @@ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 
 	geo->heads = 2;
 	geo->sectors = 4;
-	geo->cylinders = get_capacity(mddev->gendisk) / 8;
+	geo->cylinders = mddev->array_sectors / 8;
 	return 0;
 }
 
@@ -5496,6 +5611,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	mddev_t *mddev = NULL;
+	int ro;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -5628,9 +5744,37 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			goto done_unlock;
 
 		case STOP_ARRAY_RO:
-			err = do_md_stop(mddev, 1, 1);
+			err = md_set_readonly(mddev, 1);
 			goto done_unlock;
 
+		case BLKROSET:
+			if (get_user(ro, (int __user *)(arg))) {
+				err = -EFAULT;
+				goto done_unlock;
+			}
+			err = -EINVAL;
+
+			/* if the bdev is going readonly the value of mddev->ro
+			 * does not matter, no writes are coming
+			 */
+			if (ro)
+				goto done_unlock;
+
+			/* are we are already prepared for writes? */
+			if (mddev->ro != 1)
+				goto done_unlock;
+
+			/* transitioning to readauto need only happen for
+			 * arrays that call md_write_start
+			 */
+			if (mddev->pers) {
+				err = restart_array(mddev);
+				if (err == 0) {
+					mddev->ro = 2;
+					set_disk_ro(mddev->gendisk, 0);
+				}
+			}
+			goto done_unlock;
 	}
 
 	/*
@@ -5751,7 +5895,6 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 	atomic_inc(&mddev->openers);
 	mutex_unlock(&mddev->open_mutex);
 
-	check_disk_change(bdev);
  out:
 	return err;
 }
@@ -5766,21 +5909,6 @@ static int md_release(struct gendisk *disk, fmode_t mode)
 
 	return 0;
 }
-
-static int md_media_changed(struct gendisk *disk)
-{
-	mddev_t *mddev = disk->private_data;
-
-	return mddev->changed;
-}
-
-static int md_revalidate(struct gendisk *disk)
-{
-	mddev_t *mddev = disk->private_data;
-
-	mddev->changed = 0;
-	return 0;
-}
 static const struct block_device_operations md_fops =
 {
 	.owner		= THIS_MODULE,
@@ -5791,8 +5919,6 @@ static const struct block_device_operations md_fops =
 	.compat_ioctl	= md_compat_ioctl,
 #endif
 	.getgeo		= md_getgeo,
-	.media_changed	= md_media_changed,
-	.revalidate_disk= md_revalidate,
 };
 
 static int md_thread(void * arg)
@@ -5906,7 +6032,7 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev)
 	mddev->pers->error_handler(mddev,rdev);
 	if (mddev->degraded)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-	set_bit(StateChanged, &rdev->flags);
+	sysfs_notify_dirent(rdev->sysfs_state);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
@@ -6898,11 +7024,6 @@ void md_check_recovery(mddev_t *mddev)
 		if (mddev->flags)
 			md_update_sb(mddev, 0);
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
-			if (test_and_clear_bit(StateChanged, &rdev->flags))
-				sysfs_notify_dirent(rdev->sysfs_state);
-
-
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
 		    !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
 			/* resync/recovery still happening */
@@ -7039,7 +7160,7 @@ static int md_notify_reboot(struct notifier_block *this,
 				 * appears to still be in use.  Hence
 				 * the '100'.
 				 */
-				do_md_stop(mddev, 1, 100);
+				md_set_readonly(mddev, 100);
 				mddev_unlock(mddev);
 			}
 		/*

drivers/md/md.h

@@ -74,9 +74,6 @@ struct mdk_rdev_s
 #define Blocked		8		/* An error occured on an externally
 					 * managed array, don't allow writes
 					 * until it is cleared */
-#define StateChanged	9		/* Faulty or Blocked has changed during
-					 * interrupt, so it needs to be
-					 * notified by the thread */
 	wait_queue_head_t blocked_wait;
 
 	int desc_nr;			/* descriptor index in the superblock */
@@ -153,6 +150,12 @@ struct mddev_s
 	int				external_size; /* size managed
 							* externally */
 	__u64				events;
+	/* If the last 'event' was simply a clean->dirty transition, and
+	 * we didn't write it to the spares, then it is safe and simple
+	 * to just decrement the event count on a dirty->clean transition.
+	 * So we record that possibility here.
+	 */
+	int				can_decrease_events;
 
 	char				uuid[16];
 
@@ -240,7 +243,6 @@ struct mddev_s
 	atomic_t			active;		/* general refcount */
 	atomic_t			openers;	/* number of active opens */
 
-	int				changed;	/* true if we might need to reread partition info */
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
@@ -279,9 +281,6 @@ struct mddev_s
 	atomic_t			writes_pending; 
 	struct request_queue		*queue;	/* for plugging ... */
 
-	atomic_t                        write_behind; /* outstanding async IO */
-	unsigned int                    max_write_behind; /* 0 = sync */
-
 	struct bitmap                   *bitmap; /* the bitmap for the device */
 	struct {
 		struct file		*file; /* the bitmap file */
@@ -305,6 +304,7 @@ struct mddev_s
 	atomic_t 			max_corr_read_errors; /* max read retries */
 	struct list_head		all_mddevs;
 
+	struct attribute_group		*to_remove;
 	/* Generic barrier handling.
 	 * If there is a pending barrier request, all other
 	 * writes are blocked while the devices are flushed.
@@ -336,7 +336,7 @@ struct mdk_personality
 	int level;
 	struct list_head list;
 	struct module *owner;
-	int (*make_request)(struct request_queue *q, struct bio *bio);
+	int (*make_request)(mddev_t *mddev, struct bio *bio);
 	int (*run)(mddev_t *mddev);
 	int (*stop)(mddev_t *mddev);
 	void (*status)(struct seq_file *seq, mddev_t *mddev);

drivers/md/multipath.c

@@ -85,7 +85,7 @@ static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
 static void multipath_end_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct multipath_bh * mp_bh = (struct multipath_bh *)(bio->bi_private);
+	struct multipath_bh *mp_bh = bio->bi_private;
 	multipath_conf_t *conf = mp_bh->mddev->private;
 	mdk_rdev_t *rdev = conf->multipaths[mp_bh->path].rdev;
 
@@ -136,14 +136,11 @@ static void multipath_unplug(struct request_queue *q)
 }
 
 
-static int multipath_make_request (struct request_queue *q, struct bio * bio)
+static int multipath_make_request(mddev_t *mddev, struct bio * bio)
 {
-	mddev_t *mddev = q->queuedata;
 	multipath_conf_t *conf = mddev->private;
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
-	const int rw = bio_data_dir(bio);
-	int cpu;
 
 	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		md_barrier_request(mddev, bio);
@@ -155,12 +152,6 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	mp_bh->master_bio = bio;
 	mp_bh->mddev = mddev;
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	mp_bh->path = multipath_map(conf);
 	if (mp_bh->path < 0) {
 		bio_endio(bio, -EIO);

drivers/md/raid0.c

@@ -23,15 +23,17 @@
 #include <linux/slab.h>
 #include "md.h"
 #include "raid0.h"
+#include "raid5.h"
 
 static void raid0_unplug(struct request_queue *q)
 {
 	mddev_t *mddev = q->queuedata;
 	raid0_conf_t *conf = mddev->private;
 	mdk_rdev_t **devlist = conf->devlist;
+	int raid_disks = conf->strip_zone[0].nb_dev;
 	int i;
 
-	for (i=0; i<mddev->raid_disks; i++) {
+	for (i=0; i < raid_disks; i++) {
 		struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev);
 
 		blk_unplug(r_queue);
@@ -43,12 +45,13 @@ static int raid0_congested(void *data, int bits)
 	mddev_t *mddev = data;
 	raid0_conf_t *conf = mddev->private;
 	mdk_rdev_t **devlist = conf->devlist;
+	int raid_disks = conf->strip_zone[0].nb_dev;
 	int i, ret = 0;
 
 	if (mddev_congested(mddev, bits))
 		return 1;
 
-	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
+	for (i = 0; i < raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
 
 		ret |= bdi_congested(&q->backing_dev_info, bits);
@@ -66,16 +69,17 @@ static void dump_zones(mddev_t *mddev)
 	sector_t zone_start = 0;
 	char b[BDEVNAME_SIZE];
 	raid0_conf_t *conf = mddev->private;
+	int raid_disks = conf->strip_zone[0].nb_dev;
 	printk(KERN_INFO "******* %s configuration *********\n",
 		mdname(mddev));
 	h = 0;
 	for (j = 0; j < conf->nr_strip_zones; j++) {
 		printk(KERN_INFO "zone%d=[", j);
 		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
-			printk("%s/",
-			bdevname(conf->devlist[j*mddev->raid_disks
+			printk(KERN_CONT "%s/",
+			bdevname(conf->devlist[j*raid_disks
 						+ k]->bdev, b));
-		printk("]\n");
+		printk(KERN_CONT "]\n");
 
 		zone_size  = conf->strip_zone[j].zone_end - zone_start;
 		printk(KERN_INFO "        zone offset=%llukb "
@@ -88,7 +92,7 @@ static void dump_zones(mddev_t *mddev)
 	printk(KERN_INFO "**********************************\n\n");
 }
 
-static int create_strip_zones(mddev_t *mddev)
+static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf)
 {
 	int i, c, err;
 	sector_t curr_zone_end, sectors;
@@ -101,8 +105,9 @@ static int create_strip_zones(mddev_t *mddev)
 	if (!conf)
 		return -ENOMEM;
 	list_for_each_entry(rdev1, &mddev->disks, same_set) {
-		printk(KERN_INFO "raid0: looking at %s\n",
-			bdevname(rdev1->bdev,b));
+		printk(KERN_INFO "md/raid0:%s: looking at %s\n",
+		       mdname(mddev),
+		       bdevname(rdev1->bdev, b));
 		c = 0;
 
