dm-raid456 support using md/raid5.c, now with dirty-log

index 46b3a04..6fbd1c7 100644
@@ -541,14 +541,16 @@ static void mddev_unlock(mddev_t * mddev)
 		mutex_lock(&mddev->open_mutex);
 		mutex_unlock(&mddev->reconfig_mutex);
 
-		if (to_remove != &md_redundancy_group)
-			sysfs_remove_group(&mddev->kobj, to_remove);
-		if (mddev->pers == NULL ||
-		    mddev->pers->sync_request == NULL) {
-			sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
-			if (mddev->sysfs_action)
-				sysfs_put(mddev->sysfs_action);
-			mddev->sysfs_action = NULL;
+		if (mddev->kobj.sd) {
+			if (to_remove != &md_redundancy_group)
+				sysfs_remove_group(&mddev->kobj, to_remove);
+			if (mddev->pers == NULL ||
+			    mddev->pers->sync_request == NULL) {
+				sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+				if (mddev->sysfs_action)
+					sysfs_put(mddev->sysfs_action);
+				mddev->sysfs_action = NULL;
+			}
 		}
 		mutex_unlock(&mddev->open_mutex);
 	} else

@@ -1811,11 +1813,9 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 		goto fail;
 
 	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
-	if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
-		kobject_del(&rdev->kobj);
-		goto fail;
-	}
-	rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, NULL, "state");
+	if (sysfs_create_link(&rdev->kobj, ko, "block"))
+		/* failure here is OK */;
+	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
 
 	list_add_rcu(&rdev->same_set, &mddev->disks);
 	bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);

@@ -2333,8 +2333,8 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		set_bit(In_sync, &rdev->flags);
 		err = 0;
 	}
-	if (!err && rdev->sysfs_state)
-		sysfs_notify_dirent(rdev->sysfs_state);
+	if (!err)
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	return err ? err : len;
 }
 static struct rdev_sysfs_entry rdev_state =

@@ -2429,14 +2429,10 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 			rdev->raid_disk = -1;
 			return err;
 		} else
-			sysfs_notify_dirent(rdev->sysfs_state);
+			sysfs_notify_dirent_safe(rdev->sysfs_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));
-
+			/* failure here is OK */;
 		/* don't wakeup anyone, leave that to userspace. */
 	} else {
 		if (slot >= rdev->mddev->raid_disks)

@@ -2446,7 +2442,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		clear_bit(Faulty, &rdev->flags);
 		clear_bit(WriteMostly, &rdev->flags);
 		set_bit(In_sync, &rdev->flags);
-		sysfs_notify_dirent(rdev->sysfs_state);
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 	return len;
 }

@@ -3411,7 +3407,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
 	if (err)
 		return err;
 	else {
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		return len;
 	}
 }

@@ -3709,7 +3705,7 @@ action_store(mddev_t *mddev, const char *page, size_t len)
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
-	sysfs_notify_dirent(mddev->sysfs_action);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	return len;
 }
 

@@ -4255,13 +4251,14 @@ static int md_alloc(dev_t dev, char *name)
 		       disk->disk_name);
 		error = 0;
 	}
-	if (sysfs_create_group(&mddev->kobj, &md_bitmap_group))
+	if (mddev->kobj.sd &&
+	    sysfs_create_group(&mddev->kobj, &md_bitmap_group))
 		printk(KERN_DEBUG "pointless warning\n");
  abort:
 	mutex_unlock(&disks_mutex);
-	if (!error) {
+	if (!error && mddev->kobj.sd) {
 		kobject_uevent(&mddev->kobj, KOBJ_ADD);
-		mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, NULL, "array_state");
+		mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
 	}
 	mddev_put(mddev);
 	return error;

@@ -4299,7 +4296,7 @@ static void md_safemode_timeout(unsigned long data)
 	if (!atomic_read(&mddev->writes_pending)) {
 		mddev->safemode = 1;
 		if (mddev->external)
-			sysfs_notify_dirent(mddev->sysfs_state);
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 	md_wakeup_thread(mddev->thread);
 }

@@ -4371,7 +4368,7 @@ static int md_run(mddev_t *mddev)
 				return -EINVAL;
 			}
 		}
-		sysfs_notify_dirent(rdev->sysfs_state);
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 
 	spin_lock(&pers_lock);

@@ -4470,11 +4467,12 @@ static int md_run(mddev_t *mddev)
 		return err;
 	}
 	if (mddev->pers->sync_request) {
-		if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+		if (mddev->kobj.sd &&
+		    sysfs_create_group(&mddev->kobj, &md_redundancy_group))
 			printk(KERN_WARNING
 			       "md: cannot register extra attributes for %s\n",
 			       mdname(mddev));
-		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action");
+		mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action");
 	} else if (mddev->ro == 2) /* auto-readonly not meaningful */
 		mddev->ro = 0;
 

@@ -4492,8 +4490,7 @@ static int md_run(mddev_t *mddev)
 			char nm[20];
 			sprintf(nm, "rd%d", rdev->raid_disk);
 			if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
-				printk("md: cannot register %s for %s\n",
-				       nm, mdname(mddev));
+				/* failure here is OK */;
 		}
 	
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);

@@ -4505,9 +4502,8 @@ static int md_run(mddev_t *mddev)
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	md_new_event(mddev);
-	sysfs_notify_dirent(mddev->sysfs_state);
-	if (mddev->sysfs_action)
-		sysfs_notify_dirent(mddev->sysfs_action);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	return 0;
 }

@@ -4547,7 +4543,7 @@ static int restart_array(mddev_t *mddev)
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread);
-	sysfs_notify_dirent(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return 0;
 }
 

@@ -4671,7 +4667,7 @@ static int md_set_readonly(mddev_t *mddev, int is_open)
 		mddev->ro = 1;
 		set_disk_ro(mddev->gendisk, 1);
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		err = 0;	
 	}
 out:

@@ -4704,7 +4700,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		mddev->queue->backing_dev_info.congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 
 		list_for_each_entry(rdev, &mddev->disks, same_set)
 			if (rdev->raid_disk >= 0) {

@@ -4750,7 +4746,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 	err = 0;
 	blk_integrity_unregister(disk);
 	md_new_event(mddev);
-	sysfs_notify_dirent(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return err;
 }
 

@@ -5112,7 +5108,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 		if (err)
 			export_rdev(rdev);
 		else
-			sysfs_notify_dirent(rdev->sysfs_state);
+			sysfs_notify_dirent_safe(rdev->sysfs_state);
 
 		md_update_sb(mddev, 1);
 		if (mddev->degraded)

@@ -5787,7 +5783,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	if (_IOC_TYPE(cmd) == MD_MAJOR && mddev->ro && mddev->pers) {
 		if (mddev->ro == 2) {
 			mddev->ro = 0;
-			sysfs_notify_dirent(mddev->sysfs_state);
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			md_wakeup_thread(mddev->thread);
 		} else {

@@ -6032,7 +6028,7 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev)
 	mddev->pers->error_handler(mddev,rdev);
 	if (mddev->degraded)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-	sysfs_notify_dirent(rdev->sysfs_state);
+	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);

@@ -6493,7 +6489,7 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
 		spin_unlock_irq(&mddev->write_lock);
 	}
 	if (did_change)
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
 		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));

@@ -6536,7 +6532,7 @@ int md_allow_write(mddev_t *mddev)
 			mddev->safemode = 1;
 		spin_unlock_irq(&mddev->write_lock);
 		md_update_sb(mddev, 0);
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	} else
 		spin_unlock_irq(&mddev->write_lock);
 

@@ -6922,10 +6918,7 @@ static int remove_and_add_spares(mddev_t *mddev)
 					sprintf(nm, "rd%d", rdev->raid_disk);
 					if (sysfs_create_link(&mddev->kobj,
 							      &rdev->kobj, nm))
-						printk(KERN_WARNING
-						       "md: cannot register "
-						       "%s for %s\n",
-						       nm, mdname(mddev));
+						/* failure here is OK */;
 					spares++;
 					md_new_event(mddev);
 					set_bit(MD_CHANGE_DEVS, &mddev->flags);

@@ -7018,7 +7011,7 @@ void md_check_recovery(mddev_t *mddev)
 				mddev->safemode = 0;
 			spin_unlock_irq(&mddev->write_lock);
 			if (did_change)
-				sysfs_notify_dirent(mddev->sysfs_state);
+				sysfs_notify_dirent_safe(mddev->sysfs_state);
 		}
 
 		if (mddev->flags)

@@ -7057,7 +7050,7 @@ void md_check_recovery(mddev_t *mddev)
 			mddev->recovery = 0;
 			/* flag recovery needed just to double check */
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			sysfs_notify_dirent(mddev->sysfs_action);
+			sysfs_notify_dirent_safe(mddev->sysfs_action);
 			md_new_event(mddev);
 			goto unlock;
 		}

@@ -7119,7 +7112,7 @@ void md_check_recovery(mddev_t *mddev)
 				mddev->recovery = 0;
 			} else
 				md_wakeup_thread(mddev->sync_thread);
-			sysfs_notify_dirent(mddev->sysfs_action);
+			sysfs_notify_dirent_safe(mddev->sysfs_action);
 			md_new_event(mddev);
 		}
 	unlock:

@@ -7128,7 +7121,7 @@ void md_check_recovery(mddev_t *mddev)
 			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
 					       &mddev->recovery))
 				if (mddev->sysfs_action)
-					sysfs_notify_dirent(mddev->sysfs_action);
+					sysfs_notify_dirent_safe(mddev->sysfs_action);
 		}
 		mddev_unlock(mddev);
 	}

@@ -7136,7 +7129,7 @@ void md_check_recovery(mddev_t *mddev)
 
 void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
 {
-	sysfs_notify_dirent(rdev->sysfs_state);
+	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	wait_event_timeout(rdev->blocked_wait,
 			   !test_bit(Blocked, &rdev->flags),
 			   msecs_to_jiffies(5000));

index 7ab5ea1..1f680e4 100644
@@ -379,6 +379,18 @@ struct md_sysfs_entry {
 };
 extern struct attribute_group md_bitmap_group;
 
+static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name)
+{
+	if (sd)
+		return sysfs_get_dirent(sd, NULL, name);
+	return sd;
+}
+static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd)
+{
+	if (sd)
+		sysfs_notify_dirent(sd);
+}
+
 static inline char * mdname (mddev_t * mddev)
 {
 	return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";

index d2c0f94..8882da3 100644
@@ -5070,7 +5070,8 @@ static int run(mddev_t *mddev)
 	/* Ok, everything is just fine now */
 	if (mddev->to_remove == &raid5_attrs_group)
 		mddev->to_remove = NULL;
-	else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
+	else if (mddev->kobj.sd &&
+	    sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
 		printk(KERN_WARNING
 		       "md/raid:%s: failed to create sysfs attributes.\n",
 		       mdname(mddev));

@@ -5451,10 +5452,7 @@ static int raid5_start_reshape(mddev_t *mddev)
 				sprintf(nm, "rd%d", rdev->raid_disk);
 				if (sysfs_create_link(&mddev->kobj,
 						      &rdev->kobj, nm))
-					printk(KERN_WARNING
-					       "md/raid:%s: failed to create "
-					       " link %s\n",
-					       mdname(mddev), nm);
+					/* Failure here is OK */;
 			} else
 				break;
 		}

index 8882da3..8647705 100644
@@ -4480,23 +4480,15 @@ raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
 		return 0;
 }
 
