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

* 'for-linus' of git://neil.brown.name/md: (52 commits)
md: Protect access to mddev->disks list using RCU
md: only count actual openers as access which prevent a 'stop'
md: linear: Make array_size sector-based and rename it to array_sectors.
md: Make mddev->array_size sector-based.
md: Make super_type->rdev_size_change() take sector-based sizes.
md: Fix check for overlapping devices.
md: Tidy up rdev_size_store a bit:
md: Remove some unused macros.
md: Turn rdev->sb_offset into a sector-based quantity.
md: Make calc_dev_sboffset() return a sector count.
md: Replace calc_dev_size() by calc_num_sectors().
md: Make update_size() take the number of sectors.
md: Better control of when do_md_stop is allowed to stop the array.
md: get_disk_info(): Don't convert between signed and unsigned and back.
md: Simplify restart_array().
md: alloc_disk_sb(): Return proper error value.
md: Simplify sb_equal().
md: Simplify uuid_equal().
md: sb_equal(): Fix misleading printk.
md: Fix a typo in the comment to cmd_match().
...

Documentation/md.txt

···
      writing the word for the desired state, however some states
      cannot be explicitly set, and some transitions are not allowed.
 
+     Select/poll works on this file.  All changes except between
+     	active_idle and active (which can be frequent and are not
+	very interesting) are notified.  active->active_idle is
+	reported if the metadata is externally managed.
+
      clear
          No devices, no size, no level
          Writing is equivalent to STOP_ARRAY ioctl
···
 	      writemostly - device will only be subject to read
 		         requests if there are no other options.
 			 This applies only to raid1 arrays.
+	      blocked  - device has failed, metadata is "external",
+	                 and the failure hasn't been acknowledged yet.
+			 Writes that would write to this device if
+			 it were not faulty are blocked.
 	      spare    - device is working, but not a full member.
 			 This includes spares that are in the process
 			 of being recovered to
···
 	Writing "remove" removes the device from the array.
 	Writing "writemostly" sets the writemostly flag.
 	Writing "-writemostly" clears the writemostly flag.
+	Writing "blocked" sets the "blocked" flag.
+	Writing "-blocked" clear the "blocked" flag and allows writes
+		to complete.
+
+	This file responds to select/poll. Any change to 'faulty'
+	or 'blocked' causes an event.
 
       errors
 	An approximate count of read errors that have been detected on
···
         for storage of data.  This will normally be the same as the
 	component_size.  This can be written while assembling an
         array.  If a value less than the current component_size is
-        written, component_size will be reduced to this value.
+        written, it will be rejected.
 
 
 An active md device will also contain and entry for each active device
···
            corresponding operation if it was stopped with 'idle'.
 	'check' and 'repair' will start the appropriate process
            providing the current state is 'idle'.
+
+      This file responds to select/poll.  Any important change in the value
+      triggers a poll event.  Sometimes the value will briefly be
+      "recover" if a recovery seems to be needed, but cannot be
+      achieved. In that case, the transition to "recover" isn't
+      notified, but the transition away is.
+
+   degraded
+      This contains a count of the number of devices by which the
+      arrays is degraded.  So an optimal array with show '0'.  A
+      single failed/missing drive will show '1', etc.
+      This file responds to select/poll, any increase or decrease
+      in the count of missing devices will trigger an event.
 
    mismatch_count
       When performing 'check' and 'repair', and possibly when

drivers/md/bitmap.c

···
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 
-		target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512);
+		target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
 
 		if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) {
 			page->index = index;
···
 static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 {
 	mdk_rdev_t *rdev;
-	struct list_head *tmp;
 	mddev_t *mddev = bitmap->mddev;
 
-	rdev_for_each(rdev, tmp, mddev)
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev)
 		if (test_bit(In_sync, &rdev->flags)
 		    && !test_bit(Faulty, &rdev->flags)) {
 			int size = PAGE_SIZE;
···
 				    + (long)(page->index * (PAGE_SIZE/512))
 				    + size/512 > 0)
 					/* bitmap runs in to metadata */
-					return -EINVAL;
+					goto bad_alignment;
 				if (rdev->data_offset + mddev->size*2
-				    > rdev->sb_offset*2 + bitmap->offset)
+				    > rdev->sb_start + bitmap->offset)
 					/* data runs in to bitmap */
-					return -EINVAL;
-			} else if (rdev->sb_offset*2 < rdev->data_offset) {
+					goto bad_alignment;
+			} else if (rdev->sb_start < rdev->data_offset) {
 				/* METADATA BITMAP DATA */
-				if (rdev->sb_offset*2
+				if (rdev->sb_start
 				    + bitmap->offset
 				    + page->index*(PAGE_SIZE/512) + size/512
 				    > rdev->data_offset)
 					/* bitmap runs in to data */
-					return -EINVAL;
+					goto bad_alignment;
 			} else {
 				/* DATA METADATA BITMAP - no problems */
 			}
 			md_super_write(mddev, rdev,
-				       (rdev->sb_offset<<1) + bitmap->offset
+				       rdev->sb_start + bitmap->offset
 				       + page->index * (PAGE_SIZE/512),
 				       size,
 				       page);
 		}
+	rcu_read_unlock();
 
 	if (wait)
 		md_super_wait(mddev);
 	return 0;
+
+ bad_alignment:
+	rcu_read_unlock();
+	return -EINVAL;
 }
 
 static void bitmap_file_kick(struct bitmap *bitmap);
···
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
-	if (!bitmap->mddev->degraded)
-		sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+	if (bitmap->mddev->events < bitmap->events_cleared) {
+		/* rocking back to read-only */
+		bitmap->events_cleared = bitmap->mddev->events;
+		sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
+	}
 	kunmap_atomic(sb, KM_USER0);
 	write_page(bitmap, bitmap->sb_page, 1);
 }
···
 			} else
 				spin_unlock_irqrestore(&bitmap->lock, flags);
 			lastpage = page;
-/*
-			printk("bitmap clean at page %lu\n", j);
-*/
+
+			/* We are possibly going to clear some bits, so make
+			 * sure that events_cleared is up-to-date.
+			 */
+			if (bitmap->need_sync) {
+				bitmap_super_t *sb;
+				bitmap->need_sync = 0;
+				sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+				sb->events_cleared =
+					cpu_to_le64(bitmap->events_cleared);
+				kunmap_atomic(sb, KM_USER0);
+				write_page(bitmap, bitmap->sb_page, 1);
+			}
 			spin_lock_irqsave(&bitmap->lock, flags);
 			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}
···
 		if (!bmc) {
 			spin_unlock_irqrestore(&bitmap->lock, flags);
 			return;
+		}
+
+		if (success &&
+		    bitmap->events_cleared < bitmap->mddev->events) {
+			bitmap->events_cleared = bitmap->mddev->events;
+			bitmap->need_sync = 1;
 		}
 
 		if (!success && ! (*bmc & NEEDED_MASK))

drivers/md/faulty.c

···
 	rdev_for_each(rdev, tmp, mddev)
 		conf->rdev = rdev;
 
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 	mddev->private = conf;
 
 	reconfig(mddev, mddev->layout, -1);

drivers/md/linear.c

···
 		return NULL;
 
 	cnt = 0;
-	conf->array_size = 0;
+	conf->array_sectors = 0;
 
 	rdev_for_each(rdev, tmp, mddev) {
 		int j = rdev->raid_disk;
 		dev_info_t *disk = conf->disks + j;
 
-		if (j < 0 || j > raid_disks || disk->rdev) {
+		if (j < 0 || j >= raid_disks || disk->rdev) {
 			printk("linear: disk numbering problem. Aborting!\n");
 			goto out;
 		}
···
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->size = rdev->size;
-		conf->array_size += rdev->size;
+		conf->array_sectors += rdev->size * 2;
 
 		cnt++;
 	}
···
 		goto out;
 	}
 
-	min_spacing = conf->array_size;
+	min_spacing = conf->array_sectors / 2;
 	sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));
 
 	/* min_spacing is the minimum spacing that will fit the hash
···
 	 * that is larger than min_spacing as use the size of that as
 	 * the actual spacing
 	 */
-	conf->hash_spacing = conf->array_size;
+	conf->hash_spacing = conf->array_sectors / 2;
 	for (i=0; i < cnt-1 ; i++) {
 		sector_t sz = 0;
 		int j;
···
 		unsigned round;
 		unsigned long base;
 
-		sz = conf->array_size >> conf->preshift;
+		sz = conf->array_sectors >> (conf->preshift + 1);
 		sz += 1; /* force round-up */
 		base = conf->hash_spacing >> conf->preshift;
 		round = sector_div(sz, base);
···
 	curr_offset = 0;
 	i = 0;
 	for (curr_offset = 0;
-	     curr_offset < conf->array_size;
+	     curr_offset < conf->array_sectors / 2;
 	     curr_offset += conf->hash_spacing) {
 
 		while (i < raid_disks-1 &&
···
 	if (!conf)
 		return 1;
 	mddev->private = conf;
-	mddev->array_size = conf->array_size;
+	mddev->array_sectors = conf->array_sectors;
 
 	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
 	mddev->queue->unplug_fn = linear_unplug;
···
 	newconf->prev = mddev_to_conf(mddev);
 	mddev->private = newconf;
 	mddev->raid_disks++;
-	mddev->array_size = newconf->array_size;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	mddev->array_sectors = newconf->array_sectors;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	return 0;
 }
 

drivers/md/md.c

···
 {
 	atomic_inc(&md_event_count);
 	wake_up(&md_event_waiters);
-	sysfs_notify(&mddev->kobj, NULL, "sync_action");
 }
 EXPORT_SYMBOL_GPL(md_new_event);
 
···
 	INIT_LIST_HEAD(&new->all_mddevs);
 	init_timer(&new->safemode_timer);
 	atomic_set(&new->active, 1);
+	atomic_set(&new->openers, 0);
 	spin_lock_init(&new->write_lock);
 	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;
 
···
 	return NULL;
 }
 
+/* return the offset of the super block in 512byte sectors */
 static inline sector_t calc_dev_sboffset(struct block_device *bdev)
 {
-	sector_t size = bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
-	return MD_NEW_SIZE_BLOCKS(size);
+	sector_t num_sectors = bdev->bd_inode->i_size / 512;
+	return MD_NEW_SIZE_SECTORS(num_sectors);
 }
 
-static sector_t calc_dev_size(mdk_rdev_t *rdev, unsigned chunk_size)
+static sector_t calc_num_sectors(mdk_rdev_t *rdev, unsigned chunk_size)
 {
-	sector_t size;
-
-	size = rdev->sb_offset;
+	sector_t num_sectors = rdev->sb_start;
 
 	if (chunk_size)
-		size &= ~((sector_t)chunk_size/1024 - 1);
-	return size;
+		num_sectors &= ~((sector_t)chunk_size/512 - 1);
+	return num_sectors;
 }
 
 static int alloc_disk_sb(mdk_rdev_t * rdev)
···
 	rdev->sb_page = alloc_page(GFP_KERNEL);
 	if (!rdev->sb_page) {
 		printk(KERN_ALERT "md: out of memory.\n");
-		return -EINVAL;
+		return -ENOMEM;
 	}
 
 	return 0;
···
 		put_page(rdev->sb_page);
 		rdev->sb_loaded = 0;
 		rdev->sb_page = NULL;
-		rdev->sb_offset = 0;
+		rdev->sb_start = 0;
 		rdev->size = 0;
 	}
 }
···
 		return 0;
 
 
-	if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, size, rdev->sb_page, READ))
+	if (!sync_page_io(rdev->bdev, rdev->sb_start, size, rdev->sb_page, READ))
 		goto fail;
 	rdev->sb_loaded = 1;
 	return 0;
···
 
 static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
 {
-	if (	(sb1->set_uuid0 == sb2->set_uuid0) &&
-		(sb1->set_uuid1 == sb2->set_uuid1) &&
-		(sb1->set_uuid2 == sb2->set_uuid2) &&
-		(sb1->set_uuid3 == sb2->set_uuid3))
-
-		return 1;
-
-	return 0;
+	return 	sb1->set_uuid0 == sb2->set_uuid0 &&
+		sb1->set_uuid1 == sb2->set_uuid1 &&
+		sb1->set_uuid2 == sb2->set_uuid2 &&
+		sb1->set_uuid3 == sb2->set_uuid3;
 }
-
 
 static int sb_equal(mdp_super_t *sb1, mdp_super_t *sb2)
 {
···
 
 	if (!tmp1 || !tmp2) {
 		ret = 0;
-		printk(KERN_INFO "md.c: sb1 is not equal to sb2!\n");
+		printk(KERN_INFO "md.c sb_equal(): failed to allocate memory!\n");
 		goto abort;
 	}
 
···
 	tmp1->nr_disks = 0;
 	tmp2->nr_disks = 0;
 
-	if (memcmp(tmp1, tmp2, MD_SB_GENERIC_CONSTANT_WORDS * 4))
-		ret = 0;
-	else
-		ret = 1;
-
+	ret = (memcmp(tmp1, tmp2, MD_SB_GENERIC_CONSTANT_WORDS * 4) == 0);
 abort:
 	kfree(tmp1);
 	kfree(tmp2);
···
  */
 
 struct super_type  {
-	char 		*name;
-	struct module	*owner;
-	int		(*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version);
-	int		(*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev);
-	void		(*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev);
+	char		    *name;
+	struct module	    *owner;
+	int		    (*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev,
+					  int minor_version);
+	int		    (*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev);
+	void		    (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev);
+	unsigned long long  (*rdev_size_change)(mdk_rdev_t *rdev,
+						sector_t num_sectors);
 };
 