 		/* round size to chunk_size */
@@ -111,14 +116,16 @@ static int create_strip_zones(mddev_t *mddev)
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
 		list_for_each_entry(rdev2, &mddev->disks, same_set) {
-			printk(KERN_INFO "raid0:   comparing %s(%llu)",
+			printk(KERN_INFO "md/raid0:%s:   comparing %s(%llu)",
+			       mdname(mddev),
 			       bdevname(rdev1->bdev,b),
 			       (unsigned long long)rdev1->sectors);
-			printk(KERN_INFO " with %s(%llu)\n",
+			printk(KERN_CONT " with %s(%llu)\n",
 			       bdevname(rdev2->bdev,b),
 			       (unsigned long long)rdev2->sectors);
 			if (rdev2 == rdev1) {
-				printk(KERN_INFO "raid0:   END\n");
+				printk(KERN_INFO "md/raid0:%s:   END\n",
+				       mdname(mddev));
 				break;
 			}
 			if (rdev2->sectors == rdev1->sectors) {
@@ -126,20 +133,24 @@ static int create_strip_zones(mddev_t *mddev)
 				 * Not unique, don't count it as a new
 				 * group
 				 */
-				printk(KERN_INFO "raid0:   EQUAL\n");
+				printk(KERN_INFO "md/raid0:%s:   EQUAL\n",
+				       mdname(mddev));
 				c = 1;
 				break;
 			}
-			printk(KERN_INFO "raid0:   NOT EQUAL\n");
+			printk(KERN_INFO "md/raid0:%s:   NOT EQUAL\n",
+			       mdname(mddev));
 		}
 		if (!c) {
-			printk(KERN_INFO "raid0:   ==> UNIQUE\n");
+			printk(KERN_INFO "md/raid0:%s:   ==> UNIQUE\n",
+			       mdname(mddev));
 			conf->nr_strip_zones++;
-			printk(KERN_INFO "raid0: %d zones\n",
-				conf->nr_strip_zones);
+			printk(KERN_INFO "md/raid0:%s: %d zones\n",
+			       mdname(mddev), conf->nr_strip_zones);
 		}
 	}
-	printk(KERN_INFO "raid0: FINAL %d zones\n", conf->nr_strip_zones);
+	printk(KERN_INFO "md/raid0:%s: FINAL %d zones\n",
+	       mdname(mddev), conf->nr_strip_zones);
 	err = -ENOMEM;
 	conf->strip_zone = kzalloc(sizeof(struct strip_zone)*
 				conf->nr_strip_zones, GFP_KERNEL);
@@ -162,14 +173,18 @@ static int create_strip_zones(mddev_t *mddev)
 	list_for_each_entry(rdev1, &mddev->disks, same_set) {
 		int j = rdev1->raid_disk;
 
+		if (mddev->level == 10)
+			/* taking over a raid10-n2 array */
+			j /= 2;
+
 		if (j < 0 || j >= mddev->raid_disks) {
-			printk(KERN_ERR "raid0: bad disk number %d - "
-				"aborting!\n", j);
+			printk(KERN_ERR "md/raid0:%s: bad disk number %d - "
+			       "aborting!\n", mdname(mddev), j);
 			goto abort;
 		}
 		if (dev[j]) {
-			printk(KERN_ERR "raid0: multiple devices for %d - "
-				"aborting!\n", j);
+			printk(KERN_ERR "md/raid0:%s: multiple devices for %d - "
+			       "aborting!\n", mdname(mddev), j);
 			goto abort;
 		}
 		dev[j] = rdev1;
@@ -191,8 +206,8 @@ static int create_strip_zones(mddev_t *mddev)
 		cnt++;
 	}
 	if (cnt != mddev->raid_disks) {
-		printk(KERN_ERR "raid0: too few disks (%d of %d) - "
-			"aborting!\n", cnt, mddev->raid_disks);
+		printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - "
+		       "aborting!\n", mdname(mddev), cnt, mddev->raid_disks);
 		goto abort;
 	}
 	zone->nb_dev = cnt;
@@ -208,39 +223,44 @@ static int create_strip_zones(mddev_t *mddev)
 		zone = conf->strip_zone + i;
 		dev = conf->devlist + i * mddev->raid_disks;
 
-		printk(KERN_INFO "raid0: zone %d\n", i);
+		printk(KERN_INFO "md/raid0:%s: zone %d\n",
+		       mdname(mddev), i);
 		zone->dev_start = smallest->sectors;
 		smallest = NULL;
 		c = 0;
 
 		for (j=0; j<cnt; j++) {
 			rdev = conf->devlist[j];
-			printk(KERN_INFO "raid0: checking %s ...",
-				bdevname(rdev->bdev, b));
+			printk(KERN_INFO "md/raid0:%s: checking %s ...",
+			       mdname(mddev),
+			       bdevname(rdev->bdev, b));
 			if (rdev->sectors <= zone->dev_start) {
-				printk(KERN_INFO " nope.\n");
+				printk(KERN_CONT " nope.\n");
 				continue;
 			}
-			printk(KERN_INFO " contained as device %d\n", c);
+			printk(KERN_CONT " contained as device %d\n", c);
 			dev[c] = rdev;
 			c++;
 			if (!smallest || rdev->sectors < smallest->sectors) {
 				smallest = rdev;
-				printk(KERN_INFO "  (%llu) is smallest!.\n",
-					(unsigned long long)rdev->sectors);
+				printk(KERN_INFO "md/raid0:%s:  (%llu) is smallest!.\n",
+				       mdname(mddev),
+				       (unsigned long long)rdev->sectors);
 			}
 		}
 
 		zone->nb_dev = c;
 		sectors = (smallest->sectors - zone->dev_start) * c;
-		printk(KERN_INFO "raid0: zone->nb_dev: %d, sectors: %llu\n",
-			zone->nb_dev, (unsigned long long)sectors);
+		printk(KERN_INFO "md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n",
+		       mdname(mddev),
+		       zone->nb_dev, (unsigned long long)sectors);
 
 		curr_zone_end += sectors;
 		zone->zone_end = curr_zone_end;
 
-		printk(KERN_INFO "raid0: current zone start: %llu\n",
-			(unsigned long long)smallest->sectors);
+		printk(KERN_INFO "md/raid0:%s: current zone start: %llu\n",
+		       mdname(mddev),
+		       (unsigned long long)smallest->sectors);
 	}
 	mddev->queue->unplug_fn = raid0_unplug;
 	mddev->queue->backing_dev_info.congested_fn = raid0_congested;
@@ -251,7 +271,7 @@ static int create_strip_zones(mddev_t *mddev)
 	 * chunk size is a multiple of that sector size
 	 */
 	if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
-		printk(KERN_ERR "%s chunk_size of %d not valid\n",
+		printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n",
 		       mdname(mddev),
 		       mddev->chunk_sectors << 9);
 		goto abort;
@@ -261,14 +281,15 @@ static int create_strip_zones(mddev_t *mddev)
 	blk_queue_io_opt(mddev->queue,
 			 (mddev->chunk_sectors << 9) * mddev->raid_disks);
 
-	printk(KERN_INFO "raid0: done.\n");
-	mddev->private = conf;
+	printk(KERN_INFO "md/raid0:%s: done.\n", mdname(mddev));
+	*private_conf = conf;
+
 	return 0;
 abort:
 	kfree(conf->strip_zone);
 	kfree(conf->devlist);
 	kfree(conf);
-	mddev->private = NULL;
+	*private_conf = NULL;
 	return err;
 }
 
@@ -319,10 +340,12 @@ static sector_t raid0_size(mddev_t *mddev, sector_t sectors, int raid_disks)
 
 static int raid0_run(mddev_t *mddev)
 {
+	raid0_conf_t *conf;
 	int ret;
 
 	if (mddev->chunk_sectors == 0) {
-		printk(KERN_ERR "md/raid0: chunk size must be set.\n");
+		printk(KERN_ERR "md/raid0:%s: chunk size must be set.\n",
+		       mdname(mddev));
 		return -EINVAL;
 	}
 	if (md_check_no_bitmap(mddev))
@@ -330,15 +353,27 @@ static int raid0_run(mddev_t *mddev)
 	blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 	mddev->queue->queue_lock = &mddev->queue->__queue_lock;
 
-	ret = create_strip_zones(mddev);
-	if (ret < 0)
-		return ret;
+	/* if private is not null, we are here after takeover */
+	if (mddev->private == NULL) {
+		ret = create_strip_zones(mddev, &conf);
+		if (ret < 0)
+			return ret;
+		mddev->private = conf;
+	}
+	conf = mddev->private;
+	if (conf->scale_raid_disks) {
+		int i;
+		for (i=0; i < conf->strip_zone[0].nb_dev; i++)
+			conf->devlist[i]->raid_disk /= conf->scale_raid_disks;
+		/* FIXME update sysfs rd links */
+	}
 
 	/* calculate array device size */
 	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
 
-	printk(KERN_INFO "raid0 : md_size is %llu sectors.\n",
-		(unsigned long long)mddev->array_sectors);
+	printk(KERN_INFO "md/raid0:%s: md_size is %llu sectors.\n",
+	       mdname(mddev),
+	       (unsigned long long)mddev->array_sectors);
 	/* calculate the max read-ahead size.
 	 * For read-ahead of large files to be effective, we need to
 	 * readahead at least twice a whole stripe. i.e. number of devices
@@ -402,6 +437,7 @@ static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone,
 	unsigned int sect_in_chunk;
 	sector_t chunk;
 	raid0_conf_t *conf = mddev->private;
+	int raid_disks = conf->strip_zone[0].nb_dev;
 	unsigned int chunk_sects = mddev->chunk_sectors;
 
 	if (is_power_of_2(chunk_sects)) {
@@ -424,7 +460,7 @@ static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone,
 	*	+ the position in the chunk
 	*/
 	*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
-	return conf->devlist[(zone - conf->strip_zone)*mddev->raid_disks
+	return conf->devlist[(zone - conf->strip_zone)*raid_disks
 			     + sector_div(sector, zone->nb_dev)];
 }
 
@@ -444,27 +480,18 @@ static inline int is_io_in_chunk_boundary(mddev_t *mddev,
 	}
 }
 
-static int raid0_make_request(struct request_queue *q, struct bio *bio)
+static int raid0_make_request(mddev_t *mddev, struct bio *bio)
 {
-	mddev_t *mddev = q->queuedata;
 	unsigned int chunk_sects;
 	sector_t sector_offset;
 	struct strip_zone *zone;
 	mdk_rdev_t *tmp_dev;
-	const int rw = bio_data_dir(bio);
-	int cpu;
 
