Introduction

diff ./drivers/md/md.c~current~ ./drivers/md/md.c
@@ -181,7 +181,7 @@ static void mddev_put(mddev_t *mddev)
 	if (!mddev->raid_disks && list_empty(&mddev->disks)) {
 		list_del(&mddev->all_mddevs);
 		blk_put_queue(mddev->queue);
-		kfree(mddev);
+		kobject_unregister(&mddev->kobj);
 	}
 	spin_unlock(&all_mddevs_lock);
 }

@@ -1551,6 +1551,85 @@ static void analyze_sbs(mddev_t * mddev)
 
 }
 
+struct md_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(mddev_t *, char *);
+	ssize_t (*store)(mddev_t *, const char *, size_t);
+};
+
+static ssize_t
+md_show_level(mddev_t *mddev, char *page)
+{
+	mdk_personality_t *p = mddev->pers;
+	if (p == NULL)
+		return 0;
+	if (mddev->level >= 0)
+		return sprintf(page, "RAID-%d\n", mddev->level);
+	else
+		return sprintf(page, "%s\n", p->name);
+}
+
+static struct md_sysfs_entry md_level = {
+	.attr = {.name = "level", .mode = S_IRUGO },
+	.show = md_show_level,
+};
+
+static ssize_t
+md_show_rdisks(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%d\n", mddev->raid_disks);
+}
+
+static struct md_sysfs_entry md_raid_disks = {
+	.attr = {.name = "raid_disks", .mode = S_IRUGO },
+	.show = md_show_rdisks,
+};
+
+static struct attribute *md_default_attrs[] = {
+	&md_level.attr,
+	&md_raid_disks.attr,
+	NULL,
+};
+
+static ssize_t
+md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
+	mddev_t *mddev = container_of(kobj, struct mddev_s, kobj);
+
+	if (!entry->show)
+		return -EIO;
+	return entry->show(mddev, page);
+}
+
+static ssize_t
+md_attr_store(struct kobject *kobj, struct attribute *attr,
+	      const char *page, size_t length)
+{
+	struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
+	mddev_t *mddev = container_of(kobj, struct mddev_s, kobj);
+
+	if (!entry->store)
+		return -EIO;
+	return entry->store(mddev, page, length);
+}
+
+static void md_free(struct kobject *ko)
+{
+	mddev_t *mddev = container_of(ko, mddev_t, kobj);
+	kfree(mddev);
+}
+
+static struct sysfs_ops md_sysfs_ops = {
+	.show	= md_attr_show,
+	.store	= md_attr_store,
+};
+static struct kobj_type md_ktype = {
+	.release	= md_free,
+	.sysfs_ops	= &md_sysfs_ops,
+	.default_attrs	= md_default_attrs,
+};
+
 int mdp_major = 0;
 
 static struct kobject *md_probe(dev_t dev, int *part, void *data)

@@ -1592,6 +1671,11 @@ static struct kobject *md_probe(dev_t de
 	add_disk(disk);
 	mddev->gendisk = disk;
 	up(&disks_sem);
+	mddev->kobj.parent = kobject_get(&disk->kobj);
+	mddev->kobj.k_name = NULL;
+	snprintf(mddev->kobj.name, KOBJ_NAME_LEN, "%s", "md");
+	mddev->kobj.ktype = &md_ktype;
+	kobject_register(&mddev->kobj);
 	return NULL;
 }
 

diff ./include/linux/raid/md_k.h~current~ ./include/linux/raid/md_k.h
@@ -148,6 +148,8 @@ struct mddev_s
 
 	struct gendisk			*gendisk;
 
+	struct kobject			kobj;
+
 	/* Superblock information */
 	int				major_version,
 					minor_version,

diff ./drivers/md/md.c~current~ ./drivers/md/md.c
@@ -711,6 +711,7 @@ static void super_90_sync(mddev_t *mddev
 	 */
 	int i;
 	int active=0, working=0,failed=0,spare=0,nr_disks=0;
+	unsigned int fixdesc=0;
 
 	rdev->sb_size = MD_SB_BYTES;
 