-static ssize_t
-raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
+static int
+raid5_set_cache_size(mddev_t *mddev, int size)
 {
 	raid5_conf_t *conf = mddev->private;
-	unsigned long new;
 	int err;
 
-	if (len >= PAGE_SIZE)
+	if (size <= 16 || size > 32768)
 		return -EINVAL;
-	if (!conf)
-		return -ENODEV;
-
-	if (strict_strtoul(page, 10, &new))
-		return -EINVAL;
-	if (new <= 16 || new > 32768)
-		return -EINVAL;
-	while (new < conf->max_nr_stripes) {
+	while (size < conf->max_nr_stripes) {
 		if (drop_one_stripe(conf))
 			conf->max_nr_stripes--;
 		else

@@ -4505,11 +4497,31 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
 	err = md_allow_write(mddev);
 	if (err)
 		return err;
-	while (new > conf->max_nr_stripes) {
+	while (size > conf->max_nr_stripes) {
 		if (grow_one_stripe(conf))
 			conf->max_nr_stripes++;
 		else break;
 	}
+	return 0;
+}
+
+static ssize_t
+raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
+{
+	raid5_conf_t *conf = mddev->private;
+	unsigned long new;
+	int err;
+
+	if (len >= PAGE_SIZE)
+		return -EINVAL;
+	if (!conf)
+		return -ENODEV;
+
+	if (strict_strtoul(page, 10, &new))
+		return -EINVAL;
+	err = raid5_set_cache_size(mddev, new);
+	if (err)
+		return err;
 	return len;
 }
 

index 8647705..74e36a2 100644
@@ -1269,10 +1269,14 @@ static int grow_stripes(raid5_conf_t *conf, int num)
 	struct kmem_cache *sc;
 	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
-	sprintf(conf->cache_name[0],
-		"raid%d-%s", conf->level, mdname(conf->mddev));
-	sprintf(conf->cache_name[1],
-		"raid%d-%s-alt", conf->level, mdname(conf->mddev));
+	if (conf->mddev->gendisk)
+		sprintf(conf->cache_name[0],
+			"raid%d-%s", conf->level, mdname(conf->mddev));
+	else
+		sprintf(conf->cache_name[0],
+			"raid%d-%p", conf->level, conf->mddev);
+	sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]);
+
 	conf->active_name = 0;
 	sc = kmem_cache_create(conf->cache_name[conf->active_name],
 			       sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),

index 0f86f5e..bb7ab92 100644
@@ -388,7 +388,7 @@ struct raid5_private_data {
 	 * two caches.
 	 */
 	int			active_name;
-	char			cache_name[2][20];
+	char			cache_name[2][32];
 	struct kmem_cache		*slab_cache; /* for allocating stripes */
 
 	int			seq_flush, seq_write;

index 1742435..4518994 100644
@@ -1526,7 +1526,8 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 		   atomic_read(&bitmap->mddev->recovery_active) == 0);
 
 	bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
-	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
+	if (bitmap->mddev->persistent)
+		set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
 	sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
 	s = 0;
 	while (s < sector && s < bitmap->mddev->resync_max_sectors) {

index 6fbd1c7..2337cb2 100644
@@ -6726,7 +6726,8 @@ void md_do_sync(mddev_t *mddev)
 				   atomic_read(&mddev->recovery_active) == 0);
 			mddev->curr_resync_completed =
 				mddev->curr_resync;
-			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+			if (mddev->persistent)
+				set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 		}
 

index 2337cb2..d8e8a8c 100644
@@ -2690,6 +2690,24 @@ static struct kobj_type rdev_ktype = {
 	.default_attrs	= rdev_default_attrs,
 };
 
+void md_rdev_init(mdk_rdev_t *rdev)
+{
+	rdev->desc_nr = -1;
+	rdev->saved_raid_disk = -1;
+	rdev->raid_disk = -1;
+	rdev->flags = 0;
+	rdev->data_offset = 0;
+	rdev->sb_events = 0;
+	rdev->last_read_error.tv_sec  = 0;
+	rdev->last_read_error.tv_nsec = 0;
+	atomic_set(&rdev->nr_pending, 0);
+	atomic_set(&rdev->read_errors, 0);
+	atomic_set(&rdev->corrected_errors, 0);
+
+	INIT_LIST_HEAD(&rdev->same_set);
+	init_waitqueue_head(&rdev->blocked_wait);
+}
+EXPORT_SYMBOL_GPL(md_rdev_init);
 /*
  * Import a device. If 'super_format' >= 0, then sanity check the superblock
  *

@@ -2713,6 +2731,7 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 		return ERR_PTR(-ENOMEM);
 	}
 
+	md_rdev_init(rdev);
 	if ((err = alloc_disk_sb(rdev)))
 		goto abort_free;
 

@@ -2722,18 +2741,6 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 
 	kobject_init(&rdev->kobj, &rdev_ktype);
 
-	rdev->desc_nr = -1;
-	rdev->saved_raid_disk = -1;
-	rdev->raid_disk = -1;
-	rdev->flags = 0;
-	rdev->data_offset = 0;
-	rdev->sb_events = 0;
-	rdev->last_read_error.tv_sec  = 0;
-	rdev->last_read_error.tv_nsec = 0;
-	atomic_set(&rdev->nr_pending, 0);
-	atomic_set(&rdev->read_errors, 0);
-	atomic_set(&rdev->corrected_errors, 0);
-
 	size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
 	if (!size) {
 		printk(KERN_WARNING 

@@ -2762,9 +2769,6 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 		}
 	}
 
-	INIT_LIST_HEAD(&rdev->same_set);
-	init_waitqueue_head(&rdev->blocked_wait);
-
 	return rdev;
 
 abort_free:

index 1f680e4..a9cde80 100644
@@ -484,4 +484,5 @@ extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 extern void restore_bitmap_write_access(struct file *file);
 
+extern void md_rdev_init(mdk_rdev_t *rdev);
 #endif /* _MD_MD_H */

index d8e8a8c..4eccf4e 100644
@@ -416,7 +416,7 @@ static void mddev_put(mddev_t *mddev)
 	spin_unlock(&all_mddevs_lock);
 }
 
-static void mddev_init(mddev_t *mddev)
+void mddev_init(mddev_t *mddev)
 {
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);

@@ -436,6 +436,7 @@ static void mddev_init(mddev_t *mddev)
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
 }
+EXPORT_SYMBOL_GPL(mddev_init);
 
 static mddev_t * mddev_find(dev_t unit)
 {

@@ -4307,7 +4308,7 @@ static void md_safemode_timeout(unsigned long data)
 
 static int start_dirty_degraded;
 
-static int md_run(mddev_t *mddev)
+int md_run(mddev_t *mddev)
 {
 	int err;
 	mdk_rdev_t *rdev;

@@ -4511,6 +4512,7 @@ static int md_run(mddev_t *mddev)
 	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	return 0;
 }
+EXPORT_SYMBOL_GPL(md_run);
 
 static int do_md_run(mddev_t *mddev)
 {

@@ -4620,7 +4622,7 @@ static void md_clean(mddev_t *mddev)
 	mddev->bitmap_info.max_write_behind = 0;
 }
 
-static void md_stop_writes(mddev_t *mddev)
+void md_stop_writes(mddev_t *mddev)
 {
 	if (mddev->sync_thread) {
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);

@@ -4640,11 +4642,10 @@ static void md_stop_writes(mddev_t *mddev)
 		md_update_sb(mddev, 1);
 	}
 }
+EXPORT_SYMBOL_GPL(md_stop_writes);
 
-static void md_stop(mddev_t *mddev)
+void md_stop(mddev_t *mddev)
 {
-	md_stop_writes(mddev);
-
 	mddev->pers->stop(mddev);
 	if (mddev->pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;

@@ -4652,6 +4653,7 @@ static void md_stop(mddev_t *mddev)
 	mddev->pers = NULL;
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 }
+EXPORT_SYMBOL_GPL(md_stop);
 
 static int md_set_readonly(mddev_t *mddev, int is_open)
 {

@@ -4698,6 +4700,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		if (mddev->ro)
 			set_disk_ro(disk, 0);
 
+		md_stop_writes(mddev);
 		md_stop(mddev);
 		mddev->queue->merge_bvec_fn = NULL;
 		mddev->queue->unplug_fn = NULL;

index a9cde80..8e19e86 100644
@@ -484,5 +484,9 @@ extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 extern void restore_bitmap_write_access(struct file *file);
 
+extern void mddev_init(mddev_t *mddev);
+extern int md_run(mddev_t *mddev);
+extern void md_stop(mddev_t *mddev);
+extern void md_stop_writes(mddev_t *mddev);
 extern void md_rdev_init(mdk_rdev_t *rdev);
 #endif /* _MD_MD_H */

437 lines not on this page · raw message

index 5185a8f..d54f901 100644
@@ -139,6 +139,13 @@ static int dev_parms(struct raid_set *rs, char **argv)
 	return 0;
 }
 
+static void do_table_event(struct work_struct *ws)
+{
+	struct raid_set *rs = container_of(ws, struct raid_set,
+					   md.event_work);
+	dm_table_event(rs->ti->table);
+}
+
 /*
  * Construct a RAID4/5/6 mapping:
  * Args:

@@ -290,6 +297,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (rs->md.raid_disks - in_sync > rt->parity_devs)
 		goto err;
 
+	INIT_WORK(&rs->md.event_work, do_table_event);
 	ti->split_io = rs->md.chunk_sectors;
 	ti->private = rs;
 

index 4eccf4e..da860f7 100644
@@ -6039,6 +6039,8 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev)
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
+	if (mddev->event_work.func)
+		schedule_work(&mddev->event_work);
 	md_new_event_inintr(mddev);
 }
 

index 8e19e86..6318175 100644
@@ -315,6 +315,7 @@ struct mddev_s
 	struct bio *barrier;
 	atomic_t flush_pending;
 	struct work_struct barrier_work;
+	struct work_struct event_work;
 };
 
 

index 74e36a2..8839573 100644
@@ -5072,16 +5072,6 @@ static int run(mddev_t *mddev)
 							"reshape");
 	}
 
-	/* read-ahead size must cover two whole stripes, which is
-	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-	 */
-	{
-		int data_disks = conf->previous_raid_disks - conf->max_degraded;
-		int stripe = data_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
-	}
 
 	/* Ok, everything is just fine now */
 	if (mddev->to_remove == &raid5_attrs_group)

@@ -5089,8 +5079,23 @@ static int run(mddev_t *mddev)
 	else if (mddev->kobj.sd &&
 	    sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
 		printk(KERN_WARNING
-		       "md/raid:%s: failed to create sysfs attributes.\n",
+		       "raid5: failed to create sysfs attributes for %s\n",
 		       mdname(mddev));
+	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
+
+	if (mddev->queue) {
+		/* read-ahead size must cover two whole stripes, which
+		 * is 2 * (datadisks) * chunksize where 'n' is the
+		 * number of raid devices
+		 */
+		int data_disks = conf->previous_raid_disks - conf->max_degraded;
+		int stripe = data_disks *
+			((mddev->chunk_sectors << 9) / PAGE_SIZE);
+		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
+			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+
+		blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
+	}
 
 	mddev->queue->queue_lock = &conf->device_lock;
 

@@ -5098,9 +5103,6 @@ static int run(mddev_t *mddev)
 	mddev->queue->backing_dev_info.congested_data = mddev;
 	mddev->queue->backing_dev_info.congested_fn = raid5_congested;
 