 	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		md_barrier_request(mddev, bio);
 		return 0;
 	}
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	chunk_sects = mddev->chunk_sectors;
 	if (unlikely(!is_io_in_chunk_boundary(mddev, chunk_sects, bio))) {
 		sector_t sector = bio->bi_sector;
@@ -482,9 +509,9 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio)
 		else
 			bp = bio_split(bio, chunk_sects -
 				       sector_div(sector, chunk_sects));
-		if (raid0_make_request(q, &bp->bio1))
+		if (raid0_make_request(mddev, &bp->bio1))
 			generic_make_request(&bp->bio1);
-		if (raid0_make_request(q, &bp->bio2))
+		if (raid0_make_request(mddev, &bp->bio2))
 			generic_make_request(&bp->bio2);
 
 		bio_pair_release(bp);
@@ -504,9 +531,10 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio)
 	return 1;
 
 bad_map:
-	printk("raid0_make_request bug: can't convert block across chunks"
-		" or bigger than %dk %llu %d\n", chunk_sects / 2,
-		(unsigned long long)bio->bi_sector, bio->bi_size >> 10);
+	printk("md/raid0:%s: make_request bug: can't convert block across chunks"
+	       " or bigger than %dk %llu %d\n",
+	       mdname(mddev), chunk_sects / 2,
+	       (unsigned long long)bio->bi_sector, bio->bi_size >> 10);
 
 	bio_io_error(bio);
 	return 0;
@@ -519,6 +547,7 @@ static void raid0_status(struct seq_file *seq, mddev_t *mddev)
 	int j, k, h;
 	char b[BDEVNAME_SIZE];
 	raid0_conf_t *conf = mddev->private;
+	int raid_disks = conf->strip_zone[0].nb_dev;
 
 	sector_t zone_size;
 	sector_t zone_start = 0;
@@ -529,7 +558,7 @@ static void raid0_status(struct seq_file *seq, mddev_t *mddev)
 		seq_printf(seq, "=[");
 		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
 			seq_printf(seq, "%s/", bdevname(
-				conf->devlist[j*mddev->raid_disks + k]
+				conf->devlist[j*raid_disks + k]
 						->bdev, b));
 
 		zone_size  = conf->strip_zone[j].zone_end - zone_start;
@@ -544,6 +573,104 @@ static void raid0_status(struct seq_file *seq, mddev_t *mddev)
 	return;
 }
 
+static void *raid0_takeover_raid5(mddev_t *mddev)
+{
+	mdk_rdev_t *rdev;
+	raid0_conf_t *priv_conf;
+
+	if (mddev->degraded != 1) {
+		printk(KERN_ERR "md/raid0:%s: raid5 must be degraded! Degraded disks: %d\n",
+		       mdname(mddev),
+		       mddev->degraded);
+		return ERR_PTR(-EINVAL);
+	}
+
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		/* check slot number for a disk */
+		if (rdev->raid_disk == mddev->raid_disks-1) {
+			printk(KERN_ERR "md/raid0:%s: raid5 must have missing parity disk!\n",
+			       mdname(mddev));
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	/* Set new parameters */
+	mddev->new_level = 0;
+	mddev->new_chunk_sectors = mddev->chunk_sectors;
+	mddev->raid_disks--;
+	mddev->delta_disks = -1;
+	/* make sure it will be not marked as dirty */
+	mddev->recovery_cp = MaxSector;
+
+	create_strip_zones(mddev, &priv_conf);
+	return priv_conf;
+}
+
+static void *raid0_takeover_raid10(mddev_t *mddev)
+{
+	raid0_conf_t *priv_conf;
+
+	/* Check layout:
+	 *  - far_copies must be 1
+	 *  - near_copies must be 2
+	 *  - disks number must be even
+	 *  - all mirrors must be already degraded
+	 */
+	if (mddev->layout != ((1 << 8) + 2)) {
+		printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takover layout: 0x%x\n",
+		       mdname(mddev),
+		       mddev->layout);
+		return ERR_PTR(-EINVAL);
+	}
+	if (mddev->raid_disks & 1) {
+		printk(KERN_ERR "md/raid0:%s: Raid0 cannot takover Raid10 with odd disk number.\n",
+		       mdname(mddev));
+		return ERR_PTR(-EINVAL);
+	}
+	if (mddev->degraded != (mddev->raid_disks>>1)) {
+		printk(KERN_ERR "md/raid0:%s: All mirrors must be already degraded!\n",
+		       mdname(mddev));
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Set new parameters */
+	mddev->new_level = 0;
+	mddev->new_chunk_sectors = mddev->chunk_sectors;
+	mddev->delta_disks = - mddev->raid_disks / 2;
+	mddev->raid_disks += mddev->delta_disks;
+	mddev->degraded = 0;
+	/* make sure it will be not marked as dirty */
+	mddev->recovery_cp = MaxSector;
+
+	create_strip_zones(mddev, &priv_conf);
+	priv_conf->scale_raid_disks = 2;
+	return priv_conf;
+}
+
+static void *raid0_takeover(mddev_t *mddev)
+{
+	/* raid0 can take over:
+	 *  raid5 - providing it is Raid4 layout and one disk is faulty
+	 *  raid10 - assuming we have all necessary active disks
+	 */
+	if (mddev->level == 5) {
+		if (mddev->layout == ALGORITHM_PARITY_N)
+			return raid0_takeover_raid5(mddev);
+
+		printk(KERN_ERR "md/raid0:%s: Raid can only takeover Raid5 with layout: %d\n",
+		       mdname(mddev), ALGORITHM_PARITY_N);
+	}
+
+	if (mddev->level == 10)
+		return raid0_takeover_raid10(mddev);
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void raid0_quiesce(mddev_t *mddev, int state)
+{
+}
+
 static struct mdk_personality raid0_personality=
 {
 	.name		= "raid0",
@@ -554,6 +681,8 @@ static struct mdk_personality raid0_personality=
 	.stop		= raid0_stop,
 	.status		= raid0_status,
 	.size		= raid0_size,
+	.takeover	= raid0_takeover,
+	.quiesce	= raid0_quiesce,
 };
 
 static int __init raid0_init (void)

drivers/md/raid0.h

@@ -13,6 +13,9 @@ struct raid0_private_data
 	struct strip_zone *strip_zone;
 	mdk_rdev_t **devlist; /* lists of rdevs, pointed to by strip_zone->dev */
 	int nr_strip_zones;
+	int scale_raid_disks; /* divide rdev->raid_disks by this in run()
+			       * to handle conversion from raid10
+			       */
 };
 
 typedef struct raid0_private_data raid0_conf_t;

drivers/md/raid1.c

@@ -263,7 +263,7 @@ static inline void update_head_pos(int disk, r1bio_t *r1_bio)
 static void raid1_end_read_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	int mirror;
 	conf_t *conf = r1_bio->mddev->private;
 
@@ -297,7 +297,8 @@ static void raid1_end_read_request(struct bio *bio, int error)
 		 */
 		char b[BDEVNAME_SIZE];
 		if (printk_ratelimit())
-			printk(KERN_ERR "raid1: %s: rescheduling sector %llu\n",
+			printk(KERN_ERR "md/raid1:%s: %s: rescheduling sector %llu\n",
+			       mdname(conf->mddev),
 			       bdevname(conf->mirrors[mirror].rdev->bdev,b), (unsigned long long)r1_bio->sector);
 		reschedule_retry(r1_bio);
 	}
@@ -308,7 +309,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
 static void raid1_end_write_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
 	conf_t *conf = r1_bio->mddev->private;
 	struct bio *to_put = NULL;
@@ -418,7 +419,7 @@ static void raid1_end_write_request(struct bio *bio, int error)
  */
 static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 {
-	const unsigned long this_sector = r1_bio->sector;
+	const sector_t this_sector = r1_bio->sector;
 	int new_disk = conf->last_used, disk = new_disk;
 	int wonly_disk = -1;
 	const int sectors = r1_bio->sectors;
@@ -434,7 +435,7 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
  retry:
 	if (conf->mddev->recovery_cp < MaxSector &&
 	    (this_sector + sectors >= conf->next_resync)) {
-		/* Choose the first operation device, for consistancy */
+		/* Choose the first operational device, for consistancy */
 		new_disk = 0;
 
 		for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
@@ -774,9 +775,8 @@ do_sync_io:
 	return NULL;
 }
 
-static int make_request(struct request_queue *q, struct bio * bio)
+static int make_request(mddev_t *mddev, struct bio * bio)
 {
-	mddev_t *mddev = q->queuedata;
 	conf_t *conf = mddev->private;
 	mirror_info_t *mirror;
 	r1bio_t *r1_bio;
@@ -788,7 +788,6 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	struct page **behind_pages = NULL;
 	const int rw = bio_data_dir(bio);
 	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
-	int cpu;
 	bool do_barriers;
 	mdk_rdev_t *blocked_rdev;
 
@@ -834,12 +833,6 @@ static int make_request(struct request_queue *q, struct bio * bio)
 
 	bitmap = mddev->bitmap;
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	/*
 	 * make_request() can abort the operation when READA is being
 	 * used and no empty request is available.
@@ -866,6 +859,15 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		}
 		mirror = conf->mirrors + rdisk;
 
+		if (test_bit(WriteMostly, &mirror->rdev->flags) &&
+		    bitmap) {
+			/* Reading from a write-mostly device must
+			 * take care not to over-take any writes
+			 * that are 'behind'
+			 */
+			wait_event(bitmap->behind_wait,
+				   atomic_read(&bitmap->behind_writes) == 0);
+		}
 		r1_bio->read_disk = rdisk;
 
 		read_bio = bio_clone(bio, GFP_NOIO);
@@ -912,9 +914,10 @@ static int make_request(struct request_queue *q, struct bio * bio)
 			if (test_bit(Faulty, &rdev->flags)) {
 				rdev_dec_pending(rdev, mddev);
 				r1_bio->bios[i] = NULL;
-			} else
+			} else {
 				r1_bio->bios[i] = bio;
-			targets++;
+				targets++;
+			}
 		} else
 			r1_bio->bios[i] = NULL;
 	}
@@ -942,10 +945,14 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		set_bit(R1BIO_Degraded, &r1_bio->state);
 	}
 
-	/* do behind I/O ? */
+	/* do behind I/O ?
+	 * Not if there are too many, or cannot allocate memory,
+	 * or a reader on WriteMostly is waiting for behind writes 
+	 * to flush */
 	if (bitmap &&
 	    (atomic_read(&bitmap->behind_writes)
 	     < mddev->bitmap_info.max_write_behind) &&
+	    !waitqueue_active(&bitmap->behind_wait) &&
 	    (behind_pages = alloc_behind_pages(bio)) != NULL)
 		set_bit(R1BIO_BehindIO, &r1_bio->state);
 
@@ -1070,21 +1077,22 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	} else
 		set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "raid1: Disk failure on %s, disabling device.\n"
-		"raid1: Operation continuing on %d devices.\n",
-		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
+	printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n"
+	       KERN_ALERT "md/raid1:%s: Operation continuing on %d devices.\n",
+	       mdname(mddev), bdevname(rdev->bdev, b),
+	       mdname(mddev), conf->raid_disks - mddev->degraded);
 }
 
 static void print_conf(conf_t *conf)
 {
 	int i;
 