@@ -758,16 +759,28 @@ static void super_90_sync(mddev_t *mddev
 	sb->disks[0].state = (1<<MD_DISK_REMOVED);
 	ITERATE_RDEV(mddev,rdev2,tmp) {
 		mdp_disk_t *d;
+		int desc_nr;
 		if (rdev2->raid_disk >= 0 && rdev2->in_sync && !rdev2->faulty)
-			rdev2->desc_nr = rdev2->raid_disk;
+			desc_nr = rdev2->raid_disk;
 		else
-			rdev2->desc_nr = next_spare++;
+			desc_nr = next_spare++;
+		if (desc_nr != rdev2->desc_nr) {
+			fixdesc |= (1 << desc_nr);
+			rdev2->desc_nr = desc_nr;
+			if (rdev2->raid_disk >= 0) {
+				char nm[20];
+				sprintf(nm, "rd%d", rdev2->raid_disk);
+				sysfs_remove_link(&mddev->kobj, nm);
+			}
+			sysfs_remove_link(&rdev2->kobj, "block");
+			kobject_del(&rdev2->kobj);
+		}
 		d = &sb->disks[rdev2->desc_nr];
 		nr_disks++;
 		d->number = rdev2->desc_nr;
 		d->major = MAJOR(rdev2->bdev->bd_dev);
 		d->minor = MINOR(rdev2->bdev->bd_dev);
-		if (rdev2->raid_disk >= 0 && rdev->in_sync && !rdev2->faulty)
+		if (rdev2->raid_disk >= 0 && rdev2->in_sync && !rdev2->faulty)
 			d->raid_disk = rdev2->raid_disk;
 		else
 			d->raid_disk = rdev2->desc_nr; /* compatibility */

@@ -787,7 +800,22 @@ static void super_90_sync(mddev_t *mddev
 		if (test_bit(WriteMostly, &rdev2->flags))
 			d->state |= (1<<MD_DISK_WRITEMOSTLY);
 	}
-	
+	if (fixdesc)
+		ITERATE_RDEV(mddev,rdev2,tmp)
+			if (fixdesc & (1<<rdev2->desc_nr)) {
+				snprintf(rdev2->kobj.name, KOBJ_NAME_LEN, "dev%d",
+					 rdev2->desc_nr);
+				kobject_add(&rdev2->kobj);
+				sysfs_create_link(&rdev2->kobj,
+						  &rdev2->bdev->bd_disk->kobj,
+						  "block");
+				if (rdev2->raid_disk >= 0) {
+					char nm[20];
+					sprintf(nm, "rd%d", rdev2->raid_disk);
+					sysfs_create_link(&mddev->kobj,
+							  &rdev2->kobj, nm);
+				}
+			}
 	/* now set the "removed" and "faulty" bits on any missing devices */
 	for (i=0 ; i < mddev->raid_disks ; i++) {
 		mdp_disk_t *d = &sb->disks[i];

@@ -1147,6 +1175,13 @@ static int bind_rdev_to_array(mdk_rdev_t
 	list_add(&rdev->same_set, &mddev->disks);
 	rdev->mddev = mddev;
 	printk(KERN_INFO "md: bind<%s>\n", bdevname(rdev->bdev,b));
+
+	rdev->kobj.k_name = NULL;
+	snprintf(rdev->kobj.name, KOBJ_NAME_LEN, "dev%d", rdev->desc_nr);
+	rdev->kobj.parent = kobject_get(&mddev->kobj);
+	kobject_add(&rdev->kobj);
+
+	sysfs_create_link(&rdev->kobj, &rdev->bdev->bd_disk->kobj, "block");
 	return 0;
 }
 

@@ -1160,6 +1195,8 @@ static void unbind_rdev_from_array(mdk_r
 	list_del_init(&rdev->same_set);
 	printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
 	rdev->mddev = NULL;
+	sysfs_remove_link(&rdev->kobj, "block");
+	kobject_del(&rdev->kobj);
 }
 
 /*

@@ -1215,7 +1252,7 @@ static void export_rdev(mdk_rdev_t * rde
 	md_autodetect_dev(rdev->bdev->bd_dev);
 #endif
 	unlock_rdev(rdev);
-	kfree(rdev);
+	kobject_put(&rdev->kobj);
 }
 
 static void kick_rdev_from_array(mdk_rdev_t * rdev)