 /*
···
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	mdp_super_t *sb;
 	int ret;
-	sector_t sb_offset;
 
 	/*
-	 * Calculate the position of the superblock,
+	 * Calculate the position of the superblock (512byte sectors),
 	 * it's at the end of the disk.
 	 *
 	 * It also happens to be a multiple of 4Kb.
 	 */
-	sb_offset = calc_dev_sboffset(rdev->bdev);
-	rdev->sb_offset = sb_offset;
+	rdev->sb_start = calc_dev_sboffset(rdev->bdev);
 
 	ret = read_disk_sb(rdev, MD_SB_BYTES);
 	if (ret) return ret;
···
 		else 
 			ret = 0;
 	}
-	rdev->size = calc_dev_size(rdev, sb->chunk_size);
+	rdev->size = calc_num_sectors(rdev, sb->chunk_size) / 2;
 
 	if (rdev->size < sb->size && sb->level > 1)
 		/* "this cannot possibly happen" ... */
···
 }
 
 /*
+ * rdev_size_change for 0.90.0
+ */
+static unsigned long long
+super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
+{
+	if (num_sectors && num_sectors < rdev->mddev->size * 2)
+		return 0; /* component must fit device */
+	if (rdev->mddev->bitmap_offset)
+		return 0; /* can't move bitmap */
+	rdev->sb_start = calc_dev_sboffset(rdev->bdev);
+	if (!num_sectors || num_sectors > rdev->sb_start)
+		num_sectors = rdev->sb_start;
+	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
+		       rdev->sb_page);
+	md_super_wait(rdev->mddev);
+	return num_sectors / 2; /* kB for sysfs */
+}
+
+
+/*
  * version 1 superblock
  */
 
···
 {
 	struct mdp_superblock_1 *sb;
 	int ret;
-	sector_t sb_offset;
+	sector_t sb_start;
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	int bmask;
 
 	/*
-	 * Calculate the position of the superblock.
+	 * Calculate the position of the superblock in 512byte sectors.
 	 * It is always aligned to a 4K boundary and
 	 * depeding on minor_version, it can be:
 	 * 0: At least 8K, but less than 12K, from end of device
···
 	 */
 	switch(minor_version) {
 	case 0:
-		sb_offset = rdev->bdev->bd_inode->i_size >> 9;
-		sb_offset -= 8*2;
-		sb_offset &= ~(sector_t)(4*2-1);
-		/* convert from sectors to K */
-		sb_offset /= 2;
+		sb_start = rdev->bdev->bd_inode->i_size >> 9;
+		sb_start -= 8*2;
+		sb_start &= ~(sector_t)(4*2-1);
 		break;
 	case 1:
-		sb_offset = 0;
+		sb_start = 0;
 		break;
 	case 2:
-		sb_offset = 4;
+		sb_start = 8;
 		break;
 	default:
 		return -EINVAL;
 	}
-	rdev->sb_offset = sb_offset;
+	rdev->sb_start = sb_start;
 
 	/* superblock is rarely larger than 1K, but it can be larger,
 	 * and it is safe to read 4k, so we do that
···
 	if (sb->magic != cpu_to_le32(MD_SB_MAGIC) ||
 	    sb->major_version != cpu_to_le32(1) ||
 	    le32_to_cpu(sb->max_dev) > (4096-256)/2 ||
-	    le64_to_cpu(sb->super_offset) != (rdev->sb_offset<<1) ||
+	    le64_to_cpu(sb->super_offset) != rdev->sb_start ||
 	    (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
 		return -EINVAL;
 
···
 		rdev->sb_size = (rdev->sb_size | bmask) + 1;
 
 	if (minor_version
-	    && rdev->data_offset < sb_offset + (rdev->sb_size/512))
+	    && rdev->data_offset < sb_start + (rdev->sb_size/512))
 		return -EINVAL;
 
 	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
···
 	if (minor_version)
 		rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
 	else
-		rdev->size = rdev->sb_offset;
+		rdev->size = rdev->sb_start / 2;
 	if (rdev->size < le64_to_cpu(sb->data_size)/2)
 		return -EINVAL;
 	rdev->size = le64_to_cpu(sb->data_size)/2;
···
 	sb->sb_csum = calc_sb_1_csum(sb);
 }
 
+static unsigned long long
+super_1_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
+{
+	struct mdp_superblock_1 *sb;
+	sector_t max_sectors;
+	if (num_sectors && num_sectors < rdev->mddev->size * 2)
+		return 0; /* component must fit device */
+	if (rdev->sb_start < rdev->data_offset) {
+		/* minor versions 1 and 2; superblock before data */
+		max_sectors = rdev->bdev->bd_inode->i_size >> 9;
+		max_sectors -= rdev->data_offset;
+		if (!num_sectors || num_sectors > max_sectors)
+			num_sectors = max_sectors;
+	} else if (rdev->mddev->bitmap_offset) {
+		/* minor version 0 with bitmap we can't move */
+		return 0;
+	} else {
+		/* minor version 0; superblock after data */
+		sector_t sb_start;
+		sb_start = (rdev->bdev->bd_inode->i_size >> 9) - 8*2;
+		sb_start &= ~(sector_t)(4*2 - 1);
+		max_sectors = rdev->size * 2 + sb_start - rdev->sb_start;
+		if (!num_sectors || num_sectors > max_sectors)
+			num_sectors = max_sectors;
+		rdev->sb_start = sb_start;
+	}
+	sb = (struct mdp_superblock_1 *) page_address(rdev->sb_page);
+	sb->data_size = cpu_to_le64(num_sectors);
+	sb->super_offset = rdev->sb_start;
+	sb->sb_csum = calc_sb_1_csum(sb);
+	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
+		       rdev->sb_page);
+	md_super_wait(rdev->mddev);
+	return num_sectors / 2; /* kB for sysfs */
+}
 
 static struct super_type super_types[] = {
 	[0] = {
 		.name	= "0.90.0",
 		.owner	= THIS_MODULE,
-		.load_super	= super_90_load,
-		.validate_super	= super_90_validate,
-		.sync_super	= super_90_sync,
+		.load_super	    = super_90_load,
+		.validate_super	    = super_90_validate,
+		.sync_super	    = super_90_sync,
+		.rdev_size_change   = super_90_rdev_size_change,
 	},
 	[1] = {
 		.name	= "md-1",
 		.owner	= THIS_MODULE,
-		.load_super	= super_1_load,
-		.validate_super	= super_1_validate,
-		.sync_super	= super_1_sync,
+		.load_super	    = super_1_load,
+		.validate_super	    = super_1_validate,
+		.sync_super	    = super_1_sync,
+		.rdev_size_change   = super_1_rdev_size_change,
 	},
 };
 
 static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
 {
-	struct list_head *tmp, *tmp2;
 	mdk_rdev_t *rdev, *rdev2;
 
-	rdev_for_each(rdev, tmp, mddev1)
-		rdev_for_each(rdev2, tmp2, mddev2)
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev1)
+		rdev_for_each_rcu(rdev2, mddev2)
 			if (rdev->bdev->bd_contains ==
-			    rdev2->bdev->bd_contains)
+			    rdev2->bdev->bd_contains) {
+				rcu_read_unlock();
 				return 1;
-
+			}
+	rcu_read_unlock();
 	return 0;
 }
 
···
 		kobject_del(&rdev->kobj);
 		goto fail;
 	}
-	list_add(&rdev->same_set, &mddev->disks);
+	list_add_rcu(&rdev->same_set, &mddev->disks);
 	bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);
 	return 0;
 
···
 		return;
 	}
 	bd_release_from_disk(rdev->bdev, rdev->mddev->gendisk);
-	list_del_init(&rdev->same_set);
+	list_del_rcu(&rdev->same_set);
 	printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
 	rdev->mddev = NULL;
 	sysfs_remove_link(&rdev->kobj, "block");
 
 	/* We need to delay this, otherwise we can deadlock when
-	 * writing to 'remove' to "dev/state"
+	 * writing to 'remove' to "dev/state".  We also need
+	 * to delay it due to rcu usage.
 	 */
+	synchronize_rcu();
 	INIT_WORK(&rdev->del_work, md_delayed_delete);
 	kobject_get(&rdev->kobj);
 	schedule_work(&rdev->del_work);
···
 	if (rdev->mddev)
 		MD_BUG();
 	free_disk_sb(rdev);
-	list_del_init(&rdev->same_set);
 #ifndef MODULE
 	if (test_bit(AutoDetected, &rdev->flags))
 		md_autodetect_dev(rdev->bdev->bd_dev);
···
 		dprintk("%s ", bdevname(rdev->bdev,b));
 		if (!test_bit(Faulty, &rdev->flags)) {
 			md_super_write(mddev,rdev,
-				       rdev->sb_offset<<1, rdev->sb_size,
+				       rdev->sb_start, rdev->sb_size,
 				       rdev->sb_page);
 			dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
 				bdevname(rdev->bdev,b),
-				(unsigned long long)rdev->sb_offset);
+				(unsigned long long)rdev->sb_start);
 			rdev->sb_events = mddev->events;
 
 		} else
···
 
 }
 
-/* words written to sysfs files may, or my not, be \n terminated.
+/* words written to sysfs files may, or may not, be \n terminated.
  * We want to accept with case. For this we use cmd_match.
  */
 static int cmd_match(const char *cmd, const char *str)
···
 
 		err = 0;
 	}
+	if (!err)
+		sysfs_notify(&rdev->kobj, NULL, "state");
 	return err ? err : len;
 }
 static struct rdev_sysfs_entry rdev_state =
···
 		slot = -1;
 	else if (e==buf || (*e && *e!= '\n'))
 		return -EINVAL;
-	if (rdev->mddev->pers) {
+	if (rdev->mddev->pers && slot == -1) {
 		/* Setting 'slot' on an active array requires also
 		 * updating the 'rd%d' link, and communicating
 		 * with the personality with ->hot_*_disk.
···
 		 * failed/spare devices.  This normally happens automatically,
 		 * but not when the metadata is externally managed.
 		 */
-		if (slot != -1)
-			return -EBUSY;
 		if (rdev->raid_disk == -1)
 			return -EEXIST;
 		/* personality does all needed checks */
···
 		sysfs_remove_link(&rdev->mddev->kobj, nm);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
 		md_wakeup_thread(rdev->mddev->thread);
+	} else if (rdev->mddev->pers) {
+		mdk_rdev_t *rdev2;
+		struct list_head *tmp;
+		/* Activating a spare .. or possibly reactivating
+		 * if we every get bitmaps working here.
+		 */
+
+		if (rdev->raid_disk != -1)
+			return -EBUSY;
+
+		if (rdev->mddev->pers->hot_add_disk == NULL)
+			return -EINVAL;
+
+		rdev_for_each(rdev2, tmp, rdev->mddev)
+			if (rdev2->raid_disk == slot)
+				return -EEXIST;
+
+		rdev->raid_disk = slot;
+		if (test_bit(In_sync, &rdev->flags))
+			rdev->saved_raid_disk = slot;
+		else
+			rdev->saved_raid_disk = -1;
+		err = rdev->mddev->pers->
+			hot_add_disk(rdev->mddev, rdev);
+		if (err) {
+			rdev->raid_disk = -1;
+			return err;
+		} else
+			sysfs_notify(&rdev->kobj, NULL, "state");
+		sprintf(nm, "rd%d", rdev->raid_disk);
+		if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
+			printk(KERN_WARNING
+			       "md: cannot register "
+			       "%s for %s\n",
+			       nm, mdname(rdev->mddev));
+
+		/* don't wakeup anyone, leave that to userspace. */
 	} else {
 		if (slot >= rdev->mddev->raid_disks)
 			return -ENOSPC;
···
 		clear_bit(Faulty, &rdev->flags);
 		clear_bit(WriteMostly, &rdev->flags);
 		set_bit(In_sync, &rdev->flags);
+		sysfs_notify(&rdev->kobj, NULL, "state");
 	}
 	return len;
 }
···
 	unsigned long long offset = simple_strtoull(buf, &e, 10);
 	if (e==buf || (*e && *e != '\n'))
 		return -EINVAL;
-	if (rdev->mddev->pers)
+	if (rdev->mddev->pers && rdev->raid_disk >= 0)
 		return -EBUSY;
 	if (rdev->size && rdev->mddev->external)
 		/* Must set offset before size, so overlap checks
···
 static ssize_t
 rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 {
-	char *e;
-	unsigned long long size = simple_strtoull(buf, &e, 10);
+	unsigned long long size;
 	unsigned long long oldsize = rdev->size;
 	mddev_t *my_mddev = rdev->mddev;
 