-	printk("RAID1 conf printout:\n");
+	printk(KERN_DEBUG "RAID1 conf printout:\n");
 	if (!conf) {
-		printk("(!conf)\n");
+		printk(KERN_DEBUG "(!conf)\n");
 		return;
 	}
-	printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
+	printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
 		conf->raid_disks);
 
 	rcu_read_lock();
@@ -1092,7 +1100,7 @@ static void print_conf(conf_t *conf)
 		char b[BDEVNAME_SIZE];
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev)
-			printk(" disk %d, wo:%d, o:%d, dev:%s\n",
+			printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
 			       i, !test_bit(In_sync, &rdev->flags),
 			       !test_bit(Faulty, &rdev->flags),
 			       bdevname(rdev->bdev,b));
@@ -1223,7 +1231,7 @@ abort:
 
 static void end_sync_read(struct bio *bio, int error)
 {
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	int i;
 
 	for (i=r1_bio->mddev->raid_disks; i--; )
@@ -1246,7 +1254,7 @@ static void end_sync_read(struct bio *bio, int error)
 static void end_sync_write(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	mddev_t *mddev = r1_bio->mddev;
 	conf_t *conf = mddev->private;
 	int i;
@@ -1453,9 +1461,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 				char b[BDEVNAME_SIZE];
 				/* Cannot read from anywhere, array is toast */
 				md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
-				printk(KERN_ALERT "raid1: %s: unrecoverable I/O read error"
+				printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O read error"
 				       " for block %llu\n",
-				       bdevname(bio->bi_bdev,b),
+				       mdname(mddev),
+				       bdevname(bio->bi_bdev, b),
 				       (unsigned long long)r1_bio->sector);
 				md_done_sync(mddev, r1_bio->sectors, 0);
 				put_buf(r1_bio);
@@ -1577,7 +1586,7 @@ static void fix_read_error(conf_t *conf, int read_disk,
 				else {
 					atomic_add(s, &rdev->corrected_errors);
 					printk(KERN_INFO
-					       "raid1:%s: read error corrected "
+					       "md/raid1:%s: read error corrected "
 					       "(%d sectors at %llu on %s)\n",
 					       mdname(mddev), s,
 					       (unsigned long long)(sect +
@@ -1682,8 +1691,9 @@ static void raid1d(mddev_t *mddev)
 
 			bio = r1_bio->bios[r1_bio->read_disk];
 			if ((disk=read_balance(conf, r1_bio)) == -1) {
-				printk(KERN_ALERT "raid1: %s: unrecoverable I/O"
+				printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O"
 				       " read error for block %llu\n",
+				       mdname(mddev),
 				       bdevname(bio->bi_bdev,b),
 				       (unsigned long long)r1_bio->sector);
 				raid_end_bio_io(r1_bio);
@@ -1697,10 +1707,11 @@ static void raid1d(mddev_t *mddev)
 				r1_bio->bios[r1_bio->read_disk] = bio;
 				rdev = conf->mirrors[disk].rdev;
 				if (printk_ratelimit())
-					printk(KERN_ERR "raid1: %s: redirecting sector %llu to"
-					       " another mirror\n",
-					       bdevname(rdev->bdev,b),
-					       (unsigned long long)r1_bio->sector);
+					printk(KERN_ERR "md/raid1:%s: redirecting sector %llu to"
+					       " other mirror: %s\n",
+					       mdname(mddev),
+					       (unsigned long long)r1_bio->sector,
+					       bdevname(rdev->bdev,b));
 				bio->bi_sector = r1_bio->sector + rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
 				bio->bi_end_io = raid1_end_read_request;
@@ -1755,13 +1766,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	int still_degraded = 0;
 
 	if (!conf->r1buf_pool)
-	{
-/*
-		printk("sync start - bitmap %p\n", mddev->bitmap);
-*/
 		if (init_resync(conf))
 			return 0;
-	}
 
 	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
@@ -2042,7 +2048,7 @@ static conf_t *setup_conf(mddev_t *mddev)
 
 	err = -EIO;
 	if (conf->last_used < 0) {
-		printk(KERN_ERR "raid1: no operational mirrors for %s\n",
+		printk(KERN_ERR "md/raid1:%s: no operational mirrors\n",
 		       mdname(mddev));
 		goto abort;
 	}
@@ -2050,7 +2056,7 @@ static conf_t *setup_conf(mddev_t *mddev)
 	conf->thread = md_register_thread(raid1d, mddev, NULL);
 	if (!conf->thread) {
 		printk(KERN_ERR
-		       "raid1: couldn't allocate thread for %s\n",
+		       "md/raid1:%s: couldn't allocate thread\n",
 		       mdname(mddev));
 		goto abort;
 	}
@@ -2076,12 +2082,12 @@ static int run(mddev_t *mddev)
 	mdk_rdev_t *rdev;
 
 	if (mddev->level != 1) {
-		printk("raid1: %s: raid level not set to mirroring (%d)\n",
+		printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n",
 		       mdname(mddev), mddev->level);
 		return -EIO;
 	}
 	if (mddev->reshape_position != MaxSector) {
-		printk("raid1: %s: reshape_position set but not supported\n",
+		printk(KERN_ERR "md/raid1:%s: reshape_position set but not supported\n",
 		       mdname(mddev));
 		return -EIO;
 	}
@@ -2124,11 +2130,11 @@ static int run(mddev_t *mddev)
 		mddev->recovery_cp = MaxSector;
 
 	if (mddev->recovery_cp != MaxSector)
-		printk(KERN_NOTICE "raid1: %s is not clean"
+		printk(KERN_NOTICE "md/raid1:%s: not clean"
 		       " -- starting background reconstruction\n",
 		       mdname(mddev));
 	printk(KERN_INFO 
-		"raid1: raid set %s active with %d out of %d mirrors\n",
+		"md/raid1:%s: active with %d out of %d mirrors\n",
 		mdname(mddev), mddev->raid_disks - mddev->degraded, 
 		mddev->raid_disks);
 
@@ -2152,15 +2158,14 @@ static int stop(mddev_t *mddev)
 {
 	conf_t *conf = mddev->private;
 	struct bitmap *bitmap = mddev->bitmap;
-	int behind_wait = 0;
 
 	/* wait for behind writes to complete */
-	while (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
-		behind_wait++;
-		printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait);
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		schedule_timeout(HZ); /* wait a second */
+	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+		printk(KERN_INFO "md/raid1:%s: behind writes in progress - waiting to stop.\n",
+		       mdname(mddev));
 		/* need to kick something here to make sure I/O goes? */
+		wait_event(bitmap->behind_wait,
+			   atomic_read(&bitmap->behind_writes) == 0);
 	}
 
 	raise_barrier(conf);
@@ -2191,7 +2196,6 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors)
 	if (mddev->array_sectors > raid1_size(mddev, sectors, 0))
 		return -EINVAL;
 	set_capacity(mddev->gendisk, mddev->array_sectors);
-	mddev->changed = 1;
 	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp == MaxSector) {
@@ -2286,9 +2290,9 @@ static int raid1_reshape(mddev_t *mddev)
 			if (sysfs_create_link(&mddev->kobj,
 					      &rdev->kobj, nm))
 				printk(KERN_WARNING
-				       "md/raid1: cannot register "
-				       "%s for %s\n",
-				       nm, mdname(mddev));
+				       "md/raid1:%s: cannot register "
+				       "%s\n",
+				       mdname(mddev), nm);
 		}
 		if (rdev)
 			newmirrors[d2++].rdev = rdev;

drivers/md/raid10.c

@@ -24,6 +24,7 @@
 #include <linux/seq_file.h>
 #include "md.h"
 #include "raid10.h"
+#include "raid0.h"
 #include "bitmap.h"
 
 /*
@@ -255,7 +256,7 @@ static inline void update_head_pos(int slot, r10bio_t *r10_bio)
 static void raid10_end_read_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
+	r10bio_t *r10_bio = bio->bi_private;
 	int slot, dev;
 	conf_t *conf = r10_bio->mddev->private;
 
@@ -285,7 +286,8 @@ static void raid10_end_read_request(struct bio *bio, int error)
 		 */
 		char b[BDEVNAME_SIZE];
 		if (printk_ratelimit())
-			printk(KERN_ERR "raid10: %s: rescheduling sector %llu\n",
+			printk(KERN_ERR "md/raid10:%s: %s: rescheduling sector %llu\n",
+			       mdname(conf->mddev),
 			       bdevname(conf->mirrors[dev].rdev->bdev,b), (unsigned long long)r10_bio->sector);
 		reschedule_retry(r10_bio);
 	}
@@ -296,7 +298,7 @@ static void raid10_end_read_request(struct bio *bio, int error)
 static void raid10_end_write_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
+	r10bio_t *r10_bio = bio->bi_private;
 	int slot, dev;
 	conf_t *conf = r10_bio->mddev->private;
 
@@ -494,7 +496,7 @@ static int raid10_mergeable_bvec(struct request_queue *q,
  */
 static int read_balance(conf_t *conf, r10bio_t *r10_bio)
 {
-	const unsigned long this_sector = r10_bio->sector;
+	const sector_t this_sector = r10_bio->sector;
 	int disk, slot, nslot;
 	const int sectors = r10_bio->sectors;
 	sector_t new_distance, current_distance;
@@ -601,7 +603,7 @@ static void unplug_slaves(mddev_t *mddev)
 	int i;
 
 	rcu_read_lock();
-	for (i=0; i<mddev->raid_disks; i++) {
+	for (i=0; i < conf->raid_disks; i++) {
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
 			struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
@@ -635,7 +637,7 @@ static int raid10_congested(void *data, int bits)
 	if (mddev_congested(mddev, bits))
 		return 1;
 	rcu_read_lock();
-	for (i = 0; i < mddev->raid_disks && ret == 0; i++) {
+	for (i = 0; i < conf->raid_disks && ret == 0; i++) {
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
@@ -788,14 +790,12 @@ static void unfreeze_array(conf_t *conf)
 	spin_unlock_irq(&conf->resync_lock);
 }
 
-static int make_request(struct request_queue *q, struct bio * bio)
+static int make_request(mddev_t *mddev, struct bio * bio)
 {
-	mddev_t *mddev = q->queuedata;
 	conf_t *conf = mddev->private;
 	mirror_info_t *mirror;
 	r10bio_t *r10_bio;
 	struct bio *read_bio;
-	int cpu;
 	int i;
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
@@ -825,16 +825,16 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		 */
 		bp = bio_split(bio,
 			       chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
-		if (make_request(q, &bp->bio1))
+		if (make_request(mddev, &bp->bio1))
 			generic_make_request(&bp->bio1);
-		if (make_request(q, &bp->bio2))
+		if (make_request(mddev, &bp->bio2))
 			generic_make_request(&bp->bio2);
 
 		bio_pair_release(bp);
 		return 0;
 	bad_map:
-		printk("raid10_make_request bug: can't convert block across chunks"
-		       " or bigger than %dk %llu %d\n", chunk_sects/2,
+		printk("md/raid10:%s: make_request bug: can't convert block across chunks"
+		       " or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2,
 		       (unsigned long long)bio->bi_sector, bio->bi_size >> 10);
 
 		bio_io_error(bio);
@@ -850,12 +850,6 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	 */
 	wait_barrier(conf);
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
 
 	r10_bio->master_bio = bio;
@@ -1039,9 +1033,10 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	}
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "raid10: Disk failure on %s, disabling device.\n"
-		"raid10: Operation continuing on %d devices.\n",
-		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
+	printk(KERN_ALERT "md/raid10:%s: Disk failure on %s, disabling device.\n"
+	       KERN_ALERT "md/raid10:%s: Operation continuing on %d devices.\n",
+	       mdname(mddev), bdevname(rdev->bdev, b),
+	       mdname(mddev), conf->raid_disks - mddev->degraded);
 }
 
 static void print_conf(conf_t *conf)
@@ -1049,19 +1044,19 @@ static void print_conf(conf_t *conf)
 	int i;
 	mirror_info_t *tmp;
 