@@ -1414,6 +1451,94 @@ repeat:
 
 }
 
+struct rdev_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(mdk_rdev_t *, char *);
+	ssize_t (*store)(mdk_rdev_t *, const char *, size_t);
+};
+
+static ssize_t
+rdev_show_state(mdk_rdev_t *rdev, char *page)
+{
+	char *sep = "";
+	int len=0;
+
+	if (rdev->faulty) {
+		len+= sprintf(page+len, "%sfaulty",sep);
+		sep = ",";
+	}
+	if (rdev->in_sync) {
+		len += sprintf(page+len, "%sin_sync",sep);
+		sep = ",";
+	}
+	if (!rdev->faulty && !rdev->in_sync) {
+		len += sprintf(page+len, "%sspare", sep);
+		sep = ",";
+	}
+	return len+sprintf(page+len, "\n");
+}
+
+static struct rdev_sysfs_entry rdev_state = {
+	.attr = {.name = "state", .mode = S_IRUGO },
+	.show = rdev_show_state,
+};
+
+static ssize_t
+rdev_show_super(mdk_rdev_t *rdev, char *page)
+{
+	if (rdev->sb_loaded && rdev->sb_size) {
+		memcpy(page, page_address(rdev->sb_page), rdev->sb_size);
+		return rdev->sb_size;
+	} else
+		return 0;
+}
+static struct rdev_sysfs_entry rdev_super = {
+	.attr = {.name = "super", .mode = S_IRUGO },
+	.show = rdev_show_super,
+};
+static struct attribute *rdev_default_attrs[] = {
+	&rdev_state.attr,
+	&rdev_super.attr,
+	NULL,
+};
+static ssize_t
+rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
+	mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);
+
+	if (!entry->show)
+		return -EIO;
+	return entry->show(rdev, page);
+}
+
+static ssize_t
+rdev_attr_store(struct kobject *kobj, struct attribute *attr,
+	      const char *page, size_t length)
+{
+	struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
+	mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj);
+
+	if (!entry->store)
+		return -EIO;
+	return entry->store(rdev, page, length);
+}
+
+static void rdev_free(struct kobject *ko)
+{
+	mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj);
+	kfree(rdev);
+}
+static struct sysfs_ops rdev_sysfs_ops = {
+	.show		= rdev_attr_show,
+	.store		= rdev_attr_store,
+};
+static struct kobj_type rdev_ktype = {
+	.release	= rdev_free,
+	.sysfs_ops	= &rdev_sysfs_ops,
+	.default_attrs	= rdev_default_attrs,
+};
+
 /*
  * Import a device. If 'super_format' >= 0, then sanity check the superblock
  *

@@ -1445,6 +1570,10 @@ static mdk_rdev_t *md_import_device(dev_
 	if (err)
 		goto abort_free;
 
+	rdev->kobj.parent = NULL;
+	rdev->kobj.ktype = &rdev_ktype;
+	kobject_init(&rdev->kobj);
+
 	rdev->desc_nr = -1;
 	rdev->faulty = 0;
 	rdev->in_sync = 0;

@@ -1820,6 +1949,13 @@ static int do_md_run(mddev_t * mddev)
 	mddev->safemode_timer.data = (unsigned long) mddev;
 	mddev->safemode_delay = (20 * HZ)/1000 +1; /* 20 msec delay */
 	mddev->in_sync = 1;
+
+	ITERATE_RDEV(mddev,rdev,tmp)
+		if (rdev->raid_disk >= 0) {
+			char nm[20];
+			sprintf(nm, "rd%d", rdev->raid_disk);
+			sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+		}
 	
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);

@@ -1941,9 +2077,18 @@ static int do_md_stop(mddev_t * mddev, i
 	 * Free resources if final stop
 	 */
 	if (!ro) {
+		mdk_rdev_t *rdev;
+		struct list_head *tmp;
 		struct gendisk *disk;
 		printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
 
+		ITERATE_RDEV(mddev,rdev,tmp)
+			if (rdev->raid_disk >= 0) {
+				char nm[20];
+				sprintf(nm, "rd%d", rdev->raid_disk);
+				sysfs_remove_link(&mddev->kobj, nm);
+			}
+
 		export_array(mddev);
 
 		mddev->array_size = 0;