-	if (e==buf || (*e && *e != '\n'))
+	if (strict_strtoull(buf, 10, &size) < 0)
 		return -EINVAL;
-	if (my_mddev->pers)
-		return -EBUSY;
+	if (size < my_mddev->size)
+		return -EINVAL;
+	if (my_mddev->pers && rdev->raid_disk >= 0) {
+		if (my_mddev->persistent) {
+			size = super_types[my_mddev->major_version].
+				rdev_size_change(rdev, size * 2);
+			if (!size)
+				return -EBUSY;
+		} else if (!size) {
+			size = (rdev->bdev->bd_inode->i_size >> 10);
+			size -= rdev->data_offset/2;
+		}
+		if (size < my_mddev->size)
+			return -EINVAL; /* component must fit device */
+	}
+
 	rdev->size = size;
-	if (size > oldsize && rdev->mddev->external) {
+	if (size > oldsize && my_mddev->external) {
 		/* need to check that all other rdevs with the same ->bdev
 		 * do not overlap.  We need to unlock the mddev to avoid
 		 * a deadlock.  We have already changed rdev->size, and if
···
 				if (test_bit(AllReserved, &rdev2->flags) ||
 				    (rdev->bdev == rdev2->bdev &&
 				     rdev != rdev2 &&
-				     overlaps(rdev->data_offset, rdev->size,
-					    rdev2->data_offset, rdev2->size))) {
+				     overlaps(rdev->data_offset, rdev->size * 2,
+					      rdev2->data_offset,
+					      rdev2->size * 2))) {
 					overlap = 1;
 					break;
 				}
···
 			return -EBUSY;
 		}
 	}
-	if (size < my_mddev->size || my_mddev->size == 0)
-		my_mddev->size = size;
 	return len;
 }
 
···
  *     When written, doesn't tear down array, but just stops it
  * suspended (not supported yet)
  *     All IO requests will block. The array can be reconfigured.
- *     Writing this, if accepted, will block until array is quiessent
+ *     Writing this, if accepted, will block until array is quiescent
  * readonly
  *     no resync can happen.  no superblocks get written.
  *     write requests fail
···
 	return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(mddev_t * mddev, int ro);
+static int do_md_stop(mddev_t * mddev, int ro, int is_open);
 static int do_md_run(mddev_t * mddev);
 static int restart_array(mddev_t *mddev);
 
···
 		break;
 	case clear:
 		/* stopping an active array */
-		if (atomic_read(&mddev->active) > 1)
+		if (atomic_read(&mddev->openers) > 0)
 			return -EBUSY;
-		err = do_md_stop(mddev, 0);
+		err = do_md_stop(mddev, 0, 0);
 		break;
 	case inactive:
 		/* stopping an active array */
 		if (mddev->pers) {
-			if (atomic_read(&mddev->active) > 1)
+			if (atomic_read(&mddev->openers) > 0)
 				return -EBUSY;
-			err = do_md_stop(mddev, 2);
+			err = do_md_stop(mddev, 2, 0);
 		} else
 			err = 0; /* already inactive */
 		break;
···
 		break; /* not supported yet */
 	case readonly:
 		if (mddev->pers)
-			err = do_md_stop(mddev, 1);
+			err = do_md_stop(mddev, 1, 0);
 		else {
 			mddev->ro = 1;
 			set_disk_ro(mddev->gendisk, 1);
···
 	case read_auto:
 		if (mddev->pers) {
 			if (mddev->ro != 1)
-				err = do_md_stop(mddev, 1);
+				err = do_md_stop(mddev, 1, 0);
 			else
 				err = restart_array(mddev);
 			if (err == 0) {
···
 	}
 	if (err)
 		return err;
-	else
+	else {
+		sysfs_notify(&mddev->kobj, NULL, "array_state");
 		return len;
+	}
 }
 static struct md_sysfs_entry md_array_state =
 __ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
···
 	return sprintf(page, "%llu\n", (unsigned long long)mddev->size);
 }
 
-static int update_size(mddev_t *mddev, unsigned long size);
+static int update_size(mddev_t *mddev, sector_t num_sectors);
 
 static ssize_t
 size_store(mddev_t *mddev, const char *buf, size_t len)
···
 		return -EINVAL;
 
 	if (mddev->pers) {
-		err = update_size(mddev, size);
+		err = update_size(mddev, size * 2);
 		md_update_sb(mddev, 1);
 	} else {
 		if (mddev->size == 0 ||
···
 				type = "check";
 			else
 				type = "repair";
-		} else
+		} else if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
 			type = "recover";
 	}
 	return sprintf(page, "%s\n", type);
···
 	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
 		return -EBUSY;
-	else if (cmd_match(page, "resync") || cmd_match(page, "recover"))
+	else if (cmd_match(page, "resync"))
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	else if (cmd_match(page, "reshape")) {
+	else if (cmd_match(page, "recover")) {
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	} else if (cmd_match(page, "reshape")) {
 		int err;
 		if (mddev->pers->start_reshape == NULL)
 			return -EINVAL;
 		err = mddev->pers->start_reshape(mddev);
 		if (err)
 			return err;
+		sysfs_notify(&mddev->kobj, NULL, "degraded");
 	} else {
 		if (cmd_match(page, "check"))
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
···
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
+	sysfs_notify(&mddev->kobj, NULL, "sync_action");
 	return len;
 }
 
···
 sync_speed_show(mddev_t *mddev, char *page)
 {
 	unsigned long resync, dt, db;
-	resync = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active));
-	dt = ((jiffies - mddev->resync_mark) / HZ);
+	resync = mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active);
+	dt = (jiffies - mddev->resync_mark) / HZ;
 	if (!dt) dt++;
-	db = resync - (mddev->resync_mark_cnt);
-	return sprintf(page, "%ld\n", db/dt/2); /* K/sec */
+	db = resync - mddev->resync_mark_cnt;
+	return sprintf(page, "%lu\n", db/dt/2); /* K/sec */
 }
 
 static struct md_sysfs_entry md_sync_speed = __ATTR_RO(sync_speed);
···
 static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed);
 
 static ssize_t
+min_sync_show(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)mddev->resync_min);
+}
+static ssize_t
+min_sync_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	unsigned long long min;
+	if (strict_strtoull(buf, 10, &min))
+		return -EINVAL;
+	if (min > mddev->resync_max)
+		return -EINVAL;
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		return -EBUSY;
+
+	/* Must be a multiple of chunk_size */
+	if (mddev->chunk_size) {
+		if (min & (sector_t)((mddev->chunk_size>>9)-1))
+			return -EINVAL;
+	}
+	mddev->resync_min = min;
+
+	return len;
+}
+
+static struct md_sysfs_entry md_min_sync =
+__ATTR(sync_min, S_IRUGO|S_IWUSR, min_sync_show, min_sync_store);
+
+static ssize_t
 max_sync_show(mddev_t *mddev, char *page)
 {
 	if (mddev->resync_max == MaxSector)
···
 	if (strncmp(buf, "max", 3) == 0)
 		mddev->resync_max = MaxSector;
 	else {
-		char *ep;
-		unsigned long long max = simple_strtoull(buf, &ep, 10);
-		if (ep == buf || (*ep != 0 && *ep != '\n'))
+		unsigned long long max;
+		if (strict_strtoull(buf, 10, &max))
+			return -EINVAL;
+		if (max < mddev->resync_min)
 			return -EINVAL;
 		if (max < mddev->resync_max &&
 		    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
···
 	&md_sync_speed.attr,
 	&md_sync_force_parallel.attr,
 	&md_sync_completed.attr,
+	&md_min_sync.attr,
 	&md_max_sync.attr,
 	&md_suspend_lo.attr,
 	&md_suspend_hi.attr,
···
 	disk->queue = mddev->queue;
 	add_disk(disk);
 	mddev->gendisk = disk;
-	mutex_unlock(&disks_mutex);
 	error = kobject_init_and_add(&mddev->kobj, &md_ktype, &disk->dev.kobj,
 				     "%s", "md");
+	mutex_unlock(&disks_mutex);
 	if (error)
 		printk(KERN_WARNING "md: cannot register %s/md - name in use\n",
 		       disk->disk_name);
···
 {
 	mddev_t *mddev = (mddev_t *) data;
 
-	mddev->safemode = 1;
+	if (!atomic_read(&mddev->writes_pending)) {
+		mddev->safemode = 1;
+		if (mddev->external)
+			sysfs_notify(&mddev->kobj, NULL, "array_state");
+	}
 	md_wakeup_thread(mddev->thread);
 }
 
···
 		 * We don't want the data to overlap the metadata,
 		 * Internal Bitmap issues has handled elsewhere.
 		 */
-		if (rdev->data_offset < rdev->sb_offset) {
+		if (rdev->data_offset < rdev->sb_start) {
 			if (mddev->size &&
 			    rdev->data_offset + mddev->size*2
-			    > rdev->sb_offset*2) {
+			    > rdev->sb_start) {
 				printk("md: %s: data overlaps metadata\n",
 				       mdname(mddev));
 				return -EINVAL;
 			}
 		} else {
-			if (rdev->sb_offset*2 + rdev->sb_size/512
+			if (rdev->sb_start + rdev->sb_size/512
 			    > rdev->data_offset) {
 				printk("md: %s: metadata overlaps data\n",
 				       mdname(mddev));
 				return -EINVAL;
 			}
 		}
+		sysfs_notify(&rdev->kobj, NULL, "state");
 	}
 
 	md_probe(mddev->unit, NULL, NULL);
···
 		mddev->ro = 2; /* read-only, but switch on first write */
 
 	err = mddev->pers->run(mddev);
-	if (!err && mddev->pers->sync_request) {
+	if (err)
+		printk(KERN_ERR "md: pers->run() failed ...\n");
+	else if (mddev->pers->sync_request) {
 		err = bitmap_create(mddev);
 		if (err) {
 			printk(KERN_ERR "%s: failed to create bitmap (%d)\n",
···
 		}
 	}
 	if (err) {
-		printk(KERN_ERR "md: pers->run() failed ...\n");
 		module_put(mddev->pers->owner);
 		mddev->pers = NULL;
 		bitmap_destroy(mddev);
···
 	if (mddev->flags)
 		md_update_sb(mddev, 0);
 
-	set_capacity(disk, mddev->array_size<<1);
+	set_capacity(disk, mddev->array_sectors);
 
 	/* If we call blk_queue_make_request here, it will
 	 * re-initialise max_sectors etc which may have been
···
 
 	mddev->changed = 1;
 	md_new_event(mddev);
+	sysfs_notify(&mddev->kobj, NULL, "array_state");
+	sysfs_notify(&mddev->kobj, NULL, "sync_action");
+	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	kobject_uevent(&mddev->gendisk->dev.kobj, KOBJ_CHANGE);
 	return 0;
 }
···
 static int restart_array(mddev_t *mddev)
 {
 	struct gendisk *disk = mddev->gendisk;
-	int err;
 
-	/*
-	 * Complain if it has no devices
-	 */
-	err = -ENXIO;
+	/* Complain if it has no devices */
 	if (list_empty(&mddev->disks))
-		goto out;
-
-	if (mddev->pers) {
-		err = -EBUSY;
-		if (!mddev->ro)
-			goto out;
-
-		mddev->safemode = 0;
-		mddev->ro = 0;
-		set_disk_ro(disk, 0);
-
-		printk(KERN_INFO "md: %s switched to read-write mode.\n",
-			mdname(mddev));
-		/*
-		 * Kick recovery or resync if necessary
-		 */
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
-		md_wakeup_thread(mddev->sync_thread);
-		err = 0;
-	} else
-		err = -EINVAL;
-
-out:
-	return err;
+		return -ENXIO;
+	if (!mddev->pers)
+		return -EINVAL;
+	if (!mddev->ro)
+		return -EBUSY;
+	mddev->safemode = 0;
+	mddev->ro = 0;
+	set_disk_ro(disk, 0);
+	printk(KERN_INFO "md: %s switched to read-write mode.\n",
+		mdname(mddev));
+	/* Kick recovery or resync if necessary */
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(mddev->sync_thread);
+	sysfs_notify(&mddev->kobj, NULL, "array_state");
+	return 0;
 }
 
 /* similar to deny_write_access, but accounts for our holding a reference
···
  *   1 - switch to readonly
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(mddev_t * mddev, int mode)
+static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 {
 	int err = 0;
 	struct gendisk *disk = mddev->gendisk;
 
+	if (atomic_read(&mddev->openers) > is_open) {
+		printk("md: %s still in use.\n",mdname(mddev));
+		return -EBUSY;
+	}
+
 	if (mddev->pers) {
-		if (atomic_read(&mddev->active)>2) {
-			printk("md: %s still in use.\n",mdname(mddev));
-			return -EBUSY;
-		}
 
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
···
 
 		export_array(mddev);
 
-		mddev->array_size = 0;
+		mddev->array_sectors = 0;
 		mddev->size = 0;
 		mddev->raid_disks = 0;
 		mddev->recovery_cp = 0;
+		mddev->resync_min = 0;
 		mddev->resync_max = MaxSector;
 		mddev->reshape_position = MaxSector;
 		mddev->external = 0;
···
 			mdname(mddev));
 	err = 0;
 	md_new_event(mddev);
+	sysfs_notify(&mddev->kobj, NULL, "array_state");
 out:
 	return err;
 }
···
 	err = do_md_run (mddev);
 	if (err) {
 		printk(KERN_WARNING "md: do_md_run() returned %d\n", err);
-		do_md_stop (mddev, 0);
+		do_md_stop (mddev, 0, 0);
 	}
 }
 
···
 		/* on success, candidates will be empty, on error
 		 * it won't...
 		 */
-		rdev_for_each_list(rdev, tmp, candidates)
+		rdev_for_each_list(rdev, tmp, candidates) {
+			list_del_init(&rdev->same_set);
 			export_rdev(rdev);
+		}
 		mddev_put(mddev);
 	}
 	printk(KERN_INFO "md: ... autorun DONE.\n");
···
 	char *ptr, *buf = NULL;
 	int err = -ENOMEM;
 