-	printk("RAID10 conf printout:\n");
+	printk(KERN_DEBUG "RAID10 conf printout:\n");
 	if (!conf) {
-		printk("(!conf)\n");
+		printk(KERN_DEBUG "(!conf)\n");
 		return;
 	}
-	printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
+	printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
 		conf->raid_disks);
 
 	for (i = 0; i < conf->raid_disks; i++) {
 		char b[BDEVNAME_SIZE];
 		tmp = conf->mirrors + i;
 		if (tmp->rdev)
-			printk(" disk %d, wo:%d, o:%d, dev:%s\n",
+			printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
 				i, !test_bit(In_sync, &tmp->rdev->flags),
 			        !test_bit(Faulty, &tmp->rdev->flags),
 				bdevname(tmp->rdev->bdev,b));
@@ -1132,7 +1127,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 	int mirror;
 	mirror_info_t *p;
 	int first = 0;
-	int last = mddev->raid_disks - 1;
+	int last = conf->raid_disks - 1;
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
@@ -1224,7 +1219,7 @@ abort:
 
 static void end_sync_read(struct bio *bio, int error)
 {
-	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
+	r10bio_t *r10_bio = bio->bi_private;
 	conf_t *conf = r10_bio->mddev->private;
 	int i,d;
 
@@ -1261,7 +1256,7 @@ static void end_sync_read(struct bio *bio, int error)
 static void end_sync_write(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
+	r10bio_t *r10_bio = bio->bi_private;
 	mddev_t *mddev = r10_bio->mddev;
 	conf_t *conf = mddev->private;
 	int i,d;
@@ -1510,13 +1505,14 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
 		if (cur_read_error_count > max_read_errors) {
 			rcu_read_unlock();
 			printk(KERN_NOTICE
-			       "raid10: %s: Raid device exceeded "
+			       "md/raid10:%s: %s: Raid device exceeded "
 			       "read_error threshold "
 			       "[cur %d:max %d]\n",
+			       mdname(mddev),
 			       b, cur_read_error_count, max_read_errors);
 			printk(KERN_NOTICE
-			       "raid10: %s: Failing raid "
-			       "device\n", b);
+			       "md/raid10:%s: %s: Failing raid "
+			       "device\n", mdname(mddev), b);
 			md_error(mddev, conf->mirrors[d].rdev);
 			return;
 		}
@@ -1586,15 +1582,16 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
 				    == 0) {
 					/* Well, this device is dead */
 					printk(KERN_NOTICE
-					       "raid10:%s: read correction "
+					       "md/raid10:%s: read correction "
 					       "write failed"
 					       " (%d sectors at %llu on %s)\n",
 					       mdname(mddev), s,
 					       (unsigned long long)(sect+
 					       rdev->data_offset),
 					       bdevname(rdev->bdev, b));
-					printk(KERN_NOTICE "raid10:%s: failing "
+					printk(KERN_NOTICE "md/raid10:%s: %s: failing "
 					       "drive\n",
+					       mdname(mddev),
 					       bdevname(rdev->bdev, b));
 					md_error(mddev, rdev);
 				}
@@ -1622,20 +1619,21 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
 						 READ) == 0) {
 					/* Well, this device is dead */
 					printk(KERN_NOTICE
-					       "raid10:%s: unable to read back "
+					       "md/raid10:%s: unable to read back "
 					       "corrected sectors"
 					       " (%d sectors at %llu on %s)\n",
 					       mdname(mddev), s,
 					       (unsigned long long)(sect+
 						    rdev->data_offset),
 					       bdevname(rdev->bdev, b));
-					printk(KERN_NOTICE "raid10:%s: failing drive\n",
+					printk(KERN_NOTICE "md/raid10:%s: %s: failing drive\n",
+					       mdname(mddev),
 					       bdevname(rdev->bdev, b));
 
 					md_error(mddev, rdev);
 				} else {
 					printk(KERN_INFO
-					       "raid10:%s: read error corrected"
+					       "md/raid10:%s: read error corrected"
 					       " (%d sectors at %llu on %s)\n",
 					       mdname(mddev), s,
 					       (unsigned long long)(sect+
@@ -1710,8 +1708,9 @@ static void raid10d(mddev_t *mddev)
 				mddev->ro ? IO_BLOCKED : NULL;
 			mirror = read_balance(conf, r10_bio);
 			if (mirror == -1) {
-				printk(KERN_ALERT "raid10: %s: unrecoverable I/O"
+				printk(KERN_ALERT "md/raid10:%s: %s: unrecoverable I/O"
 				       " read error for block %llu\n",
+				       mdname(mddev),
 				       bdevname(bio->bi_bdev,b),
 				       (unsigned long long)r10_bio->sector);
 				raid_end_bio_io(r10_bio);
@@ -1721,8 +1720,9 @@ static void raid10d(mddev_t *mddev)
 				bio_put(bio);
 				rdev = conf->mirrors[mirror].rdev;
 				if (printk_ratelimit())
-					printk(KERN_ERR "raid10: %s: redirecting sector %llu to"
+					printk(KERN_ERR "md/raid10:%s: %s: redirecting sector %llu to"
 					       " another mirror\n",
+					       mdname(mddev),
 					       bdevname(rdev->bdev,b),
 					       (unsigned long long)r10_bio->sector);
 				bio = bio_clone(r10_bio->master_bio, GFP_NOIO);
@@ -1980,7 +1980,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 					r10_bio = rb2;
 					if (!test_and_set_bit(MD_RECOVERY_INTR,
 							      &mddev->recovery))
-						printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",
+						printk(KERN_INFO "md/raid10:%s: insufficient "
+						       "working devices for recovery.\n",
 						       mdname(mddev));
 					break;
 				}
@@ -2140,9 +2141,9 @@ raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
 	conf_t *conf = mddev->private;
 
 	if (!raid_disks)
-		raid_disks = mddev->raid_disks;
+		raid_disks = conf->raid_disks;
 	if (!sectors)
-		sectors = mddev->dev_sectors;
+		sectors = conf->dev_sectors;
 
 	size = sectors >> conf->chunk_shift;
 	sector_div(size, conf->far_copies);
@@ -2152,62 +2153,61 @@ raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
 	return size << conf->chunk_shift;
 }
 
-static int run(mddev_t *mddev)
+
+static conf_t *setup_conf(mddev_t *mddev)
 {
-	conf_t *conf;
-	int i, disk_idx, chunk_size;
-	mirror_info_t *disk;
-	mdk_rdev_t *rdev;
+	conf_t *conf = NULL;
 	int nc, fc, fo;
 	sector_t stride, size;
+	int err = -EINVAL;
 
 	if (mddev->chunk_sectors < (PAGE_SIZE >> 9) ||
 	    !is_power_of_2(mddev->chunk_sectors)) {
-		printk(KERN_ERR "md/raid10: chunk size must be "
-		       "at least PAGE_SIZE(%ld) and be a power of 2.\n", PAGE_SIZE);
-		return -EINVAL;
+		printk(KERN_ERR "md/raid10:%s: chunk size must be "
+		       "at least PAGE_SIZE(%ld) and be a power of 2.\n",
+		       mdname(mddev), PAGE_SIZE);
+		goto out;
 	}
 
 	nc = mddev->layout & 255;
 	fc = (mddev->layout >> 8) & 255;
 	fo = mddev->layout & (1<<16);
+
 	if ((nc*fc) <2 || (nc*fc) > mddev->raid_disks ||
 	    (mddev->layout >> 17)) {
-		printk(KERN_ERR "raid10: %s: unsupported raid10 layout: 0x%8x\n",
+		printk(KERN_ERR "md/raid10:%s: unsupported raid10 layout: 0x%8x\n",
 		       mdname(mddev), mddev->layout);
 		goto out;
 	}
-	/*
-	 * copy the already verified devices into our private RAID10
-	 * bookkeeping area. [whatever we allocate in run(),
-	 * should be freed in stop()]
-	 */
+
+	err = -ENOMEM;
 	conf = kzalloc(sizeof(conf_t), GFP_KERNEL);
-	mddev->private = conf;
-	if (!conf) {
-		printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
-			mdname(mddev));
+	if (!conf)
 		goto out;
-	}
+
 	conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks,
-				 GFP_KERNEL);
-	if (!conf->mirrors) {
-		printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
-		       mdname(mddev));
-		goto out_free_conf;
-	}
+				GFP_KERNEL);
+	if (!conf->mirrors)
+		goto out;
 
 	conf->tmppage = alloc_page(GFP_KERNEL);
 	if (!conf->tmppage)
-		goto out_free_conf;
+		goto out;
+
 
 	conf->raid_disks = mddev->raid_disks;
 	conf->near_copies = nc;
 	conf->far_copies = fc;
 	conf->copies = nc*fc;
 	conf->far_offset = fo;
-	conf->chunk_mask = mddev->chunk_sectors - 1;
-	conf->chunk_shift = ffz(~mddev->chunk_sectors);
+	conf->chunk_mask = mddev->new_chunk_sectors - 1;
+	conf->chunk_shift = ffz(~mddev->new_chunk_sectors);
+
+	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
+					   r10bio_pool_free, conf);
+	if (!conf->r10bio_pool)
+		goto out;
+
 	size = mddev->dev_sectors >> conf->chunk_shift;
 	sector_div(size, fc);
 	size = size * conf->raid_disks;
@@ -2221,7 +2221,8 @@ static int run(mddev_t *mddev)
 	 */
 	stride += conf->raid_disks - 1;
 	sector_div(stride, conf->raid_disks);
-	mddev->dev_sectors = stride << conf->chunk_shift;
+
+	conf->dev_sectors = stride << conf->chunk_shift;
 
 	if (fo)
 		stride = 1;
@@ -2229,18 +2230,63 @@ static int run(mddev_t *mddev)
 		sector_div(stride, fc);
 	conf->stride = stride << conf->chunk_shift;
 
-	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
-						r10bio_pool_free, conf);
-	if (!conf->r10bio_pool) {
-		printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
-			mdname(mddev));
-		goto out_free_conf;
-	}
 