-	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
-
-	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
 	chunk_size = mddev->chunk_sectors << 9;
 	blk_queue_io_min(mddev->queue, chunk_size);
 	blk_queue_io_opt(mddev->queue, chunk_size *

@@ -5523,7 +5525,7 @@ static void end_reshape(raid5_conf_t *conf)
 		/* read-ahead size must cover two whole stripes, which is
 		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
 		 */
-		{
+		if (conf->mddev->queue) {
 			int data_disks = conf->raid_disks - conf->max_degraded;
 			int stripe = data_disks * ((conf->chunk_sectors << 9)
 						   / PAGE_SIZE);

index d54f901..0e3922a 100644
@@ -17,6 +17,7 @@ struct raid_set {
 	struct dm_target *ti;
 	struct mddev_s md;
 	struct raid_type *raid_type;
+	struct target_callbacks callbacks;
 	struct raid_dev dev[0];
 };
 

@@ -146,6 +147,13 @@ static void do_table_event(struct work_struct *ws)
 	dm_table_event(rs->ti->table);
 }
 
+static int raid_is_congested(void *v, int bits)
+{
+	struct target_callbacks *cb = v;
+	struct raid_set *rs = container_of(cb, struct raid_set,
+					   callbacks);
+	return md_raid5_congested(&rs->md, bits);
+}
 /*
  * Construct a RAID4/5/6 mapping:
  * Args:

@@ -309,6 +317,10 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	if (errnum)
 		goto err;
+
+	rs->callbacks.congested_fn = raid_is_congested;
+	dm_table_add_callbacks(ti->table, &rs->callbacks);
+
 	return 0;
 err:
 	if (rs)

@@ -321,6 +333,7 @@ static void raid_dtr(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
+	list_del_init(&rs->callbacks.list);
 	md_stop(&rs->md);
 	context_free(rs);
 }

index 9924ea2..b856340 100644
@@ -68,6 +68,8 @@ struct dm_table {
 	void (*event_fn)(void *);
 	void *event_context;
 
+	struct list_head target_callbacks;
+
 	struct dm_md_mempools *mempools;
 };
 

@@ -202,6 +204,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
+	INIT_LIST_HEAD(&t->target_callbacks);
 	atomic_set(&t->holders, 0);
 
 	if (!num_targets)

@@ -1174,10 +1177,18 @@ int dm_table_resume_targets(struct dm_table *t)
 	return 0;
 }
 
+void dm_table_add_callbacks(struct dm_table *t,
+			    struct target_callbacks *cb)
+{
+	list_add(&cb->list, &t->target_callbacks);
+}
+EXPORT_SYMBOL_GPL(dm_table_add_callbacks);
+
 int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
+	struct target_callbacks *cb;
 	int r = 0;
 
 	list_for_each_entry(dd, devices, list) {

@@ -1192,6 +1203,10 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 				     bdevname(dd->dm_dev.bdev, b));
 	}
 
+	list_for_each_entry(cb, &t->target_callbacks, list)
+		if (cb->congested_fn)
+			r |= cb->congested_fn(cb, bdi_bits);
+
 	return r;
 }
 

index 8839573..c0746af 100644
@@ -3592,17 +3592,14 @@ static void raid5_unplug_device(struct request_queue *q)
 	unplug_slaves(mddev);
 }
 
-static int raid5_congested(void *data, int bits)
+int md_raid5_congested(mddev_t *mddev, int bits)
 {
-	mddev_t *mddev = data;
 	raid5_conf_t *conf = mddev->private;
 
 	/* No difference between reads and writes.  Just check
 	 * how busy the stripe_cache is
 	 */
 
-	if (mddev_congested(mddev, bits))
-		return 1;
 	if (conf->inactive_blocked)
 		return 1;
 	if (conf->quiesce)

@@ -3612,6 +3609,15 @@ static int raid5_congested(void *data, int bits)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(md_raid5_congested);
+
+static int raid5_congested(void *data, int bits)
+{
+	mddev_t *mddev = data;
+
+	return mddev_congested(mddev, bits) ||
+		md_raid5_congested(mddev, bits);
+}
 
 /* We want read requests to align with chunks where possible,
  * but write requests don't need to.

@@ -5095,13 +5101,14 @@ static int run(mddev_t *mddev)
 			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
 
 		blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
+
+		mddev->queue->backing_dev_info.congested_data = mddev;
+		mddev->queue->backing_dev_info.congested_fn = raid5_congested;
 	}
 
 	mddev->queue->queue_lock = &conf->device_lock;
 
 	mddev->queue->unplug_fn = raid5_unplug_device;
-	mddev->queue->backing_dev_info.congested_data = mddev;
-	mddev->queue->backing_dev_info.congested_fn = raid5_congested;
 
 	chunk_size = mddev->chunk_sectors << 9;
 	blk_queue_io_min(mddev->queue, chunk_size);

@@ -5131,7 +5138,8 @@ static int stop(mddev_t *mddev)
 
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
-	mddev->queue->backing_dev_info.congested_fn = NULL;
+	if (mddev->queue)
+		mddev->queue->backing_dev_info.congested_fn = NULL;
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	free_conf(conf);
 	mddev->private = NULL;

index bb7ab92..936caf8 100644
@@ -497,4 +497,5 @@ static inline int algorithm_is_DDF(int layout)
 {
 	return layout >= 8 && layout <= 10;
 }
+extern int md_raid5_congested(mddev_t *mddev, int bits);
 #endif

index 1381cd9..2b0f538 100644
@@ -187,6 +187,12 @@ struct dm_target {
 	char *error;
 };
 
+/* Each target can link one of these into the table */
+struct target_callbacks {
+	struct list_head list;
+	congested_fn *congested_fn;
+};
+
 int dm_register_target(struct target_type *t);
 void dm_unregister_target(struct target_type *t);
 

@@ -263,6 +269,12 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 			sector_t start, sector_t len, char *params);
 
 /*
+ * Target_ctr should call this if they need to add any
+ * callback
+ */
+void dm_table_add_callbacks(struct dm_table *t,
+			    struct target_callbacks *cb);
+/*
  * Finally call this to make the table ready for use.
  */
 int dm_table_complete(struct dm_table *t);

index da860f7..e44b9c6 100644
@@ -384,6 +384,51 @@ void md_barrier_request(mddev_t *mddev, struct bio *bio)
 }
 EXPORT_SYMBOL(md_barrier_request);
 
+/* Support for plugging.
+ * This mirrors the plugging support in request_queue, but does not
+ * require having a whole queue
+ */
+static void plugger_work(struct work_struct *work)
+{
+	struct plug_handle *plug =
+		container_of(work, struct plug_handle, unplug_work);
+	plug->unplug_fn(plug);
+}
+static void plugger_timeout(unsigned long data)
+{
+	struct plug_handle *plug = (void *)data;
+	kblockd_schedule_work(NULL, &plug->unplug_work);
+}
+void plugger_init(struct plug_handle *plug,
+		  void (*unplug_fn)(struct plug_handle *))
+{
+	plug->unplug_flag = 0;
+	plug->unplug_fn = unplug_fn;
+	init_timer(&plug->unplug_timer);
+	plug->unplug_timer.function = plugger_timeout;
+	plug->unplug_timer.data = (unsigned long)plug;
+	INIT_WORK(&plug->unplug_work, plugger_work);
+}
+EXPORT_SYMBOL_GPL(plugger_init);
+
+void plugger_set_plug(struct plug_handle *plug)
+{
+	if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag))
+		mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1);
+}
+EXPORT_SYMBOL_GPL(plugger_set_plug);
+
+int plugger_remove_plug(struct plug_handle *plug)
+{
+	if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) {
+		del_timer(&plug->unplug_timer);
+		return 1;
+	} else
+		return 0;
+}
+EXPORT_SYMBOL_GPL(plugger_remove_plug);
+
+
 static inline mddev_t *mddev_get(mddev_t *mddev)
 {
 	atomic_inc(&mddev->active);

index 6318175..f210482 100644
@@ -29,6 +29,26 @@
 typedef struct mddev_s mddev_t;
 typedef struct mdk_rdev_s mdk_rdev_t;
 
+/* generic plugging support - like that provided with request_queue,
+ * but does not require a request_queue
+ */
+struct plug_handle {
+	void			(*unplug_fn)(struct plug_handle *);
+	struct timer_list	unplug_timer;
+	struct work_struct	unplug_work;
+	unsigned long		unplug_flag;
+};
+#define	PLUGGED_FLAG 1
+void plugger_init(struct plug_handle *plug,
+		  void (*unplug_fn)(struct plug_handle *));
+void plugger_set_plug(struct plug_handle *plug);
+int plugger_remove_plug(struct plug_handle *plug);
+static inline void plugger_flush(struct plug_handle *plug)
+{
+	del_timer_sync(&plug->unplug_timer);
+	cancel_work_sync(&plug->unplug_work);
+}
+
 /*
  * MD's 'extended' device
  */

index c0746af..6b1802c 100644
@@ -201,11 +201,11 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 		if (test_bit(STRIPE_HANDLE, &sh->state)) {
 			if (test_bit(STRIPE_DELAYED, &sh->state)) {
 				list_add_tail(&sh->lru, &conf->delayed_list);
-				blk_plug_device(conf->mddev->queue);
+				plugger_set_plug(&conf->plug);
 			} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
 				   sh->bm_seq - conf->seq_write > 0) {
 				list_add_tail(&sh->lru, &conf->bitmap_list);
-				blk_plug_device(conf->mddev->queue);
+				plugger_set_plug(&conf->plug);
 			} else {
 				clear_bit(STRIPE_BIT_DELAY, &sh->state);
 				list_add_tail(&sh->lru, &conf->handle_list);

@@ -365,7 +365,7 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector,
 }
 
 static void unplug_slaves(mddev_t *mddev);
-static void raid5_unplug_device(struct request_queue *q);
+static void raid5_unplug_device(raid5_conf_t *conf);
 
 static struct stripe_head *
 get_active_stripe(raid5_conf_t *conf, sector_t sector,

@@ -395,7 +395,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector,
 						     < (conf->max_nr_stripes *3/4)
 						     || !conf->inactive_blocked),
 						    conf->device_lock,
-						    raid5_unplug_device(conf->mddev->queue)
+						    raid5_unplug_device(conf)
 					);
 				conf->inactive_blocked = 0;
 			} else

@@ -3532,7 +3532,7 @@ static void raid5_activate_delayed(raid5_conf_t *conf)
 			list_add_tail(&sh->lru, &conf->hold_list);
 		}
 	} else
-		blk_plug_device(conf->mddev->queue);
+		plugger_set_plug(&conf->plug);
 }
 
 static void activate_bit_delay(raid5_conf_t *conf)

@@ -3573,23 +3573,33 @@ static void unplug_slaves(mddev_t *mddev)
 	rcu_read_unlock();
 }
 
-static void raid5_unplug_device(struct request_queue *q)
+static void raid5_unplug_device(raid5_conf_t *conf)
 {
-	mddev_t *mddev = q->queuedata;
-	raid5_conf_t *conf = mddev->private;
 	unsigned long flags;
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 
-	if (blk_remove_plug(q)) {
+	if (plugger_remove_plug(&conf->plug)) {
 		conf->seq_flush++;
 		raid5_activate_delayed(conf);
 	}
-	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(conf->mddev->thread);
 