-	md_allow_write(mddev);
+	if (md_allow_write(mddev))
+		file = kmalloc(sizeof(*file), GFP_NOIO);
+	else
+		file = kmalloc(sizeof(*file), GFP_KERNEL);
 
-	file = kmalloc(sizeof(*file), GFP_KERNEL);
 	if (!file)
 		goto out;
 
···
 static int get_disk_info(mddev_t * mddev, void __user * arg)
 {
 	mdu_disk_info_t info;
-	unsigned int nr;
 	mdk_rdev_t *rdev;
 
 	if (copy_from_user(&info, arg, sizeof(info)))
 		return -EFAULT;
 
-	nr = info.number;
-
-	rdev = find_rdev_nr(mddev, nr);
+	rdev = find_rdev_nr(mddev, info.number);
 	if (rdev) {
 		info.major = MAJOR(rdev->bdev->bd_dev);
 		info.minor = MINOR(rdev->bdev->bd_dev);
···
 		}
 		if (err)
 			export_rdev(rdev);
+		else
+			sysfs_notify(&rdev->kobj, NULL, "state");
 
 		md_update_sb(mddev, 1);
+		if (mddev->degraded)
+			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 		return err;
···
 
 		if (!mddev->persistent) {
 			printk(KERN_INFO "md: nonpersistent superblock ...\n");
-			rdev->sb_offset = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
+			rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
 		} else 
-			rdev->sb_offset = calc_dev_sboffset(rdev->bdev);
-		rdev->size = calc_dev_size(rdev, mddev->chunk_size);
+			rdev->sb_start = calc_dev_sboffset(rdev->bdev);
+		rdev->size = calc_num_sectors(rdev, mddev->chunk_size) / 2;
 
 		err = bind_rdev_to_array(rdev, mddev);
 		if (err) {
···
 {
 	char b[BDEVNAME_SIZE];
 	mdk_rdev_t *rdev;
-
-	if (!mddev->pers)
-		return -ENODEV;
 
 	rdev = find_rdev(mddev, dev);
 	if (!rdev)
···
 {
 	char b[BDEVNAME_SIZE];
 	int err;
-	unsigned int size;
 	mdk_rdev_t *rdev;
 
 	if (!mddev->pers)
···
 	}
 
 	if (mddev->persistent)
-		rdev->sb_offset = calc_dev_sboffset(rdev->bdev);
+		rdev->sb_start = calc_dev_sboffset(rdev->bdev);
 	else
-		rdev->sb_offset =
-			rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
+		rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
 
-	size = calc_dev_size(rdev, mddev->chunk_size);
-	rdev->size = size;
+	rdev->size = calc_num_sectors(rdev, mddev->chunk_size) / 2;
 
 	if (test_bit(Faulty, &rdev->flags)) {
 		printk(KERN_WARNING 
···
 	return 0;
 }
 
-static int update_size(mddev_t *mddev, unsigned long size)
+static int update_size(mddev_t *mddev, sector_t num_sectors)
 {
 	mdk_rdev_t * rdev;
 	int rv;
 	struct list_head *tmp;
-	int fit = (size == 0);
+	int fit = (num_sectors == 0);
 
 	if (mddev->pers->resize == NULL)
 		return -EINVAL;
-	/* The "size" is the amount of each device that is used.
-	 * This can only make sense for arrays with redundancy.
-	 * linear and raid0 always use whatever space is available
-	 * We can only consider changing the size if no resync
-	 * or reconstruction is happening, and if the new size
-	 * is acceptable. It must fit before the sb_offset or,
-	 * if that is <data_offset, it must fit before the
-	 * size of each device.
-	 * If size is zero, we find the largest size that fits.
+	/* The "num_sectors" is the number of sectors of each device that
+	 * is used.  This can only make sense for arrays with redundancy.
+	 * linear and raid0 always use whatever space is available. We can only
+	 * consider changing this number if no resync or reconstruction is
+	 * happening, and if the new size is acceptable. It must fit before the
+	 * sb_start or, if that is <data_offset, it must fit before the size
+	 * of each device.  If num_sectors is zero, we find the largest size
+	 * that fits.
+
 	 */
 	if (mddev->sync_thread)
 		return -EBUSY;
···
 		sector_t avail;
 		avail = rdev->size * 2;
 
-		if (fit && (size == 0 || size > avail/2))
-			size = avail/2;
-		if (avail < ((sector_t)size << 1))
+		if (fit && (num_sectors == 0 || num_sectors > avail))
+			num_sectors = avail;
+		if (avail < num_sectors)
 			return -ENOSPC;
 	}
-	rv = mddev->pers->resize(mddev, (sector_t)size *2);
+	rv = mddev->pers->resize(mddev, num_sectors);
 	if (!rv) {
 		struct block_device *bdev;
 
 		bdev = bdget_disk(mddev->gendisk, 0);
 		if (bdev) {
 			mutex_lock(&bdev->bd_inode->i_mutex);
-			i_size_write(bdev->bd_inode, (loff_t)mddev->array_size << 10);
+			i_size_write(bdev->bd_inode,
+				     (loff_t)mddev->array_sectors << 9);
 			mutex_unlock(&bdev->bd_inode->i_mutex);
 			bdput(bdev);
 		}
···
 			return mddev->pers->reconfig(mddev, info->layout, -1);
 	}
 	if (info->size >= 0 && mddev->size != info->size)
-		rv = update_size(mddev, info->size);
+		rv = update_size(mddev, (sector_t)info->size * 2);
 
 	if (mddev->raid_disks    != info->raid_disks)
 		rv = update_raid_disks(mddev, info->raid_disks);
···
 	return 0;
 }
 
+/*
+ * We have a problem here : there is no easy way to give a CHS
+ * virtual geometry. We currently pretend that we have a 2 heads
+ * 4 sectors (with a BIG number of cylinders...). This drives
+ * dosfs just mad... ;-)
+ */
 static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	mddev_t *mddev = bdev->bd_disk->private_data;
···
 			goto done_unlock;
 
 		case STOP_ARRAY:
-			err = do_md_stop (mddev, 0);
+			err = do_md_stop (mddev, 0, 1);
 			goto done_unlock;
 
 		case STOP_ARRAY_RO:
-			err = do_md_stop (mddev, 1);
+			err = do_md_stop (mddev, 1, 1);
 			goto done_unlock;
 
-	/*
-	 * We have a problem here : there is no easy way to give a CHS
-	 * virtual geometry. We currently pretend that we have a 2 heads
-	 * 4 sectors (with a BIG number of cylinders...). This drives
-	 * dosfs just mad... ;-)
-	 */
 	}
 
 	/*
···
 	 * here and hit the 'default' below, so only disallow
 	 * 'md' ioctls, and switch to rw mode if started auto-readonly.
 	 */
-	if (_IOC_TYPE(cmd) == MD_MAJOR &&
-	    mddev->ro && mddev->pers) {
+	if (_IOC_TYPE(cmd) == MD_MAJOR && mddev->ro && mddev->pers) {
 		if (mddev->ro == 2) {
 			mddev->ro = 0;
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
-
+			sysfs_notify(&mddev->kobj, NULL, "array_state");
+			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			md_wakeup_thread(mddev->thread);
 		} else {
 			err = -EROFS;
 			goto abort_unlock;
···
 
 	err = 0;
 	mddev_get(mddev);
+	atomic_inc(&mddev->openers);
 	mddev_unlock(mddev);
 
 	check_disk_change(inode->i_bdev);
···
  	mddev_t *mddev = inode->i_bdev->bd_disk->private_data;
 
 	BUG_ON(!mddev);
+	atomic_dec(&mddev->openers);
 	mddev_put(mddev);
 
 	return 0;
···
 	if (!mddev->pers->error_handler)
 		return;
 	mddev->pers->error_handler(mddev,rdev);
+	if (mddev->degraded)
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+	set_bit(StateChanged, &rdev->flags);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
···
 		if (!list_empty(&mddev->disks)) {
 			if (mddev->pers)
 				seq_printf(seq, "\n      %llu blocks",
-					(unsigned long long)mddev->array_size);
+					   (unsigned long long)
+					   mddev->array_sectors / 2);
 			else
 				seq_printf(seq, "\n      %llu blocks",
-					(unsigned long long)size);
+					   (unsigned long long)size);
 		}
 		if (mddev->persistent) {
 			if (mddev->major_version != 0 ||
···
 static int is_mddev_idle(mddev_t *mddev)
 {
 	mdk_rdev_t * rdev;
-	struct list_head *tmp;
 	int idle;
 	long curr_events;
 
 	idle = 1;
-	rdev_for_each(rdev, tmp, mddev) {
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
 		curr_events = disk_stat_read(disk, sectors[0]) + 
 				disk_stat_read(disk, sectors[1]) - 
···
 			idle = 0;
 		}
 	}
+	rcu_read_unlock();
 	return idle;
 }
 
···
  */
 void md_write_start(mddev_t *mddev, struct bio *bi)
 {
+	int did_change = 0;
 	if (bio_data_dir(bi) != WRITE)
 		return;
 
···
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 		md_wakeup_thread(mddev->sync_thread);
+		did_change = 1;
 	}
 	atomic_inc(&mddev->writes_pending);
 	if (mddev->safemode == 1)
···
 			mddev->in_sync = 0;
 			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			md_wakeup_thread(mddev->thread);
+			did_change = 1;
 		}
 		spin_unlock_irq(&mddev->write_lock);
-		sysfs_notify(&mddev->kobj, NULL, "array_state");
 	}
+	if (did_change)
+		sysfs_notify(&mddev->kobj, NULL, "array_state");
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
 		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
···
  * may proceed without blocking.  It is important to call this before
  * attempting a GFP_KERNEL allocation while holding the mddev lock.
  * Must be called with mddev_lock held.
+ *
+ * In the ->external case MD_CHANGE_CLEAN can not be cleared until mddev->lock
+ * is dropped, so return -EAGAIN after notifying userspace.
  */
-void md_allow_write(mddev_t *mddev)
+int md_allow_write(mddev_t *mddev)
 {
 	if (!mddev->pers)
-		return;
+		return 0;
 	if (mddev->ro)
-		return;
+		return 0;
+	if (!mddev->pers->sync_request)
+		return 0;
 
 	spin_lock_irq(&mddev->write_lock);
 	if (mddev->in_sync) {
···
 			mddev->safemode = 1;
 		spin_unlock_irq(&mddev->write_lock);
 		md_update_sb(mddev, 0);
-
 		sysfs_notify(&mddev->kobj, NULL, "array_state");
-		/* wait for the dirty state to be recorded in the metadata */
-		wait_event(mddev->sb_wait,
-			   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
-			   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 	} else
 		spin_unlock_irq(&mddev->write_lock);
+
+	if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+		return -EAGAIN;
+	else
+		return 0;
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
···
 		max_sectors = mddev->resync_max_sectors;
 		mddev->resync_mismatches = 0;
 		/* we don't use the checkpoint if there's a bitmap */
-		if (!mddev->bitmap &&
-		    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+			j = mddev->resync_min;
+		else if (!mddev->bitmap)
 			j = mddev->recovery_cp;
+
 	} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		max_sectors = mddev->size << 1;
 	else {
···
 
  skip:
 	mddev->curr_resync = 0;
+	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 	wake_up(&resync_wait);
···
 			if (rdev->raid_disk < 0
 			    && !test_bit(Faulty, &rdev->flags)) {
 				rdev->recovery_offset = 0;
-				if (mddev->pers->hot_add_disk(mddev,rdev)) {
+				if (mddev->pers->
+				    hot_add_disk(mddev, rdev) == 0) {
 					char nm[20];
 					sprintf(nm, "rd%d", rdev->raid_disk);
 					if (sysfs_create_link(&mddev->kobj,
···
 		int spares = 0;
 
 		if (!mddev->external) {
+			int did_change = 0;
 			spin_lock_irq(&mddev->write_lock);
 			if (mddev->safemode &&
 			    !atomic_read(&mddev->writes_pending) &&
 			    !mddev->in_sync &&
 			    mddev->recovery_cp == MaxSector) {
 				mddev->in_sync = 1;
+				did_change = 1;
 				if (mddev->persistent)
 					set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			}
 			if (mddev->safemode == 1)
 				mddev->safemode = 0;
 			spin_unlock_irq(&mddev->write_lock);
+			if (did_change)
+				sysfs_notify(&mddev->kobj, NULL, "array_state");
 		}
 
 		if (mddev->flags)
 			md_update_sb(mddev, 0);
+
+		rdev_for_each(rdev, rtmp, mddev)
+			if (test_and_clear_bit(StateChanged, &rdev->flags))
+				sysfs_notify(&rdev->kobj, NULL, "state");
 
 
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
···
 			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 				/* success...*/
 				/* activate any spares */
-				mddev->pers->spare_active(mddev);
+				if (mddev->pers->spare_active(mddev))
+					sysfs_notify(&mddev->kobj, NULL,
+						     "degraded");
 			}
 			md_update_sb(mddev, 1);
 