-	conf->mddev = mddev;
 	spin_lock_init(&conf->device_lock);
+	INIT_LIST_HEAD(&conf->retry_list);
+
+	spin_lock_init(&conf->resync_lock);
+	init_waitqueue_head(&conf->wait_barrier);
+
+	conf->thread = md_register_thread(raid10d, mddev, NULL);
+	if (!conf->thread)
+		goto out;
+
+	conf->scale_disks = 0;
+	conf->mddev = mddev;
+	return conf;
+
+ out:
+	printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n",
+	       mdname(mddev));
+	if (conf) {
+		if (conf->r10bio_pool)
+			mempool_destroy(conf->r10bio_pool);
+		kfree(conf->mirrors);
+		safe_put_page(conf->tmppage);
+		kfree(conf);
+	}
+	return ERR_PTR(err);
+}
+
+static int run(mddev_t *mddev)
+{
+	conf_t *conf;
+	int i, disk_idx, chunk_size;
+	mirror_info_t *disk;
+	mdk_rdev_t *rdev;
+	sector_t size;
+
+	/*
+	 * copy the already verified devices into our private RAID10
+	 * bookkeeping area. [whatever we allocate in run(),
+	 * should be freed in stop()]
+	 */
+
+	if (mddev->private == NULL) {
+		conf = setup_conf(mddev);
+		if (IS_ERR(conf))
+			return PTR_ERR(conf);
+		mddev->private = conf;
+	}
+	conf = mddev->private;
+	if (!conf)
+		goto out;
+
 	mddev->queue->queue_lock = &conf->device_lock;
 
+	mddev->thread = conf->thread;
+	conf->thread = NULL;
+
 	chunk_size = mddev->chunk_sectors << 9;
 	blk_queue_io_min(mddev->queue, chunk_size);
 	if (conf->raid_disks % conf->near_copies)
@@ -2251,9 +2297,14 @@ static int run(mddev_t *mddev)
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		disk_idx = rdev->raid_disk;
-		if (disk_idx >= mddev->raid_disks
+		if (disk_idx >= conf->raid_disks
 		    || disk_idx < 0)
 			continue;
+		if (conf->scale_disks) {
+			disk_idx *= conf->scale_disks;
+			rdev->raid_disk = disk_idx;
+			/* MOVE 'rd%d' link !! */
+		}
 		disk = conf->mirrors + disk_idx;
 
 		disk->rdev = rdev;
@@ -2271,14 +2322,9 @@ static int run(mddev_t *mddev)
 
 		disk->head_position = 0;
 	}
-	INIT_LIST_HEAD(&conf->retry_list);
-
-	spin_lock_init(&conf->resync_lock);
-	init_waitqueue_head(&conf->wait_barrier);
-
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf)) {
-		printk(KERN_ERR "raid10: not enough operational mirrors for %s\n",
+		printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",
 		       mdname(mddev));
 		goto out_free_conf;
 	}
@@ -2297,28 +2343,21 @@ static int run(mddev_t *mddev)
 		}
 	}
 
-
-	mddev->thread = md_register_thread(raid10d, mddev, NULL);
-	if (!mddev->thread) {
-		printk(KERN_ERR
-		       "raid10: couldn't allocate thread for %s\n",
-		       mdname(mddev));
-		goto out_free_conf;
-	}
-
 	if (mddev->recovery_cp != MaxSector)
-		printk(KERN_NOTICE "raid10: %s is not clean"
+		printk(KERN_NOTICE "md/raid10:%s: not clean"
 		       " -- starting background reconstruction\n",
 		       mdname(mddev));
 	printk(KERN_INFO
-		"raid10: raid set %s active with %d out of %d devices\n",
-		mdname(mddev), mddev->raid_disks - mddev->degraded,
-		mddev->raid_disks);
+		"md/raid10:%s: active with %d out of %d devices\n",
+		mdname(mddev), conf->raid_disks - mddev->degraded,
+		conf->raid_disks);
 	/*
 	 * Ok, everything is just fine now
 	 */
-	md_set_array_sectors(mddev, raid10_size(mddev, 0, 0));
-	mddev->resync_max_sectors = raid10_size(mddev, 0, 0);
+	mddev->dev_sectors = conf->dev_sectors;
+	size = raid10_size(mddev, 0, 0);
+	md_set_array_sectors(mddev, size);
+	mddev->resync_max_sectors = size;
 
 	mddev->queue->unplug_fn = raid10_unplug;
 	mddev->queue->backing_dev_info.congested_fn = raid10_congested;
@@ -2336,7 +2375,7 @@ static int run(mddev_t *mddev)
 			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
 	}
 
-	if (conf->near_copies < mddev->raid_disks)
+	if (conf->near_copies < conf->raid_disks)
 		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
 	md_integrity_register(mddev);
 	return 0;
@@ -2348,6 +2387,7 @@ out_free_conf:
 	kfree(conf->mirrors);
 	kfree(conf);
 	mddev->private = NULL;
+	md_unregister_thread(mddev->thread);
 out:
 	return -EIO;
 }
@@ -2384,6 +2424,61 @@ static void raid10_quiesce(mddev_t *mddev, int state)
 	}
 }
 
+static void *raid10_takeover_raid0(mddev_t *mddev)
+{
+	mdk_rdev_t *rdev;
+	conf_t *conf;
+
+	if (mddev->degraded > 0) {
+		printk(KERN_ERR "md/raid10:%s: Error: degraded raid0!\n",
+		       mdname(mddev));
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Update slot numbers to obtain
+	 * degraded raid10 with missing mirrors
+	 */
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		rdev->raid_disk *= 2;
+	}
+
+	/* Set new parameters */
+	mddev->new_level = 10;
+	/* new layout: far_copies = 1, near_copies = 2 */
+	mddev->new_layout = (1<<8) + 2;
+	mddev->new_chunk_sectors = mddev->chunk_sectors;
+	mddev->delta_disks = mddev->raid_disks;
+	mddev->degraded = mddev->raid_disks;
+	mddev->raid_disks *= 2;
+	/* make sure it will be not marked as dirty */
+	mddev->recovery_cp = MaxSector;
+
+	conf = setup_conf(mddev);
+	conf->scale_disks = 2;
+	return conf;
+}
+
+static void *raid10_takeover(mddev_t *mddev)
+{
+	struct raid0_private_data *raid0_priv;
+
+	/* raid10 can take over:
+	 *  raid0 - providing it has only two drives
+	 */
+	if (mddev->level == 0) {
+		/* for raid0 takeover only one zone is supported */
+		raid0_priv = mddev->private;
+		if (raid0_priv->nr_strip_zones > 1) {
+			printk(KERN_ERR "md/raid10:%s: cannot takeover raid 0"
+			       " with more than one zone.\n",
+			       mdname(mddev));
+			return ERR_PTR(-EINVAL);
+		}
+		return raid10_takeover_raid0(mddev);
+	}
+	return ERR_PTR(-EINVAL);
+}
+
 static struct mdk_personality raid10_personality =
 {
 	.name		= "raid10",
@@ -2400,6 +2495,7 @@ static struct mdk_personality raid10_personality =
 	.sync_request	= sync_request,
 	.quiesce	= raid10_quiesce,
 	.size		= raid10_size,
+	.takeover	= raid10_takeover,
 };
 
 static int __init raid_init(void)

drivers/md/raid10.h

@@ -33,9 +33,16 @@ struct r10_private_data_s {
 					       * 1 stripe.
 					       */
 
+	sector_t		dev_sectors;  /* temp copy of mddev->dev_sectors */
+
 	int chunk_shift; /* shift from chunks to sectors */
 	sector_t chunk_mask;
 
+	int			scale_disks;  /* When starting array, multiply
+					       * each ->raid_disk by this.
+					       * Need for raid0->raid10 migration
+					       */
+
 	struct list_head	retry_list;
 	/* queue pending writes and submit them on unplug */
 	struct bio_list		pending_bio_list;
@@ -57,6 +64,11 @@ struct r10_private_data_s {
 	mempool_t *r10bio_pool;
 	mempool_t *r10buf_pool;
 	struct page		*tmppage;
+
+	/* When taking over an array from a different personality, we store
+	 * the new thread here until we fully activate the array.
+	 */
+	struct mdk_thread_s	*thread;
 };
 
 typedef struct r10_private_data_s conf_t;

drivers/md/raid5.c

@@ -53,6 +53,7 @@
 #include <linux/slab.h>
 #include "md.h"
 #include "raid5.h"
+#include "raid0.h"
 #include "bitmap.h"
 
 /*
@@ -1509,7 +1510,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		set_bit(R5_UPTODATE, &sh->dev[i].flags);
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			rdev = conf->disks[i].rdev;
-			printk_rl(KERN_INFO "raid5:%s: read error corrected"
+			printk_rl(KERN_INFO "md/raid:%s: read error corrected"
 				  " (%lu sectors at %llu on %s)\n",
 				  mdname(conf->mddev), STRIPE_SECTORS,
 				  (unsigned long long)(sh->sector
@@ -1529,7 +1530,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		atomic_inc(&rdev->read_errors);
 		if (conf->mddev->degraded >= conf->max_degraded)
 			printk_rl(KERN_WARNING
-				  "raid5:%s: read error not correctable "
+				  "md/raid:%s: read error not correctable "
 				  "(sector %llu on %s).\n",
 				  mdname(conf->mddev),
 				  (unsigned long long)(sh->sector
@@ -1538,7 +1539,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
 			/* Oh, no!!! */
 			printk_rl(KERN_WARNING
-				  "raid5:%s: read error NOT corrected!! "
+				  "md/raid:%s: read error NOT corrected!! "
 				  "(sector %llu on %s).\n",
 				  mdname(conf->mddev),
 				  (unsigned long long)(sh->sector
@@ -1547,7 +1548,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		else if (atomic_read(&rdev->read_errors)
 			 > conf->max_nr_stripes)
 			printk(KERN_WARNING
-			       "raid5:%s: Too many read errors, failing device %s.\n",
+			       "md/raid:%s: Too many read errors, failing device %s.\n",
 			       mdname(conf->mddev), bdn);
 		else
 			retry = 1;
@@ -1619,8 +1620,8 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	char b[BDEVNAME_SIZE];
-	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
-	pr_debug("raid5: error called\n");
+	raid5_conf_t *conf = mddev->private;
+	pr_debug("raid456: error called\n");
 
 	if (!test_bit(Faulty, &rdev->flags)) {
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -1636,9 +1637,13 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		}
 		set_bit(Faulty, &rdev->flags);
 		printk(KERN_ALERT
-		       "raid5: Disk failure on %s, disabling device.\n"
-		       "raid5: Operation continuing on %d devices.\n",
-		       bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
+		       "md/raid:%s: Disk failure on %s, disabling device.\n"
+		       KERN_ALERT
+		       "md/raid:%s: Operation continuing on %d devices.\n",
+		       mdname(mddev),
+		       bdevname(rdev->bdev, b),
+		       mdname(mddev),
+		       conf->raid_disks - mddev->degraded);
 	}
 }
 