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
-	unplug_slaves(mddev);
+	unplug_slaves(conf->mddev);
+}
+
+static void raid5_unplug(struct plug_handle *plug)
+{
+	raid5_conf_t *conf = container_of(plug, raid5_conf_t, plug);
+	raid5_unplug_device(conf);
+}
+
+static void raid5_unplug_queue(struct request_queue *q)
+{
+	mddev_t *mddev = q->queuedata;
+	raid5_unplug_device(mddev->private);
 }
 
 int md_raid5_congested(mddev_t *mddev, int bits)

@@ -3999,7 +4009,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 				 * add failed due to overlap.  Flush everything
 				 * and wait a while
 				 */
-				raid5_unplug_device(mddev->queue);
+				raid5_unplug_device(conf);
 				release_stripe(sh);
 				schedule();
 				goto retry;

@@ -5089,6 +5099,7 @@ static int run(mddev_t *mddev)
 		       mdname(mddev));
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
+	plugger_init(&conf->plug, raid5_unplug);
 	if (mddev->queue) {
 		/* read-ahead size must cover two whole stripes, which
 		 * is 2 * (datadisks) * chunksize where 'n' is the

@@ -5108,7 +5119,7 @@ static int run(mddev_t *mddev)
 
 	mddev->queue->queue_lock = &conf->device_lock;
 
-	mddev->queue->unplug_fn = raid5_unplug_device;
+	mddev->queue->unplug_fn = raid5_unplug_queue;
 
 	chunk_size = mddev->chunk_sectors << 9;
 	blk_queue_io_min(mddev->queue, chunk_size);

@@ -5140,7 +5151,7 @@ static int stop(mddev_t *mddev)
 	mddev->thread = NULL;
 	if (mddev->queue)
 		mddev->queue->backing_dev_info.congested_fn = NULL;
-	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+	plugger_flush(&conf->plug); /* the unplug fn references 'conf'*/
 	free_conf(conf);
 	mddev->private = NULL;
 	mddev->to_remove = &raid5_attrs_group;

index 936caf8..edf90a8 100644
@@ -398,6 +398,9 @@ struct raid5_private_data {
 					    * (fresh device added).
 					    * Cleared when a sync completes.
 					    */
+
+	struct plug_handle	plug;
+
 	/* per cpu variables */
 	struct raid5_percpu {
 		struct page	*spare_page; /* Used when checking P/Q in raid6 */

index e44b9c6..ea6577b 100644
@@ -4665,6 +4665,7 @@ static void md_clean(mddev_t *mddev)
 	mddev->bitmap_info.chunksize = 0;
 	mddev->bitmap_info.daemon_sleep = 0;
 	mddev->bitmap_info.max_write_behind = 0;
+	mddev->plug = NULL;
 }
 
 void md_stop_writes(mddev_t *mddev)

@@ -6597,6 +6598,14 @@ int md_allow_write(mddev_t *mddev)
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
+static void md_unplug(mddev_t *mddev)
+{
+	if (mddev->queue)
+		blk_unplug(mddev->queue);
+	if (mddev->plug)
+		mddev->plug->unplug_fn(mddev->plug);
+}
+
 #define SYNC_MARKS	10
 #define	SYNC_MARK_STEP	(3*HZ)
 void md_do_sync(mddev_t *mddev)

@@ -6775,7 +6784,7 @@ void md_do_sync(mddev_t *mddev)
 		     >= mddev->resync_max - mddev->curr_resync_completed
 			    )) {
 			/* time to update curr_resync_completed */
-			blk_unplug(mddev->queue);
+			md_unplug(mddev);
 			wait_event(mddev->recovery_wait,
 				   atomic_read(&mddev->recovery_active) == 0);
 			mddev->curr_resync_completed =

@@ -6853,7 +6862,7 @@ void md_do_sync(mddev_t *mddev)
 		 * about not overloading the IO subsystem. (things like an
 		 * e2fsck being done on the RAID array should execute fast)
 		 */
-		blk_unplug(mddev->queue);
+		md_unplug(mddev);
 		cond_resched();
 
 		currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2

@@ -6872,7 +6881,7 @@ void md_do_sync(mddev_t *mddev)
 	 * this also signals 'finished resyncing' to md_stop
 	 */
  out:
-	blk_unplug(mddev->queue);
+	md_unplug(mddev);
 
 	wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
 

index f210482..0bf8c18 100644
@@ -325,6 +325,8 @@ struct mddev_s
 	struct list_head		all_mddevs;
 
 	struct attribute_group		*to_remove;
+	struct plug_handle		*plug; /* if used by personality */
+
 	/* Generic barrier handling.
 	 * If there is a pending barrier request, all other
 	 * writes are blocked while the devices are flushed.

index 6b1802c..74bc7a6 100644
@@ -5100,6 +5100,7 @@ static int run(mddev_t *mddev)
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
 	plugger_init(&conf->plug, raid5_unplug);
+	mddev->plug = &conf->plug;
 	if (mddev->queue) {
 		/* read-ahead size must cover two whole stripes, which
 		 * is 2 * (datadisks) * chunksize where 'n' is the

index 0e3922a..46a5e29 100644
@@ -154,6 +154,14 @@ static int raid_is_congested(void *v, int bits)
 					   callbacks);
 	return md_raid5_congested(&rs->md, bits);
 }
+static void raid_unplug(void *v)
+{
+	struct target_callbacks *cb = v;
+	struct raid_set *rs = container_of(cb, struct raid_set,
+					   callbacks);
+	raid5_unplug_device(rs->md.private);
+}
+
 /*
  * Construct a RAID4/5/6 mapping:
  * Args:

@@ -289,6 +297,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			goto err;
 		clear_bit(In_sync, &rs->dev[rebuildA].rdev.flags);
 		rs->dev[rebuildA].rdev.recovery_offset = 0;
+	rs->callbacks.unplug_fn = raid_unplug;
 	}
 	if (rebuildB >= 0) {
 		if (rs->dev[rebuildB].dev == NULL)

index b856340..cad4992 100644
@@ -1228,6 +1228,7 @@ void dm_table_unplug_all(struct dm_table *t)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
+	struct target_callbacks *cb;
 
 	list_for_each_entry(dd, devices, list) {
 		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);

@@ -1240,6 +1241,9 @@ void dm_table_unplug_all(struct dm_table *t)
 				     dm_device_name(t->md),
 				     bdevname(dd->dm_dev.bdev, b));
 	}
+	list_for_each_entry(cb, &t->target_callbacks, list)
+		if (cb->unplug_fn)
+			cb->unplug_fn(cb);
 }
 
 struct mapped_device *dm_table_get_md(struct dm_table *t)

index 74bc7a6..efcea17 100644
@@ -365,7 +365,6 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector,
 }
 
 static void unplug_slaves(mddev_t *mddev);
-static void raid5_unplug_device(raid5_conf_t *conf);
 
 static struct stripe_head *
 get_active_stripe(raid5_conf_t *conf, sector_t sector,

@@ -3573,7 +3572,7 @@ static void unplug_slaves(mddev_t *mddev)
 	rcu_read_unlock();
 }
 
-static void raid5_unplug_device(raid5_conf_t *conf)
+void raid5_unplug_device(raid5_conf_t *conf)
 {
 	unsigned long flags;
 

@@ -3589,6 +3588,7 @@ static void raid5_unplug_device(raid5_conf_t *conf)
 
 	unplug_slaves(conf->mddev);
 }
+EXPORT_SYMBOL_GPL(raid5_unplug_device);
 
 static void raid5_unplug(struct plug_handle *plug)
 {

@@ -5116,11 +5116,10 @@ static int run(mddev_t *mddev)
 
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = raid5_congested;
-	}
-
-	mddev->queue->queue_lock = &conf->device_lock;
 
-	mddev->queue->unplug_fn = raid5_unplug_queue;
+		mddev->queue->queue_lock = &conf->device_lock;
+		mddev->queue->unplug_fn = raid5_unplug_queue;
+	}
 
 	chunk_size = mddev->chunk_sectors << 9;
 	blk_queue_io_min(mddev->queue, chunk_size);

index edf90a8..fa3938a 100644
@@ -501,4 +501,5 @@ static inline int algorithm_is_DDF(int layout)
 	return layout >= 8 && layout <= 10;
 }
 extern int md_raid5_congested(mddev_t *mddev, int bits);
+extern void raid5_unplug_device(raid5_conf_t *conf);
 #endif

index 2b0f538..5b8ac19 100644
@@ -191,6 +191,7 @@ struct dm_target {
 struct target_callbacks {
 	struct list_head list;
 	congested_fn *congested_fn;
+	void (*unplug_fn)(void *);
 };
 
 int dm_register_target(struct target_type *t);

index 46a5e29..0b72fa4 100644
@@ -435,6 +435,37 @@ static int raid_status(struct dm_target *ti, status_type_t type,
 	return 0;
 }
 
+static int raid_iterate_devices(struct dm_target *ti,
+				iterate_devices_callout_fn fn,
+				void *data)
+{
+	struct raid_set *rs = ti->private;
+	int ret = 0;
+	unsigned i = 0;
+
+	for (i = 0; !ret && i < rs->md.raid_disks; i++)
+		if (rs->dev[i].dev)
+			ret = fn(ti,
+				 rs->dev[i].dev,
+				 rs->dev[i].rdev.data_offset,
+				 rs->md.dev_sectors,
+				 data);
+
+	return ret;
+}
+
+static void raid_io_hints(struct dm_target *ti,
+			  struct queue_limits *limits)
+{
+	struct raid_set *rs = ti->private;
+	unsigned chunk_size = rs->md.chunk_sectors << 9;
+	raid5_conf_t *conf = rs->md.private;
+
+	blk_limits_io_min(limits, chunk_size);
+	blk_limits_io_opt(limits, chunk_size *
+			  (conf->raid_disks - conf->max_degraded));
+}
+
 static struct target_type raid_target = {
 	.name = "raid45",
 	.version = {1, 0, 0},

@@ -443,6 +474,8 @@ static struct target_type raid_target = {
 	.dtr = raid_dtr,
 	.map = raid_map,
 	.status = raid_status,
+	.iterate_devices = raid_iterate_devices,
+	.io_hints = raid_io_hints,
 };
 
 static int __init dm_raid_init(void)

index efcea17..be5cab8 100644
@@ -4904,7 +4904,7 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 static int run(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
-	int working_disks = 0, chunk_size;
+	int working_disks = 0;
 	int dirty_parity_disks = 0;
 	mdk_rdev_t *rdev;
 	sector_t reshape_offset = 0;

@@ -5102,6 +5102,7 @@ static int run(mddev_t *mddev)
 	plugger_init(&conf->plug, raid5_unplug);
 	mddev->plug = &conf->plug;
 	if (mddev->queue) {
+		int chunk_size;
 		/* read-ahead size must cover two whole stripes, which
 		 * is 2 * (datadisks) * chunksize where 'n' is the
 		 * number of raid devices

@@ -5119,16 +5120,16 @@ static int run(mddev_t *mddev)
 
 		mddev->queue->queue_lock = &conf->device_lock;
 		mddev->queue->unplug_fn = raid5_unplug_queue;
-	}
 