···
 			mddev->recovery = 0;
 			/* flag recovery needed just to double check */
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			sysfs_notify(&mddev->kobj, NULL, "sync_action");
 			md_new_event(mddev);
 			goto unlock;
 		}
+		/* Set RUNNING before clearing NEEDED to avoid
+		 * any transients in the value of "sync_action".
+		 */
+		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		/* Clear some bits that don't mean anything, but
 		 * might be left set
 		 */
-		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 
···
 				/* Cannot proceed */
 				goto unlock;
 			set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if ((spares = remove_and_add_spares(mddev))) {
 			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if (mddev->recovery_cp < MaxSector) {
 			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
 			/* nothing to be done ... */
 			goto unlock;
 
 		if (mddev->pers->sync_request) {
-			set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 			if (spares && mddev->bitmap && ! mddev->bitmap->file) {
 				/* We are adding a device or devices to an array
 				 * which has the bitmap stored on all devices.
···
 				mddev->recovery = 0;
 			} else
 				md_wakeup_thread(mddev->sync_thread);
+			sysfs_notify(&mddev->kobj, NULL, "sync_action");
 			md_new_event(mddev);
 		}
 	unlock:
+		if (!mddev->sync_thread) {
+			clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
+					       &mddev->recovery))
+				sysfs_notify(&mddev->kobj, NULL, "sync_action");
+		}
 		mddev_unlock(mddev);
 	}
 }
···
 
 		for_each_mddev(mddev, tmp)
 			if (mddev_trylock(mddev)) {
-				do_md_stop (mddev, 1);
+				do_md_stop (mddev, 1, 0);
 				mddev_unlock(mddev);
 			}
 		/*

drivers/md/multipath.c

···
 {
 	multipath_conf_t *conf = mddev->private;
 	struct request_queue *q;
-	int found = 0;
+	int err = -EEXIST;
 	int path;
 	struct multipath_info *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
 	print_multipath_conf(conf);
 
-	for (path=0; path<mddev->raid_disks; path++) 
+	for (path = first; path <= last; path++)
 		if ((p=conf->multipaths+path)->rdev == NULL) {
 			q = rdev->bdev->bd_disk->queue;
 			blk_queue_stack_limits(mddev->queue, q);
···
 			rdev->raid_disk = path;
 			set_bit(In_sync, &rdev->flags);
 			rcu_assign_pointer(p->rdev, rdev);
-			found = 1;
+			err = 0;
+			break;
 		}
 
 	print_multipath_conf(conf);
-	return found;
+
+	return err;
 }
 
 static int multipath_remove_disk(mddev_t *mddev, int number)
···
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 
 	mddev->queue->unplug_fn = multipath_unplug;
 	mddev->queue->backing_dev_info.congested_fn = multipath_congested;

drivers/md/raid0.c

···
 		goto out_free_conf;
 
 	/* calculate array device size */
-	mddev->array_size = 0;
+	mddev->array_sectors = 0;
 	rdev_for_each(rdev, tmp, mddev)
-		mddev->array_size += rdev->size;
+		mddev->array_sectors += rdev->size * 2;
 
 	printk("raid0 : md_size is %llu blocks.\n", 
-		(unsigned long long)mddev->array_size);
+		(unsigned long long)mddev->array_sectors / 2);
 	printk("raid0 : conf->hash_spacing is %llu blocks.\n",
 		(unsigned long long)conf->hash_spacing);
 	{
-		sector_t s = mddev->array_size;
+		sector_t s = mddev->array_sectors / 2;
 		sector_t space = conf->hash_spacing;
 		int round;
 		conf->preshift = 0;

drivers/md/raid1.c

···
 static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror = 0;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
 
-	for (mirror=0; mirror < mddev->raid_disks; mirror++)
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
+
+	for (mirror = first; mirror <= last; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,
···
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
···
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid1_remove_disk(mddev_t *mddev, int number)
···
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 
 	mddev->queue->unplug_fn = raid1_unplug;
 	mddev->queue->backing_dev_info.congested_fn = raid1_congested;
···
 	 * any io in the removed space completes, but it hardly seems
 	 * worth it.
 	 */
-	mddev->array_size = sectors>>1;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	mddev->array_sectors = sectors;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
-	if (mddev->array_size > mddev->size && mddev->recovery_cp == MaxSector) {
+	if (mddev->array_sectors / 2 > mddev->size &&
+	    mddev->recovery_cp == MaxSector) {
 		mddev->recovery_cp = mddev->size << 1;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
-	mddev->size = mddev->array_size;
+	mddev->size = mddev->array_sectors / 2;
 	mddev->resync_max_sectors = sectors;
 	return 0;
 }
···
 	conf_t *conf = mddev_to_conf(mddev);
 	int cnt, raid_disks;
 	unsigned long flags;
-	int d, d2;
+	int d, d2, err;
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_size != mddev->new_chunk ||
···
 		return -EINVAL;
 	}
 
-	md_allow_write(mddev);
+	err = md_allow_write(mddev);
+	if (err)
+		return err;
 
 	raid_disks = mddev->raid_disks + mddev->delta_disks;
 

drivers/md/raid10.c

···
 static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
 		 * very different from resync
 		 */
-		return 0;
+		return -EBUSY;
 	if (!enough(conf))
-		return 0;
+		return -EINVAL;
+
+	if (rdev->raid_disk)
+		first = last = rdev->raid_disk;
 
 	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
 	else
-		mirror = 0;
-	for ( ; mirror < mddev->raid_disks; mirror++)
+		mirror = first;
+	for ( ; mirror <= last ; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,
···
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			if (rdev->saved_raid_disk != mirror)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
···
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid10_remove_disk(mddev_t *mddev, int number)
···
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = size << (conf->chunk_shift-1);
+	mddev->array_sectors = size << conf->chunk_shift;
 	mddev->resync_max_sectors = size << conf->chunk_shift;
 
 	mddev->queue->unplug_fn = raid10_unplug;

drivers/md/raid5.c

···
 		return_bi = bi->bi_next;
 		bi->bi_next = NULL;
 		bi->bi_size = 0;
-		bi->bi_end_io(bi,
-			      test_bit(BIO_UPTODATE, &bi->bi_flags)
-			        ? 0 : -EIO);
+		bio_endio(bi, 0);
 		bi = return_bi;
 	}
 }
 
 static void print_raid5_conf (raid5_conf_t *conf);
+
+static int stripe_operations_active(struct stripe_head *sh)
+{
+	return sh->check_state || sh->reconstruct_state ||
+	       test_bit(STRIPE_BIOFILL_RUN, &sh->state) ||
+	       test_bit(STRIPE_COMPUTE_RUN, &sh->state);
+}
 
 static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 {
···
 			}
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
-			BUG_ON(sh->ops.pending);
+			BUG_ON(stripe_operations_active(sh));
 			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 				atomic_dec(&conf->preread_active_stripes);
 				if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
···
 
 	BUG_ON(atomic_read(&sh->count) != 0);
 	BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
-	BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete);
+	BUG_ON(stripe_operations_active(sh));
 
 	CHECK_DEVLOCK();
 	pr_debug("init_stripe called, stripe %llu\n",
···
 	return sh;
 }
 
-/* test_and_ack_op() ensures that we only dequeue an operation once */
-#define test_and_ack_op(op, pend) \
-do {							\
-	if (test_bit(op, &sh->ops.pending) &&		\
-		!test_bit(op, &sh->ops.complete)) {	\
-		if (test_and_set_bit(op, &sh->ops.ack)) \
-			clear_bit(op, &pend);		\
-		else					\
-			ack++;				\
-	} else						\
-		clear_bit(op, &pend);			\
-} while (0)
-
-/* find new work to run, do not resubmit work that is already
- * in flight
- */
-static unsigned long get_stripe_work(struct stripe_head *sh)
-{
-	unsigned long pending;
-	int ack = 0;
-
-	pending = sh->ops.pending;
-
-	test_and_ack_op(STRIPE_OP_BIOFILL, pending);
-	test_and_ack_op(STRIPE_OP_COMPUTE_BLK, pending);
-	test_and_ack_op(STRIPE_OP_PREXOR, pending);
-	test_and_ack_op(STRIPE_OP_BIODRAIN, pending);
-	test_and_ack_op(STRIPE_OP_POSTXOR, pending);
-	test_and_ack_op(STRIPE_OP_CHECK, pending);
-	if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending))
-		ack++;
-
-	sh->ops.count -= ack;
-	if (unlikely(sh->ops.count < 0)) {
-		printk(KERN_ERR "pending: %#lx ops.pending: %#lx ops.ack: %#lx "
-			"ops.complete: %#lx\n", pending, sh->ops.pending,
-			sh->ops.ack, sh->ops.complete);
-		BUG();
-	}
-
-	return pending;
-}
-
 static void
 raid5_end_read_request(struct bio *bi, int error);
 static void
 raid5_end_write_request(struct bio *bi, int error);
 
-static void ops_run_io(struct stripe_head *sh)
+static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int i, disks = sh->disks;
 
 	might_sleep();
 
-	set_bit(STRIPE_IO_STARTED, &sh->state);
 	for (i = disks; i--; ) {
 		int rw;
 		struct bio *bi;
···
 		rcu_read_unlock();
 
 		if (rdev) {
-			if (test_bit(STRIPE_SYNCING, &sh->state) ||
-				test_bit(STRIPE_EXPAND_SOURCE, &sh->state) ||
-				test_bit(STRIPE_EXPAND_READY, &sh->state))
+			if (s->syncing || s->expanding || s->expanded)
 				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+
+			set_bit(STRIPE_IO_STARTED, &sh->state);
 
 			bi->bi_bdev = rdev->bdev;
 			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
···
 		(unsigned long long)sh->sector);
 
 	/* clear completed biofills */
+	spin_lock_irq(&conf->device_lock);
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
 		/* acknowledge completion of a biofill operation */
 		/* and check if we need to reply to a read request,
 		 * new R5_Wantfill requests are held off until
-		 * !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending)
+		 * !STRIPE_BIOFILL_RUN
 		 */
 		if (test_and_clear_bit(R5_Wantfill, &dev->flags)) {
 			struct bio *rbi, *rbi2;
 
-			/* The access to dev->read is outside of the
-			 * spin_lock_irq(&conf->device_lock), but is protected
-			 * by the STRIPE_OP_BIOFILL pending bit
-			 */
 			BUG_ON(!dev->read);
 			rbi = dev->read;
 			dev->read = NULL;
 			while (rbi && rbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
-				spin_lock_irq(&conf->device_lock);
 				if (--rbi->bi_phys_segments == 0) {
 					rbi->bi_next = return_bi;
 					return_bi = rbi;
 				}
-				spin_unlock_irq(&conf->device_lock);
 				rbi = rbi2;
 			}
 		}
 	}
-	set_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
+	spin_unlock_irq(&conf->device_lock);
+	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
 	return_io(return_bi);
 
···
 	set_bit(R5_UPTODATE, &tgt->flags);
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 	clear_bit(R5_Wantcompute, &tgt->flags);
-	set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
+	clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
+	if (sh->check_state == check_state_compute_run)
+		sh->check_state = check_state_compute_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
 
-static struct dma_async_tx_descriptor *
-ops_run_compute5(struct stripe_head *sh, unsigned long pending)
+static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh)
 {
 	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
···
 			ASYNC_TX_XOR_ZERO_DST, NULL,
 			ops_complete_compute5, sh);
 
-	/* ack now if postxor is not set to be run */
-	if (tx && !test_bit(STRIPE_OP_POSTXOR, &pending))
-		async_tx_ack(tx);
-
 	return tx;
 }
 
···
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
-
-	set_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
 }
 
 static struct dma_async_tx_descriptor *
···
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		/* Only process blocks that are known to be uptodate */
-		if (dev->towrite && test_bit(R5_Wantprexor, &dev->flags))
+		if (test_bit(R5_Wantdrain, &dev->flags))
 			xor_srcs[count++] = dev->page;
 	}
 
···
 }
 
 static struct dma_async_tx_descriptor *
-ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		 unsigned long pending)
+ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 {
 	int disks = sh->disks;
-	int pd_idx = sh->pd_idx, i;
-
-	/* check if prexor is active which means only process blocks
-	 * that are part of a read-modify-write (Wantprexor)
-	 */
-	int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
+	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
···
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		struct bio *chosen;
-		int towrite;
 
-		towrite = 0;
-		if (prexor) { /* rmw */
-			if (dev->towrite &&
-			    test_bit(R5_Wantprexor, &dev->flags))
-				towrite = 1;
-		} else { /* rcw */
-			if (i != pd_idx && dev->towrite &&
-				test_bit(R5_LOCKED, &dev->flags))
-				towrite = 1;
-		}
-
-		if (towrite) {
+		if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
 			struct bio *wbi;
 
 			spin_lock(&sh->lock);
···
 static void ops_complete_postxor(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-
-	pr_debug("%s: stripe %llu\n", __func__,
-		(unsigned long long)sh->sector);
-
-	set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
-}
-
-static void ops_complete_write(void *stripe_head_ref)
-{
-	struct stripe_head *sh = stripe_head_ref;
 	int disks = sh->disks, i, pd_idx = sh->pd_idx;
 
 	pr_debug("%s: stripe %llu\n", __func__,
···
 			set_bit(R5_UPTODATE, &dev->flags);
 	}
 
-	set_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
-	set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
+	if (sh->reconstruct_state == reconstruct_state_drain_run)
+		sh->reconstruct_state = reconstruct_state_drain_result;
+	else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run)
+		sh->reconstruct_state = reconstruct_state_prexor_drain_result;
+	else {
+		BUG_ON(sh->reconstruct_state != reconstruct_state_run);
+		sh->reconstruct_state = reconstruct_state_result;
+	}
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
 
 static void
-ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		unsigned long pending)
+ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 {
 	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
···
 
 	int count = 0, pd_idx = sh->pd_idx, i;
 	struct page *xor_dest;
-	int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
+	int prexor = 0;
 	unsigned long flags;
-	dma_async_tx_callback callback;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
···
 	/* check if prexor is active which means only process blocks
 	 * that are part of a read-modify-write (written)
 	 */
-	if (prexor) {
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
+		prexor = 1;
 		xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
···
 		}
 	}
 