@@ -1714,8 +1719,6 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
 			pd_idx = data_disks;
 			break;
 		default:
-			printk(KERN_ERR "raid5: unsupported algorithm %d\n",
-				algorithm);
 			BUG();
 		}
 		break;
@@ -1832,10 +1835,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
 			qd_idx = raid_disks - 1;
 			break;
 
-
 		default:
-			printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
-			       algorithm);
 			BUG();
 		}
 		break;
@@ -1898,8 +1898,6 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 		case ALGORITHM_PARITY_N:
 			break;
 		default:
-			printk(KERN_ERR "raid5: unsupported algorithm %d\n",
-			       algorithm);
 			BUG();
 		}
 		break;
@@ -1958,8 +1956,6 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 			i -= 1;
 			break;
 		default:
-			printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
-			       algorithm);
 			BUG();
 		}
 		break;
@@ -1972,7 +1968,8 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 				     previous, &dummy1, &sh2);
 	if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx
 		|| sh2.qd_idx != sh->qd_idx) {
-		printk(KERN_ERR "compute_blocknr: map not correct\n");
+		printk(KERN_ERR "md/raid:%s: compute_blocknr: map not correct\n",
+		       mdname(conf->mddev));
 		return 0;
 	}
 	return r_sector;
@@ -3709,10 +3706,10 @@ static void raid5_align_endio(struct bio *bi, int error)
 
 	bio_put(bi);
 
-	mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata;
-	conf = mddev->private;
 	rdev = (void*)raid_bi->bi_next;
 	raid_bi->bi_next = NULL;
+	mddev = rdev->mddev;
+	conf = mddev->private;
 
 	rdev_dec_pending(rdev, conf->mddev);
 
@@ -3749,9 +3746,8 @@ static int bio_fits_rdev(struct bio *bi)
 }
 
 
-static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
+static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
 {
-	mddev_t *mddev = q->queuedata;
 	raid5_conf_t *conf = mddev->private;
 	int dd_idx;
 	struct bio* align_bi;
@@ -3866,16 +3862,15 @@ static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf)
 	return sh;
 }
 
-static int make_request(struct request_queue *q, struct bio * bi)
+static int make_request(mddev_t *mddev, struct bio * bi)
 {
-	mddev_t *mddev = q->queuedata;
 	raid5_conf_t *conf = mddev->private;
 	int dd_idx;
 	sector_t new_sector;
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
 	const int rw = bio_data_dir(bi);
-	int cpu, remaining;
+	int remaining;
 
 	if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
 		/* Drain all pending writes.  We only really need
@@ -3890,15 +3885,9 @@ static int make_request(struct request_queue *q, struct bio * bi)
 
 	md_write_start(mddev, bi);
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bi));
-	part_stat_unlock();
-
 	if (rw == READ &&
 	     mddev->reshape_position == MaxSector &&
-	     chunk_aligned_read(q,bi))
+	     chunk_aligned_read(mddev,bi))
 		return 0;
 
 	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
@@ -3946,7 +3935,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 		new_sector = raid5_compute_sector(conf, logical_sector,
 						  previous,
 						  &dd_idx, NULL);
-		pr_debug("raid5: make_request, sector %llu logical %llu\n",
+		pr_debug("raid456: make_request, sector %llu logical %llu\n",
 			(unsigned long long)new_sector, 
 			(unsigned long long)logical_sector);
 
@@ -4054,7 +4043,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 	 * As the reads complete, handle_stripe will copy the data
 	 * into the destination stripe and release that stripe.
 	 */
-	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+	raid5_conf_t *conf = mddev->private;
 	struct stripe_head *sh;
 	sector_t first_sector, last_sector;
 	int raid_disks = conf->previous_raid_disks;
@@ -4263,7 +4252,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 /* FIXME go_faster isn't used */
 static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
 {
-	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+	raid5_conf_t *conf = mddev->private;
 	struct stripe_head *sh;
 	sector_t max_sector = mddev->dev_sectors;
 	int sync_blocks;
@@ -4725,7 +4714,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 	if (mddev->new_level != 5
 	    && mddev->new_level != 4
 	    && mddev->new_level != 6) {
-		printk(KERN_ERR "raid5: %s: raid level not set to 4/5/6 (%d)\n",
+		printk(KERN_ERR "md/raid:%s: raid level not set to 4/5/6 (%d)\n",
 		       mdname(mddev), mddev->new_level);
 		return ERR_PTR(-EIO);
 	}
@@ -4733,12 +4722,12 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 	     && !algorithm_valid_raid5(mddev->new_layout)) ||
 	    (mddev->new_level == 6
 	     && !algorithm_valid_raid6(mddev->new_layout))) {
-		printk(KERN_ERR "raid5: %s: layout %d not supported\n",
+		printk(KERN_ERR "md/raid:%s: layout %d not supported\n",
 		       mdname(mddev), mddev->new_layout);
 		return ERR_PTR(-EIO);
 	}
 	if (mddev->new_level == 6 && mddev->raid_disks < 4) {
-		printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n",
+		printk(KERN_ERR "md/raid:%s: not enough configured devices (%d, minimum 4)\n",
 		       mdname(mddev), mddev->raid_disks);
 		return ERR_PTR(-EINVAL);
 	}
@@ -4746,8 +4735,8 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 	if (!mddev->new_chunk_sectors ||
 	    (mddev->new_chunk_sectors << 9) % PAGE_SIZE ||
 	    !is_power_of_2(mddev->new_chunk_sectors)) {
-		printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
-		       mddev->new_chunk_sectors << 9, mdname(mddev));
+		printk(KERN_ERR "md/raid:%s: invalid chunk size %d\n",
+		       mdname(mddev), mddev->new_chunk_sectors << 9);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -4789,7 +4778,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 	if (raid5_alloc_percpu(conf) != 0)
 		goto abort;
 
-	pr_debug("raid5: run(%s) called.\n", mdname(mddev));
+	pr_debug("raid456: run(%s) called.\n", mdname(mddev));
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		raid_disk = rdev->raid_disk;
@@ -4802,9 +4791,9 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 
 		if (test_bit(In_sync, &rdev->flags)) {
 			char b[BDEVNAME_SIZE];
-			printk(KERN_INFO "raid5: device %s operational as raid"
-				" disk %d\n", bdevname(rdev->bdev,b),
-				raid_disk);
+			printk(KERN_INFO "md/raid:%s: device %s operational as raid"
+			       " disk %d\n",
+			       mdname(mddev), bdevname(rdev->bdev, b), raid_disk);
 		} else
 			/* Cannot rely on bitmap to complete recovery */
 			conf->fullsync = 1;
@@ -4828,16 +4817,17 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 		 max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
 	if (grow_stripes(conf, conf->max_nr_stripes)) {
 		printk(KERN_ERR
-			"raid5: couldn't allocate %dkB for buffers\n", memory);
+		       "md/raid:%s: couldn't allocate %dkB for buffers\n",
+		       mdname(mddev), memory);
 		goto abort;
 	} else
-		printk(KERN_INFO "raid5: allocated %dkB for %s\n",
-			memory, mdname(mddev));
+		printk(KERN_INFO "md/raid:%s: allocated %dkB\n",
+		       mdname(mddev), memory);
 
 	conf->thread = md_register_thread(raid5d, mddev, NULL);
 	if (!conf->thread) {
 		printk(KERN_ERR
-		       "raid5: couldn't allocate thread for %s\n",
+		       "md/raid:%s: couldn't allocate thread.\n",
 		       mdname(mddev));
 		goto abort;
 	}
@@ -4888,7 +4878,7 @@ static int run(mddev_t *mddev)
 	sector_t reshape_offset = 0;
 
 	if (mddev->recovery_cp != MaxSector)
-		printk(KERN_NOTICE "raid5: %s is not clean"
+		printk(KERN_NOTICE "md/raid:%s: not clean"
 		       " -- starting background reconstruction\n",
 		       mdname(mddev));
 	if (mddev->reshape_position != MaxSector) {
@@ -4902,7 +4892,7 @@ static int run(mddev_t *mddev)
 		int max_degraded = (mddev->level == 6 ? 2 : 1);
 
 		if (mddev->new_level != mddev->level) {
-			printk(KERN_ERR "raid5: %s: unsupported reshape "
+			printk(KERN_ERR "md/raid:%s: unsupported reshape "
 			       "required - aborting.\n",
 			       mdname(mddev));
 			return -EINVAL;
@@ -4915,8 +4905,8 @@ static int run(mddev_t *mddev)
 		here_new = mddev->reshape_position;
 		if (sector_div(here_new, mddev->new_chunk_sectors *
 			       (mddev->raid_disks - max_degraded))) {
-			printk(KERN_ERR "raid5: reshape_position not "
-			       "on a stripe boundary\n");
+			printk(KERN_ERR "md/raid:%s: reshape_position not "
+			       "on a stripe boundary\n", mdname(mddev));
 			return -EINVAL;
 		}
 		reshape_offset = here_new * mddev->new_chunk_sectors;
@@ -4937,8 +4927,9 @@ static int run(mddev_t *mddev)
 			if ((here_new * mddev->new_chunk_sectors != 
 			     here_old * mddev->chunk_sectors) ||
 			    mddev->ro == 0) {
-				printk(KERN_ERR "raid5: in-place reshape must be started"
-				       " in read-only mode - aborting\n");
+				printk(KERN_ERR "md/raid:%s: in-place reshape must be started"
+				       " in read-only mode - aborting\n",
+				       mdname(mddev));
 				return -EINVAL;
 			}
 		} else if (mddev->delta_disks < 0
@@ -4947,11 +4938,13 @@ static int run(mddev_t *mddev)
 		    : (here_new * mddev->new_chunk_sectors >=
 		       here_old * mddev->chunk_sectors)) {
 			/* Reading from the same stripe as writing to - bad */
-			printk(KERN_ERR "raid5: reshape_position too early for "
-			       "auto-recovery - aborting.\n");
+			printk(KERN_ERR "md/raid:%s: reshape_position too early for "
+			       "auto-recovery - aborting.\n",
+			       mdname(mddev));
 			return -EINVAL;
 		}
-		printk(KERN_INFO "raid5: reshape will continue\n");
+		printk(KERN_INFO "md/raid:%s: reshape will continue\n",
+		       mdname(mddev));
 		/* OK, we should be able to continue; */
 	} else {
 		BUG_ON(mddev->level != mddev->new_level);
@@ -4993,18 +4986,6 @@ static int run(mddev_t *mddev)
 		    mddev->minor_version > 90)
 			rdev->recovery_offset = reshape_offset;
 			
-		printk("%d: w=%d pa=%d pr=%d m=%d a=%d r=%d op1=%d op2=%d\n",
-		       rdev->raid_disk, working_disks, conf->prev_algo,
-		       conf->previous_raid_disks, conf->max_degraded,
-		       conf->algorithm, conf->raid_disks, 
-		       only_parity(rdev->raid_disk,
-				   conf->prev_algo,
-				   conf->previous_raid_disks,
-				   conf->max_degraded),
-		       only_parity(rdev->raid_disk,
-				   conf->algorithm,
-				   conf->raid_disks,
-				   conf->max_degraded));
 		if (rdev->recovery_offset < reshape_offset) {
 			/* We need to check old and new layout */
 			if (!only_parity(rdev->raid_disk,
@@ -5025,7 +5006,7 @@ static int run(mddev_t *mddev)
 			   - working_disks);
 
 	if (mddev->degraded > conf->max_degraded) {
-		printk(KERN_ERR "raid5: not enough operational devices for %s"
+		printk(KERN_ERR "md/raid:%s: not enough operational devices"
 			" (%d/%d failed)\n",
 			mdname(mddev), mddev->degraded, conf->raid_disks);
 		goto abort;
@@ -5039,32 +5020,32 @@ static int run(mddev_t *mddev)
 	    mddev->recovery_cp != MaxSector) {
 		if (mddev->ok_start_degraded)
 			printk(KERN_WARNING
-			       "raid5: starting dirty degraded array: %s"
-			       "- data corruption possible.\n",
+			       "md/raid:%s: starting dirty degraded array"
+			       " - data corruption possible.\n",
 			       mdname(mddev));
 		else {
 			printk(KERN_ERR
-			       "raid5: cannot start dirty degraded array for %s\n",
+			       "md/raid:%s: cannot start dirty degraded array.\n",
 			       mdname(mddev));
 			goto abort;
 		}
 	}
 
 	if (mddev->degraded == 0)
-		printk("raid5: raid level %d set %s active with %d out of %d"
-		       " devices, algorithm %d\n", conf->level, mdname(mddev),
+		printk(KERN_INFO "md/raid:%s: raid level %d active with %d out of %d"
+		       " devices, algorithm %d\n", mdname(mddev), conf->level,
 		       mddev->raid_disks-mddev->degraded, mddev->raid_disks,
 		       mddev->new_layout);
 	else
-		printk(KERN_ALERT "raid5: raid level %d set %s active with %d"
-			" out of %d devices, algorithm %d\n", conf->level,
-			mdname(mddev), mddev->raid_disks - mddev->degraded,
-			mddev->raid_disks, mddev->new_layout);
+		printk(KERN_ALERT "md/raid:%s: raid level %d active with %d"
+		       " out of %d devices, algorithm %d\n",
+		       mdname(mddev), conf->level,
+		       mddev->raid_disks - mddev->degraded,
+		       mddev->raid_disks, mddev->new_layout);
 
 	print_raid5_conf(conf);
 
 	if (conf->reshape_progress != MaxSector) {
-		printk("...ok start reshape thread\n");
 		conf->reshape_safe = conf->reshape_progress;
 		atomic_set(&conf->reshape_stripes, 0);
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -5087,9 +5068,11 @@ static int run(mddev_t *mddev)
 	}
 
 	/* Ok, everything is just fine now */
-	if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
+	if (mddev->to_remove == &raid5_attrs_group)
+		mddev->to_remove = NULL;
+	else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
 		printk(KERN_WARNING
-		       "raid5: failed to create sysfs attributes for %s\n",
+		       "md/raid:%s: failed to create sysfs attributes.\n",
 		       mdname(mddev));
 
 	mddev->queue->queue_lock = &conf->device_lock;
@@ -5119,22 +5102,21 @@ abort:
 		free_conf(conf);
 	}
 	mddev->private = NULL;
-	printk(KERN_ALERT "raid5: failed to run raid set %s\n", mdname(mddev));
+	printk(KERN_ALERT "md/raid:%s: failed to run raid set.\n", mdname(mddev));
 	return -EIO;
 }
 
-
-
 static int stop(mddev_t *mddev)
 {
-	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+	raid5_conf_t *conf = mddev->private;
 
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
 	mddev->queue->backing_dev_info.congested_fn = NULL;
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	free_conf(conf);
-	mddev->private = &raid5_attrs_group;
+	mddev->private = NULL;
+	mddev->to_remove = &raid5_attrs_group;
 	return 0;
 }
 
@@ -5175,7 +5157,7 @@ static void printall(struct seq_file *seq, raid5_conf_t *conf)
 
 static void status(struct seq_file *seq, mddev_t *mddev)
 {
-	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+	raid5_conf_t *conf = mddev->private;
 	int i;
 
 	seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
@@ -5197,21 +5179,22 @@ static void print_raid5_conf (raid5_conf_t *conf)
 	int i;
 	struct disk_info *tmp;
 
-	printk("RAID5 conf printout:\n");
+	printk(KERN_DEBUG "RAID conf printout:\n");
 	if (!conf) {
 		printk("(conf==NULL)\n");
 		return;
 	}
-	printk(" --- rd:%d wd:%d\n", conf->raid_disks,
-		 conf->raid_disks - conf->mddev->degraded);
+	printk(KERN_DEBUG " --- level:%d rd:%d wd:%d\n", conf->level,
+	       conf->raid_disks,
+	       conf->raid_disks - conf->mddev->degraded);
 
 	for (i = 0; i < conf->raid_disks; i++) {
 		char b[BDEVNAME_SIZE];
 		tmp = conf->disks + i;
 		if (tmp->rdev)
-		printk(" disk %d, o:%d, dev:%s\n",
-			i, !test_bit(Faulty, &tmp->rdev->flags),
-			bdevname(tmp->rdev->bdev,b));
+			printk(KERN_DEBUG " disk %d, o:%d, dev:%s\n",
+			       i, !test_bit(Faulty, &tmp->rdev->flags),
+			       bdevname(tmp->rdev->bdev, b));
 	}
 }
 
@@ -5334,7 +5317,6 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
 	    raid5_size(mddev, sectors, mddev->raid_disks))
 		return -EINVAL;
 	set_capacity(mddev->gendisk, mddev->array_sectors);
-	mddev->changed = 1;
 	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
 		mddev->recovery_cp = mddev->dev_sectors;
@@ -5360,7 +5342,8 @@ static int check_stripe_cache(mddev_t *mddev)
 	    > conf->max_nr_stripes ||
 	    ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4
 	    > conf->max_nr_stripes) {
-		printk(KERN_WARNING "raid5: reshape: not enough stripes.  Needed %lu\n",
+		printk(KERN_WARNING "md/raid:%s: reshape: not enough stripes.  Needed %lu\n",
+		       mdname(mddev),
 		       ((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9)
 			/ STRIPE_SIZE)*4);
 		return 0;
@@ -5431,7 +5414,7 @@ static int raid5_start_reshape(mddev_t *mddev)
 	 */
 	if (raid5_size(mddev, 0, conf->raid_disks + mddev->delta_disks)
 	    < mddev->array_sectors) {
-		printk(KERN_ERR "md: %s: array size must be reduced "
+		printk(KERN_ERR "md/raid:%s: array size must be reduced "
 		       "before number of disks\n", mdname(mddev));
 		return -EINVAL;
 	}
@@ -5469,9 +5452,9 @@ static int raid5_start_reshape(mddev_t *mddev)
 				if (sysfs_create_link(&mddev->kobj,
 						      &rdev->kobj, nm))
 					printk(KERN_WARNING
-					       "raid5: failed to create "
-					       " link %s for %s\n",
-					       nm, mdname(mddev));
+					       "md/raid:%s: failed to create "
+					       " link %s\n",
+					       mdname(mddev), nm);
 			} else
 				break;
 		}
@@ -5548,7 +5531,6 @@ static void raid5_finish_reshape(mddev_t *mddev)
 		if (mddev->delta_disks > 0) {
 			md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 			set_capacity(mddev->gendisk, mddev->array_sectors);
-			mddev->changed = 1;
 			revalidate_disk(mddev->gendisk);
 		} else {
 			int d;
@@ -5613,6 +5595,29 @@ static void raid5_quiesce(mddev_t *mddev, int state)
 }
 
 
+static void *raid45_takeover_raid0(mddev_t *mddev, int level)
+{
+	struct raid0_private_data *raid0_priv = mddev->private;
+
+	/* for raid0 takeover only one zone is supported */
+	if (raid0_priv->nr_strip_zones > 1) {
+		printk(KERN_ERR "md/raid:%s: cannot takeover raid0 with more than one zone.\n",
+		       mdname(mddev));
+		return ERR_PTR(-EINVAL);
+	}
+
+	mddev->new_level = level;
+	mddev->new_layout = ALGORITHM_PARITY_N;
+	mddev->new_chunk_sectors = mddev->chunk_sectors;
+	mddev->raid_disks += 1;
+	mddev->delta_disks = 1;
+	/* make sure it will be not marked as dirty */
+	mddev->recovery_cp = MaxSector;
+
+	return setup_conf(mddev);
+}
+
+
 static void *raid5_takeover_raid1(mddev_t *mddev)
 {
 	int chunksect;
@@ -5737,12 +5742,13 @@ static int raid6_check_reshape(mddev_t *mddev)
 static void *raid5_takeover(mddev_t *mddev)
 {
 	/* raid5 can take over:
-	 *  raid0 - if all devices are the same - make it a raid4 layout
+	 *  raid0 - if there is only one strip zone - make it a raid4 layout
 	 *  raid1 - if there are two drives.  We need to know the chunk size
 	 *  raid4 - trivial - just use a raid4 layout.
 	 *  raid6 - Providing it is a *_6 layout
 	 */
-
+	if (mddev->level == 0)
+		return raid45_takeover_raid0(mddev, 5);
 	if (mddev->level == 1)
 		return raid5_takeover_raid1(mddev);
 	if (mddev->level == 4) {
@@ -5756,6 +5762,22 @@ static void *raid5_takeover(mddev_t *mddev)
 	return ERR_PTR(-EINVAL);
 }
 
+static void *raid4_takeover(mddev_t *mddev)
+{
+	/* raid4 can take over:
+	 *  raid0 - if there is only one strip zone
+	 *  raid5 - if layout is right
+	 */
+	if (mddev->level == 0)
+		return raid45_takeover_raid0(mddev, 4);
+	if (mddev->level == 5 &&
+	    mddev->layout == ALGORITHM_PARITY_N) {
+		mddev->new_layout = 0;
+		mddev->new_level = 4;
+		return setup_conf(mddev);
+	}
+	return ERR_PTR(-EINVAL);
+}
 
 static struct mdk_personality raid5_personality;
 
@@ -5871,6 +5893,7 @@ static struct mdk_personality raid4_personality =
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
+	.takeover	= raid4_takeover,
 };
 
 static int __init raid5_init(void)