@@ -3958,17 +4103,24 @@ void md_check_recovery(mddev_t *mddev)
 			if (rdev->raid_disk >= 0 &&
 			    (rdev->faulty || ! rdev->in_sync) &&
 			    atomic_read(&rdev->nr_pending)==0) {
-				if (mddev->pers->hot_remove_disk(mddev, rdev->raid_disk)==0)
+				if (mddev->pers->hot_remove_disk(mddev, rdev->raid_disk)==0) {
+					char nm[20];
+					sprintf(nm,"rd%d", rdev->raid_disk);
+					sysfs_remove_link(&mddev->kobj, nm);
 					rdev->raid_disk = -1;
+				}
 			}
 
 		if (mddev->degraded) {
 			ITERATE_RDEV(mddev,rdev,rtmp)
 				if (rdev->raid_disk < 0
 				    && !rdev->faulty) {
-					if (mddev->pers->hot_add_disk(mddev,rdev))
+					if (mddev->pers->hot_add_disk(mddev,rdev)) {
+						char nm[20];
+						sprintf(nm, "rd%d", rdev->raid_disk);
+						sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
 						spares++;
-					else
+					} else
 						break;
 				}
 		}

diff ./include/linux/raid/md_k.h~current~ ./include/linux/raid/md_k.h
@@ -105,6 +105,8 @@ struct mdk_rdev_s
 	int		sb_size;	/* bytes in the superblock */
 	int		preferred_minor;	/* autorun support */
 
+	struct kobject	kobj;
+
 	/* A device can be in one of three states based on two flags:
 	 * Not working:   faulty==1 in_sync==0
 	 * Fully working: faulty==0 in_sync==1

diff ./drivers/md/raid5.c~current~ ./drivers/md/raid5.c
@@ -293,9 +293,31 @@ static struct stripe_head *get_active_st
 	return sh;
 }
 
-static int grow_stripes(raid5_conf_t *conf, int num)
+static int grow_one_stripe(raid5_conf_t *conf)
 {
 	struct stripe_head *sh;
+	sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
+	if (!sh)
+		return 0;
+	memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev));
+	sh->raid_conf = conf;
+	spin_lock_init(&sh->lock);
+
+	if (grow_buffers(sh, conf->raid_disks)) {
+		shrink_buffers(sh, conf->raid_disks);
+		kmem_cache_free(conf->slab_cache, sh);
+		return 0;
+	}
+	/* we just created an active stripe so... */
+	atomic_set(&sh->count, 1);
+	atomic_inc(&conf->active_stripes);
+	INIT_LIST_HEAD(&sh->lru);
+	release_stripe(sh);
+	return 1;
+}
+
+static int grow_stripes(raid5_conf_t *conf, int num)
+{
 	kmem_cache_t *sc;
 	int devs = conf->raid_disks;
 

@@ -308,43 +330,34 @@ static int grow_stripes(raid5_conf_t *co
 		return 1;
 	conf->slab_cache = sc;
 	while (num--) {
-		sh = kmem_cache_alloc(sc, GFP_KERNEL);
-		if (!sh)
+		if (!grow_one_stripe(conf))
 			return 1;
-		memset(sh, 0, sizeof(*sh) + (devs-1)*sizeof(struct r5dev));
-		sh->raid_conf = conf;
-		spin_lock_init(&sh->lock);
-
-		if (grow_buffers(sh, conf->raid_disks)) {
-			shrink_buffers(sh, conf->raid_disks);
-			kmem_cache_free(sc, sh);
-			return 1;
-		}
-		/* we just created an active stripe so... */
-		atomic_set(&sh->count, 1);
-		atomic_inc(&conf->active_stripes);
-		INIT_LIST_HEAD(&sh->lru);
-		release_stripe(sh);
 	}
 	return 0;
 }
 
-static void shrink_stripes(raid5_conf_t *conf)
+static int drop_one_stripe(raid5_conf_t *conf)
 {
 	struct stripe_head *sh;
 