-	/* check whether this postxor is part of a write */
-	callback = test_bit(STRIPE_OP_BIODRAIN, &pending) ?
-		ops_complete_write : ops_complete_postxor;
-
 	/* 1/ if we prexor'd then the dest is reused as a source
 	 * 2/ if we did not prexor then we are redoing the parity
 	 * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
···
 	if (unlikely(count == 1)) {
 		flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
 		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
-			flags, tx, callback, sh);
+			flags, tx, ops_complete_postxor, sh);
 	} else
 		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
-			flags, tx, callback, sh);
+			flags, tx, ops_complete_postxor, sh);
 }
 
 static void ops_complete_check(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-	int pd_idx = sh->pd_idx;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) &&
-		sh->ops.zero_sum_result == 0)
-		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-
-	set_bit(STRIPE_OP_CHECK, &sh->ops.complete);
+	sh->check_state = check_state_check_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
···
 	tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
 		&sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
 
-	if (tx)
-		set_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
-	else
-		clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
-
 	atomic_inc(&sh->count);
 	tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
 		ops_complete_check, sh);
 }
 
-static void raid5_run_ops(struct stripe_head *sh, unsigned long pending)
+static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request)
 {
 	int overlap_clear = 0, i, disks = sh->disks;
 	struct dma_async_tx_descriptor *tx = NULL;
 
-	if (test_bit(STRIPE_OP_BIOFILL, &pending)) {
+	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending))
-		tx = ops_run_compute5(sh, pending);
+	if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) {
+		tx = ops_run_compute5(sh);
+		/* terminate the chain if postxor is not set to be run */
+		if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
+			async_tx_ack(tx);
+	}
 
-	if (test_bit(STRIPE_OP_PREXOR, &pending))
+	if (test_bit(STRIPE_OP_PREXOR, &ops_request))
 		tx = ops_run_prexor(sh, tx);
 
-	if (test_bit(STRIPE_OP_BIODRAIN, &pending)) {
-		tx = ops_run_biodrain(sh, tx, pending);
+	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
+		tx = ops_run_biodrain(sh, tx);
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_POSTXOR, &pending))
-		ops_run_postxor(sh, tx, pending);
+	if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
+		ops_run_postxor(sh, tx);
 
-	if (test_bit(STRIPE_OP_CHECK, &pending))
+	if (test_bit(STRIPE_OP_CHECK, &ops_request))
 		ops_run_check(sh);
-
-	if (test_bit(STRIPE_OP_IO, &pending))
-		ops_run_io(sh);
 
 	if (overlap_clear)
 		for (i = disks; i--; ) {
···
 	struct stripe_head *osh, *nsh;
 	LIST_HEAD(newstripes);
 	struct disk_info *ndisks;
-	int err = 0;
+	int err;
 	struct kmem_cache *sc;
 	int i;
 
 	if (newsize <= conf->pool_size)
 		return 0; /* never bother to shrink */
 
-	md_allow_write(conf->mddev);
+	err = md_allow_write(conf->mddev);
+	if (err)
+		return err;
 
 	/* Step 1 */
 	sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
···
 	}
 }
 
-static int
-handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
+static void
+schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
+			 int rcw, int expand)
 {
 	int i, pd_idx = sh->pd_idx, disks = sh->disks;
-	int locked = 0;
 
 	if (rcw) {
 		/* if we are not expanding this is a proper write request, and
···
 		 * stripe cache
 		 */
 		if (!expand) {
-			set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-			sh->ops.count++;
-		}
+			sh->reconstruct_state = reconstruct_state_drain_run;
+			set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		} else
+			sh->reconstruct_state = reconstruct_state_run;
 
-		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-		sh->ops.count++;
+		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 
 			if (dev->towrite) {
 				set_bit(R5_LOCKED, &dev->flags);
+				set_bit(R5_Wantdrain, &dev->flags);
 				if (!expand)
 					clear_bit(R5_UPTODATE, &dev->flags);
-				locked++;
+				s->locked++;
 			}
 		}
-		if (locked + 1 == disks)
+		if (s->locked + 1 == disks)
 			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
 				atomic_inc(&sh->raid_conf->pending_full_writes);
 	} else {
 		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
 			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
 
-		set_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
-		set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-
-		sh->ops.count += 3;
+		sh->reconstruct_state = reconstruct_state_prexor_drain_run;
+		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (i == pd_idx)
 				continue;
 
-			/* For a read-modify write there may be blocks that are
-			 * locked for reading while others are ready to be
-			 * written so we distinguish these blocks by the
-			 * R5_Wantprexor bit
-			 */
 			if (dev->towrite &&
 			    (test_bit(R5_UPTODATE, &dev->flags) ||
-			    test_bit(R5_Wantcompute, &dev->flags))) {
-				set_bit(R5_Wantprexor, &dev->flags);
+			     test_bit(R5_Wantcompute, &dev->flags))) {
+				set_bit(R5_Wantdrain, &dev->flags);
 				set_bit(R5_LOCKED, &dev->flags);
 				clear_bit(R5_UPTODATE, &dev->flags);
-				locked++;
+				s->locked++;
 			}
 		}
 	}
···
 	 */
 	set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
 	clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-	locked++;
+	s->locked++;
 
-	pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
+	pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
 		__func__, (unsigned long long)sh->sector,
-		locked, sh->ops.pending);
-
-	return locked;
+		s->locked, s->ops_request);
 }
 
 /*
···
 }
 
 static void
-handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
+handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh,
 				struct stripe_head_state *s, int disks,
 				struct bio **return_bi)
 {
···
 			md_wakeup_thread(conf->mddev->thread);
 }
 
-/* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks
- * to process
+/* fetch_block5 - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill5 to continue
  */
-static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
-			struct stripe_head_state *s, int disk_idx, int disks)
+static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s,
+			int disk_idx, int disks)
 {
 	struct r5dev *dev = &sh->dev[disk_idx];
 	struct r5dev *failed_dev = &sh->dev[s->failed_num];
 
-	/* don't schedule compute operations or reads on the parity block while
-	 * a check is in flight
-	 */
-	if ((disk_idx == sh->pd_idx) &&
-	     test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
-		return ~0;
-
 	/* is the data in this block needed, and can we get it? */
 	if (!test_bit(R5_LOCKED, &dev->flags) &&
-	    !test_bit(R5_UPTODATE, &dev->flags) && (dev->toread ||
-	    (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
-	     s->syncing || s->expanding || (s->failed &&
-	     (failed_dev->toread || (failed_dev->towrite &&
-	     !test_bit(R5_OVERWRITE, &failed_dev->flags)
-	     ))))) {
-		/* 1/ We would like to get this block, possibly by computing it,
-		 * but we might not be able to.
-		 *
-		 * 2/ Since parity check operations potentially make the parity
-		 * block !uptodate it will need to be refreshed before any
-		 * compute operations on data disks are scheduled.
-		 *
-		 * 3/ We hold off parity block re-reads until check operations
-		 * have quiesced.
+	    !test_bit(R5_UPTODATE, &dev->flags) &&
+	    (dev->toread ||
+	     (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
+	     s->syncing || s->expanding ||
+	     (s->failed &&
+	      (failed_dev->toread ||
+	       (failed_dev->towrite &&
+		!test_bit(R5_OVERWRITE, &failed_dev->flags)))))) {
+		/* We would like to get this block, possibly by computing it,
+		 * otherwise read it if the backing disk is insync
 		 */
 		if ((s->uptodate == disks - 1) &&
-		    (s->failed && disk_idx == s->failed_num) &&
-		    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
-			set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
+		    (s->failed && disk_idx == s->failed_num)) {
+			set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
 			set_bit(R5_Wantcompute, &dev->flags);
 			sh->ops.target = disk_idx;
 			s->req_compute = 1;
-			sh->ops.count++;
 			/* Careful: from this point on 'uptodate' is in the eye
 			 * of raid5_run_ops which services 'compute' operations
 			 * before writes. R5_Wantcompute flags a block that will
···
 			 * subsequent operation.
 			 */
 			s->uptodate++;
-			return 0; /* uptodate + compute == disks */
+			return 1; /* uptodate + compute == disks */
 		} else if (test_bit(R5_Insync, &dev->flags)) {
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantread, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			s->locked++;
 			pr_debug("Reading block %d (sync=%d)\n", disk_idx,
 				s->syncing);
 		}
 	}
 
-	return ~0;
+	return 0;
 }
 
-static void handle_issuing_new_read_requests5(struct stripe_head *sh,
+/**
+ * handle_stripe_fill5 - read or compute data to satisfy pending requests.
+ */
+static void handle_stripe_fill5(struct stripe_head *sh,
 			struct stripe_head_state *s, int disks)
 {
 	int i;
-
-	/* Clear completed compute operations.  Parity recovery
-	 * (STRIPE_OP_MOD_REPAIR_PD) implies a write-back which is handled
-	 * later on in this routine
-	 */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
-		!test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
-	}
 
 	/* look for blocks to read/compute, skip this if a compute
 	 * is already in flight, or if the stripe contents are in the
 	 * midst of changing due to a write
 	 */
-	if (!test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
-		!test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) &&
-		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
+	    !sh->reconstruct_state)
 		for (i = disks; i--; )
-			if (__handle_issuing_new_read_requests5(
-				sh, s, i, disks) == 0)
+			if (fetch_block5(sh, s, i, disks))
 				break;
-	}
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
 
-static void handle_issuing_new_read_requests6(struct stripe_head *sh,
+static void handle_stripe_fill6(struct stripe_head *sh,
 			struct stripe_head_state *s, struct r6_state *r6s,
 			int disks)
 {
···
 }
 
 
-/* handle_completed_write_requests
+/* handle_stripe_clean_event
  * any written block on an uptodate or failed drive can be returned.
  * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
  * never LOCKED, so we don't need to test 'failed' directly.
  */
-static void handle_completed_write_requests(raid5_conf_t *conf,
+static void handle_stripe_clean_event(raid5_conf_t *conf,
 	struct stripe_head *sh, int disks, struct bio **return_bi)
 {
 	int i;
···
 			md_wakeup_thread(conf->mddev->thread);
 }
 
-static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
+static void handle_stripe_dirtying5(raid5_conf_t *conf,
 		struct stripe_head *sh,	struct stripe_head_state *s, int disks)
 {
 	int rmw = 0, rcw = 0, i;
···
 						"%d for r-m-w\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
-					if (!test_and_set_bit(
-						STRIPE_OP_IO, &sh->ops.pending))
-						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);
···
 						"%d for Reconstruct\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
-					if (!test_and_set_bit(
-						STRIPE_OP_IO, &sh->ops.pending))
-						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);
···
 	 * simultaneously.  If this is not the case then new writes need to be
 	 * held off until the compute completes.
 	 */
-	if ((s->req_compute ||
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) &&
-		(s->locked == 0 && (rcw == 0 || rmw == 0) &&
-		!test_bit(STRIPE_BIT_DELAY, &sh->state)))
-		s->locked += handle_write_operations5(sh, rcw == 0, 0);
+	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
+	    (s->locked == 0 && (rcw == 0 || rmw == 0) &&
+	    !test_bit(STRIPE_BIT_DELAY, &sh->state)))
+		schedule_reconstruction5(sh, s, rcw == 0, 0);
 }
 