-	chunk_size = mddev->chunk_sectors << 9;
-	blk_queue_io_min(mddev->queue, chunk_size);
-	blk_queue_io_opt(mddev->queue, chunk_size *
-			 (conf->raid_disks - conf->max_degraded));
+		chunk_size = mddev->chunk_sectors << 9;
+		blk_queue_io_min(mddev->queue, chunk_size);
+		blk_queue_io_opt(mddev->queue, chunk_size *
+				 (conf->raid_disks - conf->max_degraded));
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+		list_for_each_entry(rdev, &mddev->disks, same_set)
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
+	}
 
 	return 0;
 abort:

index 0b72fa4..044faae 100644
@@ -466,6 +466,25 @@ static void raid_io_hints(struct dm_target *ti,
 			  (conf->raid_disks - conf->max_degraded));
 }
 
+static void raid_presuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	md_stop_writes(&rs->md);
+}
+
+static void raid_postsuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	mddev_suspend(&rs->md);
+}
+
+static void raid_resume(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	mddev_resume(&rs->md);
+}
+
 static struct target_type raid_target = {
 	.name = "raid45",
 	.version = {1, 0, 0},

@@ -476,6 +495,9 @@ static struct target_type raid_target = {
 	.status = raid_status,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
+	.presuspend = raid_presuspend,
+	.postsuspend = raid_postsuspend,
+	.resume = raid_resume,
 };
 
 static int __init dm_raid_init(void)

index ea6577b..21f3c35 100644
@@ -261,7 +261,7 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
  * Once ->stop is called and completes, the module will be completely
  * unused.
  */
-static void mddev_suspend(mddev_t *mddev)
+void mddev_suspend(mddev_t *mddev)
 {
 	BUG_ON(mddev->suspended);
 	mddev->suspended = 1;

@@ -269,13 +269,15 @@ static void mddev_suspend(mddev_t *mddev)
 	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
 	mddev->pers->quiesce(mddev, 1);
 }
+EXPORT_SYMBOL_GPL(mddev_suspend);
 
-static void mddev_resume(mddev_t *mddev)
+void mddev_resume(mddev_t *mddev)
 {
 	mddev->suspended = 0;
 	wake_up(&mddev->sb_wait);
 	mddev->pers->quiesce(mddev, 0);
 }
+EXPORT_SYMBOL_GPL(mddev_resume);
 
 int mddev_congested(mddev_t *mddev, int bits)
 {

index 0bf8c18..6f2c568 100644
@@ -512,4 +512,7 @@ extern int md_run(mddev_t *mddev);
 extern void md_stop(mddev_t *mddev);
 extern void md_stop_writes(mddev_t *mddev);
 extern void md_rdev_init(mdk_rdev_t *rdev);
+
+extern void mddev_suspend(mddev_t *mddev);
+extern void mddev_resume(mddev_t *mddev);
 #endif /* _MD_MD_H */

index 044faae..3fda954 100644
@@ -485,6 +485,31 @@ static void raid_resume(struct dm_target *ti)
 	mddev_resume(&rs->md);
 }
 
+/* Parse and handle a message from userspace
+ * Messages are:
+ *    stripecache  N  (pages per devices)
+ *    minspeed  N          (kibibytes per seconds)
+ */
+static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
+{
+	struct raid_set *rs = ti->private;
+
+	if (argc == 2 && strcmp(argv[0], "stripecache") == 0) {
+		unsigned long size;
+		if (strict_strtoul(argv[1], 10, &size))
+			return -EINVAL;
+		return raid5_set_cache_size(&rs->md, size);
+	}
+	if (argc == 2 && strcmp(argv[0], "minspeed") == 0) {
+		unsigned long speed;
+		if (strict_strtoul(argv[1], 10, &speed))
+			return -EINVAL;
+		rs->md.sync_speed_min = speed;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static struct target_type raid_target = {
 	.name = "raid45",
 	.version = {1, 0, 0},

@@ -498,6 +523,7 @@ static struct target_type raid_target = {
 	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
 	.resume = raid_resume,
+	.message = raid_message,
 };
 
 static int __init dm_raid_init(void)

index be5cab8..8ac122d 100644
@@ -4500,7 +4500,7 @@ raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
 		return 0;
 }
 
-static int
+int
 raid5_set_cache_size(mddev_t *mddev, int size)
 {
 	raid5_conf_t *conf = mddev->private;

@@ -4524,6 +4524,7 @@ raid5_set_cache_size(mddev_t *mddev, int size)
 	}
 	return 0;
 }
+EXPORT_SYMBOL(raid5_set_cache_size);
 
 static ssize_t
 raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)

index fa3938a..292a9c6 100644
@@ -502,4 +502,5 @@ static inline int algorithm_is_DDF(int layout)
 }
 extern int md_raid5_congested(mddev_t *mddev, int bits);
 extern void raid5_unplug_device(raid5_conf_t *conf);
+extern int raid5_set_cache_size(mddev_t *mddev, int size);
 #endif

index 4518994..67fb32d 100644
@@ -13,7 +13,6 @@
  * Still to do:
  *
  * flush after percent set rather than just time based. (maybe both).
- * wait if count gets too high, wake when it drops to half.
  */
 
 #include <linux/blkdev.h>

@@ -51,9 +50,6 @@
 #define INJECT_FATAL_FAULT_3 0 /* undef */
 #endif
 
-//#define DPRINTK PRINTK /* set this NULL to avoid verbose debug output */
-#define DPRINTK(x...) do { } while(0)
-
 #ifndef PRINTK
 #  if DEBUG > 0
 #    define PRINTK(x...) printk(KERN_DEBUG x)

@@ -62,12 +58,11 @@
 #  endif
 #endif
 
-static inline char * bmname(struct bitmap *bitmap)
+static inline char *bmname(struct bitmap *bitmap)
 {
 	return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
 }
 
-
 /*
  * just a placeholder - calls kmalloc for bitmap pages
  */

@@ -78,7 +73,7 @@ static unsigned char *bitmap_alloc_page(struct bitmap *bitmap)
 #ifdef INJECT_FAULTS_1
 	page = NULL;
 #else
-	page = kmalloc(PAGE_SIZE, GFP_NOIO);
+	page = kzalloc(PAGE_SIZE, GFP_NOIO);
 #endif
 	if (!page)
 		printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap));

@@ -107,7 +102,8 @@ static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page)
  * if we find our page, we increment the page's refcount so that it stays
  * allocated while we're using it
  */
-static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create)
+static int bitmap_checkpage(struct bitmap *bitmap,
+			    unsigned long page, int create)
 __releases(bitmap->lock)
 __acquires(bitmap->lock)
 {

@@ -121,7 +117,6 @@ __acquires(bitmap->lock)
 		return -EINVAL;
 	}
 
-
 	if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */
 		return 0;
 

@@ -131,43 +126,34 @@ __acquires(bitmap->lock)
 	if (!create)
 		return -ENOENT;
 
-	spin_unlock_irq(&bitmap->lock);
-
 	/* this page has not been allocated yet */
 
-	if ((mappage = bitmap_alloc_page(bitmap)) == NULL) {
+	spin_unlock_irq(&bitmap->lock);
+	mappage = bitmap_alloc_page(bitmap);
+	spin_lock_irq(&bitmap->lock);
+
+	if (mappage == NULL) {
 		PRINTK("%s: bitmap map page allocation failed, hijacking\n",
 			bmname(bitmap));
 		/* failed - set the hijacked flag so that we can use the
 		 * pointer as a counter */
-		spin_lock_irq(&bitmap->lock);
 		if (!bitmap->bp[page].map)
 			bitmap->bp[page].hijacked = 1;
-		goto out;
-	}
-
-	/* got a page */
-
-	spin_lock_irq(&bitmap->lock);
-
-	/* recheck the page */
-
-	if (bitmap->bp[page].map || bitmap->bp[page].hijacked) {
+	} else if (bitmap->bp[page].map ||
+		   bitmap->bp[page].hijacked) {
 		/* somebody beat us to getting the page */
 		bitmap_free_page(bitmap, mappage);
 		return 0;
-	}
+	} else {
 
-	/* no page was in place and we have one, so install it */
+		/* no page was in place and we have one, so install it */
 
-	memset(mappage, 0, PAGE_SIZE);
-	bitmap->bp[page].map = mappage;
-	bitmap->missing_pages--;
-out:
+		bitmap->bp[page].map = mappage;
+		bitmap->missing_pages--;
+	}
 	return 0;
 }
 
-
 /* if page is completely empty, put it back on the free list, or dealloc it */
 /* if page was hijacked, unmark the flag so it might get alloced next time */
 /* Note: lock should be held when calling this */

@@ -183,26 +169,15 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
 	if (bitmap->bp[page].hijacked) { /* page was hijacked, undo this now */
 		bitmap->bp[page].hijacked = 0;
 		bitmap->bp[page].map = NULL;
-		return;
+	} else {
+		/* normal case, free the page */
+		ptr = bitmap->bp[page].map;
+		bitmap->bp[page].map = NULL;
+		bitmap->missing_pages++;
+		bitmap_free_page(bitmap, ptr);
 	}
-
-	/* normal case, free the page */
-
-#if 0
-/* actually ... let's not.  We will probably need the page again exactly when
- * memory is tight and we are flusing to disk
- */
-	return;
-#else
-	ptr = bitmap->bp[page].map;
-	bitmap->bp[page].map = NULL;
-	bitmap->missing_pages++;
-	bitmap_free_page(bitmap, ptr);
-	return;
-#endif
 }
 
-
 /*
  * bitmap file handling - read and write the bitmap file and its superblock
  */

@@ -220,11 +195,14 @@ static struct page *read_sb_page(mddev_t *mddev, loff_t offset,
 
 	mdk_rdev_t *rdev;
 	sector_t target;
+	int did_alloc = 0;
 
-	if (!page)
+	if (!page) {
 		page = alloc_page(GFP_KERNEL);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		did_alloc = 1;
+	}
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		if (! test_bit(In_sync, &rdev->flags)

@@ -242,6 +220,8 @@ static struct page *read_sb_page(mddev_t *mddev, loff_t offset,
 			return page;
 		}
 	}
+	if (did_alloc)
+		put_page(page);
 	return ERR_PTR(-EIO);
 
 }

@@ -286,49 +266,51 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 	mddev_t *mddev = bitmap->mddev;
 
 	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
-			int size = PAGE_SIZE;
-			loff_t offset = mddev->bitmap_info.offset;
-			if (page->index == bitmap->file_pages-1)
-				size = roundup(bitmap->last_page_size,
-					       bdev_logical_block_size(rdev->bdev));
-			/* Just make sure we aren't corrupting data or
-			 * metadata
-			 */
-			if (mddev->external) {
-				/* Bitmap could be anywhere. */
-				if (rdev->sb_start + offset + (page->index *(PAGE_SIZE/512)) >
-				    rdev->data_offset &&
-				    rdev->sb_start + offset < 
-				    rdev->data_offset + mddev->dev_sectors +
-				    (PAGE_SIZE/512))
-					goto bad_alignment;
-			} else if (offset < 0) {
-				/* DATA  BITMAP METADATA  */
-				if (offset
-				    + (long)(page->index * (PAGE_SIZE/512))
-				    + size/512 > 0)
-					/* bitmap runs in to metadata */
-					goto bad_alignment;
-				if (rdev->data_offset + mddev->dev_sectors
-				    > rdev->sb_start + offset)
-					/* data runs in to bitmap */
-					goto bad_alignment;
-			} else if (rdev->sb_start < rdev->data_offset) {
-				/* METADATA BITMAP DATA */
-				if (rdev->sb_start
-				    + offset
-				    + page->index*(PAGE_SIZE/512) + size/512
-				    > rdev->data_offset)
-					/* bitmap runs in to data */
-					goto bad_alignment;
-			} else {
-				/* DATA METADATA BITMAP - no problems */
-			}
-			md_super_write(mddev, rdev,
-				       rdev->sb_start + offset
-				       + page->index * (PAGE_SIZE/512),
-				       size,
-				       page);
+		int size = PAGE_SIZE;
+		loff_t offset = mddev->bitmap_info.offset;
+		if (page->index == bitmap->file_pages-1)
+			size = roundup(bitmap->last_page_size,
+				       bdev_logical_block_size(rdev->bdev));
+		/* Just make sure we aren't corrupting data or
+		 * metadata
+		 */
+		if (mddev->external) {
+			/* Bitmap could be anywhere. */
+			if (rdev->sb_start + offset + (page->index
+						       * (PAGE_SIZE/512))
+			    > rdev->data_offset
+			    &&
+			    rdev->sb_start + offset
+			    < (rdev->data_offset + mddev->dev_sectors
+			     + (PAGE_SIZE/512)))
+				goto bad_alignment;
+		} else if (offset < 0) {
+			/* DATA  BITMAP METADATA  */
+			if (offset
+			    + (long)(page->index * (PAGE_SIZE/512))
+			    + size/512 > 0)
+				/* bitmap runs in to metadata */
+				goto bad_alignment;
+			if (rdev->data_offset + mddev->dev_sectors
+			    > rdev->sb_start + offset)
+				/* data runs in to bitmap */
+				goto bad_alignment;
+		} else if (rdev->sb_start < rdev->data_offset) {
+			/* METADATA BITMAP DATA */
+			if (rdev->sb_start
+			    + offset
+			    + page->index*(PAGE_SIZE/512) + size/512
+			    > rdev->data_offset)
+				/* bitmap runs in to data */
+				goto bad_alignment;
+		} else {
+			/* DATA METADATA BITMAP - no problems */
+		}
+		md_super_write(mddev, rdev,
+			       rdev->sb_start + offset
+			       + page->index * (PAGE_SIZE/512),
+			       size,
+			       page);
 	}
 
 	if (wait)

@@ -364,10 +346,9 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
 			bh = bh->b_this_page;
 		}
 
-		if (wait) {
+		if (wait)
 			wait_event(bitmap->write_wait,
 				   atomic_read(&bitmap->pending_writes)==0);
-		}
 	}
 	if (bitmap->flags & BITMAP_WRITE_ERROR)
 		bitmap_file_kick(bitmap);

@@ -424,7 +405,7 @@ static struct page *read_page(struct file *file, unsigned long index,
 	struct buffer_head *bh;
 	sector_t block;
 
-	PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_SIZE,
+	PRINTK("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE,
 			(unsigned long long)index << PAGE_SHIFT);
 
 	page = alloc_page(GFP_KERNEL);

@@ -478,7 +459,7 @@ static struct page *read_page(struct file *file, unsigned long index,
 	}
 out:
 	if (IS_ERR(page))
-		printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n",
+		printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %ld\n",
 			(int)PAGE_SIZE,
 			(unsigned long long)index << PAGE_SHIFT,
 			PTR_ERR(page));

@@ -664,11 +645,14 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
 	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	old = le32_to_cpu(sb->state) & bits;
 	switch (op) {
-		case MASK_SET: sb->state |= cpu_to_le32(bits);
-				break;
-		case MASK_UNSET: sb->state &= cpu_to_le32(~bits);
-				break;
-		default: BUG();
+	case MASK_SET:
+		sb->state |= cpu_to_le32(bits);
+		break;
+	case MASK_UNSET:
+		sb->state &= cpu_to_le32(~bits);
+		break;
+	default:
+		BUG();
 	}
 	kunmap_atomic(sb, KM_USER0);
 	return old;

@@ -710,12 +694,12 @@ static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned lon
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
 					unsigned long chunk)
 {
-	if (file_page_index(bitmap, chunk) >= bitmap->file_pages) return NULL;
+	if (file_page_index(bitmap, chunk) >= bitmap->file_pages)
+		return NULL;
 	return bitmap->filemap[file_page_index(bitmap, chunk)
 			       - file_page_index(bitmap, 0)];
 }
 
-
 static void bitmap_file_unmap(struct bitmap *bitmap)
 {
 	struct page **map, *sb_page;

@@ -766,7 +750,6 @@ static void bitmap_file_put(struct bitmap *bitmap)
 	}
 }
 
-
 /*
  * bitmap_file_kick - if an error occurs while manipulating the bitmap file
  * then it is no longer reliable, so we stop using it and we mark the file

@@ -785,7 +768,6 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 				ptr = d_path(&bitmap->file->f_path, path,
 					     PAGE_SIZE);
 
-
 			printk(KERN_ALERT
 			      "%s: kicking failed bitmap file %s from array!\n",
 			      bmname(bitmap), IS_ERR(ptr) ? "" : ptr);

@@ -803,9 +785,9 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 }
 
 enum bitmap_page_attr {
-	BITMAP_PAGE_DIRTY = 0, // there are set bits that need to be synced
-	BITMAP_PAGE_CLEAN = 1, // there are bits that might need to be cleared
-	BITMAP_PAGE_NEEDWRITE=2, // there are cleared bits that need to be synced
+	BITMAP_PAGE_DIRTY = 0,     /* there are set bits that need to be synced */
+	BITMAP_PAGE_CLEAN = 1,     /* there are bits that might need to be cleared */
+	BITMAP_PAGE_NEEDWRITE = 2, /* there are cleared bits that need to be synced */
 };
 
 static inline void set_page_attr(struct bitmap *bitmap, struct page *page,

@@ -840,15 +822,15 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	void *kaddr;
 	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
 
-	if (!bitmap->filemap) {
+	if (!bitmap->filemap)
 		return;
-	}
 
 	page = filemap_get_page(bitmap, chunk);
-	if (!page) return;
+	if (!page)
+		return;
 	bit = file_page_offset(bitmap, chunk);
 
- 	/* set the bit */
+	/* set the bit */
 	kaddr = kmap_atomic(page, KM_USER0);
 	if (bitmap->flags & BITMAP_HOSTENDIAN)
 		set_bit(bit, kaddr);

@@ -859,7 +841,6 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 
 	/* record page number so it gets flushed to disk when unplug occurs */
 	set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
-
 }
 
 /* this gets called when the md device is ready to unplug its underlying

@@ -892,7 +873,7 @@ void bitmap_unplug(struct bitmap *bitmap)
 			wait = 1;
 		spin_unlock_irqrestore(&bitmap->lock, flags);
 
-		if (dirty | need_write)
+		if (dirty || need_write)
 			write_page(bitmap, page, 0);
 	}
 	if (wait) { /* if any writes were performed, we need to wait on them */

@@ -905,6 +886,7 @@ void bitmap_unplug(struct bitmap *bitmap)
 	if (bitmap->flags & BITMAP_WRITE_ERROR)
 		bitmap_file_kick(bitmap);
 }
+EXPORT_SYMBOL(bitmap_unplug);
 
 static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
 /* * bitmap_init_from_disk -- called at bitmap_create time to initialize

@@ -947,7 +929,6 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 	if (!bitmap->mddev->bitmap_info.external)
 		bytes += sizeof(bitmap_super_t);
 
-	
 	num_pages = (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
 
 	if (file && i_size_read(file->f_mapping->host) < bytes) {

@@ -966,7 +947,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 
 	/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
 	bitmap->filemap_attr = kzalloc(
-		roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
+		roundup(DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
 		GFP_KERNEL);
 	if (!bitmap->filemap_attr)
 		goto err;

@@ -1021,7 +1002,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 			if (outofdate) {
 				/*
 				 * if bitmap is out of date, dirty the
-			 	 * whole page and write it out
+				 * whole page and write it out
 				 */
 				paddr = kmap_atomic(page, KM_USER0);
 				memset(paddr + offset, 0xff,

@@ -1052,7 +1033,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 		}
 	}
 
- 	/* everything went OK */
+	/* everything went OK */
 	ret = 0;
 	bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);
 

@@ -1080,21 +1061,16 @@ void bitmap_write_all(struct bitmap *bitmap)
 	 */
 	int i;
 
-	for (i=0; i < bitmap->file_pages; i++)
+	for (i = 0; i < bitmap->file_pages; i++)
 		set_page_attr(bitmap, bitmap->filemap[i],
 			      BITMAP_PAGE_NEEDWRITE);
 }
 
-
 static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
 {
 	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	bitmap->bp[page].count += inc;
-/*
-	if (page == 0) printk("count page 0, offset %llu: %d gives %d\n",
-			      (unsigned long long)offset, inc, bitmap->bp[page].count);
-*/
 	bitmap_checkfree(bitmap, page);
 }
 static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,

@@ -1197,14 +1173,11 @@ void bitmap_daemon_work(mddev_t *mddev)
 					 (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
 					 &blocks, 0);
 		if (bmc) {
-/*
-  if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc);
-*/
 			if (*bmc)
 				bitmap->allclean = 0;
 
 			if (*bmc == 2) {
-				*bmc=1; /* maybe clear the bit next time */
+				*bmc = 1; /* maybe clear the bit next time */
 				set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 			} else if (*bmc == 1 && !bitmap->need_sync) {
 				/* we can clear the bit */

@@ -1243,7 +1216,7 @@ void bitmap_daemon_work(mddev_t *mddev)
 
  done:
 	if (bitmap->allclean == 0)
-		bitmap->mddev->thread->timeout = 
+		bitmap->mddev->thread->timeout =
 			bitmap->mddev->bitmap_info.daemon_sleep;
 	mutex_unlock(&mddev->bitmap_info.mutex);
 }

@@ -1265,7 +1238,7 @@ __acquires(bitmap->lock)
 
 	if (bitmap_checkpage(bitmap, page, create) < 0) {
 		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
-		*blocks = csize - (offset & (csize- 1));
+		*blocks = csize - (offset & (csize - 1));
 		return NULL;
 	}
 	/* now locked ... */

@@ -1276,12 +1249,12 @@ __acquires(bitmap->lock)
 		int hi = (pageoff > PAGE_COUNTER_MASK);
 		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
 					  PAGE_COUNTER_SHIFT - 1);
-		*blocks = csize - (offset & (csize- 1));
+		*blocks = csize - (offset & (csize - 1));
 		return  &((bitmap_counter_t *)
 			  &bitmap->bp[page].map)[hi];
 	} else { /* page is allocated */
 		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
-		*blocks = csize - (offset & (csize- 1));
+		*blocks = csize - (offset & (csize - 1));
 		return (bitmap_counter_t *)
 			&(bitmap->bp[page].map[pageoff]);
 	}

@@ -1289,7 +1262,8 @@ __acquires(bitmap->lock)
 
 int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
 {
-	if (!bitmap) return 0;
+	if (!bitmap)
+		return 0;
 
 	if (behind) {
 		int bw;

@@ -1328,10 +1302,10 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 			continue;
 		}
 
-		switch(*bmc) {
+		switch (*bmc) {
 		case 0:
 			bitmap_file_set_bit(bitmap, offset);
-			bitmap_count_page(bitmap,offset, 1);
+			bitmap_count_page(bitmap, offset, 1);
 			blk_plug_device_unlocked(bitmap->mddev->queue);
 			/* fall through */
 		case 1:

@@ -1345,16 +1319,19 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 		offset += blocks;
 		if (sectors > blocks)
 			sectors -= blocks;
-		else sectors = 0;
+		else
+			sectors = 0;
 	}
 	bitmap->allclean = 0;
 	return 0;
 }
+EXPORT_SYMBOL(bitmap_startwrite);
 
 void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
 		     int success, int behind)
 {
-	if (!bitmap) return;
+	if (!bitmap)
+		return;
 	if (behind) {
 		if (atomic_dec_and_test(&bitmap->behind_writes))
 			wake_up(&bitmap->behind_wait);

@@ -1391,18 +1368,20 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 			wake_up(&bitmap->overflow_wait);
 
 		(*bmc)--;
-		if (*bmc <= 2) {
+		if (*bmc <= 2)
 			set_page_attr(bitmap,
 				      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
 				      BITMAP_PAGE_CLEAN);
-		}
+
 		spin_unlock_irqrestore(&bitmap->lock, flags);
 		offset += blocks;
 		if (sectors > blocks)
 			sectors -= blocks;
-		else sectors = 0;
+		else
+			sectors = 0;
 	}
 }
+EXPORT_SYMBOL(bitmap_endwrite);
 
 static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
 			       int degraded)

@@ -1455,14 +1434,14 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
 	}
 	return rv;
 }
+EXPORT_SYMBOL(bitmap_start_sync);
 
 void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
 {
 	bitmap_counter_t *bmc;
 	unsigned long flags;
-/*
-	if (offset == 0) printk("bitmap_end_sync 0 (%d)\n", aborted);
-*/	if (bitmap == NULL) {
+
+	if (bitmap == NULL) {
 		*blocks = 1024;
 		return;
 	}

@@ -1471,26 +1450,23 @@ void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int ab
 	if (bmc == NULL)
 		goto unlock;
 	/* locked */
-/*
-	if (offset == 0) printk("bitmap_end sync found 0x%x, blocks %d\n", *bmc, *blocks);
-*/
 	if (RESYNC(*bmc)) {
 		*bmc &= ~RESYNC_MASK;
 
 		if (!NEEDED(*bmc) && aborted)
 			*bmc |= NEEDED_MASK;
 		else {
-			if (*bmc <= 2) {
+			if (*bmc <= 2)
 				set_page_attr(bitmap,
 					      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
 					      BITMAP_PAGE_CLEAN);
-			}
 		}
 	}
  unlock:
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 	bitmap->allclean = 0;
 }
+EXPORT_SYMBOL(bitmap_end_sync);
 
 void bitmap_close_sync(struct bitmap *bitmap)
 {

@@ -1507,6 +1483,7 @@ void bitmap_close_sync(struct bitmap *bitmap)
 		sector += blocks;
 	}
 }
+EXPORT_SYMBOL(bitmap_close_sync);
 
 void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 {

@@ -1537,6 +1514,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 	bitmap->last_end_sync = jiffies;
 	sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
 }
+EXPORT_SYMBOL(bitmap_cond_end_sync);
 
 static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
 {

@@ -1553,9 +1531,9 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
 		spin_unlock_irq(&bitmap->lock);
 		return;
 	}
-	if (! *bmc) {
+	if (!*bmc) {
 		struct page *page;
-		*bmc = 1 | (needed?NEEDED_MASK:0);
+		*bmc = 1 | (needed ? NEEDED_MASK : 0);
 		bitmap_count_page(bitmap, offset, 1);
 		page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
 		set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);

@@ -1720,9 +1698,9 @@ int bitmap_create(mddev_t *mddev)
 	bitmap->chunkshift = ffz(~mddev->bitmap_info.chunksize);
 
 	/* now that chunksize and chunkshift are set, we can use these macros */
- 	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
+	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
 			CHUNK_BLOCK_SHIFT(bitmap);
- 	pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
+	pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
 
 	BUG_ON(!pages);
 

@@ -1775,11 +1753,11 @@ static ssize_t
 location_show(mddev_t *mddev, char *page)
 {
 	ssize_t len;
-	if (mddev->bitmap_info.file) {
+	if (mddev->bitmap_info.file)
 		len = sprintf(page, "file");
-	} else if (mddev->bitmap_info.offset) {
+	else if (mddev->bitmap_info.offset)
 		len = sprintf(page, "%+lld", (long long)mddev->bitmap_info.offset);
-	} else
+	else
 		len = sprintf(page, "none");
 	len += sprintf(page+len, "\n");
 	return len;

@@ -1868,7 +1846,7 @@ timeout_show(mddev_t *mddev, char *page)
 	ssize_t len;
 	unsigned long secs = mddev->bitmap_info.daemon_sleep / HZ;
 	unsigned long jifs = mddev->bitmap_info.daemon_sleep % HZ;
-	
+
 	len = sprintf(page, "%lu", secs);
 	if (jifs)
 		len += sprintf(page+len, ".%03u", jiffies_to_msecs(jifs));

@@ -2050,12 +2028,3 @@ struct attribute_group md_bitmap_group = {
 	.attrs = md_bitmap_attrs,
 };
 
-
-/* the bitmap API -- for raid personalities */
-EXPORT_SYMBOL(bitmap_startwrite);
-EXPORT_SYMBOL(bitmap_endwrite);
-EXPORT_SYMBOL(bitmap_start_sync);
-EXPORT_SYMBOL(bitmap_end_sync);
-EXPORT_SYMBOL(bitmap_unplug);
-EXPORT_SYMBOL(bitmap_close_sync);
-EXPORT_SYMBOL(bitmap_cond_end_sync);

index 67fb32d..8af4d65 100644
@@ -1358,7 +1358,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 		    bitmap->events_cleared < bitmap->mddev->events) {
 			bitmap->events_cleared = bitmap->mddev->events;
 			bitmap->need_sync = 1;
-			sysfs_notify_dirent(bitmap->sysfs_can_clear);
+			sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
 		}
 
 		if (!success && ! (*bmc & NEEDED_MASK))

@@ -1643,7 +1643,7 @@ int bitmap_create(mddev_t *mddev)
 	struct file *file = mddev->bitmap_info.file;
 	int err;
 	sector_t start;
-	struct sysfs_dirent *bm;
+	struct sysfs_dirent *bm = NULL;
 
 	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
 

@@ -1664,7 +1664,8 @@ int bitmap_create(mddev_t *mddev)
 
 	bitmap->mddev = mddev;
 
-	bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap");
+	if (mddev->kobj.sd)
+		bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap");
 	if (bm) {
 		bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear");
 		sysfs_put(bm);

index 8af4d65..3f04699 100644
@@ -1296,7 +1296,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 			prepare_to_wait(&bitmap->overflow_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
 			spin_unlock_irq(&bitmap->lock);
-			blk_unplug(bitmap->mddev->queue);
+			md_unplug(bitmap->mddev);
 			schedule();
 			finish_wait(&bitmap->overflow_wait, &__wait);
 			continue;

@@ -1306,7 +1306,6 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 		case 0:
 			bitmap_file_set_bit(bitmap, offset);
 			bitmap_count_page(bitmap, offset, 1);
-			blk_plug_device_unlocked(bitmap->mddev->queue);
 			/* fall through */
 		case 1:
 			*bmc = 2;

index 21f3c35..f24efd2 100644
@@ -6600,7 +6600,7 @@ int md_allow_write(mddev_t *mddev)
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
-static void md_unplug(mddev_t *mddev)
+void md_unplug(mddev_t *mddev)
 {
 	if (mddev->queue)
 		blk_unplug(mddev->queue);

index 6f2c568..a97e4b0 100644
@@ -506,6 +506,7 @@ extern int md_integrity_register(mddev_t *mddev);
 extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 extern void restore_bitmap_write_access(struct file *file);
+extern void md_unplug(mddev_t *mddev);
 
 extern void mddev_init(mddev_t *mddev);
 extern int md_run(mddev_t *mddev);

index 3f04699..29a3c86 100644
@@ -1235,29 +1235,32 @@ __acquires(bitmap->lock)
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
 	sector_t csize;
+	int err;
+
+	err = bitmap_checkpage(bitmap, page, create);
 
-	if (bitmap_checkpage(bitmap, page, create) < 0) {
+	if (bitmap->bp[page].hijacked ||
+	    bitmap->bp[page].map == NULL)
+		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
+					  PAGE_COUNTER_SHIFT - 1);
+	else
 		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
-		*blocks = csize - (offset & (csize - 1));
+	*blocks = csize - (offset & (csize - 1));
+
+	if (err < 0)
 		return NULL;
-	}
+
 	/* now locked ... */
 
 	if (bitmap->bp[page].hijacked) { /* hijacked pointer */
 		/* should we use the first or second counter field
 		 * of the hijacked pointer? */
 		int hi = (pageoff > PAGE_COUNTER_MASK);
-		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
-					  PAGE_COUNTER_SHIFT - 1);
-		*blocks = csize - (offset & (csize - 1));
 		return  &((bitmap_counter_t *)
 			  &bitmap->bp[page].map)[hi];
-	} else { /* page is allocated */
-		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
-		*blocks = csize - (offset & (csize - 1));
+	} else /* page is allocated */
 		return (bitmap_counter_t *)
 			&(bitmap->bp[page].map[pageoff]);
-	}
 }
 
 int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)

index 1ed0094..935a49b 100644
@@ -94,7 +94,7 @@ retry:
 	return -ESRCH;
 }
 
-static int build_constructor_string(struct dm_target *ti,
+static int build_constructor_string(sector_t log_size,
 				    unsigned argc, char **argv,
 				    char **ctr_str)
 {

@@ -114,7 +114,7 @@ static int build_constructor_string(struct dm_target *ti,
 		return -ENOMEM;
 	}
 
-	str_size = sprintf(str, "%llu", (unsigned long long)ti->len);
+	str_size = sprintf(str, "%llu", (unsigned long long)log_size);
 	for (i = 0; i < argc; i++)
 		str_size += sprintf(str + str_size, " %s", argv[i]);
 

@@ -136,6 +136,7 @@ static int build_constructor_string(struct dm_target *ti,
  * else.
  */
 static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+			 sector_t log_size,
 			 unsigned argc, char **argv)
 {
 	int r = 0;

@@ -171,7 +172,9 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	spin_lock_init(&lc->flush_lock);
 	INIT_LIST_HEAD(&lc->flush_list);
 
-	str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str);
+	str_size = build_constructor_string(log_size,
+					    argc - 1, argv + 1,
+					    &ctr_str);
 	if (str_size < 0) {
 		kfree(lc);
 		return str_size;

@@ -197,7 +200,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	}
 
 	lc->region_size = (uint32_t)rdata;
-	lc->region_count = dm_sector_div_up(ti->len, lc->region_size);
+	lc->region_count = dm_sector_div_up(log_size, lc->region_size);
 
 out:
 	if (r) {

index 5a08be0..a232c14 100644
@@ -146,6 +146,7 @@ EXPORT_SYMBOL(dm_dirty_log_type_unregister);
 
 struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
 			struct dm_target *ti,
+			sector_t log_size,
 			int (*flush_callback_fn)(struct dm_target *ti),
 			unsigned int argc, char **argv)
 {

@@ -164,7 +165,7 @@ struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
 
 	log->flush_callback_fn = flush_callback_fn;
 	log->type = type;
-	if (type->ctr(log, ti, argc, argv)) {
+	if (type->ctr(log, ti, log_size, argc, argv)) {
 		kfree(log);
 		put_type(type);
 		return NULL;

@@ -335,9 +336,9 @@ static int read_header(struct log_c *log)
 	return 0;
 }
 
-static int _check_region_size(struct dm_target *ti, uint32_t region_size)
+static int _check_region_size(sector_t log_size, uint32_t region_size)
 {
-	if (region_size < 2 || region_size > ti->len)
+	if (region_size < 2 || region_size > log_size)
 		return 0;
 
 	if (!is_power_of_2(region_size))

@@ -353,6 +354,7 @@ static int _check_region_size(struct dm_target *ti, uint32_t region_size)
  *--------------------------------------------------------------*/
 #define BYTE_SHIFT 3
 static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
+			      sector_t log_size,
 			      unsigned int argc, char **argv,
 			      struct dm_dev *dev)
 {

@@ -382,12 +384,12 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 	}
 
 	if (sscanf(argv[0], "%u", &region_size) != 1 ||
-	    !_check_region_size(ti, region_size)) {
+	    !_check_region_size(log_size, region_size)) {
 		DMWARN("invalid region size %s", argv[0]);
 		return -EINVAL;
 	}
 
-	region_count = dm_sector_div_up(ti->len, region_size);
+	region_count = dm_sector_div_up(log_size, region_size);
 
 	lc = kmalloc(sizeof(*lc), GFP_KERNEL);
 	if (!lc) {

@@ -507,9 +509,10 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 }
 
 static int core_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+		    sector_t log_size,
 		    unsigned int argc, char **argv)
 {
-	return create_log_context(log, ti, argc, argv, NULL);
+	return create_log_context(log, ti, log_size, argc, argv, NULL);
 }
 
 static void destroy_log_context(struct log_c *lc)

@@ -533,6 +536,7 @@ static void core_dtr(struct dm_dirty_log *log)
  * argv contains log_device region_size followed optionally by [no]sync
  *--------------------------------------------------------------*/
 static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+		    sector_t log_size,
 		    unsigned int argc, char **argv)
 {
 	int r;

@@ -547,7 +551,7 @@ static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	if (r)
 		return r;
 
-	r = create_log_context(log, ti, argc - 1, argv + 1, dev);
+	r = create_log_context(log, ti, log_size, argc - 1, argv + 1, dev);
 	if (r) {
 		dm_put_device(ti, dev);
 		return r;

index ddda531..ea732fc 100644
@@ -968,8 +968,8 @@ static struct dm_dirty_log *create_dirty_log(struct dm_target *ti,
 		return NULL;
 	}
 
-	dl = dm_dirty_log_create(argv[0], ti, mirror_flush, param_count,
-				 argv + 2);
+	dl = dm_dirty_log_create(argv[0], ti, ti->len, mirror_flush,
+				 param_count, argv + 2);
 	if (!dl) {
 		ti->error = "Error creating mirror dirty log";
 		return NULL;

index 7084503..641419f 100644
@@ -33,6 +33,7 @@ struct dm_dirty_log_type {
 	struct list_head list;
 
 	int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti,
+		   sector_t log_size,
 		   unsigned argc, char **argv);
 	void (*dtr)(struct dm_dirty_log *log);
 

@@ -137,7 +138,7 @@ int dm_dirty_log_type_unregister(struct dm_dirty_log_type *type);
  * type->constructor/destructor() directly.
  */
 struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
-			struct dm_target *ti,
+			struct dm_target *ti, sector_t log_size,
 			int (*flush_callback_fn)(struct dm_target *ti),
 			unsigned argc, char **argv);
 void dm_dirty_log_destroy(struct dm_dirty_log *log);

index a232c14..5a08be0 100644
@@ -146,7 +146,6 @@ EXPORT_SYMBOL(dm_dirty_log_type_unregister);
 
 struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
 			struct dm_target *ti,
-			sector_t log_size,
 			int (*flush_callback_fn)(struct dm_target *ti),
 			unsigned int argc, char **argv)
 {

@@ -165,7 +164,7 @@ struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
 
 	log->flush_callback_fn = flush_callback_fn;
 	log->type = type;
-	if (type->ctr(log, ti, log_size, argc, argv)) {
+	if (type->ctr(log, ti, argc, argv)) {
 		kfree(log);
 		put_type(type);
 		return NULL;

@@ -336,9 +335,9 @@ static int read_header(struct log_c *log)
 	return 0;
 }
 
-static int _check_region_size(sector_t log_size, uint32_t region_size)
+static int _check_region_size(struct dm_target *ti, uint32_t region_size)
 {
-	if (region_size < 2 || region_size > log_size)
+	if (region_size < 2 || region_size > ti->len)
 		return 0;
 
 	if (!is_power_of_2(region_size))

@@ -354,7 +353,6 @@ static int _check_region_size(sector_t log_size, uint32_t region_size)
  *--------------------------------------------------------------*/
 #define BYTE_SHIFT 3
 static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
-			      sector_t log_size,
 			      unsigned int argc, char **argv,
 			      struct dm_dev *dev)
 {

@@ -384,12 +382,12 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 	}
 
 	if (sscanf(argv[0], "%u", &region_size) != 1 ||
-	    !_check_region_size(log_size, region_size)) {
+	    !_check_region_size(ti, region_size)) {
 		DMWARN("invalid region size %s", argv[0]);
 		return -EINVAL;
 	}
 
-	region_count = dm_sector_div_up(log_size, region_size);
+	region_count = dm_sector_div_up(ti->len, region_size);
 
 	lc = kmalloc(sizeof(*lc), GFP_KERNEL);
 	if (!lc) {

@@ -509,10 +507,9 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 }
 
 static int core_ctr(struct dm_dirty_log *log, struct dm_target *ti,
-		    sector_t log_size,
 		    unsigned int argc, char **argv)
 {
-	return create_log_context(log, ti, log_size, argc, argv, NULL);
+	return create_log_context(log, ti, argc, argv, NULL);
 }
 
 static void destroy_log_context(struct log_c *lc)

@@ -536,7 +533,6 @@ static void core_dtr(struct dm_dirty_log *log)
  * argv contains log_device region_size followed optionally by [no]sync
  *--------------------------------------------------------------*/
 static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti,
-		    sector_t log_size,
 		    unsigned int argc, char **argv)
 {
 	int r;

@@ -551,7 +547,7 @@ static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	if (r)
 		return r;
 
-	r = create_log_context(log, ti, log_size, argc - 1, argv + 1, dev);
+	r = create_log_context(log, ti, argc - 1, argv + 1, dev);
 	if (r) {
 		dm_put_device(ti, dev);
 		return r;

index ea732fc..ddda531 100644
@@ -968,8 +968,8 @@ static struct dm_dirty_log *create_dirty_log(struct dm_target *ti,
 		return NULL;
 	}
 
-	dl = dm_dirty_log_create(argv[0], ti, ti->len, mirror_flush,
-				 param_count, argv + 2);
+	dl = dm_dirty_log_create(argv[0], ti, mirror_flush, param_count,
+				 argv + 2);
 	if (!dl) {
 		ti->error = "Error creating mirror dirty log";
 		return NULL;

index 3dcbc4a..33d2be8 100644
@@ -192,7 +192,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	int recovery = 1;
 	long raid_devs;
 	long rebuildA, rebuildB;
-	sector_t sectors_per_dev, chunks;
+	sector_t sectors_per_dev, chunks, ti_len_sav;
 	struct raid_set *rs = NULL;
 	int in_sync, i;
 	struct dm_dirty_log *log = NULL;

@@ -281,8 +281,10 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (sector_div(chunks, chunk_size))
 		goto err;
 
-	log = dm_dirty_log_create(log_argv[0], ti, sectors_per_dev,
-				  NULL, log_cnt, log_argv+2);
+	ti_len_sav = ti->len;
+	ti->len = sectors_per_dev;
+	log = dm_dirty_log_create(log_argv[0], ti, NULL, log_cnt, log_argv+2);
+	ti->len = ti_len_sav;
 	err = "Error creating dirty log";
 	if (!log)
 		goto err;

index 641419f..7084503 100644
@@ -33,7 +33,6 @@ struct dm_dirty_log_type {
 	struct list_head list;
 
 	int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti,
-		   sector_t log_size,
 		   unsigned argc, char **argv);
 	void (*dtr)(struct dm_dirty_log *log);
 

@@ -138,7 +137,7 @@ int dm_dirty_log_type_unregister(struct dm_dirty_log_type *type);
  * type->constructor/destructor() directly.
  */
 struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
-			struct dm_target *ti, sector_t log_size,
+			struct dm_target *ti,
 			int (*flush_callback_fn)(struct dm_target *ti),
 			unsigned argc, char **argv);
 void dm_dirty_log_destroy(struct dm_dirty_log *log);

index 29a3c86..9376526 100644
@@ -29,6 +29,7 @@
 #include "md.h"
 #include "bitmap.h"
 
+#include <linux/dm-dirty-log.h>
 /* debug macros */
 
 #define DEBUG 0

@@ -694,6 +695,8 @@ static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned lon
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
 					unsigned long chunk)
 {
+	if (bitmap->filemap == NULL)
+		return NULL;
 	if (file_page_index(bitmap, chunk) >= bitmap->file_pages)
 		return NULL;
 	return bitmap->filemap[file_page_index(bitmap, chunk)

@@ -793,19 +796,28 @@ enum bitmap_page_attr {
 static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
 				enum bitmap_page_attr attr)
 {
-	__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	if (page)
+		__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	else
+		__set_bit(attr, &bitmap->logattrs);
 }
 
 static inline void clear_page_attr(struct bitmap *bitmap, struct page *page,
 				enum bitmap_page_attr attr)
 {
-	__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	if (page)
+		__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	else
+		__clear_bit(attr, &bitmap->logattrs);
 }
 
 static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page,
 					   enum bitmap_page_attr attr)
 {
-	return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	if (page)
+		return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	else
+		return test_bit(attr, &bitmap->logattrs);
 }
 
 /*

@@ -818,27 +830,30 @@ static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *p
 static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 {
 	unsigned long bit;
-	struct page *page;
+	struct page *page = NULL;
 	void *kaddr;
 	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
 
-	if (!bitmap->filemap)
-		return;
-
-	page = filemap_get_page(bitmap, chunk);
-	if (!page)
-		return;
-	bit = file_page_offset(bitmap, chunk);
+	if (!bitmap->filemap) {
+		struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
+		if (log)
+			log->type->mark_region(log, chunk);
+	} else {
 
-	/* set the bit */
-	kaddr = kmap_atomic(page, KM_USER0);
-	if (bitmap->flags & BITMAP_HOSTENDIAN)
-		set_bit(bit, kaddr);
-	else
-		ext2_set_bit(bit, kaddr);
-	kunmap_atomic(kaddr, KM_USER0);
-	PRINTK("set file bit %lu page %lu\n", bit, page->index);
+		page = filemap_get_page(bitmap, chunk);
+		if (!page)
+			return;
+		bit = file_page_offset(bitmap, chunk);
 
+		/* set the bit */
+		kaddr = kmap_atomic(page, KM_USER0);
+		if (bitmap->flags & BITMAP_HOSTENDIAN)
+			set_bit(bit, kaddr);
+		else
+			ext2_set_bit(bit, kaddr);
+		kunmap_atomic(kaddr, KM_USER0);
+		PRINTK("set file bit %lu page %lu\n", bit, page->index);
+	}
 	/* record page number so it gets flushed to disk when unplug occurs */
 	set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
 }