-	while (1) {
-		spin_lock_irq(&conf->device_lock);
-		sh = get_free_stripe(conf);
-		spin_unlock_irq(&conf->device_lock);
-		if (!sh)
-			break;
-		if (atomic_read(&sh->count))
-			BUG();
-		shrink_buffers(sh, conf->raid_disks);
-		kmem_cache_free(conf->slab_cache, sh);
-		atomic_dec(&conf->active_stripes);
-	}
+	spin_lock_irq(&conf->device_lock);
+	sh = get_free_stripe(conf);
+	spin_unlock_irq(&conf->device_lock);
+	if (!sh)
+		return 0;
+	if (atomic_read(&sh->count))
+		BUG();
+	shrink_buffers(sh, conf->raid_disks);
+	kmem_cache_free(conf->slab_cache, sh);
+	atomic_dec(&conf->active_stripes);
+	return 1;
+}
+
+static void shrink_stripes(raid5_conf_t *conf)
+{
+	while (drop_one_stripe(conf))
+		;
+
 	kmem_cache_destroy(conf->slab_cache);
 	conf->slab_cache = NULL;
 }

@@ -1718,6 +1731,108 @@ static void raid5d (mddev_t *mddev)
 	PRINTK("--- raid5d inactive\n");
 }
 
+struct raid5_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(raid5_conf_t *, char *);
+	ssize_t (*store)(raid5_conf_t *, const char *, ssize_t);
+};
+
+static ssize_t
+raid5_show_stripe_cache_size(raid5_conf_t *conf, char *page)
+{
+	return sprintf(page, "%d\n", conf->max_nr_stripes);
+}
+
+static ssize_t
+raid5_store_stripe_cache_size(raid5_conf_t *conf, const char *page, ssize_t len)
+{
+	char *end;
+	int new;
+	if (len >= PAGE_SIZE)
+		return -EINVAL;
+
+	new = simple_strtoul(page, &end, 10);
+	if (!*page || (*end && *end != '\n') )
+		return -EINVAL;
+	if (new <= 16 || new > 32768)
+		return -EINVAL;
+	while (new < conf->max_nr_stripes) {
+		if (drop_one_stripe(conf))
+			conf->max_nr_stripes--;
+		else
+			break;
+	}
+	while (new > conf->max_nr_stripes) {
+		if (grow_one_stripe(conf))
+			conf->max_nr_stripes++;
+		else break;
+	}
+	return len;
+}
+static struct raid5_sysfs_entry raid5_stripecache_size = {
+	.attr = {.name = "stripe_cache_size", .mode = S_IRUGO | S_IWUSR },
+	.show = raid5_show_stripe_cache_size,
+	.store = raid5_store_stripe_cache_size,
+};
+
+static ssize_t
+raid5_show_stripe_cache_active(raid5_conf_t *conf, char *page)
+{
+	return sprintf(page, "%d\n", atomic_read(&conf->active_stripes));
+}
+
+static struct raid5_sysfs_entry raid5_stripecache_active = {
+	.attr = {.name = "stripe_cache_active", .mode = S_IRUGO},
+	.show = raid5_show_stripe_cache_active,
+};
+
+static struct attribute *raid5_default_attrs[] = {
+	&raid5_stripecache_size.attr,
+	&raid5_stripecache_active.attr,
+	NULL,
+};
+
+static ssize_t
+raid5_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+{
+	struct raid5_sysfs_entry *entry = container_of(attr, struct raid5_sysfs_entry, attr);
+	raid5_conf_t *conf = container_of(kobj, raid5_conf_t, kobj);
+
+	if (!entry->show)
+		return -EIO;
+	return entry->show(conf, page);
+}
+
+static ssize_t
+raid5_attr_store(struct kobject *kobj, struct attribute *attr,
+	      const char *page, size_t length)
+{
+	struct raid5_sysfs_entry *entry = container_of(attr, struct raid5_sysfs_entry, attr);
+	raid5_conf_t *conf = container_of(kobj, raid5_conf_t, kobj);
+
+	if (!entry->store)
+		return -EIO;
+	return entry->store(conf, page, length);
+}
+
+static void raid5_free(struct kobject *ko)
+{
+	raid5_conf_t *conf = container_of(ko, raid5_conf_t, kobj);
+	kfree(conf);
+}
+
+
+static struct sysfs_ops raid5_sysfs_ops = {
+	.show		= raid5_attr_show,
+	.store		= raid5_attr_store,
+};
+
+static struct kobj_type raid5_ktype = {
+	.release	= raid5_free,
+	.sysfs_ops	= &raid5_sysfs_ops,
+	.default_attrs	= raid5_default_attrs,
+};
+
 static int run(mddev_t *mddev)
 {
 	raid5_conf_t *conf;

@@ -1859,6 +1974,10 @@ memory = conf->max_nr_stripes * (sizeof(
 	}
 
 	/* Ok, everything is just fine now */
+	conf->kobj.parent = kobject_get(&mddev->kobj);
+	strcpy(conf->kobj.name, "raid5");
+	conf->kobj.ktype = &raid5_ktype;
+	kobject_register(&conf->kobj);
 
 	if (mddev->bitmap)
 		mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;

@@ -1883,7 +2002,7 @@ abort:
 
 
 
-static int stop (mddev_t *mddev)
+static int stop(mddev_t *mddev)
 {
 	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
 

@@ -1892,7 +2011,7 @@ static int stop (mddev_t *mddev)
 	shrink_stripes(conf);
 	free_pages((unsigned long) conf->stripe_hashtbl, HASH_PAGES_ORDER);
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
-	kfree(conf);
+	kobject_unregister(&conf->kobj);
 	mddev->private = NULL;
 	return 0;
 }

diff ./include/linux/raid/raid5.h~current~ ./include/linux/raid/raid5.h
@@ -228,6 +228,7 @@ struct raid5_private_data {
 					    * Cleared when a sync completes.
 					    */
 
+	struct kobject		kobj;
 	/*
 	 * Free stripes pool
 	 */

diff ./drivers/md/md.c~current~ ./drivers/md/md.c
@@ -1714,9 +1714,60 @@ static struct md_sysfs_entry md_raid_dis
 	.show = md_show_rdisks,
 };
 
+static ssize_t
+md_show_scan(mddev_t *mddev, char *page)
+{
+	char *type = "none";
+	if (mddev->recovery &
+	    ((1<<MD_RECOVERY_RUNNING) || (1<<MD_RECOVERY_NEEDED))) {
+		if (mddev->recovery & (1<<MD_RECOVERY_SYNC)) {
+			if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+				type = "resync";
+			else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+				type = "check";
+			else
+				type = "repair";
+		} else
+			type = "recover";
+	}
+	return sprintf(page, "%s\n", type);
+}
+
+static ssize_t
+md_store_scan(mddev_t *mddev, const char *page, size_t len)
+{
+	int canscan=0;
+	if (mddev->recovery &
+	    ((1<<MD_RECOVERY_RUNNING) || (1<<MD_RECOVERY_NEEDED)))
+		return -EBUSY;
+	down(&mddev->reconfig_sem);
+	if (mddev->pers && mddev->pers->sync_request)
+		canscan=1;
+	up(&mddev->reconfig_sem);
+	if (!canscan)
+		return -EINVAL;
+
+	if (strcmp(page, "check")==0 || strcmp(page, "check\n")==0)
+		set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	else if (strcmp(page, "repair")!=0 && strcmp(page, "repair\n")!=0)
+		return -EINVAL;
+	set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+	set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
+	return len;
+}
+
+static struct md_sysfs_entry md_scan_mode = {
+	.attr = {.name = "scan_mode", .mode = S_IRUGO|S_IWUSR },
+	.show = md_show_scan,
+	.store = md_store_scan,
+};
+
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
 	&md_raid_disks.attr,
+	&md_scan_mode.attr,
 	NULL,
 };
 

@@ -3851,7 +3902,8 @@ static void md_do_sync(mddev_t *mddev)
 
 	is_mddev_idle(mddev); /* this also initializes IO event counters */
 	/* we don't use the checkpoint if there's a bitmap */
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap)
+	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap
+	    && ! test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 		j = mddev->recovery_cp;
 	else
 		j = 0;

@@ -4089,9 +4141,13 @@ void md_check_recovery(mddev_t *mddev)
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			goto unlock;
 		}
-		if (mddev->recovery)
-			/* probably just the RECOVERY_NEEDED flag */
-			mddev->recovery = 0;
+		/* Clear some bits that don't mean anything, but
+		 * might be left set
+		 */
+		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		clear_bit(MD_RECOVERY_ERR, &mddev->recovery);
+		clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
+		clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 
 		/* no recovery is running.
 		 * remove any failed drives, then

@@ -4125,14 +4181,17 @@ void md_check_recovery(mddev_t *mddev)
 				}
 		}
 
-		if (!spares && (mddev->recovery_cp == MaxSector )) {
-			/* nothing we can do ... */
+		if (spares) {
+			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+		} else if (mddev->recovery_cp < MaxSector) {
+			set_bit(MD_RECOVERY_SYNC, &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)
-				set_bit(MD_RECOVERY_SYNC, &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.

diff ./include/linux/raid/md_k.h~current~ ./include/linux/raid/md_k.h
@@ -182,6 +182,8 @@ struct mddev_s
 	 * ERR:      and IO error was detected - abort the resync/recovery
 	 * INTR:     someone requested a (clean) early abort.
 	 * DONE:     thread is done and is waiting to be reaped
+	 * REQUEST:  user-space has requested a sync (used with SYNC)
+	 * CHECK:    user-space request for for check-only, no repair
 	 */
 #define	MD_RECOVERY_RUNNING	0
 #define	MD_RECOVERY_SYNC	1

@@ -189,6 +191,8 @@ struct mddev_s
 #define	MD_RECOVERY_INTR	3
 #define	MD_RECOVERY_DONE	4
 #define	MD_RECOVERY_NEEDED	5
+#define	MD_RECOVERY_REQUESTED	6
+#define	MD_RECOVERY_CHECK	7
 	unsigned long			recovery;
 
 	int				in_sync;	/* know to not need resync */

diff ./drivers/md/md.c~current~ ./drivers/md/md.c
@@ -1758,16 +1758,29 @@ md_store_scan(mddev_t *mddev, const char
 	return len;
 }
 
+static ssize_t
+md_show_mismatch(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%llu\n",
+		       (unsigned long long) mddev->resync_mismatches);
+}
+
 static struct md_sysfs_entry md_scan_mode = {
 	.attr = {.name = "scan_mode", .mode = S_IRUGO|S_IWUSR },
 	.show = md_show_scan,
 	.store = md_store_scan,
 };
 
+static struct md_sysfs_entry md_mismatches = {
+	.attr = {.name = "mismatch_cnt", .mode = S_IRUGO },
+	.show = md_show_mismatch,
+};
+
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
 	&md_raid_disks.attr,
 	&md_scan_mode.attr,
+	&md_mismatches.attr,
 	NULL,
 };
 

@@ -3884,12 +3897,13 @@ static void md_do_sync(mddev_t *mddev)
 		}
 	} while (mddev->curr_resync < 2);
 
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
 		/* resync follows the size requested by the personality,
 		 * which defaults to physical size, but can be virtual size
 		 */
 		max_sectors = mddev->resync_max_sectors;
-	else
+		mddev->resync_mismatches = 0;
+	} else
 		/* recovery follows the physical size of devices */
 		max_sectors = mddev->size << 1;
 

diff ./drivers/md/raid5.c~current~ ./drivers/md/raid5.c
@@ -1292,6 +1292,11 @@ static void handle_stripe(struct stripe_
 			    !memcmp(pagea, pagea+4, STRIPE_SIZE-4)) {
 				/* 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);
 			}
 		}
 		if (!test_bit(STRIPE_INSYNC, &sh->state)) {

diff ./include/linux/raid/md_k.h~current~ ./include/linux/raid/md_k.h
@@ -175,6 +175,10 @@ struct mddev_s
 	sector_t			resync_mark_cnt;/* blocks written at resync_mark */
 
 	sector_t			resync_max_sectors; /* may be set by personality */
+
+	sector_t			resync_mismatches; /* count of sectors where
+							    * parity/replica mismatch found
+							    */
 	/* recovery/resync flags 
 	 * NEEDED:   we might need to start a resync/recover
 	 * RUNNING:  a thread is running, or about to be started