-static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
+static void handle_stripe_dirtying6(raid5_conf_t *conf,
 		struct stripe_head *sh,	struct stripe_head_state *s,
 		struct r6_state *r6s, int disks)
 {
···
 static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 				struct stripe_head_state *s, int disks)
 {
-	int canceled_check = 0;
+	struct r5dev *dev = NULL;
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 
-	/* complete a check operation */
-	if (test_and_clear_bit(STRIPE_OP_CHECK, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_CHECK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_CHECK, &sh->ops.pending);
+	switch (sh->check_state) {
+	case check_state_idle:
+		/* start a new check operation if there are no failures */
 		if (s->failed == 0) {
-			if (sh->ops.zero_sum_result == 0)
-				/* parity is correct (on disc,
-				 * not in buffer any more)
-				 */
-				set_bit(STRIPE_INSYNC, &sh->state);
-			else {
-				conf->mddev->resync_mismatches +=
-					STRIPE_SECTORS;
-				if (test_bit(
-				     MD_RECOVERY_CHECK, &conf->mddev->recovery))
-					/* don't try to repair!! */
-					set_bit(STRIPE_INSYNC, &sh->state);
-				else {
-					set_bit(STRIPE_OP_COMPUTE_BLK,
-						&sh->ops.pending);
-					set_bit(STRIPE_OP_MOD_REPAIR_PD,
-						&sh->ops.pending);
-					set_bit(R5_Wantcompute,
-						&sh->dev[sh->pd_idx].flags);
-					sh->ops.target = sh->pd_idx;
-					sh->ops.count++;
-					s->uptodate++;
-				}
-			}
-		} else
-			canceled_check = 1; /* STRIPE_INSYNC is not set */
-	}
-
-	/* start a new check operation if there are no failures, the stripe is
-	 * not insync, and a repair is not in flight
-	 */
-	if (s->failed == 0 &&
-	    !test_bit(STRIPE_INSYNC, &sh->state) &&
-	    !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-		if (!test_and_set_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
 			BUG_ON(s->uptodate != disks);
+			sh->check_state = check_state_run;
+			set_bit(STRIPE_OP_CHECK, &s->ops_request);
 			clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
-			sh->ops.count++;
 			s->uptodate--;
+			break;
 		}
-	}
-
-	/* check if we can clear a parity disk reconstruct */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
-	    test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-
-		clear_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
-	}
-
-
-	/* Wait for check parity and compute block operations to complete
-	 * before write-back.  If a failure occurred while the check operation
-	 * was in flight we need to cycle this stripe through handle_stripe
-	 * since the parity block may not be uptodate
-	 */
-	if (!canceled_check && !test_bit(STRIPE_INSYNC, &sh->state) &&
-	    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending) &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) {
-		struct r5dev *dev;
-		/* either failed parity check, or recovery is happening */
-		if (s->failed == 0)
-			s->failed_num = sh->pd_idx;
 		dev = &sh->dev[s->failed_num];
+		/* fall through */
+	case check_state_compute_result:
+		sh->check_state = check_state_idle;
+		if (!dev)
+			dev = &sh->dev[sh->pd_idx];
+
+		/* check that a write has not made the stripe insync */
+		if (test_bit(STRIPE_INSYNC, &sh->state))
+			break;
+
+		/* either failed parity check, or recovery is happening */
 		BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
 		BUG_ON(s->uptodate != disks);
 
 		set_bit(R5_LOCKED, &dev->flags);
+		s->locked++;
 		set_bit(R5_Wantwrite, &dev->flags);
-		if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-			sh->ops.count++;
 
 		clear_bit(STRIPE_DEGRADED, &sh->state);
-		s->locked++;
 		set_bit(STRIPE_INSYNC, &sh->state);
+		break;
+	case check_state_run:
+		break; /* we will be called again upon completion */
+	case check_state_check_result:
+		sh->check_state = check_state_idle;
+
+		/* if a failure occurred during the check operation, leave
+		 * STRIPE_INSYNC not set and let the stripe be handled again
+		 */
+		if (s->failed)
+			break;
+
+		/* handle a successful check operation, if parity is correct
+		 * we are done.  Otherwise update the mismatch count and repair
+		 * parity if !MD_RECOVERY_CHECK
+		 */
+		if (sh->ops.zero_sum_result == 0)
+			/* parity is correct (on disc,
+			 * not in buffer any more)
+			 */
+			set_bit(STRIPE_INSYNC, &sh->state);
+		else {
+			conf->mddev->resync_mismatches += STRIPE_SECTORS;
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+				/* don't try to repair!! */
+				set_bit(STRIPE_INSYNC, &sh->state);
+			else {
+				sh->check_state = check_state_compute_run;
+				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+				set_bit(R5_Wantcompute,
+					&sh->dev[sh->pd_idx].flags);
+				sh->ops.target = sh->pd_idx;
+				s->uptodate++;
+			}
+		}
+		break;
+	case check_state_compute_run:
+		break;
+	default:
+		printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
+		       __func__, sh->check_state,
+		       (unsigned long long) sh->sector);
+		BUG();
 	}
 }
 
···
 	struct bio *return_bi = NULL;
 	struct stripe_head_state s;
 	struct r5dev *dev;
-	unsigned long pending = 0;
 	mdk_rdev_t *blocked_rdev = NULL;
 	int prexor;
 
 	memset(&s, 0, sizeof(s));
-	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
-		"ops=%lx:%lx:%lx\n", (unsigned long long)sh->sector, sh->state,
-		atomic_read(&sh->count), sh->pd_idx,
-		sh->ops.pending, sh->ops.ack, sh->ops.complete);
+	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
+		 "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state,
+		 atomic_read(&sh->count), sh->pd_idx, sh->check_state,
+		 sh->reconstruct_state);
 
 	spin_lock(&sh->lock);
 	clear_bit(STRIPE_HANDLE, &sh->state);
···
 	s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
 	s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
+
 	/* Now to look around and see what can be done */
-
-	/* clean-up completed biofill operations */
-	if (test_bit(STRIPE_OP_BIOFILL, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
-	}
-
 	rcu_read_lock();
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
···
 		/* maybe we can request a biofill operation
 		 *
 		 * new wantfill requests are only permitted while
-		 * STRIPE_OP_BIOFILL is clear
+		 * ops_complete_biofill is guaranteed to be inactive
 		 */
 		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
-			!test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+		    !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
 			set_bit(R5_Wantfill, &dev->flags);
 
 		/* now count some things */
···
 		goto unlock;
 	}
 
-	if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
-		sh->ops.count++;
+	if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+		set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+		set_bit(STRIPE_BIOFILL_RUN, &sh->state);
+	}
 
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 		" to_write=%d failed=%d failed_num=%d\n",
···
 	 * need to be failed
 	 */
 	if (s.failed > 1 && s.to_read+s.to_write+s.written)
-		handle_requests_to_failed_array(conf, sh, &s, disks,
-						&return_bi);
+		handle_failed_stripe(conf, sh, &s, disks, &return_bi);
 	if (s.failed > 1 && s.syncing) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
 		clear_bit(STRIPE_SYNCING, &sh->state);
···
 	       !test_bit(R5_LOCKED, &dev->flags) &&
 	       test_bit(R5_UPTODATE, &dev->flags)) ||
 	       (s.failed == 1 && s.failed_num == sh->pd_idx)))
-		handle_completed_write_requests(conf, sh, disks, &return_bi);
+		handle_stripe_clean_event(conf, sh, disks, &return_bi);
 
 	/* Now we might consider reading some blocks, either to check/generate
 	 * parity, or to satisfy requests
 	 * or to load a block that is being partially written.
 	 */
 	if (s.to_read || s.non_overwrite ||
-	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding ||
-	    test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
-		handle_issuing_new_read_requests5(sh, &s, disks);
+	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
+		handle_stripe_fill5(sh, &s, disks);
 
 	/* Now we check to see if any write operations have recently
 	 * completed
 	 */
-
-	/* leave prexor set until postxor is done, allows us to distinguish
-	 * a rmw from a rcw during biodrain
-	 */
 	prexor = 0;
-	if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) &&
-		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
 		prexor = 1;
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
-
-		for (i = disks; i--; )
-			clear_bit(R5_Wantprexor, &sh->dev[i].flags);
-	}
-
-	/* if only POSTXOR is set then this is an 'expand' postxor */
-	if (test_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete) &&
-		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.ack);
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+	if (sh->reconstruct_state == reconstruct_state_drain_result ||
+	    sh->reconstruct_state == reconstruct_state_prexor_drain_result) {
+		sh->reconstruct_state = reconstruct_state_idle;
 
 		/* All the 'written' buffers and the parity block are ready to
 		 * be written back to disk
···
 				(i == sh->pd_idx || dev->written)) {
 				pr_debug("Writing block %d\n", i);
 				set_bit(R5_Wantwrite, &dev->flags);
-				if (!test_and_set_bit(
-				    STRIPE_OP_IO, &sh->ops.pending))
-					sh->ops.count++;
 				if (prexor)
 					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
···
 	 * 2/ A 'check' operation is in flight, as it may clobber the parity
 	 *    block.
 	 */
-	if (s.to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) &&
-			  !test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
-		handle_issuing_new_write_requests5(conf, sh, &s, disks);
+	if (s.to_write && !sh->reconstruct_state && !sh->check_state)
+		handle_stripe_dirtying5(conf, sh, &s, disks);
 
 	/* maybe we need to check and possibly fix the parity for this stripe
 	 * Any reads will already have been scheduled, so we just see if enough
 	 * data is available.  The parity check is held off while parity
 	 * dependent operations are in flight.
 	 */
-	if ((s.syncing && s.locked == 0 &&
-	     !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
-	     !test_bit(STRIPE_INSYNC, &sh->state)) ||
-	      test_bit(STRIPE_OP_CHECK, &sh->ops.pending) ||
-	      test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending))
+	if (sh->check_state ||
+	    (s.syncing && s.locked == 0 &&
+	     !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
+	     !test_bit(STRIPE_INSYNC, &sh->state)))
 		handle_parity_checks5(conf, sh, &s, disks);
 
 	if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
···
 		dev = &sh->dev[s.failed_num];
 		if (!test_bit(R5_ReWrite, &dev->flags)) {
 			set_bit(R5_Wantwrite, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			set_bit(R5_ReWrite, &dev->flags);
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		} else {
 			/* let's read it back */
 			set_bit(R5_Wantread, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		}
 	}
 
-	/* Finish postxor operations initiated by the expansion
-	 * process
-	 */
-	if (test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete) &&
-		!test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending)) {
-
+	/* Finish reconstruct operations initiated by the expansion process */
+	if (sh->reconstruct_state == reconstruct_state_result) {
+		sh->reconstruct_state = reconstruct_state_idle;
 		clear_bit(STRIPE_EXPANDING, &sh->state);
-
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-
-		for (i = conf->raid_disks; i--; ) {
+		for (i = conf->raid_disks; i--; )
 			set_bit(R5_Wantwrite, &sh->dev[i].flags);
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
-		}
 	}
 
 	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
-		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+	    !sh->reconstruct_state) {
 		/* Need to write out all blocks after computing parity */
 		sh->disks = conf->raid_disks;
 		sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
 			conf->raid_disks);
-		s.locked += handle_write_operations5(sh, 1, 1);
-	} else if (s.expanded &&
-		   s.locked == 0 &&
-		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+		schedule_reconstruction5(sh, &s, 1, 1);
+	} else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
 		atomic_dec(&conf->reshape_stripes);
 		wake_up(&conf->wait_for_overlap);
···
 	}
 
 	if (s.expanding && s.locked == 0 &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
 		handle_stripe_expansion(conf, sh, NULL);
-
-	if (sh->ops.count)
-		pending = get_stripe_work(sh);
 
  unlock:
 	spin_unlock(&sh->lock);
···
 	if (unlikely(blocked_rdev))
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
-	if (pending)
-		raid5_run_ops(sh, pending);
+	if (s.ops_request)
+		raid5_run_ops(sh, s.ops_request);
+
+	ops_run_io(sh, &s);
 
 	return_io(return_bi);
-
 }
 
 static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
···
 	 * might need to be failed
 	 */
 	if (s.failed > 2 && s.to_read+s.to_write+s.written)
-		handle_requests_to_failed_array(conf, sh, &s, disks,
-						&return_bi);
+		handle_failed_stripe(conf, sh, &s, disks, &return_bi);
 	if (s.failed > 2 && s.syncing) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
 		clear_bit(STRIPE_SYNCING, &sh->state);
···
 	     ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
 			     && !test_bit(R5_LOCKED, &qdev->flags)
 			     && test_bit(R5_UPTODATE, &qdev->flags)))))
-		handle_completed_write_requests(conf, sh, disks, &return_bi);
+		handle_stripe_clean_event(conf, sh, disks, &return_bi);
 
 	/* Now we might consider reading some blocks, either to check/generate
 	 * parity, or to satisfy requests
···
 	 */
 	if (s.to_read || s.non_overwrite || (s.to_write && s.failed) ||
 	    (s.syncing && (s.uptodate < disks)) || s.expanding)
-		handle_issuing_new_read_requests6(sh, &s, &r6s, disks);
+		handle_stripe_fill6(sh, &s, &r6s, disks);
 
 	/* now to consider writing and what else, if anything should be read */
 	if (s.to_write)
-		handle_issuing_new_write_requests6(conf, sh, &s, &r6s, disks);
+		handle_stripe_dirtying6(conf, sh, &s, &r6s, disks);
 
 	/* maybe we need to check and possibly fix the parity for this stripe
 	 * Any reads will already have been scheduled, so we just see if enough
···
 	}
 
 	if (s.expanding && s.locked == 0 &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
 		handle_stripe_expansion(conf, sh, &r6s);
 
  unlock:
···
 	if (unlikely(blocked_rdev))
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
+	ops_run_io(sh, &s);
+
 	return_io(return_bi);
-
-	for (i=disks; i-- ;) {
-		int rw;
-		struct bio *bi;
-		mdk_rdev_t *rdev;
-		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-			rw = WRITE;
-		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
-			rw = READ;
-		else
-			continue;
-
-		set_bit(STRIPE_IO_STARTED, &sh->state);
-
-		bi = &sh->dev[i].req;
-
-		bi->bi_rw = rw;
-		if (rw == WRITE)
-			bi->bi_end_io = raid5_end_write_request;
-		else
-			bi->bi_end_io = raid5_end_read_request;
-
-		rcu_read_lock();
-		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (rdev && test_bit(Faulty, &rdev->flags))
-			rdev = NULL;
-		if (rdev)
-			atomic_inc(&rdev->nr_pending);
-		rcu_read_unlock();
-
-		if (rdev) {
-			if (s.syncing || s.expanding || s.expanded)
-				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
-
-			bi->bi_bdev = rdev->bdev;
-			pr_debug("for %llu schedule op %ld on disc %d\n",
-				(unsigned long long)sh->sector, bi->bi_rw, i);
-			atomic_inc(&sh->count);
-			bi->bi_sector = sh->sector + rdev->data_offset;
-			bi->bi_flags = 1 << BIO_UPTODATE;
-			bi->bi_vcnt = 1;
-			bi->bi_max_vecs = 1;
-			bi->bi_idx = 0;
-			bi->bi_io_vec = &sh->dev[i].vec;
-			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
-			bi->bi_io_vec[0].bv_offset = 0;
-			bi->bi_size = STRIPE_SIZE;
-			bi->bi_next = NULL;
-			if (rw == WRITE &&
-			    test_bit(R5_ReWrite, &sh->dev[i].flags))
-				atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
-			generic_make_request(bi);
-		} else {
-			if (rw == WRITE)
-				set_bit(STRIPE_DEGRADED, &sh->state);
-			pr_debug("skip op %ld on disc %d for sector %llu\n",
-				bi->bi_rw, i, (unsigned long long)sh->sector);
-			clear_bit(R5_LOCKED, &sh->dev[i].flags);
-			set_bit(STRIPE_HANDLE, &sh->state);
-		}
-	}
 }
 
 static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
···
 		if ( rw == WRITE )
 			md_write_end(mddev);
 
-		bi->bi_end_io(bi,
-			      test_bit(BIO_UPTODATE, &bi->bi_flags)
-			        ? 0 : -EIO);
+		bio_endio(bi, 0);
 	}
 	return 0;
 }
···
 			    j == raid6_next_disk(sh->pd_idx, sh->disks))
 				continue;
 			s = compute_blocknr(sh, j);
-			if (s < (mddev->array_size<<1)) {
+			if (s < mddev->array_sectors) {
 				skipped = 1;
 				continue;
 			}
···
 	spin_lock_irq(&conf->device_lock);
 	remaining = --raid_bio->bi_phys_segments;
 	spin_unlock_irq(&conf->device_lock);
-	if (remaining == 0) {
-
-		raid_bio->bi_end_io(raid_bio,
-			      test_bit(BIO_UPTODATE, &raid_bio->bi_flags)
-			        ? 0 : -EIO);
-	}
+	if (remaining == 0)
+		bio_endio(raid_bio, 0);
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_stripe);
 	return handled;
···
 {
 	raid5_conf_t *conf = mddev_to_conf(mddev);
 	unsigned long new;
+	int err;
+
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
 	if (!conf)
···
 		else
 			break;
 	}
-	md_allow_write(mddev);
+	err = md_allow_write(mddev);
+	if (err)
+		return err;
 	while (new > conf->max_nr_stripes) {
 		if (grow_one_stripe(conf))
 			conf->max_nr_stripes++;
···
 	mddev->queue->backing_dev_info.congested_data = mddev;
 	mddev->queue->backing_dev_info.congested_fn = raid5_congested;
 
-	mddev->array_size =  mddev->size * (conf->previous_raid_disks -
+	mddev->array_sectors = 2 * mddev->size * (conf->previous_raid_disks -
 					    conf->max_degraded);
 
 	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
···
 static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	raid5_conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int disk;
 	struct disk_info *p;
+	int first = 0;
+	int last = conf->raid_disks - 1;
 
 	if (mddev->degraded > conf->max_degraded)
 		/* no point adding a device */
-		return 0;
+		return -EINVAL;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
 	/*
 	 * find the disk ... but prefer rdev->saved_raid_disk
 	 * if possible.
 	 */
 	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
 	    conf->disks[rdev->saved_raid_disk].rdev == NULL)
 		disk = rdev->saved_raid_disk;
 	else
-		disk = 0;
-	for ( ; disk < conf->raid_disks; disk++)
+		disk = first;
+	for ( ; disk <= last ; disk++)
 		if ((p=conf->disks + disk)->rdev == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			rdev->raid_disk = disk;
-			found = 1;
+			err = 0;
 			if (rdev->saved_raid_disk != disk)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
 			break;
 		}
 	print_raid5_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid5_resize(mddev_t *mddev, sector_t sectors)
···
 	raid5_conf_t *conf = mddev_to_conf(mddev);
 
 	sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
-	mddev->array_size = (sectors * (mddev->raid_disks-conf->max_degraded))>>1;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	mddev->array_sectors = sectors * (mddev->raid_disks
+					  - conf->max_degraded);
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
 	if (sectors/2  > mddev->size && mddev->recovery_cp == MaxSector) {
 		mddev->recovery_cp = mddev->size << 1;
···
 	rdev_for_each(rdev, rtmp, mddev)
 		if (rdev->raid_disk < 0 &&
 		    !test_bit(Faulty, &rdev->flags)) {
-			if (raid5_add_disk(mddev, rdev)) {
+			if (raid5_add_disk(mddev, rdev) == 0) {
 				char nm[20];
 				set_bit(In_sync, &rdev->flags);
 				added_devices++;
···
 	struct block_device *bdev;
 
 	if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
-		conf->mddev->array_size = conf->mddev->size *
+		conf->mddev->array_sectors = 2 * conf->mddev->size *
 			(conf->raid_disks - conf->max_degraded);
-		set_capacity(conf->mddev->gendisk, conf->mddev->array_size << 1);
+		set_capacity(conf->mddev->gendisk, conf->mddev->array_sectors);
 		conf->mddev->changed = 1;
 
 		bdev = bdget_disk(conf->mddev->gendisk, 0);
 		if (bdev) {
 			mutex_lock(&bdev->bd_inode->i_mutex);
-			i_size_write(bdev->bd_inode, (loff_t)conf->mddev->array_size << 10);
+			i_size_write(bdev->bd_inode,
+				     (loff_t)conf->mddev->array_sectors << 9);
 			mutex_unlock(&bdev->bd_inode->i_mutex);
 			bdput(bdev);
 		}

include/linux/raid/bitmap.h

···
 	unsigned long syncchunk;
 
 	__u64	events_cleared;
+	int need_sync;
 
 	/* bitmap spinlock */
 	spinlock_t lock;

include/linux/raid/linear.h

···
 	struct linear_private_data *prev;	/* earlier version */
 	dev_info_t		**hash_table;
 	sector_t		hash_spacing;
-	sector_t		array_size;
+	sector_t		array_sectors;
 	int			preshift; /* shift before dividing by hash_spacing */
 	dev_info_t		disks[0];
 };

include/linux/raid/md.h

···
 			struct page *page, int rw);
 extern void md_do_sync(mddev_t *mddev);
 extern void md_new_event(mddev_t *mddev);
-extern void md_allow_write(mddev_t *mddev);
+extern int md_allow_write(mddev_t *mddev);
 extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 
 #endif /* CONFIG_MD */

include/linux/raid/md_k.h

···
 	int		sb_loaded;
 	__u64		sb_events;
 	sector_t	data_offset;	/* start of data in array */
-	sector_t	sb_offset;
+	sector_t 	sb_start;	/* offset of the super block (in 512byte sectors) */
 	int		sb_size;	/* bytes in the superblock */
 	int		preferred_minor;	/* autorun support */
 
···
 #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 */
···
 	int				raid_disks;
 	int				max_disks;
 	sector_t			size; /* used size of component devices */
-	sector_t			array_size; /* exported array size */
+	sector_t			array_sectors; /* exported array size */
 	__u64				events;
 
 	char				uuid[16];
···
 	 * NEEDED:   we might need to start a resync/recover
 	 * RUNNING:  a thread is running, or about to be started
 	 * SYNC:     actually doing a resync, not a recovery
+	 * RECOVER:  doing recovery, or need to try it.
 	 * INTR:     resync needs to be aborted for some reason
 	 * DONE:     thread is done and is waiting to be reaped
 	 * REQUEST:  user-space has requested a sync (used with SYNC)
···
 	 */
 #define	MD_RECOVERY_RUNNING	0
 #define	MD_RECOVERY_SYNC	1
+#define	MD_RECOVERY_RECOVER	2
 #define	MD_RECOVERY_INTR	3
 #define	MD_RECOVERY_DONE	4
 #define	MD_RECOVERY_NEEDED	5
···
 
 	int				in_sync;	/* know to not need resync */
 	struct mutex			reconfig_mutex;
-	atomic_t			active;
+	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
···
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
 	sector_t			recovery_cp;
+	sector_t			resync_min;	/* user requested sync
+							 * starts here */
 	sector_t			resync_max;	/* resync should pause
 							 * when it gets here */
 
···
  */
 #define rdev_for_each(rdev, tmp, mddev)				\
 	rdev_for_each_list(rdev, tmp, (mddev)->disks)
+
+#define rdev_for_each_rcu(rdev, mddev)				\
+	list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set)
 
 typedef struct mdk_thread_s {
 	void			(*run) (mddev_t *mddev);

include/linux/raid/md_p.h

···
  */
 #define MD_RESERVED_BYTES		(64 * 1024)
 #define MD_RESERVED_SECTORS		(MD_RESERVED_BYTES / 512)
-#define MD_RESERVED_BLOCKS		(MD_RESERVED_BYTES / BLOCK_SIZE)
 
 #define MD_NEW_SIZE_SECTORS(x)		((x & ~(MD_RESERVED_SECTORS - 1)) - MD_RESERVED_SECTORS)
-#define MD_NEW_SIZE_BLOCKS(x)		((x & ~(MD_RESERVED_BLOCKS - 1)) - MD_RESERVED_BLOCKS)
 
 #define MD_SB_BYTES			4096
 #define MD_SB_WORDS			(MD_SB_BYTES / 4)
-#define MD_SB_BLOCKS			(MD_SB_BYTES / BLOCK_SIZE)
 #define MD_SB_SECTORS			(MD_SB_BYTES / 512)
 
 /*

include/linux/raid/raid5.h

···
  *    the compute block completes.
  */
 
+/*
+ * Operations state - intermediate states that are visible outside of sh->lock
+ * In general _idle indicates nothing is running, _run indicates a data
+ * processing operation is active, and _result means the data processing result
+ * is stable and can be acted upon.  For simple operations like biofill and
+ * compute that only have an _idle and _run state they are indicated with
+ * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN)
+ */
+/**
+ * enum check_states - handles syncing / repairing a stripe
+ * @check_state_idle - check operations are quiesced
+ * @check_state_run - check operation is running
+ * @check_state_result - set outside lock when check result is valid
+ * @check_state_compute_run - check failed and we are repairing
+ * @check_state_compute_result - set outside lock when compute result is valid
+ */
+enum check_states {
+	check_state_idle = 0,
+	check_state_run, /* parity check */
+	check_state_check_result,
+	check_state_compute_run, /* parity repair */
+	check_state_compute_result,
+};
+
+/**
+ * enum reconstruct_states - handles writing or expanding a stripe
+ */
+enum reconstruct_states {
+	reconstruct_state_idle = 0,
+	reconstruct_state_prexor_drain_run,	/* prexor-write */
+	reconstruct_state_drain_run,		/* write */
+	reconstruct_state_run,			/* expand */
+	reconstruct_state_prexor_drain_result,
+	reconstruct_state_drain_result,
+	reconstruct_state_result,
+};
+
 struct stripe_head {
 	struct hlist_node	hash;
 	struct list_head	lru;			/* inactive_list or handle_list */
···
 	spinlock_t		lock;
 	int			bm_seq;	/* sequence number for bitmap flushes */
 	int			disks;			/* disks in stripe */
+	enum check_states	check_state;
+	enum reconstruct_states reconstruct_state;
 	/* stripe_operations
-	 * @pending - pending ops flags (set for request->issue->complete)
-	 * @ack - submitted ops flags (set for issue->complete)
-	 * @complete - completed ops flags (set for complete)
 	 * @target - STRIPE_OP_COMPUTE_BLK target
-	 * @count - raid5_runs_ops is set to run when this is non-zero
 	 */
 	struct stripe_operations {
-		unsigned long	   pending;
-		unsigned long	   ack;
-		unsigned long	   complete;
 		int		   target;
-		int		   count;
 		u32		   zero_sum_result;
 	} ops;
 	struct r5dev {
···
 	int locked, uptodate, to_read, to_write, failed, written;
 	int to_fill, compute, req_compute, non_overwrite;
 	int failed_num;
+	unsigned long ops_request;
 };
 
 /* r6_state - extra state data only relevant to r6 */
···
 #define	R5_Wantfill	12 /* dev->toread contains a bio that needs
 				    * filling
 				    */
-#define	R5_Wantprexor	13 /* distinguish blocks ready for rmw from
-				    * other "towrites"
-				    */
+#define R5_Wantdrain	13 /* dev->towrite needs to be drained */
 /*
  * Write method
  */
···
 #define	STRIPE_EXPAND_READY	11
 #define	STRIPE_IO_STARTED	12 /* do not count towards 'bypass_count' */
 #define	STRIPE_FULL_WRITE	13 /* all blocks are set to be overwritten */
+#define	STRIPE_BIOFILL_RUN	14
+#define	STRIPE_COMPUTE_RUN	15
 /*
- * Operations flags (in issue order)
+ * Operation request flags
  */
 #define STRIPE_OP_BIOFILL	0
 #define STRIPE_OP_COMPUTE_BLK	1
···
 #define STRIPE_OP_BIODRAIN	3
 #define STRIPE_OP_POSTXOR	4
 #define STRIPE_OP_CHECK	5
-#define STRIPE_OP_IO		6
-
-/* modifiers to the base operations
- * STRIPE_OP_MOD_REPAIR_PD - compute the parity block and write it back
- * STRIPE_OP_MOD_DMA_CHECK - parity is not corrupted by the check
- */
-#define STRIPE_OP_MOD_REPAIR_PD 7
-#define STRIPE_OP_MOD_DMA_CHECK 8
 
 /*
  * Plugging: